Key result
Multimodal deep learning predicts in-hospital mortality in critical HF with an AUC of ~0.77.
Why the study?
Clinical notes contain contextualized information beyond structured data that may improve the precision of hospital outcome evaluation for heart failure patients.
Does a multimodal deep learning model combining admission notes and tabular data improve the prediction of in-hospital mortality in patients with critical heart failure compared to unimodal models?
Observational (n=21,814)
Yes
Does a multimodal deep learning model combining admission notes and tabular data improve the prediction of in-hospital mortality in patients with critical heart failure compared to unimodal models?
Answers are grounded in this paper and cite their sources.
A multimodal deep learning model combining admission clinical notes and tabular data accurately predicts in-hospital mortality in patients with critical heart failure, outperforming unimodal approaches.
BACKGROUND Clinical notes contain contextualized information beyond structured data related to patients’ past and current health status. OBJECTIVE This study aimed to design a multimodal deep learning approach to improve the evaluation precision of hospital outcomes for heart failure (HF) using admission clinical notes and easily collected tabular data. METHODS Data for the development and validation of the multimodal model were retrospectively derived from 3 open-access US databases, including the Medical Information Mart for Intensive Care III v1.4 (MIMIC-III) and MIMIC-IV v1.0, collected from a teaching hospital from 2001 to 2019, and the eICU Collaborative Research Database v1.2, collected from 208 hospitals from 2014 to 2015. The study cohorts consisted of all patients with critical HF. The clinical notes, including chief complaint, history of present illness, physical examination, medical history, and admission medication, as well as clinical variables recorded in electronic health records, were analyzed. We developed a deep learning mortality prediction model for in-hospital patients, which underwent complete internal, prospective, and external evaluation. The Integrated Gradients and SHapley Additive exPlanations (SHAP) methods were used to analyze the importance of risk factors. RESULTS The study included 9989 (16.4%) patients in the development set, 2497 (14.1%) patients in the internal validation set, 1896 (18.3%) in the prospective validation set, and 7432 (15%) patients in the external validation set. The area under the receiver operating characteristic curve of the models was 0.838 (95% CI 0.827-0.851), 0.849 (95% CI 0.841-0.856), and 0.767 (95% CI 0.762-0.772), for the internal, prospective, and external validation sets, respectively. The area under the receiver operating characteristic curve of the multimodal model outperformed that of the unimodal models in all test sets, and tabular data contributed to higher discrimination. The medical history and physical examination were more useful than other factors in early assessments. CONCLUSIONS The multimodal deep learning model for combining admission notes and clinical tabular data showed promising efficacy as a potentially novel method in evaluating the risk of mortality in patients with HF, providing more accurate and timely decision support.
No takes yet. Share an insight, caveat, or question.
Gao et al. (2023) conducted an observational in Critical heart failure (n=21,814). Multimodal deep learning model vs. Unimodal models was evaluated on In-hospital mortality prediction (Area under the receiver operating characteristic curve) (AUC 0.767, 95% CI 0.762-0.772). A multimodal deep learning model combining admission notes and tabular data predicted in-hospital mortality in critical heart failure with an external validation AUC of 0.767 (95% CI 0.762-0.772).
Synapse has enriched 10 related papers. Consider them for comparative context: