Miranda Oshin, Fan Peihao, Qi Xiguang, Wang Haohan, Brannock M Daniel, Kosten Thomas, Ryan Neal David, Kirisci Levent, Wang LiRong
University of Pittsburgh.
University of Illinois Urbana-Champaign.
Res Sq. 2023 May 25:rs.3.rs-2949487. doi: 10.21203/rs.3.rs-2949487/v1.
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.
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).
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.
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.
预测精神障碍患者中的高风险事件对于个性化干预至关重要。在我们之前的研究中，我们通过利用电子病历（EMR）开发了一种基于深度学习的模型DeepBiomarker，以预测创伤后应激障碍（PTSD）患者中与自杀相关事件的患者结局。
我们通过整合多模态信息改进了深度学习模型，以开发DeepBiomarker2：来自EMR数据的实验室检查、药物使用、诊断以及健康的社会决定因素（SDoH）参数（个体和社区层面），用于结局预测。我们进一步完善了贡献分析以识别关键因素。我们应用DeepBiomarker2分析了匹兹堡大学医学中心38807例被诊断为PTSD的患者的EMR数据，以确定他们发生酒精和物质使用障碍（ASUD）的风险。
DeepBiomarker2预测PTSD患者在接下来3个月内是否会被诊断为ASUD的c统计量（受试者工作特征曲线下面积）为0.93。我们使用贡献分析技术来识别用于ASUD预测的关键实验室检查、药物使用和诊断。这些确定的因素表明，能量代谢、血液循环、炎症和微生物群的调节参与了塑造促进PTSD患者ASUD风险的病理生理途径。我们的研究发现，诸如奥昔布宁、氧化镁、克林霉素、西替利嗪、孟鲁司特和文拉法辛等保护性药物都有可能降低ASUD的风险。
DeepBiomarker2可以高精度预测ASUD风险，并能进一步识别潜在风险因素以及具有有益作用的药物。我们相信我们的方法将有助于在各种临床场景中对PTSD进行个性化干预。
