Jimeng Sun

Xuan Zhang, Limei Wang, Jacob Helwig et al. · cambridge, mit

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences. Today, AI has started to advance natural sciences by improving, accelerating, and enabling our understanding of natural phenomena at a wide range of spatial and temporal scales, giving rise to a new area of research known as AI for science (AI4Science). Being an emerging research paradigm, AI4Science is unique in that it is an enormous and highly interdisciplinary area. Thus, a unified and technical treatment of this field is needed yet challenging. This work aims to provide a technically thorough account of a subarea of AI4Science; namely, AI for quantum, atomistic, and continuum systems. These areas aim at understanding the physical world from the subatomic (wavefunctions and electron density), atomic (molecules, proteins, materials, and interactions), to macro (fluids, climate, and subsurface) scales and form an important subarea of AI4Science. A unique advantage of focusing on these areas is that they largely share a common set of challenges, thereby allowing a unified and foundational treatment. A key common challenge is how to capture physics first principles, especially symmetries, in natural systems by deep learning methods. We provide an in-depth yet intuitive account of techniques to achieve equivariance to symmetry transformations. We also discuss other common technical challenges, including explainability, out-of-distribution generalization, knowledge transfer with foundation and large language models, and uncertainty quantification. To facilitate learning and education, we provide categorized lists of resources that we found to be useful. We strive to be thorough and unified and hope this initial effort may trigger more community interests and efforts to further advance AI4Science.

Tianfan Fu, Wenhao Gao, Connor W. Coley et al.

Structure-based drug design (SBDD) aims to discover drug candidates by finding molecules (ligands) that bind tightly to a disease-related protein (targets), which is the primary approach to computer-aided drug discovery. Recently, applying deep generative models for three-dimensional (3D) molecular design conditioned on protein pockets to solve SBDD has attracted much attention, but their formulation as probabilistic modeling often leads to unsatisfactory optimization performance. On the other hand, traditional combinatorial optimization methods such as genetic algorithms (GA) have demonstrated state-of-the-art performance in various molecular optimization tasks. However, they do not utilize protein target structure to inform design steps but rely on a random-walk-like exploration, which leads to unstable performance and no knowledge transfer between different tasks despite the similar binding physics. To achieve a more stable and efficient SBDD, we propose Reinforced Genetic Algorithm (RGA) that uses neural models to prioritize the profitable design steps and suppress random-walk behavior. The neural models take the 3D structure of the targets and ligands as inputs and are pre-trained using native complex structures to utilize the knowledge of the shared binding physics from different targets and then fine-tuned during optimization. We conduct thorough empirical studies on optimizing binding affinity to various disease targets and show that RGA outperforms the baselines in terms of docking scores and is more robust to random initializations. The ablation study also indicates that the training on different targets helps improve performance by leveraging the shared underlying physics of the binding processes. The code is available at https://github.com/futianfan/reinforced-genetic-algorithm.

Zifeng Wang, Zhenbang Wu, Dinesh Agarwal et al.

Existing vision-text contrastive learning like CLIP aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction. However, medical image-text datasets are orders of magnitude below the general images and captions from the internet. Moreover, previous methods encounter many false negatives, i.e., images and reports from separate patients probably carry the same semantics but are wrongly treated as negatives. In this paper, we decouple images and texts for multimodal contrastive learning thus scaling the usable training data in a combinatorial magnitude with low cost. We also propose to replace the InfoNCE loss with semantic matching loss based on medical knowledge to eliminate false negatives in contrastive learning. We prove that MedCLIP is a simple yet effective framework: it outperforms state-of-the-art methods on zero-shot prediction, supervised classification, and image-text retrieval. Surprisingly, we observe that with only 20K pre-training data, MedCLIP wins over the state-of-the-art method (using around 200K data). Our code is available at https://github.com/RyanWangZf/MedCLIP.

Zifeng Wang, Jimeng Sun

Clinical trials are essential for drug development but are extremely expensive and time-consuming to conduct. It is beneficial to study similar historical trials when designing a clinical trial. However, lengthy trial documents and lack of labeled data make trial similarity search difficult. We propose a zero-shot clinical trial retrieval method, Trial2Vec, which learns through self-supervision without annotating similar clinical trials. Specifically, the meta-structure of trial documents (e.g., title, eligibility criteria, target disease) along with clinical knowledge (e.g., UMLS knowledge base https://www.nlm.nih.gov/research/umls/index.html) are leveraged to automatically generate contrastive samples. Besides, Trial2Vec encodes trial documents considering meta-structure thus producing compact embeddings aggregating multi-aspect information from the whole document. We show that our method yields medically interpretable embeddings by visualization and it gets a 15% average improvement over the best baselines on precision/recall for trial retrieval, which is evaluated on our labeled 1600 trial pairs. In addition, we prove the pre-trained embeddings benefit the downstream trial outcome prediction task over 240k trials. Software ias available at https://github.com/RyanWangZf/Trial2Vec.

Qiao Jin, Zifeng Wang, Charalampos S. Floudas et al. · tsinghua

Patient recruitment is challenging for clinical trials. We introduce TrialGPT, an end-to-end framework for zero-shot patient-to-trial matching with large language models. TrialGPT comprises three modules: it first performs large-scale filtering to retrieve candidate trials (TrialGPT-Retrieval); then predicts criterion-level patient eligibility (TrialGPT-Matching); and finally generates trial-level scores (TrialGPT-Ranking). We evaluate TrialGPT on three cohorts of 183 synthetic patients with over 75,000 trial annotations. TrialGPT-Retrieval can recall over 90% of relevant trials using less than 6% of the initial collection. Manual evaluations on 1,015 patient-criterion pairs show that TrialGPT-Matching achieves an accuracy of 87.3% with faithful explanations, close to the expert performance. The TrialGPT-Ranking scores are highly correlated with human judgments and outperform the best-competing models by 43.8% in ranking and excluding trials. Furthermore, our user study reveals that TrialGPT can reduce the screening time by 42.6% in patient recruitment. Overall, these results have demonstrated promising opportunities for patient-to-trial matching with TrialGPT.

Pengcheng Jiang, Zhiyi Shi, Kelly Hong et al.

Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which constraints remain open, and which claims have actually been checked. We argue that this formulation puts too much routine state management inside the policy: reinforcement learning is forced to optimize both semantic search decisions and recoverable bookkeeping that the environment can maintain more reliably. We introduce Harness-1, a 20B search agent (retrieval subagent) trained with reinforcement learning inside a stateful search harness. The harness maintains environment-side working memory, including a candidate pool, an importance-tagged curated set, compact evidence links, verification records, compressed and deduplicated observations, and budget-aware context rendering. The policy retains the semantic decisions: what to search, which documents to keep or discard, what to verify, and when to stop. Across eight retrieval benchmarks spanning web, finance, patents, and multi-hop QA, Harness-1 achieves 0.730 average curated recall, outperforming the next strongest open search subagent by +11.4 points and remaining competitive with much larger frontier-model searchers. Its gains are especially strong on held-out transfer benchmarks, suggesting that reinforcement learning over explicit search state can produce retrieval behaviors that generalize beyond the training domains. Our code is available at https://github.com/pat-jj/harness-1.

Yilin Wen, Zifeng Wang, Jimeng Sun

Large language models (LLMs) have achieved remarkable performance in natural language understanding and generation tasks. However, they often suffer from limitations such as difficulty in incorporating new knowledge, generating hallucinations, and explaining their reasoning process. To address these challenges, we propose a novel prompting pipeline, named \method, that leverages knowledge graphs (KGs) to enhance LLMs' inference and transparency. Our method enables LLMs to comprehend KG inputs and infer with a combination of implicit and external knowledge. Moreover, our method elicits the mind map of LLMs, which reveals their reasoning pathways based on the ontology of knowledge. We evaluate our method on diverse question \& answering tasks, especially in medical domains, and show significant improvements over baselines. We also introduce a new hallucination evaluation benchmark and analyze the effects of different components of our method. Our results demonstrate the effectiveness and robustness of our method in merging knowledge from LLMs and KGs for combined inference. To reproduce our results and extend the framework further, we make our codebase available at https://github.com/wyl-willing/MindMap.

Zhenbang Wu, Huaxiu Yao, Zhe Su et al. · cmu

Drug recommendation assists doctors in prescribing personalized medications to patients based on their health conditions. Existing drug recommendation solutions adopt the supervised multi-label classification setup and only work with existing drugs with sufficient prescription data from many patients. However, newly approved drugs do not have much historical prescription data and cannot leverage existing drug recommendation methods. To address this, we formulate the new drug recommendation as a few-shot learning problem. Yet, directly applying existing few-shot learning algorithms faces two challenges: (1) complex relations among diseases and drugs and (2) numerous false-negative patients who were eligible but did not yet use the new drugs. To tackle these challenges, we propose EDGE, which can quickly adapt to the recommendation for a new drug with limited prescription data from a few support patients. EDGE maintains a drug-dependent multi-phenotype few-shot learner to bridge the gap between existing and new drugs. Specifically, EDGE leverages the drug ontology to link new drugs to existing drugs with similar treatment effects and learns ontology-based drug representations. Such drug representations are used to customize the metric space of the phenotype-driven patient representations, which are composed of a set of phenotypes capturing complex patient health status. Lastly, EDGE eliminates the false-negative supervision signal using an external drug-disease knowledge base. We evaluate EDGE on two real-world datasets: the public EHR data (MIMIC-IV) and private industrial claims data. Results show that EDGE achieves 7.3% improvement on the ROC-AUC score over the best baseline.

Zifeng Wang, Brandon Theodorou, Tianfan Fu et al.

Clinical trials are conducted to test the effectiveness and safety of potential drugs in humans for regulatory approval. Machine learning (ML) has recently emerged as a new tool to assist in clinical trials. Despite this progress, there have been few efforts to document and benchmark ML4Trial algorithms available to the ML research community. Additionally, the accessibility to clinical trial-related datasets is limited, and there is a lack of well-defined clinical tasks to facilitate the development of new algorithms. To fill this gap, we have developed PyTrial that provides benchmarks and open-source implementations of a series of ML algorithms for clinical trial design and operations. In this paper, we thoroughly investigate 34 ML algorithms for clinical trials across 6 different tasks, including patient outcome prediction, trial site selection, trial outcome prediction, patient-trial matching, trial similarity search, and synthetic data generation. We have also collected and prepared 23 ML-ready datasets as well as their working examples in Jupyter Notebooks for quick implementation and testing. PyTrial defines each task through a simple four-step process: data loading, model specification, model training, and model evaluation, all achievable with just a few lines of code. Furthermore, our modular API architecture empowers practitioners to expand the framework to incorporate new algorithms and tasks effortlessly. The code is available at https://github.com/RyanWangZf/PyTrial.

Zifeng Wang, Jimeng Sun

Accessing longitudinal multimodal Electronic Healthcare Records (EHRs) is challenging due to privacy concerns, which hinders the use of ML for healthcare applications. Synthetic EHRs generation bypasses the need to share sensitive real patient records. However, existing methods generate single-modal EHRs by unconditional generation or by longitudinal inference, which falls short of low flexibility and makes unrealistic EHRs. In this work, we propose to formulate EHRs generation as a text-to-text translation task by language models (LMs), which suffices to highly flexible event imputation during generation. We also design prompt learning to control the generation conditioned by numerical and categorical demographic features. We evaluate synthetic EHRs quality by two perplexity measures accounting for their longitudinal pattern (longitudinal imputation perplexity, lpl) and the connections cross modalities (cross-modality imputation perplexity, mpl). Moreover, we utilize two adversaries: membership and attribute inference attacks for privacy-preserving evaluation. Experiments on MIMIC-III data demonstrate the superiority of our methods on realistic EHRs generation (53.1\% decrease of lpl and 45.3\% decrease of mpl on average compared to the best baselines) with low privacy risks. Software is available at https://github.com/RyanWangZf/PromptEHR.

Zifeng Wang, Jimeng Sun

Tabular data (or tables) are the most widely used data format in machine learning (ML). However, ML models often assume the table structure keeps fixed in training and testing. Before ML modeling, heavy data cleaning is required to merge disparate tables with different columns. This preprocessing often incurs significant data waste (e.g., removing unmatched columns and samples). How to learn ML models from multiple tables with partially overlapping columns? How to incrementally update ML models as more columns become available over time? Can we leverage model pretraining on multiple distinct tables? How to train an ML model which can predict on an unseen table? To answer all those questions, we propose to relax fixed table structures by introducing a Transferable Tabular Transformer (TransTab) for tables. The goal of TransTab is to convert each sample (a row in the table) to a generalizable embedding vector, and then apply stacked transformers for feature encoding. One methodology insight is combining column description and table cells as the raw input to a gated transformer model. The other insight is to introduce supervised and self-supervised pretraining to improve model performance. We compare TransTab with multiple baseline methods on diverse benchmark datasets and five oncology clinical trial datasets. Overall, TransTab ranks 1.00, 1.00, 1.78 out of 12 methods in supervised learning, feature incremental learning, and transfer learning scenarios, respectively; and the proposed pretraining leads to 2.3% AUC lift on average over the supervised learning.

Yuanqi Du, Tianfan Fu, Jimeng Sun et al.

Molecule design is a fundamental problem in molecular science and has critical applications in a variety of areas, such as drug discovery, material science, etc. However, due to the large searching space, it is impossible for human experts to enumerate and test all molecules in wet-lab experiments. Recently, with the rapid development of machine learning methods, especially generative methods, molecule design has achieved great progress by leveraging machine learning models to generate candidate molecules. In this paper, we systematically review the most relevant work in machine learning models for molecule design. We start with a brief review of the mainstream molecule featurization and representation methods (including 1D string, 2D graph, and 3D geometry) and general generative methods (deep generative and combinatorial optimization methods). Then we summarize all the existing molecule design problems into several venues according to the problem setup, including input, output types and goals. Finally, we conclude with the open challenges and point out future opportunities of machine learning models for molecule design in real-world applications.

Namkyeong Lee, Heewoong Noh, Gyoung S. Na et al.

Machine learning (ML) has seen promising developments in materials science, yet its efficacy largely depends on detailed crystal structural data, which are often complex and hard to obtain, limiting their applicability in real-world material synthesis processes. An alternative, using compositional descriptors, offers a simpler approach by indicating the elemental ratios of compounds without detailed structural insights. However, accurately representing materials solely with compositional descriptors presents challenges due to polymorphism, where a single composition can correspond to various structural arrangements, creating ambiguities in its representation. To this end, we introduce PCRL, a novel approach that employs probabilistic modeling of composition to capture the diverse polymorphs from available structural information. Extensive evaluations on sixteen datasets demonstrate the effectiveness of PCRL in learning compositional representation, and our analysis highlights its potential applicability of PCRL in material discovery. The source code for PCRL is available at https://github.com/Namkyeong/PCRL.

Brandon Theodorou, Cao Xiao, Jimeng Sun

Synthetic electronic health records (EHRs) that are both realistic and preserve privacy can serve as an alternative to real EHRs for machine learning (ML) modeling and statistical analysis. However, generating high-fidelity and granular electronic health record (EHR) data in its original, highly-dimensional form poses challenges for existing methods due to the complexities inherent in high-dimensional data. In this paper, we propose Hierarchical Autoregressive Language mOdel (HALO) for generating longitudinal high-dimensional EHR, which preserve the statistical properties of real EHR and can be used to train accurate ML models without privacy concerns. Our HALO method, designed as a hierarchical autoregressive model, generates a probability density function of medical codes, clinical visits, and patient records, allowing for the generation of realistic EHR data in its original, unaggregated form without the need for variable selection or aggregation. Additionally, our model also produces high-quality continuous variables in a longitudinal and probabilistic manner. We conducted extensive experiments and demonstrate that HALO can generate high-fidelity EHR data with high-dimensional disease code probabilities (d > 10,000), disease co-occurrence probabilities within visits (d > 1,000,000), and conditional probabilities across consecutive visits (d > 5,000,000) and achieve above 0.9 R2 correlation in comparison to real EHR data. This performance then enables downstream ML models trained on its synthetic data to achieve comparable accuracy to models trained on real data (0.938 AUROC with HALO data vs. 0.943 with real data). Finally, using a combination of real and synthetic data enhances the accuracy of ML models beyond that achieved by using only real EHR data.

Zhen Lin, Shubhendu Trivedi, Jimeng Sun

We develop Temporal Quantile Adjustment (TQA), a general method to construct efficient and valid prediction intervals (PIs) for regression on cross-sectional time series data. Such data is common in many domains, including econometrics and healthcare. A canonical example in healthcare is predicting patient outcomes using physiological time-series data, where a population of patients composes a cross-section. Reliable PI estimators in this setting must address two distinct notions of coverage: cross-sectional coverage across a cross-sectional slice, and longitudinal coverage along the temporal dimension for each time series. Recent works have explored adapting Conformal Prediction (CP) to obtain PIs in the time series context. However, none handles both notions of coverage simultaneously. CP methods typically query a pre-specified quantile from the distribution of nonconformity scores on a calibration set. TQA adjusts the quantile to query in CP at each time $t$, accounting for both cross-sectional and longitudinal coverage in a theoretically-grounded manner. The post-hoc nature of TQA facilitates its use as a general wrapper around any time series regression model. We validate TQA's performance through extensive experimentation: TQA generally obtains efficient PIs and improves longitudinal coverage while preserving cross-sectional coverage.

Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi et al. · stanford

Cutting-edge agentic AI systems are built on foundation models that can be adapted to plan, reason, and interact with external tools to perform increasingly complex and specialized tasks. As these systems grow in capability and scope, adaptation becomes a central mechanism for improving performance, reliability, and generalization. In this paper, we unify the rapidly expanding research landscape into a systematic framework that spans both agent adaptations and tool adaptations. We further decompose these into tool-execution-signaled and agent-output-signaled forms of agent adaptation, as well as agent-agnostic and agent-supervised forms of tool adaptation. We demonstrate that this framework helps clarify the design space of adaptation strategies in agentic AI, makes their trade-offs explicit, and provides practical guidance for selecting or switching among strategies during system design. We then review the representative approaches in each category, analyze their strengths and limitations, and highlight key open challenges and future opportunities. Overall, this paper aims to offer a conceptual foundation and practical roadmap for researchers and practitioners seeking to build more capable, efficient, and reliable agentic AI systems.

Zhen Lin, Shubhendu Trivedi, Cao Xiao et al.

Many real-world multi-label prediction problems involve set-valued predictions that must satisfy specific requirements dictated by downstream usage. We focus on a typical scenario where such requirements, separately encoding $\textit{value}$ and $\textit{cost}$, compete with each other. For instance, a hospital might expect a smart diagnosis system to capture as many severe, often co-morbid, diseases as possible (the value), while maintaining strict control over incorrect predictions (the cost). We present a general pipeline, dubbed as FavMac, to maximize the value while controlling the cost in such scenarios. FavMac can be combined with almost any multi-label classifier, affording distribution-free theoretical guarantees on cost control. Moreover, unlike prior works, it can handle real-world large-scale applications via a carefully designed online update mechanism, which is of independent interest. Our methodological and theoretical contributions are supported by experiments on several healthcare tasks and synthetic datasets - FavMac furnishes higher value compared with several variants and baselines while maintaining strict cost control. Our code is available at https://github.com/zlin7/FavMac

Pengcheng Jiang, Cao Xiao, Tianfan Fu et al.

Molecular representation learning is vital for various downstream applications, including the analysis and prediction of molecular properties and side effects. While Graph Neural Networks (GNNs) have been a popular framework for modeling molecular data, they often struggle to capture the full complexity of molecular representations. In this paper, we introduce a novel method called GODE, which accounts for the dual-level structure inherent in molecules. Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph. GODE integrates individual molecular graph representations with multi-domain biochemical data from knowledge graphs. By pre-training two GNNs on different graph structures and employing contrastive learning, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures. This fusion yields a more robust and informative representation, enhancing molecular property predictions by leveraging both chemical and biological information. When fine-tuned across 11 chemical property tasks, our model significantly outperforms existing benchmarks, achieving an average ROC-AUC improvement of 12.7% for classification tasks and an average RMSE/MAE improvement of 34.4% for regression tasks. Notably, GODE surpasses the current leading model in property prediction, with advancements of 2.2% in classification and 7.2% in regression tasks.

Rakshith S Srinivasa, Cheng Qian, Brandon Theodorou et al.

The ongoing pandemic has highlighted the importance of reliable and efficient clinical trials in healthcare. Trial sites, where the trials are conducted, are chosen mainly based on feasibility in terms of medical expertise and access to a large group of patients. More recently, the issue of diversity and inclusion in clinical trials is gaining importance. Different patient groups may experience the effects of a medical drug/ treatment differently and hence need to be included in the clinical trials. These groups could be based on ethnicity, co-morbidities, age, or economic factors. Thus, designing a method for trial site selection that accounts for both feasibility and diversity is a crucial and urgent goal. In this paper, we formulate this problem as a ranking problem with fairness constraints. Using principles of fairness in machine learning, we learn a model that maps a clinical trial description to a ranked list of potential trial sites. Unlike existing fairness frameworks, the group membership of each trial site is non-binary: each trial site may have access to patients from multiple groups. We propose fairness criteria based on demographic parity to address such a multi-group membership scenario. We test our method on 480 real-world clinical trials and show that our model results in a list of potential trial sites that provides access to a diverse set of patients while also ensuing a high number of enrolled patients.

Chaoqi Yang, Cheng Qian, Jimeng Sun

Low-rank tensor factorization or completion is well-studied and applied in various online settings, such as online tensor factorization (where the temporal mode grows) and online tensor completion (where incomplete slices arrive gradually). However, in many real-world settings, tensors may have more complex evolving patterns: (i) one or more modes can grow; (ii) missing entries may be filled; (iii) existing tensor elements can change. Existing methods cannot support such complex scenarios. To fill the gap, this paper proposes a Generalized Online Canonical Polyadic (CP) Tensor factorization and completion framework (named GOCPT) for this general setting, where we maintain the CP structure of such dynamic tensors during the evolution. We show that existing online tensor factorization and completion setups can be unified under the GOCPT framework. Furthermore, we propose a variant, named GOCPTE, to deal with cases where historical tensor elements are unavailable (e.g., privacy protection), which achieves similar fitness as GOCPT but with much less computational cost. Experimental results demonstrate that our GOCPT can improve fitness by up to 2:8% on the JHU Covid data and 9:2% on a proprietary patient claim dataset over baselines. Our variant GOCPTE shows up to 1:2% and 5:5% fitness improvement on two datasets with about 20% speedup compared to the best model.

Zifeng Wang, Cao Xiao, Jimeng Sun

Clinical trials are essential to drug development but time-consuming, costly, and prone to failure. Accurate trial outcome prediction based on historical trial data promises better trial investment decisions and more trial success. Existing trial outcome prediction models were not designed to model the relations among similar trials, capture the progression of features and designs of similar trials, or address the skewness of trial data which causes inferior performance for less common trials. To fill the gap and provide accurate trial outcome prediction, we propose Sequential Predictive mOdeling of clinical Trial outcome (SPOT) that first identifies trial topics to cluster the multi-sourced trial data into relevant trial topics. It then generates trial embeddings and organizes them by topic and time to create clinical trial sequences. With the consideration of each trial sequence as a task, it uses a meta-learning strategy to achieve a point where the model can rapidly adapt to new tasks with minimal updates. In particular, the topic discovery module enables a deeper understanding of the underlying structure of the data, while sequential learning captures the evolution of trial designs and outcomes. This results in predictions that are not only more accurate but also more interpretable, taking into account the temporal patterns and unique characteristics of each trial topic. We demonstrate that SPOT wins over the prior methods by a significant margin on trial outcome benchmark data: with a 21.5\% lift on phase I, an 8.9\% lift on phase II, and a 5.5\% lift on phase III trials in the metric of the area under precision-recall curve (PR-AUC).

Brandon Theodorou, Cao Xiao, Jimeng Sun

Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials based on longitudinal patient electronic health records (EHR) data and eligibility criteria of clinical trials. However, they either depend on trial-specific expert rules that cannot expand to other trials or perform matching at a very general level with a black-box model where the lack of interpretability makes the model results difficult to be adopted. To provide accurate and interpretable patient trial matching, we introduce a personalized dynamic tree-based memory network model named TREEMENT. It utilizes hierarchical clinical ontologies to expand the personalized patient representation learned from sequential EHR data, and then uses an attentional beam-search query learned from eligibility criteria embedding to offer a granular level of alignment for improved performance and interpretability. We evaluated TREEMENT against existing models on real-world datasets and demonstrated that TREEMENT outperforms the best baseline by 7% in terms of error reduction in criteria-level matching and achieves state-of-the-art results in its trial-level matching ability. Furthermore, we also show TREEMENT can offer good interpretability to make the model results easier for adoption.

Jintai Chen, Jiahuan Yan, Qiyuan Chen et al.

Data organized in tabular format is ubiquitous in real-world applications, and users often craft tables with biased feature definitions and flexibly set prediction targets of their interests. Thus, a rapid development of a robust, effective, dataset-versatile, user-friendly tabular prediction approach is highly desired. While Gradient Boosting Decision Trees (GBDTs) and existing deep neural networks (DNNs) have been extensively utilized by professional users, they present several challenges for casual users, particularly: (i) the dilemma of model selection due to their different dataset preferences, and (ii) the need for heavy hyperparameter searching, failing which their performances are deemed inadequate. In this paper, we delve into this question: Can we develop a deep learning model that serves as a "sure bet" solution for a wide range of tabular prediction tasks, while also being user-friendly for casual users? We delve into three key drawbacks of deep tabular models, encompassing: (P1) lack of rotational variance property, (P2) large data demand, and (P3) over-smooth solution. We propose ExcelFormer, addressing these challenges through a semi-permeable attention module that effectively constrains the influence of less informative features to break the DNNs' rotational invariance property (for P1), data augmentation approaches tailored for tabular data (for P2), and attentive feedforward network to boost the model fitting capability (for P3). These designs collectively make ExcelFormer a "sure bet" solution for diverse tabular datasets. Extensive and stratified experiments conducted on real-world datasets demonstrate that our model outperforms previous approaches across diverse tabular data prediction tasks, and this framework can be friendly to casual users, offering ease of use without the heavy hyperparameter tuning.

Namkyeong Lee, Siddhartha Laghuvarapu, Chanyoung Park et al.

Recently, there has been a growing interest among researchers in understanding molecules and their textual descriptions through molecule language models (MoLM). However, despite some early promising developments, the advancement of MoLM still trails significantly behind that of vision language models (VLM). This is because unique challenges exist apart from VLM in the field of MoLM due to 1) a limited amount of molecule-text paired data and 2) missing expertise that occurred due to the specialized areas of focus among the experts. To this end, we propose AMOLE, which 1) augments molecule-text pairs with structural similarity preserving loss, and 2) transfers the expertise between the molecules. Specifically, AMOLE enriches molecule-text pairs by sharing descriptions among structurally similar molecules with a novel structural similarity preserving loss. Moreover, we propose an expertise reconstruction loss to transfer knowledge from molecules that have extensive expertise to those with less expertise. Extensive experiments on various downstream tasks demonstrate the superiority of AMOLE in comprehending molecules and their descriptions, highlighting its potential for application in real-world drug discovery. The source code for AMOLE is available at https://github.com/Namkyeong/AMOLE.

Harsh Parikh, Kentaro Hoffman, Haoqi Sun et al.

Epileptiform activity (EA) is associated with worse outcomes including increased risk of disability and death. However, the effect of EA on the neurologic outcome is confounded by the feedback between treatment with anti-seizure medications (ASM) and EA burden. A randomized clinical trial is challenging due to the sequential nature of EA-ASM feedback, as well as ethical reasons. However, some mechanistic knowledge is available, e.g., how drugs are absorbed. This knowledge together with observational data could provide a more accurate effect estimate using causal inference. We performed a retrospective cross-sectional study with 995 patients with the modified Rankin Scale (mRS) at discharge as the outcome and the EA burden defined as the mean or maximum proportion of time spent with EA in six-hour windows in the first 24 hours of electroencephalography as the exposure. We estimated the change in discharge mRS if everyone in the dataset had experienced a certain EA burden and were untreated. We combined pharmacological modeling with an interpretable matching method to account for confounding and EA-ASM feedback. Our matched groups' quality was validated by the neurologists. Having a maximum EA burden greater than 75% when untreated had a 22% increased chance of a poor outcome (severe disability or death), and mild but long-lasting EA increased the risk of a poor outcome by 14%. The effect sizes were heterogeneous depending on pre-admission profile, e.g., patients with hypoxic-ischemic encephalopathy (HIE) or acquired brain injury (ABI) were more affected. Interventions should put a higher priority on patients with an average EA burden higher than 10%, while treatment should be more conservative when the maximum EA burden is low.

Chaoqi Yang, M. Brandon Westover, Jimeng Sun

The vast amount of health data has been continuously collected for each patient, providing opportunities to support diverse healthcare predictive tasks such as seizure detection and hospitalization prediction. Existing models are mostly trained on other patients data and evaluated on new patients. Many of them might suffer from poor generalizability. One key reason can be overfitting due to the unique information related to patient identities and their data collection environments, referred to as patient covariates in the paper. These patient covariates usually do not contribute to predicting the targets but are often difficult to remove. As a result, they can bias the model training process and impede generalization. In healthcare applications, most existing domain generalization methods assume a small number of domains. In this paper, considering the diversity of patient covariates, we propose a new setting by treating each patient as a separate domain (leading to many domains). We develop a new domain generalization method ManyDG, that can scale to such many-domain problems. Our method identifies the patient domain covariates by mutual reconstruction and removes them via an orthogonal projection step. Extensive experiments show that ManyDG can boost the generalization performance on multiple real-world healthcare tasks (e.g., 3.7% Jaccard improvements on MIMIC drug recommendation) and support realistic but challenging settings such as insufficient data and continuous learning.

Junyi Gao, Chaoqi Yang, George Heintz et al.

The COVID-19 pandemic has caused devastating economic and social disruption, straining the resources of healthcare institutions worldwide. This has led to a nationwide call for models to predict hospitalization and severe illness in patients with COVID-19 to inform distribution of limited healthcare resources. We respond to one of these calls specific to the pediatric population. To address this challenge, we study two prediction tasks for the pediatric population using electronic health records: 1) predicting which children are more likely to be hospitalized, and 2) among hospitalized children, which individuals are more likely to develop severe symptoms. We respond to the national Pediatric COVID-19 data challenge with a novel machine learning model, MedML. MedML extracts the most predictive features based on medical knowledge and propensity scores from over 6 million medical concepts and incorporates the inter-feature relationships between heterogeneous medical features via graph neural networks (GNN). We evaluate MedML across 143,605 patients for the hospitalization prediction task and 11,465 patients for the severity prediction task using data from the National Cohort Collaborative (N3C) dataset. We also report detailed group-level and individual-level feature importance analyses to evaluate the model interpretability. MedML achieves up to a 7% higher AUROC score and up to a 14% higher AUPRC score compared to the best baseline machine learning models and performs well across all nine national geographic regions and over all three-month spans since the start of the pandemic. Our cross-disciplinary research team has developed a method of incorporating clinical domain knowledge as the framework for a new type of machine learning model that is more predictive and explainable than current state-of-the-art data-driven feature selection methods.

Xihao Piao, Pei Gao, Zheng Chen et al.

The medical community believes binary medical event outcomes in EHR data contain sufficient information for making a sensible recommendation. However, there are two challenges to effectively utilizing such data: (1) modeling the relationship between massive 0,1 event outcomes is difficult, even with expert knowledge; (2) in practice, learning can be stalled by the binary values since the equally important 0 entries propagate no learning signals. Currently, there is a large gap between the assumed sufficient information and the reality that no promising results have been shown by utilizing solely the binary data: visiting or secondary information is often necessary to reach acceptable performance. In this paper, we attempt to build the first successful binary EHR data-oriented drug recommendation system by tackling the two difficulties, making sensible drug recommendations solely using the binary EHR medical records. To this end, we take a statistical perspective to view the EHR data as a sample from its cohorts and transform them into continuous Bernoulli probabilities. The transformed entries not only model a deterministic binary event with a distribution but also allow reflecting \emph{event-event} relationship by conditional probability. A graph neural network is learned on top of the transformation. It captures event-event correlations while emphasizing \emph{event-to-patient} features. Extensive results demonstrate that the proposed method achieves state-of-the-art performance on large-scale databases, outperforming baseline methods that use secondary information by a large margin. The source code is available at \url{https://github.com/chenzRG/BEHRMecom}

Zhenbang Wu, Cao Xiao, Lucas M Glass et al.

Given a deep learning model trained on data from a source site, how to deploy the model to a target hospital automatically? How to accommodate heterogeneous medical coding systems across different hospitals? Standard approaches rely on existing medical code mapping tools, which have significant practical limitations. To tackle this problem, we propose AutoMap to automatically map the medical codes across different EHR systems in a coarse-to-fine manner: (1) Ontology-level Alignment: We leverage the ontology structure to learn a coarse alignment between the source and target medical coding systems; (2) Code-level Refinement: We refine the alignment at a fine-grained code level for the downstream tasks using a teacher-student framework. We evaluate AutoMap using several deep learning models with two real-world EHR datasets: eICU and MIMIC-III. Results show that AutoMap achieves relative improvements up to 3.9% (AUC-ROC) and 8.7% (AUC-PR) for mortality prediction, and up to 4.7% (AUC-ROC) and 3.7% (F1) for length-of-stay estimation. Further, we show that AutoMap can provide accurate mapping across coding systems. Lastly, we demonstrate that AutoMap can adapt to the two challenging scenarios: (1) mapping between completely different coding systems and (2) between completely different hospitals.

Zifeng Wang, Chufan Gao, Lucas M. Glass et al.

A clinical trial is an essential step in drug development, which is often costly and time-consuming. In silico trials are clinical trials conducted digitally through simulation and modeling as an alternative to traditional clinical trials. AI-enabled in silico trials can increase the case group size by creating virtual cohorts as controls. In addition, it also enables automation and optimization of trial design and predicts the trial success rate. This article systematically reviews papers under three main topics: clinical simulation, individualized predictive modeling, and computer-aided trial design. We focus on how machine learning (ML) may be applied in these applications. In particular, we present the machine learning problem formulation and available data sources for each task. We end with discussing the challenges and opportunities of AI for in silico trials in real-world applications.

Zhen Lin, Shubhendu Trivedi, Jimeng Sun

Cross-sectional prediction is common in many domains such as healthcare, including forecasting tasks using electronic health records, where different patients form a cross-section. We focus on the task of constructing valid prediction intervals (PIs) in time series regression with a cross-section. A prediction interval is considered valid if it covers the true response with (a pre-specified) high probability. We first distinguish between two notions of validity in such a setting: cross-sectional and longitudinal. Cross-sectional validity is concerned with validity across the cross-section of the time series data, while longitudinal validity accounts for the temporal dimension. Coverage guarantees along both these dimensions are ideally desirable; however, we show that distribution-free longitudinal validity is theoretically impossible. Despite this limitation, we propose Conformal Prediction with Temporal Dependence (CPTD), a procedure that is able to maintain strict cross-sectional validity while improving longitudinal coverage. CPTD is post-hoc and light-weight, and can easily be used in conjunction with any prediction model as long as a calibration set is available. We focus on neural networks due to their ability to model complicated data such as diagnosis codes for time series regression, and perform extensive experimental validation to verify the efficacy of our approach. We find that CPTD outperforms baselines on a variety of datasets by improving longitudinal coverage and often providing more efficient (narrower) PIs.

Hanyin Wang, Chufan Gao, Christopher Dantona et al.

In the U.S. inpatient payment system, the Diagnosis-Related Group (DRG) is pivotal, but its assignment process is inefficient. The study introduces DRG-LLaMA, an advanced large language model (LLM) fine-tuned on clinical notes to enhance DRGs assignment. Utilizing LLaMA as the foundational model and optimizing it through Low-Rank Adaptation (LoRA) on 236,192 MIMIC-IV discharge summaries, our DRG-LLaMA-7B model exhibited a noteworthy macro-averaged F1 score of 0.327, a top-1 prediction accuracy of 52.0%, and a macro-averaged Area Under the Curve (AUC) of 0.986, with a maximum input token length of 512. This model surpassed the performance of prior leading models in DRG prediction, showing a relative improvement of 40.3% and 35.7% in macro-averaged F1 score compared to ClinicalBERT and CAML, respectively. Applied to base DRG and complication or comorbidity (CC)/major complication or comorbidity (MCC) prediction, DRG-LLaMA achieved a top-1 prediction accuracy of 67.8% and 67.5%, respectively. Additionally, our findings indicate that DRG-LLaMA's performance correlates with increased model parameters and input context lengths.

Tao Feng, Zifeng Wang, Jimeng Sun

The recent advancement of large language models (LLMs) has been achieved through a combo of instruction tuning and human alignment. However, building manually crafted instruction datasets and performing human alignment become the bottleneck for scaling the development of LLMs. In this paper, we exploit the idea of leveraging AI models in lieu of humans as the teacher to train student LLMs. Our method is inspired by how human students refine their writing skills by following the rubrics and learning from the revisions offered by their tutors. Specifically, we employ a teacher LLM to create a curriculum for instruction tuning of the student LLM, namely Curriculum Instruction TunING (CITING). It encompasses two main steps: (1) the teacher LLM crafts the rubrics for evaluating the answers corresponding to various types of questions, and (2) the student LLM learns to follow the rubrics and perform self-correction from the revision made by the teacher. We further iteratively carry out it to embody the procedure of CITING. We compare CITING to a series of state-of-the-art baselines on four datasets. Our method demonstrates strong improvement in terms of articulate, in-depth, and comprehensive by GPT-4 evaluation. Specifically, it achieves an average winning rate of 79.4% over SFT, 73.4% over RLHF, 78.1% over RRHF, and 76.3% over RAFT, respectively.

Siddhartha Laghuvarapu, Rohan Deb, Jimeng Sun

Uncertainty quantification is essential for deploying machine learning models in high-stakes domains such as scientific discovery and healthcare. Conformal Prediction (CP) provides finite-sample coverage guarantees under exchangeability, an assumption often violated in practice due to distribution shift. Under covariate shift, restoring validity requires importance weighting, yet accurate density-ratio estimation becomes unstable when training and test distributions exhibit limited support overlap. We propose KMM-CP, a conformal prediction framework based on Kernel Mean Matching (KMM) for covariate-shift correction. We show that KMM directly controls the bias-variance components governing conformal coverage error by minimizing RKHS moment discrepancy under explicit weight constraints, and establish asymptotic coverage guarantees under mild conditions. We then introduce a selective extension that identifies regions of reliable support overlap and restricts conformal correction to this subset, further improving stability in low-overlap regimes. Experiments on molecular property prediction benchmarks with realistic distribution shifts show that KMM-CP reduces coverage gap by over 50% compared to existing approaches. The code is available at https://github.com/siddharthal/KMM-CP.

Arjun Chatterjee, Sayeed Sajjad Razin, John Wu et al.

Quantifying uncertainty in clinical predictions is critical for high-stakes diagnosis tasks. Conformal prediction offers a principled approach by providing prediction sets with theoretical coverage guarantees. However, in practice, patient distribution shifts violate the i.i.d. assumptions underlying standard conformal methods, leading to poor coverage in healthcare settings. In this work, we evaluate several conformal prediction approaches on EEG seizure classification, a task with known distribution shift challenges and label uncertainty. We demonstrate that personalized calibration strategies can improve coverage by over 20 percentage points while maintaining comparable prediction set sizes. Our implementation is available via PyHealth, an open-source healthcare AI framework: https://github.com/sunlabuiuc/PyHealth.

John Wu, Yongda Fan, Zhenbang Wu et al.

Difficulty replicating baselines, high computational costs, and required domain expertise create persistent barriers to clinical AI research. To address these challenges, we introduce PyHealth 2.0, an enhanced clinical deep learning toolkit that enables predictive modeling in as few as 7 lines of code. PyHealth 2.0 offers three key contributions: (1) a comprehensive toolkit addressing reproducibility and compatibility challenges by unifying 15+ datasets, 20+ clinical tasks, 25+ models, 5+ interpretability methods, and uncertainty quantification including conformal prediction within a single framework that supports diverse clinical data modalities - signals, imaging, and electronic health records - with translation of 5+ medical coding standards; (2) accessibility-focused design accommodating multimodal data and diverse computational resources with up to 39x faster processing and 20x lower memory usage, enabling work from 16GB laptops to production systems; and (3) an active open-source community of 400+ members lowering domain expertise barriers through extensive documentation, reproducible research contributions, and collaborations with academic health systems and industry partners, including multi-language support via RHealth. PyHealth 2.0 establishes an open-source foundation and community advancing accessible, reproducible healthcare AI. Available at pip install pyhealth.

Yongda Fan, John Wu, Andrea Fitzpatrick et al.

Clinical decisions are high-stakes and require explicit justification, making model interpretability essential for auditing deep clinical models prior to deployment. As the ecosystem of model architectures and explainability methods expands, critical questions remain: Do architectural features like attention improve explainability? Do interpretability approaches generalize across clinical tasks? While prior benchmarking efforts exist, they often lack extensibility and reproducibility, and critically, fail to systematically examine how interpretability varies across the interplay of clinical tasks and model architectures. To address these gaps, we present a comprehensive benchmark evaluating interpretability methods across diverse clinical prediction tasks and model architectures. Our analysis reveals that: (1) attention when leveraged properly is a highly efficient approach for faithfully interpreting model predictions; (2) black-box interpreters like KernelSHAP and LIME are computationally infeasible for time-series clinical prediction tasks; and (3) several interpretability approaches are too unreliable to be trustworthy. From our findings, we discuss several guidelines on improving interpretability within clinical predictive pipelines. To support reproducibility and extensibility, we provide our implementations via PyHealth, a well-documented open-source framework: https://github.com/sunlabuiuc/PyHealth.

Ruiyu Wang, Zifeng Wang, Jimeng Sun

Tabular data prediction is a fundamental machine learning task for many applications. Existing methods predominantly employ discriminative modeling and operate under the assumption of a fixed target column, necessitating re-training for every new predictive task. Inspired by the generative power of large language models (LLMs), this paper exploits the idea of building universal tabular data predictors based on generative modeling, namely UniPredict. Here, we demonstrate the scalability of an LLM to extensive tabular datasets, enabling it to comprehend diverse tabular inputs and predict target variables following the provided instructions. Specifically, we train a single LLM on an aggregation of 169 tabular datasets with diverse targets and compare its performance against baselines that are trained on each dataset separately. We observe this versatile UniPredict model demonstrates an advantage over other models, ranging from 5.4% to 13.4%, when compared with the best tree-boosting baseline and the best neural network baseline, respectively. We further test UniPredict in few-shot learning settings on another 62 tabular datasets. Our method achieves strong performance in quickly adapting to new tasks. In low-resource few-shot setup, we observed a 100%+ performance advantage compared with XGBoost, and significant margin over all baselines. We envision that UniPredict sheds light on developing a universal tabular data prediction system that learns from data at scale and serves a wide range of prediction tasks.

Ziwei Yang, Rikuto Kotoge, Xihao Piao et al.

Framing the investigation of diverse cancers as a machine learning problem has recently shown significant potential in multi-omics analysis and cancer research. Empowering these successful machine learning models are the high-quality training datasets with sufficient data volume and adequate preprocessing. However, while there exist several public data portals, including The Cancer Genome Atlas (TCGA) multi-omics initiative or open-bases such as the LinkedOmics, these databases are not off-the-shelf for existing machine learning models. In this paper, we introduce MLOmics, an open cancer multi-omics database aiming at serving better the development and evaluation of bioinformatics and machine learning models. MLOmics contains 8,314 patient samples covering all 32 cancer types with four omics types, stratified features, and extensive baselines. Complementary support for downstream analysis and bio-knowledge linking are also included to support interdisciplinary analysis.

Yuyang Dai, Zheng Chen, Jathurshan Pradeepkumar et al.

Epilepsy diagnosis and treatment require evidence-intensive reasoning across heterogeneous clinical knowledge, including biosignal patterns, genetic mechanisms, pharmacogenomics, treatment strategies, and patient outcomes. In this work, we present \textsc{EpiGraph}, a large-scale epilepsy knowledge graph and benchmark for evaluating knowledge-augmented clinical reasoning. \textsc{EpiGraph} integrates 48,166 peer-reviewed papers and seven clinical resources into a heterogeneous graph containing 24,324 entities and 32,009 evidence-grounded triplets across five clinical layers. Built upon this graph, \textsc{EpiBench} defines five clinically motivated tasks spanning clinical decision-making, EEG report generation, pharmacogenomic precision medicine, treatment recommendation, and deep research planning. We evaluate six LLMs under both standard and Graph-RAG settings. Results show that integrating \textsc{EpiGraph} consistently improves performance across all tasks, with the largest gains observed in pharmacogenomic reasoning (+30--41\%). Our findings demonstrate that structured epilepsy knowledge substantially enhances evidence-grounded clinical reasoning and provides a practical benchmark framework for evaluating knowledge-augmented LLMs in real-world neurological settings. Our code is available at: https://github.com/LabRAI/EEG-KG.

Chufan Gao, Xulin Fan, Jimeng Sun et al.

Relation extraction aims to classify the relationships between two entities into pre-defined categories. While previous research has mainly focused on sentence-level relation extraction, recent studies have expanded the scope to document-level relation extraction. Traditional relation extraction methods heavily rely on human-annotated training data, which is time-consuming and labor-intensive. To mitigate the need for manual annotation, recent weakly-supervised approaches have been developed for sentence-level relation extraction while limited work has been done on document-level relation extraction. Weakly-supervised document-level relation extraction faces significant challenges due to an imbalanced number "no relation" instances and the failure of directly probing pretrained large language models for document relation extraction. To address these challenges, we propose PromptRE, a novel weakly-supervised document-level relation extraction method that combines prompting-based techniques with data programming. Furthermore, PromptRE incorporates the label distribution and entity types as prior knowledge to improve the performance. By leveraging the strengths of both prompting and data programming, PromptRE achieves improved performance in relation classification and effectively handles the "no relation" problem. Experimental results on ReDocRED, a benchmark dataset for document-level relation extraction, demonstrate the superiority of PromptRE over baseline approaches.

Pengcheng Xu, Tao Feng, Tianfan Fu et al.

In this work, we introduce a method to fine-tune a Transformer-based generative model for molecular de novo design. Leveraging the superior sequence learning capacity of Transformers over Recurrent Neural Networks (RNNs), our model can generate molecular structures with desired properties effectively. In contrast to the traditional RNN-based models, our proposed method exhibits superior performance in generating compounds predicted to be active against various biological targets, capturing long-term dependencies in the molecular structure sequence. The model's efficacy is demonstrated across numerous tasks, including generating analogues to a query structure and producing compounds with particular attributes, outperforming the baseline RNN-based methods. Our approach can be used for scaffold hopping, library expansion starting from a single molecule, and generating compounds with high predicted activity against biological targets.

Siddhartha Laghuvarapu, Zhen Lin, Jimeng Sun

In drug discovery, it is vital to confirm the predictions of pharmaceutical properties from computational models using costly wet-lab experiments. Hence, obtaining reliable uncertainty estimates is crucial for prioritizing drug molecules for subsequent experimental validation. Conformal Prediction (CP) is a promising tool for creating such prediction sets for molecular properties with a coverage guarantee. However, the exchangeability assumption of CP is often challenged with covariate shift in drug discovery tasks: Most datasets contain limited labeled data, which may not be representative of the vast chemical space from which molecules are drawn. To address this limitation, we propose a method called CoDrug that employs an energy-based model leveraging both training data and unlabelled data, and Kernel Density Estimation (KDE) to assess the densities of a molecule set. The estimated densities are then used to weigh the molecule samples while building prediction sets and rectifying for distribution shift. In extensive experiments involving realistic distribution drifts in various small-molecule drug discovery tasks, we demonstrate the ability of CoDrug to provide valid prediction sets and its utility in addressing the distribution shift arising from de novo drug design models. On average, using CoDrug can reduce the coverage gap by over 35% when compared to conformal prediction sets not adjusted for covariate shift.

Paul Landes, Pranav Herur, Adam Cross et al.

Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does not encode whether responses are grounded with respect to a reference. These issues limit the use of LLMs in domains where strict factual correctness is crucial, such as clinical decision support. Existing hallucination detection approaches improve factuality through retrieval augmentation, self-consistency, or claim verification, but generally do not learn directly over alignment topology. To leverage alignment topology as an inductive bias, we construct aligned bipartite graphs between reference information and LLM outputs and train a graph neural network (GNN) to model alignment structure using message passing. The method achieves state-of-the-art results on four diverse hallucination and question-answering datasets, outperforming all compared methods, including foundational LLMs such as GPT-4o.

Chufan Gao, Mandis Beigi, Afrah Shafquat et al.

Analyzing data from past clinical trials is part of the ongoing effort to optimize the design, implementation, and execution of new clinical trials and more efficiently bring life-saving interventions to market. While there have been recent advances in the generation of static context synthetic clinical trial data, due to both limited patient availability and constraints imposed by patient privacy needs, the generation of fine-grained synthetic time-sequential clinical trial data has been challenging. Given that patient trajectories over an entire clinical trial are of high importance for optimizing trial design and efforts to prevent harmful adverse events, there is a significant need for the generation of high-fidelity time-sequence clinical trial data. Here we introduce TrialSynth, a Variational Autoencoder (VAE) designed to address the specific challenges of generating synthetic time-sequence clinical trial data. Distinct from related clinical data VAE methods, the core of our method leverages Hawkes Processes (HP), which are particularly well-suited for modeling event-type and time gap prediction needed to capture the structure of sequential clinical trial data. Our experiments demonstrate that TrialSynth surpasses the performance of other comparable methods that can generate sequential clinical trial data at varying levels of fidelity / privacy tradeoff, enabling the generation of highly accurate event sequences across multiple real-world sequential event datasets with small patient source populations. Notably, our empirical findings highlight that TrialSynth not only outperforms existing clinical sequence-generating methods but also produces data with superior utility while empirically preserving patient privacy.

Haohui Jia, Zheng Chen, Lingwei Zhu et al.

Modeling neural population dynamics is crucial for foundational neuroscientific research and various clinical applications. Conventional latent variable methods typically model continuous brain dynamics through discretizing time with recurrent architecture, which necessarily results in compounded cumulative prediction errors and failure of capturing instantaneous, nonlinear characteristics of EEGs. We propose ODEBRAIN, a Neural ODE latent dynamic forecasting framework to overcome these challenges by integrating spatio-temporal-frequency features into spectral graph nodes, followed by a Neural ODE modeling the continuous latent dynamics. Our design ensures that latent representations can capture stochastic variations of complex brain states at any given time point. Extensive experiments verify that ODEBRAIN can improve significantly over existing methods in forecasting EEG dynamics with enhanced robustness and generalization capabilities.

Kaizhao Liang, Xu Cao, Kuei-Da Liao et al.

Disease progression simulation is a crucial area of research that has significant implications for clinical diagnosis, prognosis, and treatment. One major challenge in this field is the lack of continuous medical imaging monitoring of individual patients over time. To address this issue, we develop a novel framework termed Progressive Image Editing (PIE) that enables controlled manipulation of disease-related image features, facilitating precise and realistic disease progression simulation. Specifically, we leverage recent advancements in text-to-image generative models to simulate disease progression accurately and personalize it for each patient. We theoretically analyze the iterative refining process in our framework as a gradient descent with an exponentially decayed learning rate. To validate our framework, we conduct experiments in three medical imaging domains. Our results demonstrate the superiority of PIE over existing methods such as Stable Diffusion Walk and Style-Based Manifold Extrapolation based on CLIP score (Realism) and Disease Classification Confidence (Alignment). Our user study collected feedback from 35 veteran physicians to assess the generated progressions. Remarkably, 76.2% of the feedback agrees with the fidelity of the generated progressions. To our best knowledge, PIE is the first of its kind to generate disease progression images meeting real-world standards. It is a promising tool for medical research and clinical practice, potentially allowing healthcare providers to model disease trajectories over time, predict future treatment responses, and improve patient outcomes.

Hanyin Wang, Chufan Gao, Bolun Liu et al.

Proprietary Large Language Models (LLMs) such as GPT-4 and Gemini have demonstrated promising capabilities in clinical text summarization tasks. However, due to patient data privacy concerns and computational costs, many healthcare providers prefer using small, locally-hosted models over external generic LLMs. This study presents a comprehensive domain- and task-specific adaptation process for the open-source LLaMA-2 13 billion parameter model, enabling it to generate high-quality clinical notes from outpatient patient-doctor dialogues. Our process incorporates continued pretraining, supervised fine-tuning, and reinforcement learning from both AI and human feedback. We introduced a new approach, DistillDirect, for performing on-policy reinforcement learning with Gemini 1.0 Pro as the teacher model. Our resulting model, LLaMA-Clinic, can generate clinical notes comparable in quality to those authored by physicians. In a blinded physician reader study, the majority (92.8%) of individual evaluations rated the notes generated by LLaMA-Clinic as "acceptable" or higher across three criteria: real-world readiness, completeness, and accuracy. In the more challenging "Assessment and Plan" section, LLaMA-Clinic matched physician-authored notes in real-world readiness score. We highlight key considerations for future clinical note-generation tasks, emphasizing the importance of pre-defining a "best practice" note format, rather than relying on LLMs to determine this for clinical practice.

Trisha Das, Mandis Beigi, Jacob Aptekar et al.

Clinical trial amendments frequently introduce delays, increased costs, and administrative burden, with eligibility criteria being the most commonly amended component. We introduce \textit{eligibility criteria amendment prediction}, a novel NLP task that aims to forecast whether the eligibility criteria of an initial trial protocol will undergo future amendments. To support this task, we release $\texttt{AMEND++}$, a benchmark suite comprising two datasets: $\texttt{AMEND}$, which captures eligibility-criteria version histories and amendment labels from public clinical trials, and $\verb|AMEND_LLM|$, a refined subset curated using an LLM-based denoising pipeline to isolate substantive changes. We further propose $\textit{Change-Aware Masked Language Modeling}$ (CAMLM), a revision-aware pretraining strategy that leverages historical edits to learn amendment-sensitive representations. Experiments across diverse baselines show that CAMLM consistently improves amendment prediction, enabling more robust and cost-effective clinical trial design.

Pengcheng Jiang, Lang Cao, Ruike Zhu et al. · amazon-science

Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation (RAG) methods provide external information, the lack of explicit organization among retrieved passages limits their effectiveness, leading to brittle reasoning pathways. Recent interpretability studies highlighting the importance of structured intermediate reasoning further align with this perspective. We propose Retrieval-And-Structuring (RAS), a framework that dynamically constructs query-specific knowledge graphs through iterative retrieval and structured knowledge building. RAS interleaves targeted retrieval planning with incremental graph construction, enabling models to assemble and reason over evolving knowledge structures tailored to each query. On seven knowledge-intensive benchmarks, RAS consistently outperforms strong baselines, achieving up to 6.4% and 7.0% gains with open-source and proprietary LLMs, respectively. Our results demonstrate that dynamic, query-specific knowledge structuring offers a robust path to improving reasoning accuracy and robustness in language model generation. Our data and code can be found at https://github.com/pat-jj/RAS.