dorsal/arxiv
View SchemaDT-ICU: Towards Explainable Digital Twins for ICU Patient Monitoring via Multi-Modal and Multi-Task Iterative Inference
| Authors | Wen Guo |
|---|---|
| Categories | |
| ArXiv ID | 2601.07778vv1 |
| URL | https://arxiv.org/abs/2601.07778 |
| License | http://creativecommons.org/licenses/by/4.0/ |
Abstract
We introduce DT-ICU, a multimodal digital twin framework for continuous risk estimation in intensive care. DT-ICU integrates variable-length clinical time series with static patient information in a unified multitask architecture, enabling predictions to be updated as new observations accumulate over the ICU stay. We evaluate DT-ICU on the large, publicly available MIMIC-IV dataset, where it consistently outperforms established baseline models under different evaluation settings. Our test-length analysis shows that meaningful discrimination is achieved shortly after admission, while longer observation windows further improve the ranking of high-risk patients in highly imbalanced cohorts. To examine how the model leverages heterogeneous data sources, we perform systematic modality ablations, revealing that the model learnt a reasonable structured reliance on interventions, physiological response observations, and contextual information. These analyses provide interpretable insights into how multimodal signals are combined and how trade-offs between sensitivity and precision emerge. Together, these results demonstrate that DT-ICU delivers accurate, temporally robust, and interpretable predictions, supporting its potential as a practical digital twin framework for continuous patient monitoring in critical care. The source code and trained model weights for DT-ICU are publicly available at https://github.com/GUO-W/DT-ICU-release.
{
"annotation_id": "6ae87de9-9570-4121-81c7-1ccff007479e",
"date_created": "2026-02-17T05:53:12.592000Z",
"date_modified": "2026-02-17T05:53:12.592000Z",
"file_hash": "e36519ee5021909cf317f0802b77d090e7f51dfe7547afa1150b33fc20b3a5c9",
"private": false,
"record": {
"abstract": "We introduce DT-ICU, a multimodal digital twin framework for continuous risk estimation in intensive care. DT-ICU integrates variable-length clinical time series with static patient information in a unified multitask architecture, enabling predictions to be updated as new observations accumulate over the ICU stay. We evaluate DT-ICU on the large, publicly available MIMIC-IV dataset, where it consistently outperforms established baseline models under different evaluation settings. Our test-length analysis shows that meaningful discrimination is achieved shortly after admission, while longer observation windows further improve the ranking of high-risk patients in highly imbalanced cohorts. To examine how the model leverages heterogeneous data sources, we perform systematic modality ablations, revealing that the model learnt a reasonable structured reliance on interventions, physiological response observations, and contextual information. These analyses provide interpretable insights into how multimodal signals are combined and how trade-offs between sensitivity and precision emerge. Together, these results demonstrate that DT-ICU delivers accurate, temporally robust, and interpretable predictions, supporting its potential as a practical digital twin framework for continuous patient monitoring in critical care. The source code and trained model weights for DT-ICU are publicly available at https://github.com/GUO-W/DT-ICU-release.",
"arxiv_id": "2601.07778",
"authors": [
"Wen Guo"
],
"categories": [
"cs.LG",
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"title": "DT-ICU: Towards Explainable Digital Twins for ICU Patient Monitoring via Multi-Modal and Multi-Task Iterative Inference",
"url": "https://arxiv.org/abs/2601.07778",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "48edbb48-66da-4003-b31c-fd2937892a05",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}