Multicenter Development and Validation of a Multimodal Deep Learning Model to Predict Moderate to Severe AKI

Key Points We developed and validated a multimodal (structured and unstructured data) model to predict moderate to severe AKI using multicenter data. This multimodal AKI risk score accurately identifies patients who will develop stage 2 AKI over 2 days earlier than serum creatinine alone. The multimodal model performed better than a model based solely on structured data and performed similarly during temporal and site-based validation. Background Prior models for the early identification of AKI have used structured data ( e.g ., vital signs and laboratory values). We aimed to develop and validate a deep learning model to predict moderate to severe AKI by combining structured data and information from unstructured notes. Methods Adults (18 years or older) admitted to the University of Wisconsin (2009–2020) and the University of Chicago Medicine (2016–2022) were eligible for inclusion. Patients were excluded if they had no documented serum creatinine (SCr), ESKD, an admission SCr ≥3.0 mg/dl, developed ≥stage 2 AKI before reaching the wards or intensive care unit, or required dialysis (KRT) within the first 48 hours. Text from unstructured notes was mapped to standardized concept unique identifiers to create predictor variables, and structured data variables were also included. An intermediate fusion deep learning recurrent neural network architecture was used to predict ≥stage 2 AKI within the next 48 hours. This multimodal model was developed in the first 80% of the data and temporally validated in the next 20%. Results There were 339,998 admissions in the derivation cohort and 84,581 in the validation cohort, with 12,748 (3%) developing ≥stage 2 AKI. Patients with ≥stage 2 AKI were older, more likely to be male, had higher baseline SCr, and were more commonly in the intensive care unit ( P < 0.001 for all). The multimodal model outperformed a model based only on structured data for all outcomes, with an area under the receiver operating characteristic curve (95% confidence interval) of 0.88 (0.88 to 0.88) for predicting ≥stage 2 AKI and 0.93 (0.93 to 0.94) for receiving KRT. The area under the precision-recall-curve for ≥stage 2 AKI was 0.20. The results were similar during external validation. Conclusions We developed and validated a multimodal deep learning model using structured and unstructured data that predicts the development of severe AKI across the hospital stay for earlier intervention.