Deep learning model for personalized prediction of positive MRSA culture using time-series electronic health records

Abstract

Methicillin-resistant Staphylococcus aureus (MRSA) poses significant morbidity and mortality in hospitals. Rapid, accurate risk stratification of MRSA is crucial for optimizing antibiotic therapy. Our study introduced a deep learning model, PyTorch_EHR, which leverages electronic health record (EHR) time-series data, including wide-variety patient specific data, to predict MRSA culture positivity within two weeks. 8,164 MRSA and 22,393 non-MRSA patient events from Memorial Hermann Hospital System, Houston, Texas are used for model development. PyTorch_EHR outperforms logistic regression (LR) and light gradient boost machine (LGBM) models in accuracy (AUROC^PyTorch_EHR = 0.911, AUROC^LR = 0.857, AUROC^LGBM = 0.892). External validation with 393,713 patient events from the Medical Information Mart for Intensive Care (MIMIC)-IV dataset in Boston confirms its superior accuracy (AUROC^PyTorch_EHR = 0.859, AUROC^LR = 0.816, AUROC^LGBM = 0.838). Our model effectively stratifies patients into high-, medium-, and low-risk categories, potentially optimizing antimicrobial therapy and reducing unnecessary MRSA-specific antimicrobials. This highlights the advantage of deep learning models in predicting MRSA positive cultures, surpassing traditional machine learning models and supporting clinicians' judgments.

Fig. 1. Cumulative Incidence Curve of Positive MRSA Over Two Weeks in the MHHS and MIMIC-IV Datasets.

a and b show cumulative incidence of MRSA cultures in Memorial Hermann Hospital System (MHHS) and Medical Information Mart for Intensive Care (MIMIC)-IV datasets, respectively. Both figures were generated based on the risk predicted by our model in test datasets. Given the significant imbalance in the MIMIC-IV dataset, even high-risk patients achieved 20% positivity compared to the MHHS dataset. In contrast, the low-risk patient group had fewer false negatives. The shaded area in the graph represents the 95% confidence intervals. MHHS Memorial Hermann Hospital System, MIMIC Medical Information Mart for Intensive Care, MRSA Methicillin Resistant Staphylococcus aureus.

Fig. 2. Schematic Structure of Deep Learning-Based Prediction Model for MRSA-Positive Cultures.

a summarizes the overall structure of the model used to predict MRSA-positive cultures over a two-week period from the index culture. Our model integrates multiple structural data tables from Electronic Health Records (EHRs) as time-sequenced data prior to the index time. A deep learning-based model (PyTorch_EHR) is employed to predict MRSA-positive cultures over two weeks from the index time. b describes scenarios where patients experience multiple events over time. EHR: Electronic Health Records, MRSA: Methicillin-Resistant Staphylococcus aureus.