Peter Szolovits

Eric Lehman, Evan Hernandez, Diwakar Mahajan et al. · mit

Although recent advances in scaling large language models (LLMs) have resulted in improvements on many NLP tasks, it remains unclear whether these models trained primarily with general web text are the right tool in highly specialized, safety critical domains such as clinical text. Recent results have suggested that LLMs encode a surprising amount of medical knowledge. This raises an important question regarding the utility of smaller domain-specific language models. With the success of general-domain LLMs, is there still a need for specialized clinical models? To investigate this question, we conduct an extensive empirical analysis of 12 language models, ranging from 220M to 175B parameters, measuring their performance on 3 different clinical tasks that test their ability to parse and reason over electronic health records. As part of our experiments, we train T5-Base and T5-Large models from scratch on clinical notes from MIMIC III and IV to directly investigate the efficiency of clinical tokens. We show that relatively small specialized clinical models substantially outperform all in-context learning approaches, even when finetuned on limited annotated data. Further, we find that pretraining on clinical tokens allows for smaller, more parameter-efficient models that either match or outperform much larger language models trained on general text. We release the code and the models used under the PhysioNet Credentialed Health Data license and data use agreement.

Eric Lehman, Vladislav Lialin, Katelyn Y. Legaspi et al.

Existing question answering (QA) datasets derived from electronic health records (EHR) are artificially generated and consequently fail to capture realistic physician information needs. We present Discharge Summary Clinical Questions (DiSCQ), a newly curated question dataset composed of 2,000+ questions paired with the snippets of text (triggers) that prompted each question. The questions are generated by medical experts from 100+ MIMIC-III discharge summaries. We analyze this dataset to characterize the types of information sought by medical experts. We also train baseline models for trigger detection and question generation (QG), paired with unsupervised answer retrieval over EHRs. Our baseline model is able to generate high quality questions in over 62% of cases when prompted with human selected triggers. We release this dataset (and all code to reproduce baseline model results) to facilitate further research into realistic clinical QA and QG: https://github.com/elehman16/discq.

Matthew McDermott, Anand Dighe, Peter Szolovits et al. · harvard

Objective: Reflex testing protocols allow clinical laboratories to perform second line diagnostic tests on existing specimens based on the results of initially ordered tests. Reflex testing can support optimal clinical laboratory test ordering and diagnosis. In current clinical practice, reflex testing typically relies on simple "if-then" rules; however, this limits their scope since most test ordering decisions involve more complexity than a simple rule will allow. Here, using the analyte ferritin as an example, we propose an alternative machine learning-based approach to "smart" reflex testing with a wider scope and greater impact than traditional rule-based approaches. Methods: Using patient data, we developed a machine learning model to predict whether a patient getting CBC testing will also have ferritin testing ordered, consider applications of this model to "smart" reflex testing, and evaluate the model by comparing its performance to possible rule-based approaches. Results: Our underlying machine learning models performed moderately well in predicting ferritin test ordering and demonstrated greater suitability to reflex testing than rule-based approaches. Using chart review, we demonstrate that our model may improve ferritin test ordering. Finally, as a secondary goal, we demonstrate that ferritin test results are missing not at random (MNAR), a finding with implications for unbiased imputation of missing test results. Conclusions: Machine learning may provide a foundation for new types of reflex testing with enhanced benefits for clinical diagnosis and laboratory utilization management.

Elena Sergeeva, Anastasia Sergeeva, Huiyun Tang et al.

Previous research on expert advice-taking shows that humans exhibit two contradictory behaviors: on the one hand, people tend to overvalue their own opinions undervaluing the expert opinion, and on the other, people often defer to other people's advice even if the advice itself is rather obviously wrong. In our study, we conduct an exploratory evaluation of users' AI-advice accepting behavior when evaluating the truthfulness of a health-related statement in different "advice quality" settings. We find that even feedback that is confined to just stating that "the AI thinks that the statement is false/true" results in more than half of people moving their statement veracity assessment towards the AI suggestion. The different types of advice given influence the acceptance rates, but the sheer effect of getting a suggestion is often bigger than the suggestion-type effect.

Geeticka Chauhan, Ruizhi Liao, William Wells et al.

We propose and demonstrate a novel machine learning algorithm that assesses pulmonary edema severity from chest radiographs. While large publicly available datasets of chest radiographs and free-text radiology reports exist, only limited numerical edema severity labels can be extracted from radiology reports. This is a significant challenge in learning such models for image classification. To take advantage of the rich information present in the radiology reports, we develop a neural network model that is trained on both images and free-text to assess pulmonary edema severity from chest radiographs at inference time. Our experimental results suggest that the joint image-text representation learning improves the performance of pulmonary edema assessment compared to a supervised model trained on images only. We also show the use of the text for explaining the image classification by the joint model. To the best of our knowledge, our approach is the first to leverage free-text radiology reports for improving the image model performance in this application. Our code is available at https://github.com/RayRuizhiLiao/joint_chestxray.

Di Jin, Zhijing Jin, Joey Tianyi Zhou et al.

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness of these models by exposing the maliciously crafted adversarial examples. In this paper, we present TextFooler, a simple but strong baseline to generate natural adversarial text. By applying it to two fundamental natural language tasks, text classification and textual entailment, we successfully attacked three target models, including the powerful pre-trained BERT, and the widely used convolutional and recurrent neural networks. We demonstrate the advantages of this framework in three ways: (1) effective---it outperforms state-of-the-art attacks in terms of success rate and perturbation rate, (2) utility-preserving---it preserves semantic content and grammaticality, and remains correctly classified by humans, and (3) efficient---it generates adversarial text with computational complexity linear to the text length. *The code, pre-trained target models, and test examples are available at https://github.com/jind11/TextFooler.

Willie Boag, Elena Sergeeva, Saurabh Kulshreshtha et al.

Clinical notes often describe important aspects of a patient's stay and are therefore critical to medical research. Clinical concept extraction (CCE) of named entities - such as problems, tests, and treatments - aids in forming an understanding of notes and provides a foundation for many downstream clinical decision-making tasks. Historically, this task has been posed as a standard named entity recognition (NER) sequence tagging problem, and solved with feature-based methods using handengineered domain knowledge. Recent advances, however, have demonstrated the efficacy of LSTM-based models for NER tasks, including CCE. This work presents CliNER 2.0, a simple-to-install, open-source tool for extracting concepts from clinical text. CliNER 2.0 uses a word- and character- level LSTM model, and achieves state-of-the-art performance. For ease of use, the tool also includes pre-trained models available for public use.

Emily Alsentzer, Marie-Laure Charpignon, Bill Chen et al.

The 6th Annual Conference on Health, Inference, and Learning (CHIL 2025), hosted by the Association for Health Learning and Inference (AHLI), was held in person on June 25-27, 2025, at the University of California, Berkeley, in Berkeley, California, USA. As part of this year's program, we hosted Research Roundtables to catalyze collaborative, small-group dialogue around critical, timely topics at the intersection of machine learning and healthcare. Each roundtable was moderated by a team of senior and junior chairs who fostered open exchange, intellectual curiosity, and inclusive engagement. The sessions emphasized rigorous discussion of key challenges, exploration of emerging opportunities, and collective ideation toward actionable directions in the field. In total, eight roundtables were held by 19 roundtable chairs on topics of "Explainability, Interpretability, and Transparency," "Uncertainty, Bias, and Fairness," "Causality," "Domain Adaptation," "Foundation Models," "Learning from Small Medical Data," "Multimodal Methods," and "Scalable, Translational Healthcare Solutions."

Di Jin, Elena Sergeeva, Wei-Hung Weng et al.

The increasing availability of large collections of electronic health record (EHR) data and unprecedented technical advances in deep learning (DL) have sparked a surge of research interest in developing DL based clinical decision support systems for diagnosis, prognosis, and treatment. Despite the recognition of the value of deep learning in healthcare, impediments to further adoption in real healthcare settings remain due to the black-box nature of DL. Therefore, there is an emerging need for interpretable DL, which allows end users to evaluate the model decision making to know whether to accept or reject predictions and recommendations before an action is taken. In this review, we focus on the interpretability of the DL models in healthcare. We start by introducing the methods for interpretability in depth and comprehensively as a methodological reference for future researchers or clinical practitioners in this field. Besides the methods' details, we also include a discussion of advantages and disadvantages of these methods and which scenarios each of them is suitable for, so that interested readers can know how to compare and choose among them for use. Moreover, we discuss how these methods, originally developed for solving general-domain problems, have been adapted and applied to healthcare problems and how they can help physicians better understand these data-driven technologies. Overall, we hope this survey can help researchers and practitioners in both artificial intelligence (AI) and clinical fields understand what methods we have for enhancing the interpretability of their DL models and choose the optimal one accordingly.

Sijia Liu, Andrew Wen, Liwei Wang et al.

While we pay attention to the latest advances in clinical natural language processing (NLP), we can notice some resistance in the clinical and translational research community to adopt NLP models due to limited transparency, interpretability, and usability. In this study, we proposed an open natural language processing development framework. We evaluated it through the implementation of NLP algorithms for the National COVID Cohort Collaborative (N3C). Based on the interests in information extraction from COVID-19 related clinical notes, our work includes 1) an open data annotation process using COVID-19 signs and symptoms as the use case, 2) a community-driven ruleset composing platform, and 3) a synthetic text data generation workflow to generate texts for information extraction tasks without involving human subjects. The corpora were derived from texts from three different institutions (Mayo Clinic, University of Kentucky, University of Minnesota). The gold standard annotations were tested with a single institution's (Mayo) ruleset. This resulted in performances of 0.876, 0.706, and 0.694 in F-scores for Mayo, Minnesota, and Kentucky test datasets, respectively. The study as a consortium effort of the N3C NLP subgroup demonstrates the feasibility of creating a federated NLP algorithm development and benchmarking platform to enhance multi-institution clinical NLP study and adoption. Although we use COVID-19 as a use case in this effort, our framework is general enough to be applied to other domains of interest in clinical NLP.

Matthew B. A. McDermott, Brendan Yap, Peter Szolovits et al.

Language model pre-training and derived methods are incredibly impactful in machine learning. However, there remains considerable uncertainty on exactly why pre-training helps improve performance for fine-tuning tasks. This is especially true when attempting to adapt language-model pre-training to domains outside of natural language. Here, we analyze this problem by exploring how existing pre-training methods impose relational structure in their induced per-sample latent spaces -- i.e., what constraints do pre-training methods impose on the distance or geometry between the pre-trained embeddings of two samples $\vec x_i$ and $\vec x_j$. Through a comprehensive review of existing pre-training methods, we find that this question remains open. This is true despite theoretical analyses demonstrating the importance of understanding this form of induced structure. Based on this review, we introduce a descriptive framework for pre-training that allows for a granular, comprehensive understanding of how relational structure can be induced. We present a theoretical analysis of this framework from first principles and establish a connection between the relational inductive bias of pre-training and fine-tuning performance. We also show how to use the framework to define new pre-training methods. We build upon these findings with empirical studies on benchmarks spanning 3 data modalities and ten fine-tuning tasks. These experiments validate our theoretical analyses, inform the design of novel pre-training methods, and establish consistent improvements over a compelling suite of baseline methods.

Matthew B. A. McDermott, Brendan Yap, Harry Hsu et al.

Recent developments in Natural Language Processing (NLP) demonstrate that large-scale, self-supervised pre-training can be extremely beneficial for downstream tasks. These ideas have been adapted to other domains, including the analysis of the amino acid sequences of proteins. However, to date most attempts on protein sequences rely on direct masked language model style pre-training. In this work, we design a new, adversarial pre-training method for proteins, extending and specializing similar advances in NLP. We show compelling results in comparison to traditional MLM pre-training, though further development is needed to ensure the gains are worth the significant computational cost.

Di Jin, Eileen Pan, Nassim Oufattole et al.

Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively. We implement both rule-based and popular neural methods by sequentially combining a document retriever and a machine comprehension model. Through experiments, we find that even the current best method can only achieve 36.7\%, 42.0\%, and 70.1\% of test accuracy on the English, traditional Chinese, and simplified Chinese questions, respectively. We expect MedQA to present great challenges to existing OpenQA systems and hope that it can serve as a platform to promote much stronger OpenQA models from the NLP community in the future.

Matthew B. A. McDermott, Bret Nestor, Evan Kim et al.

Multi-task learning (MTL) is a machine learning technique aiming to improve model performance by leveraging information across many tasks. It has been used extensively on various data modalities, including electronic health record (EHR) data. However, despite significant use on EHR data, there has been little systematic investigation of the utility of MTL across the diverse set of possible tasks and training schemes of interest in healthcare. In this work, we examine MTL across a battery of tasks on EHR time-series data. We find that while MTL does suffer from common negative transfer, we can realize significant gains via MTL pre-training combined with single-task fine-tuning. We demonstrate that these gains can be achieved in a task-independent manner and offer not only minor improvements under traditional learning, but also notable gains in a few-shot learning context, thereby suggesting this could be a scalable vehicle to offer improved performance in important healthcare contexts.

So Yeon Min, Preethi Raghavan, Peter Szolovits

Knowledge Graphs (KG), composed of entities and relations, provide a structured representation of knowledge. For easy access to statistical approaches on relational data, multiple methods to embed a KG into f(KG) $\in$ R^d have been introduced. We propose TransINT, a novel and interpretable KG embedding method that isomorphically preserves the implication ordering among relations in the embedding space. Given implication rules, TransINT maps set of entities (tied by a relation) to continuous sets of vectors that are inclusion-ordered isomorphically to relation implications. With a novel parameter sharing scheme, TransINT enables automatic training on missing but implied facts without rule grounding. On a benchmark dataset, we outperform the best existing state-of-the-art rule integration embedding methods with significant margins in link Prediction and triple Classification. The angles between the continuous sets embedded by TransINT provide an interpretable way to mine semantic relatedness and implication rules among relations.

Matthew B. A. McDermott, Tzu Ming Harry Hsu, Wei-Hung Weng et al.

It is often infeasible or impossible to obtain ground truth labels for medical data. To circumvent this, one may build rule-based or other expert-knowledge driven labelers to ingest data and yield silver labels absent any ground-truth training data. One popular such labeler is CheXpert, a labeler that produces diagnostic labels for chest X-ray radiology reports. CheXpert is very useful, but is relatively computationally slow, especially when integrated with end-to-end neural pipelines, is non-differentiable so can't be used in any applications that require gradients to flow through the labeler, and does not yield probabilistic outputs, which limits our ability to improve the quality of the silver labeler through techniques such as active learning. In this work, we solve all three of these problems with $\texttt{CheXpert++}$, a BERT-based, high-fidelity approximation to CheXpert. $\texttt{CheXpert++}$ achieves 99.81\% parity with CheXpert, which means it can be reliably used as a drop-in replacement for CheXpert, all while being significantly faster, fully differentiable, and probabilistic in output. Error analysis of $\texttt{CheXpert++}$ also demonstrates that $\texttt{CheXpert++}$ has a tendency to actually correct errors in the CheXpert labels, with $\texttt{CheXpert++}$ labels being more often preferred by a clinician over CheXpert labels (when they disagree) on all but one disease task. To further demonstrate the utility of these advantages in this model, we conduct a proof-of-concept active learning study, demonstrating we can improve accuracy on an expert labeled random subset of report sentences by approximately 8\% over raw, unaltered CheXpert by using one-iteration of active-learning inspired re-training. These findings suggest that simple techniques in co-learning and active learning can yield high-quality labelers under minimal, and controllable human labeling demands.

Aaron Sonabend-W, Junwei Lu, Leo A. Celi et al.

Offline Reinforcement Learning (RL) is a promising approach for learning optimal policies in environments where direct exploration is expensive or unfeasible. However, the adoption of such policies in practice is often challenging, as they are hard to interpret within the application context, and lack measures of uncertainty for the learned policy value and its decisions. To overcome these issues, we propose an Expert-Supervised RL (ESRL) framework which uses uncertainty quantification for offline policy learning. In particular, we have three contributions: 1) the method can learn safe and optimal policies through hypothesis testing, 2) ESRL allows for different levels of risk averse implementations tailored to the application context, and finally, 3) we propose a way to interpret ESRL's policy at every state through posterior distributions, and use this framework to compute off-policy value function posteriors. We provide theoretical guarantees for our estimators and regret bounds consistent with Posterior Sampling for RL (PSRL). Sample efficiency of ESRL is independent of the chosen risk aversion threshold and quality of the behavior policy.

Bhanu Pratap Singh Rawat, Wei-Hung Weng, So Yeon Min et al.

We explore state-of-the-art neural models for question answering on electronic medical records and improve their ability to generalize better on previously unseen (paraphrased) questions at test time. We enable this by learning to predict logical forms as an auxiliary task along with the main task of answer span detection. The predicted logical forms also serve as a rationale for the answer. Further, we also incorporate medical entity information in these models via the ERNIE architecture. We train our models on the large-scale emrQA dataset and observe that our multi-task entity-enriched models generalize to paraphrased questions ~5% better than the baseline BERT model.

Di Jin, Zhijing Jin, Joey Tianyi Zhou et al.

Current summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure. We propose a new task, Stylistic Headline Generation (SHG), to enrich the headlines with three style options (humor, romance and clickbait), in order to attract more readers. With no style-specific article-headline pair (only a standard headline summarization dataset and mono-style corpora), our method TitleStylist generates style-specific headlines by combining the summarization and reconstruction tasks into a multitasking framework. We also introduced a novel parameter sharing scheme to further disentangle the style from the text. Through both automatic and human evaluation, we demonstrate that TitleStylist can generate relevant, fluent headlines with three target styles: humor, romance, and clickbait. The attraction score of our model generated headlines surpasses that of the state-of-the-art summarization model by 9.68%, and even outperforms human-written references.

Di Jin, Zhijing Jin, Joey Tianyi Zhou et al.

State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible in many cases, domain adaptation methods are needed. In this work, we propose a simple but effect approach to the semi-supervised domain adaptation scenario of NMT, where the aim is to improve the performance of a translation model on the target domain consisting of only non-parallel data with the help of supervised source domain data. This approach iteratively trains a Transformer-based NMT model via three training objectives: language modeling, back-translation, and supervised translation. We evaluate this method on two adaptation settings: adaptation between specific domains and adaptation from a general domain to specific domains, and on two language pairs: German to English and Romanian to English. With substantial performance improvement achieved---up to +19.31 BLEU over the strongest baseline, and +47.69 BLEU improvement over the unadapted model---we present this method as a simple but tough-to-beat baseline in the field of semi-supervised domain adaptation for NMT.

Wei-Hung Weng, Peter Szolovits

Information in electronic health records (EHR), such as clinical narratives, examination reports, lab measurements, demographics, and other patient encounter entries, can be transformed into appropriate data representations that can be used for downstream clinical machine learning tasks using representation learning. Learning better representations is critical to improve the performance of downstream tasks. Due to the advances in machine learning, we now can learn better and meaningful representations from EHR through disentangling the underlying factors inside data and distilling large amounts of information and knowledge from heterogeneous EHR sources. In this chapter, we first introduce the background of learning representations and reasons why we need good EHR representations in machine learning for medicine and healthcare in Section 1. Next, we explain the commonly-used machine learning and evaluation methods for representation learning using a deep learning approach in Section 2. Following that, we review recent related studies of learning patient state representation from EHR for clinical machine learning tasks in Section 3. Finally, in Section 4 we discuss more techniques, studies, and challenges for learning natural language representations when free texts, such as clinical notes, examination reports, or biomedical literature are used. We also discuss challenges and opportunities in these rapidly growing research fields.

Geeticka Chauhan, Matthew B. A. McDermott, Peter Szolovits

Systematic comparison of methods for relation extraction (RE) is difficult because many experiments in the field are not described precisely enough to be completely reproducible and many papers fail to report ablation studies that would highlight the relative contributions of their various combined techniques. In this work, we build a unifying framework for RE, applying this on three highly used datasets (from the general, biomedical and clinical domains) with the ability to be extendable to new datasets. By performing a systematic exploration of modeling, pre-processing and training methodologies, we find that choices of pre-processing are a large contributor performance and that omission of such information can further hinder fair comparison. Other insights from our exploration allow us to provide recommendations for future research in this area.

Guanxiong Liu, Tzu-Ming Harry Hsu, Matthew McDermott et al.

The automatic generation of radiology reports given medical radiographs has significant potential to operationally and improve clinical patient care. A number of prior works have focused on this problem, employing advanced methods from computer vision and natural language generation to produce readable reports. However, these works often fail to account for the particular nuances of the radiology domain, and, in particular, the critical importance of clinical accuracy in the resulting generated reports. In this work, we present a domain-aware automatic chest X-ray radiology report generation system which first predicts what topics will be discussed in the report, then conditionally generates sentences corresponding to these topics. The resulting system is fine-tuned using reinforcement learning, considering both readability and clinical accuracy, as assessed by the proposed Clinically Coherent Reward. We verify this system on two datasets, Open-I and MIMIC-CXR, and demonstrate that our model offers marked improvements on both language generation metrics and CheXpert assessed accuracy over a variety of competitive baselines.

Wei-Hung Weng, Yu-An Chung, Peter Szolovits

As patients' access to their doctors' clinical notes becomes common, translating professional, clinical jargon to layperson-understandable language is essential to improve patient-clinician communication. Such translation yields better clinical outcomes by enhancing patients' understanding of their own health conditions, and thus improving patients' involvement in their own care. Existing research has used dictionary-based word replacement or definition insertion to approach the need. However, these methods are limited by expert curation, which is hard to scale and has trouble generalizing to unseen datasets that do not share an overlapping vocabulary. In contrast, we approach the clinical word and sentence translation problem in a completely unsupervised manner. We show that a framework using representation learning, bilingual dictionary induction and statistical machine translation yields the best precision at 10 of 0.827 on professional-to-consumer word translation, and mean opinion scores of 4.10 and 4.28 out of 5 for clinical correctness and layperson readability, respectively, on sentence translation. Our fully-unsupervised strategy overcomes the curation problem, and the clinically meaningful evaluation reduces biases from inappropriate evaluators, which are critical in clinical machine learning.

Uma M. Girkar, Ryo Uchimido, Li-wei H. Lehman et al.

Determining whether hypotensive patients in intensive care units (ICUs) should receive fluid bolus therapy (FBT) has been an extremely challenging task for intensive care physicians as the corresponding increase in blood pressure has been hard to predict. Our study utilized regression models and attention-based recurrent neural network (RNN) algorithms and a multi-clinical information system large-scale database to build models that can predict the successful response to FBT among hypotensive patients in ICUs. We investigated both time-aggregated modeling using logistic regression algorithms with regularization and time-series modeling using the long short term memory network (LSTM) and the gated recurrent units network (GRU) with the attention mechanism for clinical interpretability. Among all modeling strategies, the stacked LSTM with the attention mechanism yielded the most predictable model with the highest accuracy of 0.852 and area under the curve (AUC) value of 0.925. The study results may help identify hypotensive patients in ICUs who will have sufficient blood pressure recovery after FBT.

Tzu-Ming Harry Hsu, Wei-Hung Weng, Willie Boag et al.

Joint embeddings between medical imaging modalities and associated radiology reports have the potential to offer significant benefits to the clinical community, ranging from cross-domain retrieval to conditional generation of reports to the broader goals of multimodal representation learning. In this work, we establish baseline joint embedding results measured via both local and global retrieval methods on the soon to be released MIMIC-CXR dataset consisting of both chest X-ray images and the associated radiology reports. We examine both supervised and unsupervised methods on this task and show that for document retrieval tasks with the learned representations, only a limited amount of supervision is needed to yield results comparable to those of fully-supervised methods.

Yuan Luo, Peter Szolovits

This paper presents a Lisp architecture for a portable NLP system, termed LAPNLP, for processing clinical notes. LAPNLP integrates multiple standard, customized and in-house developed NLP tools. Our system facilitates portability across different institutions and data systems by incorporating an enriched Common Data Model (CDM) to standardize necessary data elements. It utilizes UMLS to perform domain adaptation when integrating generic domain NLP tools. It also features stand-off annotations that are specified by positional reference to the original document. We built an interval tree based search engine to efficiently query and retrieve the stand-off annotations by specifying positional requirements. We also developed a utility to convert an inline annotation format to stand-off annotations to enable the reuse of clinical text datasets with inline annotations. We experimented with our system on several NLP facilitated tasks including computational phenotyping for lymphoma patients and semantic relation extraction for clinical notes. These experiments showcased the broader applicability and utility of LAPNLP.

Di Jin, Peter Szolovits

In evidence-based medicine (EBM), defining a clinical question in terms of the specific patient problem aids the physicians to efficiently identify appropriate resources and search for the best available evidence for medical treatment. In order to formulate a well-defined, focused clinical question, a framework called PICO is widely used, which identifies the sentences in a given medical text that belong to the four components typically reported in clinical trials: Participants/Problem (P), Intervention (I), Comparison (C) and Outcome (O). In this work, we propose a novel deep learning model for recognizing PICO elements in biomedical abstracts. Based on the previous state-of-the-art bidirectional long-short term memory (biLSTM) plus conditional random field (CRF) architecture, we add another layer of biLSTM upon the sentence representation vectors so that the contextual information from surrounding sentences can be gathered to help infer the interpretation of the current one. In addition, we propose two methods to further generalize and improve the model: adversarial training and unsupervised pre-training over large corpora. We tested our proposed approach over two benchmark datasets. One is the PubMed-PICO dataset, where our best results outperform the previous best by 5.5%, 7.9%, and 5.8% for P, I, and O elements in terms of F1 score, respectively. And for the other dataset named NICTA-PIBOSO, the improvements for P/I/O elements are 2.4%, 13.6%, and 1.0% in F1 score, respectively. Overall, our proposed deep learning model can obtain unprecedented PICO element detection accuracy while avoiding the need for any manual feature selection.

Di Jin, Peter Szolovits

Prevalent models based on artificial neural network (ANN) for sentence classification often classify sentences in isolation without considering the context in which sentences appear. This hampers the traditional sentence classification approaches to the problem of sequential sentence classification, where structured prediction is needed for better overall classification performance. In this work, we present a hierarchical sequential labeling network to make use of the contextual information within surrounding sentences to help classify the current sentence. Our model outperforms the state-of-the-art results by 2%-3% on two benchmarking datasets for sequential sentence classification in medical scientific abstracts.

Willie Boag, Harini Suresh, Leo Anthony Celi et al.

In this work, we characterize the doctor-patient relationship using a machine learning-derived trust score. We show that this score has statistically significant racial associations, and that by modeling trust directly we find stronger disparities in care than by stratifying on race. We further demonstrate that mistrust is indicative of worse outcomes, but is only weakly associated with physiologically-created severity scores. Finally, we describe sentiment analysis experiments indicating patients with higher levels of mistrust have worse experiences and interactions with their caregivers. This work is a step towards measuring fairer machine learning in the healthcare domain.

Wei-Hung Weng, Peter Szolovits

Mapping and translating professional but arcane clinical jargons to consumer language is essential to improve the patient-clinician communication. Researchers have used the existing biomedical ontologies and consumer health vocabulary dictionary to translate between the languages. However, such approaches are limited by expert efforts to manually build the dictionary, which is hard to be generalized and scalable. In this work, we utilized the embeddings alignment method for the word mapping between unparalleled clinical professional and consumer language embeddings. To map semantically similar words in two different word embeddings, we first independently trained word embeddings on both the corpus with abundant clinical professional terms and the other with mainly healthcare consumer terms. Then, we aligned the embeddings by the Procrustes algorithm. We also investigated the approach with the adversarial training with refinement. We evaluated the quality of the alignment through the similar words retrieval both by computing the model precision and as well as judging qualitatively by human. We show that the Procrustes algorithm can be performant for the professional consumer language embeddings alignment, whereas adversarial training with refinement may find some relations between two languages.

Willie Boag, Tristan Naumann, Peter Szolovits

Clinical notes often describe the most important aspects of a patient's physiology and are therefore critical to medical research. However, these notes are typically inaccessible to researchers without prior removal of sensitive protected health information (PHI), a natural language processing (NLP) task referred to as deidentification. Tools to automatically de-identify clinical notes are needed but are difficult to create without access to those very same notes containing PHI. This work presents a first step toward creating a large synthetically-identified corpus of clinical notes and corresponding PHI annotations in order to facilitate the development de-identification tools. Further, one such tool is evaluated against this corpus in order to understand the advantages and shortcomings of this approach.

Wei-Hung Weng, Mingwu Gao, Ze He et al.

Glycemic control is essential for critical care. However, it is a challenging task because there has been no study on personalized optimal strategies for glycemic control. This work aims to learn personalized optimal glycemic trajectories for severely ill septic patients by learning data-driven policies to identify optimal targeted blood glucose levels as a reference for clinicians. We encoded patient states using a sparse autoencoder and adopted a reinforcement learning paradigm using policy iteration to learn the optimal policy from data. We also estimated the expected return following the policy learned from the recorded glycemic trajectories, which yielded a function indicating the relationship between real blood glucose values and 90-day mortality rates. This suggests that the learned optimal policy could reduce the patients' estimated 90-day mortality rate by 6.3%, from 31% to 24.7%. The result demonstrates that reinforcement learning with appropriate patient state encoding can potentially provide optimal glycemic trajectories and allow clinicians to design a personalized strategy for glycemic control in septic patients.

Aniruddh Raghu, Matthieu Komorowski, Imran Ahmed et al.

Sepsis is a leading cause of mortality in intensive care units and costs hospitals billions annually. Treating a septic patient is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. In this work, we propose an approach to deduce treatment policies for septic patients by using continuous state-space models and deep reinforcement learning. Our model learns clinically interpretable treatment policies, similar in important aspects to the treatment policies of physicians. The learned policies could be used to aid intensive care clinicians in medical decision making and improve the likelihood of patient survival.

Harini Suresh, Nathan Hunt, Alistair Johnson et al.

Real-time prediction of clinical interventions remains a challenge within intensive care units (ICUs). This task is complicated by data sources that are noisy, sparse, heterogeneous and outcomes that are imbalanced. In this paper, we integrate data from all available ICU sources (vitals, labs, notes, demographics) and focus on learning rich representations of this data to predict onset and weaning of multiple invasive interventions. In particular, we compare both long short-term memory networks (LSTM) and convolutional neural networks (CNN) for prediction of five intervention tasks: invasive ventilation, non-invasive ventilation, vasopressors, colloid boluses, and crystalloid boluses. Our predictions are done in a forward-facing manner to enable "real-time" performance, and predictions are made with a six hour gap time to support clinically actionable planning. We achieve state-of-the-art results on our predictive tasks using deep architectures. We explore the use of feature occlusion to interpret LSTM models, and compare this to the interpretability gained from examining inputs that maximally activate CNN outputs. We show that our models are able to significantly outperform baselines in intervention prediction, and provide insight into model learning, which is crucial for the adoption of such models in practice.

Aniruddh Raghu, Matthieu Komorowski, Leo Anthony Celi et al.

Sepsis is a leading cause of mortality in intensive care units (ICUs) and costs hospitals billions annually. Treating a septic patient is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. Understanding more about a patient's physiological state at a given time could hold the key to effective treatment policies. In this work, we propose a new approach to deduce optimal treatment policies for septic patients by using continuous state-space models and deep reinforcement learning. Learning treatment policies over continuous spaces is important, because we retain more of the patient's physiological information. Our model is able to learn clinically interpretable treatment policies, similar in important aspects to the treatment policies of physicians. Evaluating our algorithm on past ICU patient data, we find that our model could reduce patient mortality in the hospital by up to 3.6% over observed clinical policies, from a baseline mortality of 13.7%. The learned treatment policies could be used to aid intensive care clinicians in medical decision making and improve the likelihood of patient survival.

Ji Young Lee, Franck Dernoncourt, Peter Szolovits

Recent approaches based on artificial neural networks (ANNs) have shown promising results for named-entity recognition (NER). In order to achieve high performances, ANNs need to be trained on a large labeled dataset. However, labels might be difficult to obtain for the dataset on which the user wants to perform NER: label scarcity is particularly pronounced for patient note de-identification, which is an instance of NER. In this work, we analyze to what extent transfer learning may address this issue. In particular, we demonstrate that transferring an ANN model trained on a large labeled dataset to another dataset with a limited number of labels improves upon the state-of-the-art results on two different datasets for patient note de-identification.

Franck Dernoncourt, Ji Young Lee, Peter Szolovits

Named-entity recognition (NER) aims at identifying entities of interest in a text. Artificial neural networks (ANNs) have recently been shown to outperform existing NER systems. However, ANNs remain challenging to use for non-expert users. In this paper, we present NeuroNER, an easy-to-use named-entity recognition tool based on ANNs. Users can annotate entities using a graphical web-based user interface (BRAT): the annotations are then used to train an ANN, which in turn predict entities' locations and categories in new texts. NeuroNER makes this annotation-training-prediction flow smooth and accessible to anyone.

Ji Young Lee, Franck Dernoncourt, Peter Szolovits

Over 50 million scholarly articles have been published: they constitute a unique repository of knowledge. In particular, one may infer from them relations between scientific concepts, such as synonyms and hyponyms. Artificial neural networks have been recently explored for relation extraction. In this work, we continue this line of work and present a system based on a convolutional neural network to extract relations. Our model ranked first in the SemEval-2017 task 10 (ScienceIE) for relation extraction in scientific articles (subtask C).

Harini Suresh, Peter Szolovits, Marzyeh Ghassemi

We use autoencoders to create low-dimensional embeddings of underlying patient phenotypes that we hypothesize are a governing factor in determining how different patients will react to different interventions. We compare the performance of autoencoders that take fixed length sequences of concatenated timesteps as input with a recurrent sequence-to-sequence autoencoder. We evaluate our methods on around 35,500 patients from the latest MIMIC III dataset from Beth Israel Deaconess Hospital.

Franck Dernoncourt, Ji Young Lee, Peter Szolovits

Existing models based on artificial neural networks (ANNs) for sentence classification often do not incorporate the context in which sentences appear, and classify sentences individually. However, traditional sentence classification approaches have been shown to greatly benefit from jointly classifying subsequent sentences, such as with conditional random fields. In this work, we present an ANN architecture that combines the effectiveness of typical ANN models to classify sentences in isolation, with the strength of structured prediction. Our model achieves state-of-the-art results on two different datasets for sequential sentence classification in medical abstracts.

Ji Young Lee, Franck Dernoncourt, Ozlem Uzuner et al.

Patient notes contain a wealth of information of potentially great interest to medical investigators. However, to protect patients' privacy, Protected Health Information (PHI) must be removed from the patient notes before they can be legally released, a process known as patient note de-identification. The main objective for a de-identification system is to have the highest possible recall. Recently, the first neural-network-based de-identification system has been proposed, yielding state-of-the-art results. Unlike other systems, it does not rely on human-engineered features, which allows it to be quickly deployed, but does not leverage knowledge from human experts or from electronic health records (EHRs). In this work, we explore a method to incorporate human-engineered features as well as features derived from EHRs to a neural-network-based de-identification system. Our results show that the addition of features, especially the EHR-derived features, further improves the state-of-the-art in patient note de-identification, including for some of the most sensitive PHI types such as patient names. Since in a real-life setting patient notes typically come with EHRs, we recommend developers of de-identification systems to leverage the information EHRs contain.

Franck Dernoncourt, Ji Young Lee, Ozlem Uzuner et al.

Objective: Patient notes in electronic health records (EHRs) may contain critical information for medical investigations. However, the vast majority of medical investigators can only access de-identified notes, in order to protect the confidentiality of patients. In the United States, the Health Insurance Portability and Accountability Act (HIPAA) defines 18 types of protected health information (PHI) that needs to be removed to de-identify patient notes. Manual de-identification is impractical given the size of EHR databases, the limited number of researchers with access to the non-de-identified notes, and the frequent mistakes of human annotators. A reliable automated de-identification system would consequently be of high value. Materials and Methods: We introduce the first de-identification system based on artificial neural networks (ANNs), which requires no handcrafted features or rules, unlike existing systems. We compare the performance of the system with state-of-the-art systems on two datasets: the i2b2 2014 de-identification challenge dataset, which is the largest publicly available de-identification dataset, and the MIMIC de-identification dataset, which we assembled and is twice as large as the i2b2 2014 dataset. Results: Our ANN model outperforms the state-of-the-art systems. It yields an F1-score of 97.85 on the i2b2 2014 dataset, with a recall 97.38 and a precision of 97.32, and an F1-score of 99.23 on the MIMIC de-identification dataset, with a recall 99.25 and a precision of 99.06. Conclusion: Our findings support the use of ANNs for de-identification of patient notes, as they show better performance than previously published systems while requiring no feature engineering.

Ross D. Shachter, Stig K. Andersen, Peter Szolovits

In this paper we propose a new approach to probabilistic inference on belief networks, global conditioning, which is a simple generalization of Pearl's (1986b) method of loopcutset conditioning. We show that global conditioning, as well as loop-cutset conditioning, can be thought of as a special case of the method of Lauritzen and Spiegelhalter (1988) as refined by Jensen et al (199Oa; 1990b). Nonetheless, this approach provides new opportunities for parallel processing and, in the case of sequential processing, a tradeoff of time for memory. We also show how a hybrid method (Suermondt and others 1990) combining loop-cutset conditioning with Jensen's method can be viewed within our framework. By exploring the relationships between these methods, we develop a unifying framework in which the advantages of each approach can be combined successfully.