DeepBiomarker: Identifying Important Lab Tests from Electronic Medical Records for the Prediction of Suicide-Related Events among PTSD Patients

Abstract

Identifying patients with high risk of suicide is critical for suicide prevention. We examined lab tests together with medication use and diagnosis from electronic medical records (EMR) data for prediction of suicide-related events (SREs; suicidal ideations, attempts and deaths) in post-traumatic stress disorder (PTSD) patients, a population with a high risk of suicide. We developed DeepBiomarker, a deep-learning model through augmenting the data, including lab tests, and integrating contribution analysis for key factor identification. We applied DeepBiomarker to analyze EMR data of 38,807 PTSD patients from the University of Pittsburgh Medical Center. Our model predicted whether a patient would have an SRE within the following 3 months with an area under curve score of 0.930. Through contribution analysis, we identified important lab tests for suicide prediction. These identified factors imply that the regulation of the immune system, respiratory system, cardiovascular system, and gut microbiome were involved in shaping the pathophysiological pathways promoting depression and suicidal risks in PTSD patients. Our results showed that abnormal lab tests combined with medication use and diagnosis could facilitate predicting SRE risk. Moreover, this may imply beneficial effects for suicide prevention by treating comorbidities associated with these biomarkers.

Disentangling the effects of PTSD from Gulf War Illness in male veterans via a systems-wide analysis of immune cell, cytokine, and symptom measures

“…While all groups had hematocrit values within this range the GWI H condition had a statistically significantly higher level than control with a medium effect size. This lower level, however, is at odds with prior studies finding elevated HCT levels in PTSD compared to control [ 99 – 101 ]. While pathologically increased HCT is associated with hypercoagulability [ 102 ], and long-term risk of cardiovascular mortality [ 103 ], decreased HCT is associated with anemia.…”

Machine learning and the prediction of suicide in psychiatric populations: a systematic review

“… Zheng et al, [ 108 ] 52 MDD with suicidal attemps (40/12); 61 MDD without suicidal attempts (36/25); 98 HC (49/49) MDD Not specified XBoost Sociodemographic, clinical and cognitive features (total: 20 features) Suicide attempts Acc: 0.71 AUC: 0.82 Sens: 0.6 Spec: 0.79 PPV: 0.69 NPV: 0.71 Adding cognitive information significantly increased model prediction; the most important feature was HAMD-24 score Shin et al, [ 70 ] 83 MDD (64/19); 83 HC (69/14) MDD Not specified Naive Bayes classifier (5-folds CV) Sociodemographic and text-based High vs low-risk suicide (based on the MINI interview) Acc: 0.75 AUC: 0.80 Sens: 0.82 Spec: 0.65 When predicting suicide, only the ensemble analyses (namely, sociodemographic + text) resulted in significant prediction. Demographic alone: AUC 0.5 Text alone: AUC 0.64 Miranda et al, [ 36 ] 38807 PTSD patients PTSD Not specified RNN EMRs, including sociodemographic, clinical and lab features (>100 features) Suicide-related events within 3 months AUC:0.92 Lab tests (i.e., glucose, glucose urine, chloride, hemoglobin (HGB), hematocrit, mean corpuscular volume, white blood cell, neutrophils, potassium, INR, calcium, mean platelet volume) combined with medications and diagnoses can enhance the prediction of suicide in PTSD patients. Zelkowitz et al, [ 32 ] 3166 (1789/1377) Mixed diagnoses (not specified) Not specified RF, CART (10-folds CV) >700 demographic and clinical features Nonfatal suicide attempt within 30 days RF AUC: 0.86 for men AUC: 0.86 for women CART AUC: 0.79 for men AUC: 0.81 for women Women: Histories of self-poisoning, substance-related disorders, and eating disorders were important predictors.…”

“…Regarding the predicted outcome, 41 (51%) studies used ML to predict lifetime suicide attempts (e.g., retrospective assessed past attempts), while only 16 (19.7%) longitudinally assessed the risk of suicide using future risk/attempts as an outcome. Specifically, five studies [ 28 – 32 ] predicted the attempts/death at 1 month after the actual evaluation, the study by Chen and colleagues [ 33 ] predicted suicide attempts at both one and 3 months from the assessment, while three studies [ 34 – 36 ] predicted suicide risk at three months, and Nock and colleagues [ 37 ] predicted suicide between 1 and 6 months. Three studies [ 38 – 40 ] predicted suicide attempts at 12 months, and one study [ 41 ] stratified suicide risk at 12 months after the actual assessment.…”

“…Only four studies (4.9%) focused on genetics and epigenetics features in order to predict suicide, and a single study [ 46 ] explored the predictive value of the human metabolome, employing 123 plasma metabolites, to predict suicide. Lastly, three studies [ 36 , 51 , 83 ] used blood biochemistry in association with clinical and sociodemographic data.…”

Unveiling the Enigma: Exploring Risk Factors and Mechanisms for Psychotic Symptoms in Alzheimer’s Disease through Electronic Medical Records with Deep Learning Models

“…In our previous study, we built a deep-learning-based model, DeepBiomarker, through modification of an established deep-learning framework, Pytorch_EHR [33,34]. In DeepBiomarker, we used diagnosis, medication use, and lab tests as the input, implemented data augmentation technologies to improve the model performance, and also integrated a perturbation-based approach [35] for risk factor identification.…”