mlsanityData to 7 Oct 2026

SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis

arXiv 2511.11935 ↗First posted 14 Nov 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Deep-learning survival models for electronic health record (EHR) data are hard to compare across papers because the upstream preprocessing step, which includes cohort definition, time discretisation, missingness handling, and censoring rules, is typically undocumented and inconsistent. A reported difference in concordance between two mortality models can therefore reflect any of these choices rather than a modelling contribution. We present SurvBench, an open-source preprocessing pipeline that converts raw PhysioNet exports into model-ready tensors for survival analysis. SurvBench covers four critical-care databases (MIMIC-IV, eICU, MC-MED, HiRID) and four input modalities: time-series vitals and laboratory values, static demographics, International Classification of Diseases (ICD) codes, and radiology report embeddings. Every preprocessing decision is controlled through YAML configuration. Imputation, scaling, and feature filtering are fit on the training fold only. Missingness is recorded as a binary mask alongside each feature tensor. The pipeline handles single-risk endpoints (in-hospital and in-ICU mortality) and competing-risks endpoints (a three-way emergency-department admission pathway, with home discharge treated as administrative censoring). We also provide support for harmonised cross-dataset external validation between eICU and MIMIC-IV. SurvBench is publicly available at https://github.com/munibmesinovic/SurvBench, providing a robust platform that future deep-learning EHR survival work, especially nascent multi-modal approaches, can be measured against under matched preprocessing.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 34 of its 140 references that are in the map. First posted on arXiv 14 Nov 2025.

Builds on

34 of 140 references.

References · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  3. 2019Publicly Available Clinical BERT Embeddingscited by 995
  4. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  5. 2019ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmissioncited by 487
  6. 2020Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease predictioncited by 368
  7. 2016DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Networkcited by 354
  8. 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 344
  9. 2017Multitask learning and benchmarking with clinical time series datacited by 287
  10. 2018Scalable and accurate deep learning for electronic health recordscited by 275
  11. 2019Time-to-Event Prediction with Neural Networks and Cox Regressioncited by 173
  12. 2020Challenges in Deploying Machine Learning: a Survey of Case Studiescited by 151
22 more
  1. 2017Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysiscited by 145
  2. 2019MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-IIIcited by 121
  3. 2015Learning to Diagnose with LSTM Recurrent Neural Networkscited by 99
  4. 2023Deep Learning for Survival Analysis: A Reviewcited by 75
  5. 2018A Scalable Discrete-Time Survival Model for Neural Networkscited by 70
  6. 2022Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequencescited by 67
  7. 2018Effective Ways to Build and Evaluate Individual Survival Distributionscited by 64
  8. 2016Deep Survival Analysiscited by 60
  9. 2017Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifiercited by 47
  10. 2019Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Taskscited by 39
  11. 2022An Extensive Data Processing Pipeline for MIMIC-IVcited by 39
  12. 2021Comprehensive Comparative Study of Multi-Label Classification Methodscited by 38
  13. 2021HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Datacited by 38
  14. 2014An introduction to Docker for reproducible research, with examples from the R environmentcited by 25
  15. 2019TAPER: Time-Aware Patient EHR Representationcited by 22
  16. 2023Mimic-IV-ICD: A new benchmark for eXtreme MultiLabel Classificationcited by 19
  17. 2016Good Enough Practices in Scientific Computingcited by 9
  18. 2023DySurv: dynamic deep learning model for survival analysis with conditional variational inferencecited by 9
  19. 2024MEL: Efficient Multi-Task Evolutionary Learning for High-Dimensional Feature Selectioncited by 6
  20. 2024Benchmarking with MIMIC-IV, an irregular, spare clinical time series datasetcited by 5
  21. 2025Revisiting the MIMIC-IV Benchmark: Experiments Using Language Models for Electronic Health Recordscited by 5
  22. 2023Bio+Clinical BERT, BERT Base, and CNN Performance Comparison for Predicting Drug-Review Satisfactioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ECG-biometrics-bench: A Unified Framework for Reproducible Benchmarking of ECG Biometricscited by 0