Can machine learning identify childhood characteristics that predict future development of bipolar disorder a decade later?

Early identification of bipolar disorder may provide appropriate support and treatment, however there is no current evidence for statistically predicting whether a child will develop bipolar disorder. Machine learning methods offer an opportunity for developing empirically-based predictors of bipolar disorder. This study examined whether bipolar disorder can be predicted using clinical data and machine learning algorithms. 492 children, ages 6-18 at baseline, were recruited from longitudinal case-control family studies. Participants were assessed at baseline, then followed-up after 10 years. In addition to sociodemographic data, children were assessed with psychometric scales, structured diagnostic interviews, and cognitive and social functioning assessments. Using the Balanced Random Forest algorithm, we examined whether the diagnostic outcome of full or subsyndromal bipolar disorder could be predicted from baseline data. 45 children (10%) developed bipolar disorder at follow-up. The model predicted subsequent bipolar disorder with 75% sensitivity, 76% specificity, and an Area Under the Receiver Operating Characteristics of 75%. Predictors best differentiating between children who did or did not develop bipolar disorder were the Child Behavioral Checklist Externalizing and Internalizing behaviors, the Child Behavioral Checklist Total t-score, problematic school functions indexed through the Child Behavioral Checklist School Competence scale, and the Child Behavioral Checklist Anxiety/Depression and Aggression scales. Our study provides the first quantitative model to predict bipolar disorder. Longitudinal prediction may help clinicians assess children with emergent psychopathology for future risk of bipolar disorder, an area of clinical and scientific importance. Machine learning algorithms could be implemented to alert clinicians to risk for bipolar disorder.
Competing Interests: Declaration of competing interest Dr. Mai Uchida is partially supported by a K award, grant number 1K23MH122667-01. Dr. Uchida also provided a one-time consultation to the Moderna scientific advisory board. Allison Green received funding from the Eunice Kennedy Shriver National Institute of Child Health & Human Development of the National Institutes of Health under award number T32HD007475. In the past year, Dr. Faraone received income, potential income, travel expenses continuing education support and/or research support from Aardvark, Akili, Genomind, Ironshore, KemPharm/Corium, Noven, Ondosis, Otsuka, Rhodes, Supernus, Takeda, Tris and Vallon. With his institution, he has US patent US20130217707 A1 for the use of sodium-hydrogen exchange inhibitors in the treatment of ADHD. In previous years, he received support from: Alcobra, Arbor, Aveksham, CogCubed, Eli Lilly, Enzymotec, Impact, Janssen, Lundbeck/Takeda, McNeil, NeuroLifeSciences, Neurovance, Novartis, Pfizer, Shire, and Sunovion. He also receives royalties from books published by Guilford Press: Straight Talk about Your Child's Mental Health; Oxford University Press: Schizophrenia: The Facts; and Elsevier: ADHD: Non-Pharmacologic Interventions. He is also Program Director of www.adhdinadults.com. Dr. Faraone is supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No 965381; NIMH grants U01AR076092-01A1, 1R21MH1264940, R01MH116037; Oregon Health and Science University, Otsuka Pharmaceuticals, Noven Pharmaceuticals Incorporated, and Supernus Pharmaceutical Company. Dr. Joseph Biederman is currently receiving research support from the following sources: AACAP, Feinstein Institute for Medical Research, Genentech, Headspace Inc., NIDA, Pfizer Pharmaceuticals, Roche TCRC Inc., Sunovion Pharmaceuticals Inc., Takeda/Shire Pharmaceuticals Inc., Tris, and NIH. Dr. Biederman and his program have received royalties from a copyrighted rating scale used for ADHD diagnoses, paid by Biomarin, Bracket Global, Cogstate, Ingenix, Medavent Prophase, Shire/Takeda, Sunovion, and Theravance; these royalties were paid to the Department of Psychiatry at MGH. Through Partners Healthcare Innovation, Dr. Biederman has a partnership with MEMOTEXT to commercialize a digital health intervention to improve adherence in ADHD. Through MGH corporate licensing, Dr. Biederman has a US Patent (#14/027,676) for a non-stimulant treatment for ADHD, a US Patent (#10,245,271 B2) on a treatment of impaired cognitive flexibility, and a patent pending (#61/233,686) on a method to prevent stimulant abuse. In 2022: Dr. Biederman received honoraria from the MGH Psychiatry Academy for tuition-funded CME courses. In 2021: Dr. Biederman received an honorarium for a scientific presentation from Multi-Health Systems, and a one-time consultation for Cowen Healthcare Investments. He received honoraria from AACAP, the American Psychiatric Nurses Association, BIAL - Portela & C(a). S.A. (Portugal), Medscape Education, and MGH Psychiatry Academy for tuition-funded CME courses. In 2020: Dr. Biederman received an honorarium for a scientific presentation from Tris and from the Institute of Integrated Sciences – INI (Brazil), and research support from the Food & Drug Administration. He received honoraria from Medlearning Inc, NYU, and MGH Psychiatry Academy for tuition-funded CME courses. In 2019, Dr. Biederman was a consultant for Akili, Avekshan, Jazz Pharma, and Shire/Takeda. He received research support from Lundbeck AS and Neurocentria Inc. Through MGH CTNI, he participated in a scientific advisory board for Supernus. He received honoraria from the MGH Psychiatry Academy for tuition-funded CME courses. Dr. Qasim Bukhari, Ms. Maura DiSalvo, Dr. Guilla Serra, Ms. Chloe Hutt Vater, Dr. Satrajit Ghosh, and Dr. John Gabrieli do not have any financial relationships to disclose.
(Copyright © 2022 Elsevier Ltd. All rights reserved.)