DeepBiomarker2: Prediction of alcohol and substance use disorder risk in post-traumatic stress disorder patients using electronic medical records and multiple social determinants of health

Abstract

Introduction: Prediction of high-risk events amongst patients with mental disorders is critical for personalized interventions. In our previous study, we developed a deep learning-based model, DeepBiomarker by utilizing electronic medical records (EMR) to predict the outcomes of patients with suicide-related events in post-traumatic stress disorder (PTSD) patients. Methods We improved our deep learning model to develop DeepBiomarker2 through data integration of multimodal information: lab tests, medication use, diagnosis, and social determinants of health (SDoH) parameters (both individual and neighborhood level) from EMR data for outcome prediction. We further refined our contribution analysis for identifying key factors. We applied DeepBiomarker2 to analyze EMR data of 38,807 patients from University of Pittsburgh Medical Center diagnosed with PTSD to determine their risk of developing alcohol and substance use disorder (ASUD). Results DeepBiomarker2 predicted whether a PTSD patient will have a diagnosis of ASUD within the following 3 months with a c-statistic (receiver operating characteristic AUC) of 0·93. We used contribution analysis technology to identify key lab tests, medication use and diagnosis for ASUD prediction. These identified factors imply that the regulation of the energy metabolism, blood circulation, inflammation, and microbiome is involved in shaping the pathophysiological pathways promoting ASUD risks in PTSD patients. Our study found protective medications such as oxybutynin, magnesium oxide, clindamycin, cetirizine, montelukast and venlafaxine all have a potential to reduce risk of ASUDs. Discussion DeepBiomarker2 can predict ASUD risk with high accuracy and can further identify potential risk factors along with medications with beneficial effects. We believe that our approach will help in personalized interventions of PTSD for a variety of clinical scenarios.

Prediction of Adverse Events Risk in Patients with Comorbid Post- Traumatic Stress Disorder and Alcohol Use Disorder Using Electronic Medical Records by Deep Learning Models

“…The model captures temporal dependencies and assigns weights to relevant events( 24 ). Building upon this framework and our previous DeepBiomarker models, DeepBiomarker and DeepBiomarker2, we applied our model to the current dataset( 12 , 25 ). We integrated individual lab test results, SDoH parameters, medications, and diagnoses as input just as mentioned in our previous versions.…”

“…Additionally, we utilized the False Discovery Rate (FDR) adjusted p-value, which considers the ratio of false positive results to total positive test results, providing a more accurate measure( 30 ). To enhance our assessment, we introduced improvements in the calculation of FC and the scaling of RC for all features( 10 , 12 ) .…”

“…), and community/neighborhood-level SDoH indicators (e.g., nSES index, etc.) for high-risk patient outcomes( 10 – 12 ). Our overarching goal is to leverage EMRs to predict risks and develop evidence-based interventions that allow healthcare practitioners to customize treatment plans for each patient.…”