Multitask learning and benchmarking with clinical time series data
Not on the map. Why?
Abstract (arXiv)
Health care is one of the most exciting frontiers in data mining and machine learning. Successful adoption of electronic health records (EHRs) created an explosion in digital clinical data available for analysis, but progress in machine learning for healthcare research has been difficult to measure because of the absence of publicly available benchmark data sets. To address this problem, we propose four clinical prediction benchmarks using data derived from the publicly available Medical Information Mart for Intensive Care (MIMIC-III) database. These tasks cover a range of clinical problems including modeling risk of mortality, forecasting length of stay, detecting physiologic decline, and phenotype classification. We propose strong linear and neural baselines for all four tasks and evaluate the effect of deep supervision, multitask training and data-specific architectural modifications on the performance of neural models.
Key facts. Cited by 287 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Mar 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 44; 2022: 44; 2023: 54; 2024: 49; 2025: 50; 2026: 46.
287 papers.
Sort:
By area:
- 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
- 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
- 2023ForecastPFN: Synthetically-Trained Zero-Shot Forecastingcited by 102
- 2023EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Modelscited by 101
- 2021Time Series Prediction using Deep Learning Methods in Healthcarecited by 71
- 2024FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusioncited by 67
- 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 66
- 2023Benchmarking Distribution Shift in Tabular Data with TableShiftcited by 64
- 2023GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphscited by 57
- 2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 56
- 2023Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Seriescited by 54
- 2022MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray imagescited by 53
38 more
- 2024DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistencycited by 51
- 2022A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Predictioncited by 48
- 2023Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Eventscited by 46
- 2022The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanationscited by 41
- 2022An Extensive Data Processing Pipeline for MIMIC-IVcited by 39
- 2021HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Datacited by 38
- 2022Contrastive Learning for Unsupervised Domain Adaptation of Time Seriescited by 36
- 2022GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source Learningcited by 35
- 2021Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologiescited by 34
- 2022Improving Medical Predictions by Irregular Multimodal Electronic Health Records Modelingcited by 33
- 2021Neighborhood Contrastive Learning Applied to Online Patient Monitoringcited by 32
- 2021X-CAL: Explicit Calibration for Survival Analysiscited by 30
- 2021Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Seriescited by 30
- 2021Benchmarking emergency department triage prediction models with machine learning and large public electronic health recordscited by 30
- 2021Towards Generating Real-World Time Series Datacited by 26
- 2023Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicinecited by 24
- 2024Open (Clinical) LLMs are Sensitive to Instruction Phrasingscited by 23
- 2021Predicting Patient Outcomes with Graph Representation Learningcited by 21
- 2023Probabilistic Imputation for Time-series Classification with Missing Datacited by 21
- 2024RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Recordscited by 21
- 2025MIRA: Medical Time Series Foundation Model for Real-World Health Datacited by 21
- 2022Individual Privacy Accounting with Gaussian Differential Privacycited by 19
- 2022The Missing Indicator Method: From Low to High Dimensionscited by 19
- 2021Heterogeneous Multi-task Learning with Expert Diversitycited by 18
- 2023DuETT: Dual Event Time Transformer for Electronic Health Recordscited by 17
- 2023Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methodscited by 17
- 2023Sequential Multi-Dimensional Self-Supervised Learning for Clinical Time Seriescited by 16
- 2021MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Datasetcited by 15
- 2024Multi-modal Deep Learningcited by 15
- 2021AttDMM: An Attentive Deep Markov Model for Risk Scoring in Intensive Care Unitscited by 14
- 2022Integrating Physiological Time Series and Clinical Notes with Transformer for Early Prediction of Sepsiscited by 14
- 2023LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learningcited by 14
- 2023Self-supervised Representation Learning From Random Data Projectorscited by 14
- 2025Multimodal Medical Code Tokenizercited by 14
- 2022Multimodal data matters: language model pre-training over structured and unstructured electronic health recordscited by 13
- 2022Partitioned Variational Inference: A Framework for Probabilistic Federated Learningcited by 13
- 2021VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Modelscited by 12
- 2021A comparison of approaches to improve worst-case predictive model performance over patient subpopulationscited by 12
50 most cited of 287 All 287 (JSON)
- 2026BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecasting27 Sep 2026
- 2026MTLiquid: Enabling Efficient Multi-Task Learning using Liquid Neural Networks for Lightweight Healthcare Monitoring Systems27 Sep 2026
- 2026SMARtCARE: Privacy-Preserving Agentic AI Systems for Bounded-Autonomy Clinical Decision Support24 Sep 2026
- 2026Rethinking How We Evaluate Methodological Progress in Health AI16 Sep 2026
- 2026SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence30 Aug 2026
- 2026Predicting Multiple Clinical Outcomes Related to Functional Recovery and Social Isolation Among Older Adults After Lower-Limb Fracture or Hip Replacement24 Aug 2026
- 2026Future Querying: Can LLMs Serve as Implicit Medical World Models?24 Aug 2026
- 2026Physiological World Models for Human State Transitions15 Aug 2026
- 2026CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility13 Aug 2026
- 2026Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness12 Aug 2026
- 2026QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction6 Aug 2026
- 2026CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study1 Aug 2026
38 more
- 2026Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study25 Jul 2026
- 2026Toward Automated Detection of Documentation Inconsistencies in Electronic Health Records24 Jul 2026
- 2026MissHyper: Restoring Clinical Synchronicity in Missingness-Guided Hypergraph Forecasting24 Jul 2026
- 2026Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction10 Jul 2026
- 2026Generative Bayesian Filtering for State Estimation9 Jul 2026
- 2026A General Multimodal Probing Framework for Data Fusion and Prediction with Frozen Large Language Models: Evidence from Multimodal EHR Data27 Jun 2026
- 2026A Longitudinal Attribute-Conditioned Neural Network for Modeling Health-State Transition Probabilities in Temporally Irregular Data: The LANTERN Framework11 Jun 2026
- 2026Is Fairness Truly Fair? Towards Reliable Lipschitz Fairness in Multi-Task Learning via Fixed-texorpdfstringδdelta Alignment9 Jun 2026
- 2026TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs8 Jun 2026
- 2026Disentangling Latent Risk Pathways via Bayesian Hypergraph Inference4 Jun 2026
- 2026Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction4 Jun 2026
- 2026Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognition: Robustness, Efficiency, and Clinical Utility26 May 2026
- 2026On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series25 May 2026
- 2026Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset21 May 2026
- 2026Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs21 May 2026
- 2026Learning to Select Source-Traceable Evidence for Language-Model Prediction from Irregular Clinical Time Series19 May 2026
- 2026MILM: Large Language Models for Multimodal Irregular Time Series with Informative Sampling13 May 2026
- 2026EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records12 May 2026
- 2026Fortifying Time Series: DTW-Certified Robust Anomaly Detection8 May 2026
- 2026A Domain Incremental Continual Learning Benchmark for ICU Time Series Model Transportability5 May 2026
- 2026Personalized Digital Health Modeling with Adaptive Support Users3 May 2026
- 2026OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction18 Apr 2026
- 2026CURA: Clinical Uncertainty Risk Alignment for Language Model-Based Risk Prediction16 Apr 2026
- 2026A Clinical Point Cloud Paradigm for In-Hospital Mortality Prediction from Multi-Level Incomplete Multimodal EHRs6 Apr 2026
- 2026On Interpolation Formulas Describing Neural Network Generalization14 Mar 2026
- 2026EveryQuery: A Promptable Foundation Model for Clinical Prediction Tasks over Electronic Health Records9 Mar 2026
- 2026When Does Multimodal Learning Help in Healthcare? A Benchmark on EHR and Chest X-Ray Fusion27 Feb 2026
- 2026Fair feature attribution for multi-output prediction: a Shapley-based perspective26 Feb 2026
- 2026A Statistical Approach for Modeling Irregular Multivariate Time Series with Missing Observations23 Feb 2026
- 2026Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction13 Feb 2026
- 2026Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing2 Feb 2026
- 2026PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning23 Jan 2026
- 2026A Multimodal Data Processing Pipeline for MIMIC-IV Dataset8 Jan 2026
- 2026GroupSegment-SHAP: Shapley Value Explanations with Group-Segment Players for Multivariate Time Series3 Jan 2026
- 2025Knowledge Graph Augmented Large Language Models for Disease Prediction1 Dec 2025
- 2025VitalBench: A Rigorous Multi-Center Benchmark for Long-Term Vital Sign Prediction in Intraoperative Care14 Nov 2025
- 2025SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis14 Nov 2025
- 2025Cross-Modal Alignment via Variational Copula Modelling5 Nov 2025
50 newest of 287 All 287 (JSON)
- 2026Physiological World Models for Human State Transitionscited by 0
- 2026Physiological World Models for Human State Transitions15 Aug 2026
- 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
- 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
- 2023ForecastPFN: Synthetically-Trained Zero-Shot Forecastingcited by 102
- 2023EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Modelscited by 101
- 2021Time Series Prediction using Deep Learning Methods in Healthcarecited by 71
- 2023Benchmarking Distribution Shift in Tabular Data with TableShiftcited by 64
- 2023GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphscited by 57
- 2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 56
- 2023Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Seriescited by 54
- 2022MedFuse: Multi-modal fusion with clinical time-series data and chest X-ray imagescited by 53
- 2024DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistencycited by 51
- 2022A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Predictioncited by 48
12 most cited of 275 All 275 (JSON)
- 2026BITS: Rethinking Fair and Comprehensive Evaluation for Irregular Time Series Forecasting27 Sep 2026
- 2026MTLiquid: Enabling Efficient Multi-Task Learning using Liquid Neural Networks for Lightweight Healthcare Monitoring Systems27 Sep 2026
- 2026Rethinking How We Evaluate Methodological Progress in Health AI16 Sep 2026
- 2026SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence30 Aug 2026
- 2026Predicting Multiple Clinical Outcomes Related to Functional Recovery and Social Isolation Among Older Adults After Lower-Limb Fracture or Hip Replacement24 Aug 2026
- 2026Future Querying: Can LLMs Serve as Implicit Medical World Models?24 Aug 2026
- 2026CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility13 Aug 2026
- 2026Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness12 Aug 2026
- 2026QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest Mortality Prediction6 Aug 2026
- 2026CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study1 Aug 2026
- 2026Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study25 Jul 2026
- 2026Toward Automated Detection of Documentation Inconsistencies in Electronic Health Records24 Jul 2026
12 newest of 275 All 275 (JSON)