Health Care Analytics With Time-Invariant and Time-Variant Feature Importance to Predict Hospital-Acquired Acute Kidney Injury: Observational Longitudinal Study

Abstract

Background Acute kidney injury (AKI) develops in 4% of hospitalized patients and is a marker of clinical deterioration and nephrotoxicity. AKI onset is highly variable in hospitals, which makes it difficult to time biomarker assessment in all patients for preemptive care. Objective The study sought to apply machine learning techniques to electronic health records and predict hospital-acquired AKI by a 48-hour lead time, with the aim to create an AKI surveillance algorithm that is deployable in real time. Methods The data were sourced from 20,732 case admissions in 16,288 patients over 1 year in our institution. We enhanced the bidirectional recurrent neural network model with a novel time-invariant and time-variant aggregated module to capture important clinical features temporal to AKI in every patient. Time-series features included laboratory parameters that preceded a 48-hour prediction window before AKI onset; the latter’s corresponding reference was the final in-hospital serum creatinine performed in case admissions without AKI episodes. Results The cohort was of mean age 53 (SD 25) years, of whom 29%, 12%, 12%, and 53% had diabetes, ischemic heart disease, cancers, and baseline eGFR <90 mL/min/1.73 m2, respectively. There were 911 AKI episodes in 869 patients. We derived and validated an algorithm in the testing dataset with an AUROC of 0.81 (0.78-0.85) for predicting AKI. At a 15% prediction threshold, our model generated 699 AKI alerts with 2 false positives for every true AKI and predicted 26% of AKIs. A lowered 5% prediction threshold improved the recall to 60% but generated 3746 AKI alerts with 6 false positives for every true AKI. Representative interpretation results produced by our model alluded to the top-ranked features that predicted AKI that could be categorized in association with sepsis, acute coronary syndrome, nephrotoxicity, or multiorgan injury, specific to every case at risk. Conclusions We generated an accurate algorithm from electronic health records through machine learning that predicted AKI by a lead time of at least 48 hours. The prediction threshold could be adjusted during deployment to optimize recall and minimize alert fatigue, while its precision could potentially be augmented by targeted AKI biomarker assessment in the high-risk cohort identified.

Using machine learning to predict adverse events in acute coronary syndrome: A retrospective study

“…Identifying patients at high risk of developing AKI, MI, and poor outcomes remains a challenge in cardiovascular medicine. 11 , 12 Although traditional risk factors are helpful to identify high‐risk populations, they are limited for individual risk assessment. Even when using global summary scores, over‐ or undertreatment is inevitable.…”

Predictive Models for Health Deterioration: Understanding Disease Pathways for Personalized Medicine

“…With a reported AUROC of 92.1%, the model significantly outperformed baseline models and was deemed clinically applicable. A similar study by Chua et al (71) on acute kidney disease, using a smaller dataset of 16,288 patients (a total of 20,732 case admissions) from the National…”

Research frontiers and trends in the application of artificial intelligence to sepsis: A bibliometric analysis

“…Sepsis has always been a hot topic in the field of critical care medicine with respect to prevention, diagnosis, and treatment of AKI (42). There has been some success in identifying the subtypes of AKI associated with sepsis using machine learning (43)(44)(45). In spite of this, there remains a need for further research in order to determine the optimal treatment for different subtypes of AKI, as well as whether this treatment can improve the prognosis of patients.…”