Using Machine Learning Imputed Outcomes to Assess Drug-Dependent Risk of Self-Harm in Patients with Bipolar Disorder: A Comparative Effectiveness Study

Anastasiya Nestsiarovich   ¹ , MD, PhD ;   Praveen Kumar   ² , MSc ;   Nicolas Raymond Lauve   ² , BSc ;   Nathaniel G Hurwitz   ³ , MD ;   Aurélien J Mazurie   ⁴ , PhD ;   Daniel C Cannon   ⁵ , MS ;   Yiliang Zhu   ⁶ , PhD ;   Stuart James Nelson   ⁷ , MD ;   Annette S Crisanti   ⁸ , PhD ;   Berit Kerner   ⁹ , MD ;   Mauricio Tohen   ⁸ , MD, DrPH, MBA ;   Douglas J Perkins   ¹ , PhD ;   Christophe Gerard Lambert   ^{1, 10} , PhD

¹ Center for Global Health, Department of Internal Medicine, University of New Mexico Health Sciences Center, Albuquerque, NM, United States

² Department of Computer Science, The University of New Mexico, Albuquerque, NM, United States

³ New Mexico Behavioral Health Institute, Las Vegas, NM, United States

⁴ TwoFoldChange Consulting, Bozeman, MT, United States

⁵ Iterative Consulting, Albuquerque, NM, United States

⁶ Division of Epidemiology, Biostatistics, and Preventive Medicine, Department of Internal Medicine, The University of New Mexico Health Sciences Center, Albuquerque, NM, United States

⁷ Biomedical Informatics Center, George Washington University, Washington, DC, DC, United States

⁸ Department of Psychiatry & Behavioral Sciences, University of New Mexico Health Sciences Center, Albuquerque, NM, United States

⁹ Semel Institute for Neuroscience and Human Behavior, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, United States

¹⁰ Division of Translational Informatics, Department of Internal Medicine, University of New Mexico Health Sciences Center, Albuquerque, NM, United States