Utilizing Machine Learning to Forecast 3-Month Remission Outcomes in Bipolar Disorder Patients Treated with Lithium

Abstract

Introduction

Lithium remains a first-line mood stabilizer for bipolar disorder; yet, only a subset of patients achieves symptomatic remission. Early prediction of treatment response could guide personalized management. In this study, we leveraged machine learning algorithms to predict 3-month remission, defined as a Montgomery–Åsberg Depression Rating Scale score≤10, in 593 patients with bipolar disorder initiating lithium.

Methods

In this retrospective cohort, baseline sociodemographic, clinical and laboratory data as well as concomitant medication usage were collected. Montgomery Åsberg Depression Rating Scale and Mania Rating Scale were administered at baseline and 3 months. Data were preprocessed (missing imputation and normalization) and then split into 80% training and 20% test sets. We evaluated various machine learning techniques such as random forest, XGBoost, neural network and support vector machines with five-fold cross validation. Performance metrics included area under the receiver operating characteristic curve and accuracy.

Results

The mean age was 44±16.9 years and 53% of participants were females. The remission rate at 3 months was 44%. The random forest model (augmented by polynomial transformations) performed best (area under the receiver operating characteristic curve=0.76 and accuracy=0.64) improving by 10% of the standard logistic model. Key predictors included the baseline Montgomery Åsberg Depression Rating Scale and Mania Rating Scale, creatinine, thyroid-stimulating hormone levels, body mass index and age.

Discussion

Machine learning, particularly gradient boosted trees, can help to predict the 3-month remission in bipolar disorder patients who start lithium therapy. Incorporating clinical and laboratory features enhances the early identification of likely responders, enabling personalized treatment strategies.

Keywords

Lithium - bipolar disorder - machine learning - remission

Publication History

Received: 25 June 2025

Accepted after revision: 11 November 2025

Article published online:
19 December 2025

• References

• 1 Hui TP, Kandola A, Shen L. et al. A systematic review and meta-analysis of clinical predictors of lithium response in bipolar disorder. Acta Psychiatrica Scand 2019; 140: 94
• 2 Sesso G, Bargnesi F, Olzi F. et al. Efficacy and Safety of Lithium for Suicide and Suicide-Related Behaviors in Youth: A Review of the Literature. Brain Sci 2024; 14: 1139
• 3 Köhler-Forsberg O, Sloth KH, Sylvia LG. et al. Response and remission rates during 24 weeks of mood-stabilizing treatment for bipolar depression depending on early non-response. Psychiatry Res 2021; 305: 114194
• 4 Cole DP, Thase ME, Mallinger AG. et al. Slower Treatment Response in Bipolar Depression Predicted by Lower Pretreatment Thyroid Function. AJP 2002; 159: 116-121
• 5 Duce HL, Duff CJ, Zaidi S. et al. Evaluation of thyroid function monitoring in people treated with lithium: Advice based on real-world data. Bipolar Disord 2023; 25: 402-409
• 6 Pardossi S, Pinzi M, Cattolico M. et al. Insights into the Incidence, Course, and Management of Lithium-Induced Hypothyroidism in Real-World Psychiatric Practice in Italy. Pharmaceuticals 2024; 17: 1425
• 7 Banerjee U, Dasgupta A, Rout JK. et al. Effects of lithium therapy on Na+–K+-ATPase activity and lipid peroxidation in bipolar disorder. Prog Neuro-Psychopharmacol Biol Psychiatry 2012; 37: 56-61
• 8 Chan JKN, Solmi M, Correll CU. et al. Lithium for Bipolar Disorder and Risk of Thyroid Dysfunction and Chronic Kidney Disease. JAMA Netw Open 2025; 8: e2458608
• 9 Chen ZS, Kulkarni P, Galatzer-Levy IR. et al. Modern Views of Machine Learning for Precision Psychiatry. Patterns 2022; 3: 100602
• 10 Campos-Ugaz WA, Garay JPP, Rivera-Lozada O. et al. An Overview of Bipolar Disorder Diagnosis Using Machine Learning Approaches: Clinical Opportunities and Challenges. Iran J Psychiatry 2023; 18: 237
• 11 Joslyn C, Hawes DJ, Hunt C. et al. Is age of onset associated with severity, prognosis, and clinical features in bipolar disorder? A meta-analytic review. Bipolar Disord 2016; 18: 389-403
• 12 Malhi GS, Gessler D, Outhred T. The use of lithium for the treatment of bipolar disorder: Recommendations from clinical practice guidelines. J Affect Disord 2017; 217: 266-280
• 13 Amanollahi M, Jameie M, Looha MA. et al. Machine learning applied to the prediction of relapse, hospitalization, and suicide in bipolar disorder using neuroimaging and clinical data: A systematic review. J Affect Disord 2024; 361: 778-797
• 14 Marrero-Polanco J, Joyce JB, Grant CW. et al. Predicting remission after acute phase pharmacotherapy in patients with bipolar I depression: A machine learning approach with cross-trial and cross-drug replication. Bipolar Disord 2025; 27: 36-46
• 15 Nunes A, Ardau R, Berghöfer A. et al. Prediction of lithium response using clinical data. Acta Psychiatr Scand 2020; 141: 131-141
• 16 Fleck DE, Ernest N, Adler CM. et al. Prediction of lithium response in first-episode mania using the LITHium Intelligent Agent (LITHIA): Pilot data and proof-of-concept. Bipolar Disord 2017; 19: 259-272
• 17 Feng X, Ma Y, Ruan S. et al. Utilizing AI models to identify and predict phase transition patterns of bipolar disorder patients. J Big Data 2025; 12: 102
• 18 Wallert J, Boberg J, Kaldo V. et al. Predicting remission after internet-delivered psychotherapy in patients with depression using machine learning and multi-modal data. Transl Psychiatry 2022; 12: 1-10
• 19 Cearns M, Amare AT, Schubert KO. et al. Using polygenic scores and clinical data for bipolar disorder patient stratification and lithium response prediction: machine learning approach. Br J Psychiatry 2022; 220 (04) 219-228
• 20 Toniolo RA, Silva M, Fernandes F, de BF. et al. A randomized, double-blind, placebo-controlled, proof-of-concept trial of creatine monohydrate as adjunctive treatment for bipolar depression. J Neural Transm 2017; 125: 247
• 21 Romão J, Melo A, André R. et al. Machine Learning as a Tool to Find New Pharmacological Targets in Mood Disorders: A Systematic Review. Curr Treat Options Psych 2024; 11: 241-264
• 22 Pigoni A, Delvecchio G, Madonna D. et al. Can Machine Learning help us in dealing with treatment resistant depression? A review. J Affect Disord 2019; 259: 21-26
• 23 Zhou Y, Li Y, Wang C, Liu T. An overview of bipolar disorder diagnosis using machine learning approaches: Clinical opportunities and challenges. Front Psychiatry 2024; 15: 1369894