Rishikesan Kamaleswaran

Yanbo Xu, Alind Khare, Glenn Matlin et al. · gatech

Machine Learning (ML) research has focused on maximizing the accuracy of predictive tasks. ML models, however, are increasingly more complex, resource intensive, and costlier to deploy in resource-constrained environments. These issues are exacerbated for prediction tasks with sequential classification on progressively transitioned stages with ''happens-before'' relation between them.We argue that it is possible to ''unfold'' a monolithic single multi-class classifier, typically trained for all stages using all data, into a series of single-stage classifiers. Each single-stage classifier can be cascaded gradually from cheaper to more expensive binary classifiers that are trained using only the necessary data modalities or features required for that stage. UnfoldML is a cost-aware and uncertainty-based dynamic 2D prediction pipeline for multi-stage classification that enables (1) navigation of the accuracy/cost tradeoff space, (2) reducing the spatio-temporal cost of inference by orders of magnitude, and (3) early prediction on proceeding stages. UnfoldML achieves orders of magnitude better cost in clinical settings, while detecting multi-stage disease development in real time. It achieves within 0.1% accuracy from the highest-performing multi-class baseline, while saving close to 20X on spatio-temporal cost of inference and earlier (3.5hrs) disease onset prediction. We also show that UnfoldML generalizes to image classification, where it can predict different level of labels (from coarse to fine) given different level of abstractions of a image, saving close to 5X cost with as little as 0.4% accuracy reduction.

Alireza Rafiei, Ronald Moore, Sina Jahromi et al.

As a subset of machine learning, meta-learning, or learning to learn, aims at improving the model's capabilities by employing prior knowledge and experience. A meta-learning paradigm can appropriately tackle the conventional challenges of traditional learning approaches, such as insufficient number of samples, domain shifts, and generalization. These unique characteristics position meta-learning as a suitable choice for developing influential solutions in various healthcare contexts, where the available data is often insufficient, and the data collection methodologies are different. This survey discusses meta-learning broad applications in the healthcare domain to provide insight into how and where it can address critical healthcare challenges. We first describe the theoretical foundations and pivotal methods of meta-learning. We then divide the employed meta-learning approaches in the healthcare domain into two main categories of multi/single-task learning and many/few-shot learning and survey the studies. Finally, we highlight the current challenges in meta-learning research, discuss the potential solutions, and provide future perspectives on meta-learning in healthcare.

Song Wei, Yao Xie, Christopher S. Josef et al.

We present a generalized linear structural causal model, coupled with a novel data-adaptive linear regularization, to recover causal directed acyclic graphs (DAGs) from time series. By leveraging a recently developed stochastic monotone Variational Inequality (VI) formulation, we cast the causal discovery problem as a general convex optimization. Furthermore, we develop a non-asymptotic recovery guarantee and quantifiable uncertainty by solving a linear program to establish confidence intervals for a wide range of non-linear monotone link functions. We validate our theoretical results and show the competitive performance of our method via extensive numerical experiments. Most importantly, we demonstrate the effectiveness of our approach in recovering highly interpretable causal DAGs over Sepsis Associated Derangements (SADs) while achieving comparable prediction performance to powerful ``black-box'' models such as XGBoost. Thus, the future adoption of our proposed method to conduct continuous surveillance of high-risk patients by clinicians is much more likely.

Mehak Arora, Hassan Mortagy, Nathan Dwarshuis et al.

The objective of this work is to develop an Electronic Medical Record (EMR) data processing tool that confers clinical context to Machine Learning (ML) algorithms for error handling, bias mitigation and interpretability. We present Trust-MAPS, an algorithm that translates clinical domain knowledge into high-dimensional, mixed-integer programming models that capture physiological and biological constraints on clinical measurements. EMR data is projected onto this constrained space, effectively bringing outliers to fall within a physiologically feasible range. We then compute the distance of each data point from the constrained space modeling healthy physiology to quantify deviation from the norm. These distances, termed "trust-scores," are integrated into the feature space for downstream ML applications. We demonstrate the utility of Trust-MAPS by training a binary classifier for early sepsis prediction on data from the 2019 PhysioNet Computing in Cardiology Challenge, using the XGBoost algorithm and applying SMOTE for overcoming class-imbalance. The Trust-MAPS framework shows desirable behavior in handling potential errors and boosting predictive performance. We achieve an AUROC of 0.91 (0.89, 0.92 : 95% CI) for predicting sepsis 6 hours before onset - a marked 15% improvement over a baseline model trained without Trust-MAPS. Trust-scores emerge as clinically meaningful features that not only boost predictive performance for clinical decision support tasks, but also lend interpretability to ML models. This work is the first to translate clinical domain knowledge into mathematical constraints, model cross-vital dependencies, and identify aberrations in high-dimensional medical data. Our method allows for error handling in EMR, and confers interpretability and superior predictive power to models trained for clinical decision support.

Ronald Moore, Rishikesan Kamaleswaran

Sepsis is a deadly condition affecting many patients in the hospital. Recent studies have shown that patients diagnosed with sepsis have significant mortality and morbidity, resulting from the body's dysfunctional host response to infection. Clinicians often rely on the use of Sequential Organ Failure Assessment (SOFA), Systemic Inflammatory Response Syndrome (SIRS), and the Modified Early Warning Score (MEWS) to identify early signs of clinical deterioration requiring further work-up and treatment. However, many of these tools are manually computed and were not designed for automated computation. There have been different methods used for developing sepsis onset models, but many of these models must be trained on a sufficient number of patient observations in order to form accurate sepsis predictions. Additionally, the accurate annotation of patients with sepsis is a major ongoing challenge. In this paper, we propose the use of Active Learning Recurrent Neural Networks (ALRts) for short temporal horizons to improve the prediction of irregularly sampled temporal events such as sepsis. We show that an active learning RNN model trained on limited data can form robust sepsis predictions comparable to models using the entire training dataset.

Yixuan Yang, Mehak Arora, Ryan Zhang et al.

We present Clin-JEPA, a multi-phase co-training framework for joint-embedding predictive (JEPA) pretraining on EHR patient trajectories. JEPA architectures have enabled latent-space planning in robotics and high-quality representation learning in vision, but extending the paradigm to EHR data -- to obtain a single backbone that simultaneously forecasts patient trajectories and serves diverse downstream risk-prediction tasks without per-task fine-tuning -- remains an open challenge. Existing JEPA frameworks either discard the predictor after pretraining (I-JEPA, V-JEPA) or train it on a frozen pretrained encoder (V-JEPA 2-AC), leaving the encoder unaware of the rollout signal that the retained predictor must use at inference; co-training the encoder and predictor under a shared JEPA prediction objective would supply this grounding, but naïve co-training is unstable, with representation collapse and online/target drift causing autoregressive rollout to diverge. Clin-JEPA's five-phase pretraining curriculum -- predictor warmup, joint refinement, EMA target alignment, hard sync, and predictor finalization -- addresses each failure mode by phase, stably co-training a Qwen3-8B-based encoder and a 92M-parameter latent trajectory predictor. On MIMIC-IV ICU data, three independent evaluations support the framework: (1) latent $\ell_1$ rollout drift uniquely converges ($-$15.7%) over 48-hour horizons while baselines and ablations diverge (+3% to +4951%); (2) the encoder learns a clinically discriminative latent geometry (deteriorating-patient cohorts displace 4.83$\times$ further than stable patients in latent space, vs $\leq$2.62$\times$ for baseline encoders); (3) a single backbone outperforms strong tabular and sequence baselines on multi-task downstream evaluation. Clin-JEPA achieves mean AUROC 0.851 on ICareFM EEP and 0.883 on 8 binary risk tasks (+0.038 and +0.041 vs baseline average).

Kunyu Yu, Rui Yang, Jingchi Liao et al.

Foundation models have emerged as a powerful approach for processing electronic health records (EHRs), offering flexibility to handle diverse medical data modalities. In this study, we present a comprehensive benchmark that evaluates the performance, fairness, and interpretability of foundation models, both as unimodal encoders and as multimodal learners, using the publicly available MIMIC-IV database. To support consistent and reproducible evaluation, we developed a standardized data processing pipeline that harmonizes heterogeneous clinical records into an analysis-ready format. We systematically compared eight foundation models, encompassing both unimodal and multimodal models, as well as domain-specific and general-purpose variants. Our findings demonstrate that incorporating multiple data modalities leads to consistent improvements in predictive performance without introducing additional bias. Through this benchmark, we aim to support the development of effective and trustworthy multimodal artificial intelligence (AI) systems for real-world clinical applications. Our code is available at https://github.com/nliulab/MIMIC-Multimodal.

Alireza Rafiei, Ronald Moore, Tilendra Choudhary et al.

Objective: Blood transfusions, crucial in managing anemia and coagulopathy in ICU settings, require accurate prediction for effective resource allocation and patient risk assessment. However, existing clinical decision support systems have primarily targeted a particular patient demographic with unique medical conditions and focused on a single type of blood transfusion. This study aims to develop an advanced machine learning-based model to predict the probability of transfusion necessity over the next 24 hours for a diverse range of non-traumatic ICU patients. Methods: We conducted a retrospective cohort study on 72,072 adult non-traumatic ICU patients admitted to a high-volume US metropolitan academic hospital between 2016 and 2020. We developed a meta-learner and various machine learning models to serve as predictors, training them annually with four-year data and evaluating on the fifth, unseen year, iteratively over five years. Results: The experimental results revealed that the meta-model surpasses the other models in different development scenarios. It achieved notable performance metrics, including an Area Under the Receiver Operating Characteristic (AUROC) curve of 0.97, an accuracy rate of 0.93, and an F1-score of 0.89 in the best scenario. Conclusion: This study pioneers the use of machine learning models for predicting blood transfusion needs in a diverse cohort of critically ill patients. The findings of this evaluation confirm that our model not only predicts transfusion requirements effectively but also identifies key biomarkers for making transfusion decisions.

Jeffrey Smith, Andre Holder, Rishikesan Kamaleswaran et al.

With the growing prevalence of machine learning and artificial intelligence-based medical decision support systems, it is equally important to ensure that these systems provide patient outcomes in a fair and equitable fashion. This paper presents an innovative framework for detecting areas of algorithmic bias in medical-AI decision support systems. Our approach efficiently identifies potential biases in medical-AI models, specifically in the context of sepsis prediction, by employing the Classification and Regression Trees (CART) algorithm with conformity scores. We verify our methodology by conducting a series of synthetic data experiments, showcasing its ability to estimate areas of bias in controlled settings precisely. The effectiveness of the concept is further validated by experiments using electronic medical records from Grady Memorial Hospital in Atlanta, Georgia. These tests demonstrate the practical implementation of our strategy in a clinical environment, where it can function as a vital instrument for guaranteeing fairness and equity in AI-based medical decisions.

Mahmoud Alwakeel, Aditya Nagori, Vijay Krishnamoorthy et al.

Objectives: To evaluate the current limitations of large language models (LLMs) in medical question answering, focusing on the quality of datasets used for their evaluation. Materials and Methods: Widely-used benchmark datasets, including MedQA, MedMCQA, PubMedQA, and MMLU, were reviewed for their rigor, transparency, and relevance to clinical scenarios. Alternatives, such as challenge questions in medical journals, were also analyzed to identify their potential as unbiased evaluation tools. Results: Most existing datasets lack clinical realism, transparency, and robust validation processes. Publicly available challenge questions offer some benefits but are limited by their small size, narrow scope, and exposure to LLM training. These gaps highlight the need for secure, comprehensive, and representative datasets. Conclusion: A standardized framework is critical for evaluating LLMs in medicine. Collaborative efforts among institutions and policymakers are needed to ensure datasets and methodologies are rigorous, unbiased, and reflective of clinical complexities.

Anni Zhou, Raheem Beyah, Rishikesan Kamaleswaran

In critical care settings, timely and accurate predictions can significantly impact patient outcomes, especially for conditions like sepsis, where early intervention is crucial. We aim to model patient-specific reward functions in a contextual multi-armed bandit setting. The goal is to leverage patient-specific clinical features to optimize decision-making under uncertainty. This paper proposes NeuroSep-CP-LCB, a novel integration of neural networks with contextual bandits and conformal prediction tailored for early sepsis detection. Unlike the algorithm pool selection problem in the previous paper, where the primary focus was identifying the most suitable pre-trained model for prediction tasks, this work directly models the reward function using a neural network, allowing for personalized and adaptive decision-making. Combining the representational power of neural networks with the robustness of conformal prediction intervals, this framework explicitly accounts for uncertainty in offline data distributions and provides actionable confidence bounds on predictions.

Anni Zhou, Beyah Raheem, Rishikesan Kamaleswaran et al.

Sepsis is a life-threatening syndrome with high morbidity and mortality in hospitals. Early prediction of sepsis plays a crucial role in facilitating early interventions for septic patients. However, early sepsis prediction systems with uncertainty quantification and adaptive learning are scarce. This paper proposes Sepsyn-OLCP, a novel online learning algorithm for early sepsis prediction by integrating conformal prediction for uncertainty quantification and Bayesian bandits for adaptive decision-making. By combining the robustness of Bayesian models with the statistical uncertainty guarantees of conformal prediction methodologies, this algorithm delivers accurate and trustworthy predictions, addressing the critical need for reliable and adaptive systems in high-stakes healthcare applications such as early sepsis prediction. We evaluate the performance of Sepsyn-OLCP in terms of regret in stochastic bandit setting, the area under the receiver operating characteristic curve (AUROC), and F-measure. Our results show that Sepsyn-OLCP outperforms existing individual models, increasing AUROC of a neural network from 0.64 to 0.73 without retraining and high computational costs. And the model selection policy converges to the optimal strategy in the long run. We propose a novel reinforcement learning-based framework integrated with conformal prediction techniques to provide uncertainty quantification for early sepsis prediction. The proposed methodology delivers accurate and trustworthy predictions, addressing a critical need in high-stakes healthcare applications like early sepsis prediction.

Seibi Kobara, Alireza Rafiei, Masoud Nateghi et al.

Breast cancer is a significant public health concern and is the leading cause of cancer-related deaths among women. Despite advances in breast cancer treatments, medication non-adherence remains a major problem. As electronic health records do not typically capture patient-reported outcomes that may reveal information about medication-related experiences, social media presents an attractive resource for enhancing our understanding of the patients' treatment experiences. In this paper, we developed natural language processing (NLP) based methodologies to study information posted by an automatically curated breast cancer cohort from social media. We employed a transformer-based classifier to identify breast cancer patients/survivors on X (Twitter) based on their self-reported information, and we collected longitudinal data from their profiles. We then designed a multi-layer rule-based model to develop a breast cancer therapy-associated side effect lexicon and detect patterns of medication usage and associated side effects among breast cancer patients. 1,454,637 posts were available from 583,962 unique users, of which 62,042 were detected as breast cancer members using our transformer-based model. 198 cohort members mentioned breast cancer medications with tamoxifen as the most common. Our side effect lexicon identified well-known side effects of hormone and chemotherapy. Furthermore, it discovered a subject feeling towards cancer and medications, which may suggest a pre-clinical phase of side effects or emotional distress. This analysis highlighted not only the utility of NLP techniques in unstructured social media data to identify self-reported breast cancer posts, medication usage patterns, and treatment side effects but also the richness of social data on such clinical questions.

Kaiyuan Wu, Aditya Nagori, Rishikesan Kamaleswaran

Objective: Large language models (LLMs) show promise for clinical discharge planning, but their use is constrained by hallucination, omissions, and miscalibrated confidence. We introduce a self-improving, cache-optional Planner-Auditor framework that improves safety and reliability by decoupling generation from deterministic validation and targeted replay. Materials and Methods: We implemented an agentic, retrospective, FHIR-native evaluation pipeline using MIMIC-IV-on-FHIR. For each patient, the Planner (LLM) generates a structured discharge action plan with an explicit confidence estimate. The Auditor is a deterministic module that evaluates multi-task coverage, tracks calibration (Brier score, ECE proxies), and monitors action-distribution drift. The framework supports two-tier self-improvement: (i) within-episode regeneration when enabled, and (ii) cross-episode discrepancy buffering with replay for high-confidence, low-coverage cases. Results: While context caching improved performance over baseline, the self-improvement loop was the primary driver of gains, increasing task coverage from 32% to 86%. Calibration improved substantially, with reduced Brier/ECE and fewer high-confidence misses. Discrepancy buffering further corrected persistent high-confidence omissions during replay. Discussion: Feedback-driven regeneration and targeted replay act as effective control mechanisms to reduce omissions and improve confidence reliability in structured clinical planning. Separating an LLM Planner from a rule-based, observational Auditor enables systematic reliability measurement and safer iteration without model retraining. Conclusion: The Planner-Auditor framework offers a practical pathway toward safer automated discharge planning using interoperable FHIR data access and deterministic auditing, supported by reproducible ablations and reliability-focused evaluation.

Mahmoud Alwakeel, Aditya Nagori, An-Kwok Ian Wong et al.

Large Language Models have been tested on medical student-level questions, but their performance in specialized fields like Critical Care Medicine (CCM) is less explored. This study evaluated Meta-Llama 3.1 models (8B and 70B parameters) on 871 CCM questions. Llama3.1:70B outperformed 8B by 30%, with 60% average accuracy. Performance varied across domains, highest in Research (68.4%) and lowest in Renal (47.9%), highlighting the need for broader future work to improve models across various subspecialty domains.

Aditya Nagori, Ricardo Accorsi Casonatto, Ayush Gautam et al.

The surge in scientific publications challenges traditional review methods, demanding tools that integrate structured metadata with full-text analysis. Hybrid Retrieval Augmented Generation (RAG) systems, combining graph queries with vector search offer promise but are typically static, rely on proprietary tools, and lack uncertainty estimates. We present an agentic approach that encapsulates the hybrid RAG pipeline within an autonomous agent capable of (1) dynamically selecting between GraphRAG and VectorRAG for each query, (2) adapting instruction-tuned generation in real time to researcher needs, and (3) quantifying uncertainty during inference. This dynamic orchestration improves relevance, reduces hallucinations, and promotes reproducibility. Our pipeline ingests bibliometric open-access data from PubMed, arXiv, and Google Scholar APIs, builds a Neo4j citation-based knowledge graph (KG), and embeds full-text PDFs into a FAISS vector store (VS) using the all-MiniLM-L6-v2 model. A Llama-3.3-70B agent selects GraphRAG (translating queries to Cypher for KG) or VectorRAG (combining sparse and dense retrieval with re-ranking). Instruction tuning refines domain-specific generation, and bootstrapped evaluation yields standard deviation for evaluation metrics. On synthetic benchmarks mimicking real-world queries, the Instruction-Tuned Agent with Direct Preference Optimization (DPO) outperforms the baseline, achieving a gain of 0.63 in VS Context Recall and a 0.56 gain in overall Context Precision. Additional gains include 0.24 in VS Faithfulness, 0.12 in both VS Precision and KG Answer Relevance, 0.11 in overall Faithfulness score, 0.05 in KG Context Recall, and 0.04 in both VS Answer Relevance and overall Precision. These results highlight the system's improved reasoning over heterogeneous sources and establish a scalable framework for autonomous, agentic scientific discovery.

Mehak Arora, Ayman Ali, Kaiyuan Wu et al.

In intensive care units (ICUs), patients with complex clinical conditions require vigilant monitoring and prompt interventions. Chest X-rays (CXRs) are a vital diagnostic tool, providing insights into clinical trajectories, but their irregular acquisition limits their utility. Existing tools for CXR interpretation are constrained by cross-sectional analysis, failing to capture temporal dynamics. To address this, we introduce CXR-TFT, a novel multi-modal framework that integrates temporally sparse CXR imaging and radiology reports with high-frequency clinical data, such as vital signs, laboratory values, and respiratory flow sheets, to predict the trajectory of CXR findings in critically ill patients. CXR-TFT leverages latent embeddings from a vision encoder that are temporally aligned with hourly clinical data through interpolation. A transformer model is then trained to predict CXR embeddings at each hour, conditioned on previous embeddings and clinical measurements. In a retrospective study of 20,000 ICU patients, CXR-TFT demonstrated high accuracy in forecasting abnormal CXR findings up to 12 hours before they became radiographically evident. This predictive capability in clinical data holds significant potential for enhancing the management of time-sensitive conditions like acute respiratory distress syndrome, where early intervention is crucial and diagnoses are often delayed. By providing distinctive temporal resolution in prognostic CXR analysis, CXR-TFT offers actionable 'whole patient' insights that can directly improve clinical outcomes.

Aditya Nagori, Ayush Gautam, Matthew O. Wiens et al.

Clustering patient subgroups is essential for personalized care and efficient resource use. Traditional clustering methods struggle with high-dimensional, heterogeneous healthcare data and lack contextual understanding. This study evaluates Large Language Model (LLM) based clustering against classical methods using a pediatric sepsis dataset from a low-income country (LIC), containing 2,686 records with 28 numerical and 119 categorical variables. Patient records were serialized into text with and without a clustering objective. Embeddings were generated using quantized LLAMA 3.1 8B, DeepSeek-R1-Distill-Llama-8B with low-rank adaptation(LoRA), and Stella-En-400M-V5 models. K-means clustering was applied to these embeddings. Classical comparisons included K-Medoids clustering on UMAP and FAMD-reduced mixed data. Silhouette scores and statistical tests evaluated cluster quality and distinctiveness. Stella-En-400M-V5 achieved the highest Silhouette Score (0.86). LLAMA 3.1 8B with the clustering objective performed better with higher number of clusters, identifying subgroups with distinct nutritional, clinical, and socioeconomic profiles. LLM-based methods outperformed classical techniques by capturing richer context and prioritizing key features. These results highlight potential of LLMs for contextual phenotyping and informed decision-making in resource-limited settings.

Alan Wu, Tilendra Choudhary, Pulakesh Upadhyaya et al.

Sepsis-induced acute respiratory failure (ARF) is a serious complication with a poor prognosis. This paper presents a deep representation learningbased phenotyping method to identify distinct groups of clinical trajectories of septic patients with ARF. For this retrospective study, we created a dataset from electronic medical records (EMR) consisting of data from sepsis patients admitted to medical intensive care units who required at least 24 hours of invasive mechanical ventilation at a quarternary care academic hospital in southeast USA for the years 2016-2021. A total of N=3349 patient encounters were included in this study. Clustering Representation Learning on Incomplete Time Series Data (CRLI) algorithm was applied to a parsimonious set of EMR variables in this data set. To validate the optimal number of clusters, the K-means algorithm was used in conjunction with dynamic time warping. Our model yielded four distinct patient phenotypes that were characterized as liver dysfunction/heterogeneous, hypercapnia, hypoxemia, and multiple organ dysfunction syndrome by a critical care expert. A Kaplan-Meier analysis to compare the 28-day mortality trends exhibited significant differences (p < 0.005) between the four phenotypes. The study demonstrates the utility of our deep representation learning-based approach in unraveling phenotypes that reflect the heterogeneity in sepsis-induced ARF in terms of different mortality outcomes and severity. These phenotypes might reveal important clinical insights into an effective prognosis and tailored treatment strategies.

Song Wei, Hanyu Zhang, Ronald Moore et al.

We present a Transfer Causal Learning (TCL) framework when target and source domains share the same covariate/feature spaces, aiming to improve causal effect estimation accuracy in limited data. Limited data is very common in medical applications, where some rare medical conditions, such as sepsis, are of interest. Our proposed method, named \texttt{$\ell_1$-TCL}, incorporates $\ell_1$ regularized TL for nuisance models (e.g., propensity score model); the TL estimator of the nuisance parameters is plugged into downstream average causal/treatment effect estimators (e.g., inverse probability weighted estimator). We establish non-asymptotic recovery guarantees for the \texttt{$\ell_1$-TCL} with generalized linear model (GLM) under the sparsity assumption in the high-dimensional setting, and demonstrate the empirical benefits of \texttt{$\ell_1$-TCL} through extensive numerical simulation for GLM and recent neural network nuisance models. Our method is subsequently extended to real data and generates meaningful insights consistent with medical literature, a case where all baseline methods fail.

Song Wei, Yao Xie, Christopher S. Josef et al.

We present a generalized linear structural causal model, coupled with a novel data-adaptive linear regularization, to recover causal directed acyclic graphs (DAGs) from time series. By leveraging a recently developed stochastic monotone Variational Inequality (VI) formulation, we cast the causal discovery problem as a general convex optimization. Furthermore, we develop a non-asymptotic recovery guarantee and quantifiable uncertainty by solving a linear program to establish confidence intervals for a wide range of non-linear monotone link functions. We validate our theoretical results and show the competitive performance of our method via extensive numerical experiments. Most importantly, we demonstrate the effectiveness of our approach in recovering highly interpretable causal DAGs over Sepsis Associated Derangements (SADs) while achieving comparable prediction performance to powerful ``black-box'' models such as XGBoost. Thus, the future adoption of our proposed method to conduct continuous surveillance of high-risk patients by clinicians is much more likely.

Aditya Singh, Akram Mohammed, Lokesh Chinthala et al.

Fever can provide valuable information for diagnosis and prognosis of various diseases such as pneumonia, dengue, sepsis, etc., therefore, predicting fever early can help in the effectiveness of treatment options and expediting the treatment process. This study aims to develop novel algorithms that can accurately predict fever onset in critically ill patients by applying machine learning technique on continuous physiological data. We analyzed continuous physiological data collected every 5-minute from a cohort of over 200,000 critically ill patients admitted to an Intensive Care Unit (ICU) over a 2-year period. Each episode of fever from the same patient were considered as an independent event, with separations of at least 24 hours. We extracted descriptive statistical features from six physiological data streams, including heart rate, respiration, systolic and diastolic blood pressure, mean arterial pressure, and oxygen saturation, and use these features to independently predict the onset of fever. Using a bootstrap aggregation method, we created a balanced dataset of 7,801 afebrile and febrile patients and analyzed features up to 4 hours before the fever onset. We found that supervised machine learning methods can predict fever up to 4 hours before onset in critically ill patients with high recall, precision, and F1-score. This study demonstrates the viability of using machine learning to predict fever among hospitalized adults. The discovery of salient physiomarkers through machine learning and deep learning techniques has the potential to further accelerate the development and implementation of innovative care delivery protocols and strategies for medically vulnerable patients.