MIMIC-III

MIMIC-III is a publicly available critical care database that contains de-identified health data from patients admitted to intensive care units, and it is used to evaluate predictive models for clinical time-series analysis.

Papers using MIMIC-III (14)

StayLTC: A Cost-Effective Multimodal Framework for Hospital Length of Stay Forecasting2025Temporal Dynamic Embedding for Irregularly Sampled Time Series2025Recurrent Neural Networks for Multivariate Time Series with Missing Values2016 · 236 citesTransfer Learning for Clinical Time Series Analysis using Deep Neural Networks2019 · 82 citesAttend and Diagnose: Clinical Time Series Analysis using Attention Models2017 · 44 citesTransfer Learning for Clinical Time Series Analysis using Recurrent Neural Networks2018 · 18 citesMulti-view Integration Learning for Irregularly-sampled Clinical Time Series2021 · 4 citesFeatures Fusion Framework for Multimodal Irregular Time-series Events2022 · 4 citesA Transformer-based Diffusion Probabilistic Model for Heart Rate and Blood Pressure Forecasting in Intensive Care Unit2023 · 3 citesBayesian Recurrent Framework for Missing Data Imputation and Prediction with Clinical Time Series2019 · 2 citesImproving Irregularly Sampled Time Series Learning with Dense Descriptors of Time2020 · 2 citesBenchmarking with MIMIC-IV, an irregular, spare clinical time series dataset2024 · 1 citesNo Imputation Needed: A Switch Approach to Irregularly Sampled Time Series2023On the Importance of Step-wise Embeddings for Heterogeneous Clinical Time-Series2023