Using machine learning to develop a clinical prediction model for SSRI-associated bleeding: a feasibility study.

INTRODUCTION: Adverse drug events (ADEs) are associated with poor outcomes and increased costs but may be prevented with prediction tools. With the National Institute of Health All of Us (AoU) database, we employed machine learning (ML) to predict selective serotonin reuptake inhibitor (SSRI)-associated bleeding. METHODS: The AoU program, beginning in 05/2018, continues to recruit ≥ 18 years old individuals across the United States. Participants completed surveys and consented to contribute electronic health record (EHR) for research. Using the EHR, we determined participants who were exposed to SSRIs (citalopram, escitalopram, fluoxetine, fluvoxamine, paroxetine, sertraline, vortioxetine). Features (n = 88) were selected with clinicians' input and comprised sociodemographic, lifestyle, comorbidities, and medication use information. We identified bleeding events with validated EHR algorithms and applied logistic regression, decision tree, random forest, and extreme gradient boost to predict bleeding during SSRI exposure. We assessed model performance with area under the receiver operating characteristic curve statistic (AUC) and defined clinically significant features as resulting in > 0.01 decline in AUC after removal from the model, in three of four ML models. RESULTS: There were 10,362 participants exposed to SSRIs, with 9.6% experiencing a bleeding event during SSRI exposure. For each SSRI, performance across all four ML models was relatively consistent. AUCs from the best models ranged 0.632-0.698. Clinically significant features included health literacy for escitalopram, and bleeding history and socioeconomic status for all SSRIs. CONCLUSIONS: We demonstrated feasibility of predicting ADEs using ML. Incorporating genomic features and drug interactions with deep learning models may improve ADE prediction.

Study of Sleep Disorders among Young Children Using Hindi Translated and Validated Version of Pediatric Sleep Questionnaire.

OBJECTIVE: The objective of this study is to assess the prevalence of sleep disorders among children aging between 4 and 9 years using Hindi version of Pediatric Sleep Questionnaire (PSQ). METHODS: This study had two parts first, translation and validation of PSQ into Hindi language, and second, assessment of the prevalence of sleep disorders using PSQ Hindi version. Hindi PSQ was distributed in randomly chosen primary schools in a semi-urban area. The children were requested to get them filled by their parents. When the questionnaires were returned, responses were analyzed. RESULTS: Most of the items of the Hindi version had perfect agreement with original questionnaire in a bilingual population (κ =1). Totally, 435 children were included in the field study having average age of 6.3 years. Obstructive sleep apnea was reported in 7.5% children; symptoms suggestive of restless legs syndrome were reported by 2%-3%; teeth grinding by 13.9% and sleep talking by 22.6% children. CONCLUSION: PSQ Hindi version is a validated tool to screen for sleep disorders among children. Sleep disorders are fairly prevalent among young children in India.