Faculty, Staff and Student Publications
Language
English
Publication Date
6-1-2024
Journal
Journal of Biomedical Informatics
DOI
10.1016/j.jbi.2024.104648
PMID
38692464
PMCID
PMC12374600
PubMedCentral® Posted Date
8-25-2025
PubMedCentral® Full Text Version
Author MSS
Abstract
Background: Advances in artificial intelligence (AI) have realized the potential of revolutionizing healthcare, such as predicting disease progression via longitudinal inspection of Electronic Health Records (EHRs) and lab tests from patients admitted to Intensive Care Units (ICU). Although substantial literature exists addressing broad subjects, including the prediction of mortality, length-of-stay, and readmission, studies focusing on forecasting Acute Kidney Injury (AKI), specifically dialysis anticipation like Continuous Renal Replacement Therapy (CRRT) are scarce. The technicality of how to implement AI remains elusive.
Objective: This study aims to elucidate the important factors and methods that are required to develop effective predictive models of AKI and CRRT for patients admitted to ICU, using EHRs in the Medical Information Mart for Intensive Care (MIMIC) database.
Methods: We conducted a comprehensive comparative analysis of established predictive models, considering both time-series measurements and clinical notes from MIMIC-IV databases. Subsequently, we proposed a novel multi-modal model which integrates embeddings of top-performing unimodal models, including Long Short-Term Memory (LSTM) and BioMedBERT, and leverages both unstructured clinical notes and structured time series measurements derived from EHRs to enable the early prediction of AKI and CRRT.
Results: Our multimodal model achieved a lead time of at least 12 h ahead of clinical manifestation, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.888 for AKI and 0.997 for CRRT, as well as an Area Under the Precision Recall Curve (AUPRC) of 0.727 for AKI and 0.840 for CRRT, respectively, which significantly outperformed the baseline models. Additionally, we performed a SHapley Additive exPlanation (SHAP) analysis using the expected gradients algorithm, which highlighted important, previously underappreciated predictive features for AKI and CRRT.
Conclusion: Our study revealed the importance and the technicality of applying longitudinal, multimodal modeling to improve early prediction of AKI and CRRT, offering insights for timely interventions. The performance and interpretability of our model indicate its potential for further assessment towards clinical applications, to ultimately optimize AKI management and enhance patient outcomes.
Keywords
Acute Kidney Injury, Humans, Intensive Care Units, Electronic Health Records, Longitudinal Studies, Renal Replacement Therapy, Artificial Intelligence, Forecasting, Length of Stay, Male, Databases, Factual, Female, Acute Kidney Injury (AKI), Continuous Renal Replacement Therapy (CRRT), Electronic Health Records (EHRs), multi-modal, Long Short-Term Memory (LSTM), BioMedBERT
Published Open-Access
yes
Recommended Citation
Tan, Yukun; Dede, Merve; Mohanty, Vakul; et al., "Forecasting Acute Kidney Injury and Resource Utilization in ICU Patients Using Longitudinal, Multimodal Models" (2024). Faculty, Staff and Student Publications. 686.
https://digitalcommons.library.tmc.edu/uthshis_docs/686