ABSTRACT
Purpose of review: Machine learning, a hot area of research today, has been attempted to be applied in various fields of clinical medicine. This paper reviews the current status of research on machine learning in the filed of bipolar disorder, including applications in the diagnosis, identification and the accurate treatment of bipolar disorder, and the prediction of suicidal behaviors in bipolar disorder. It also discusses the advantages and shortcomings and prospects of the applications of machine learning in bipolar disorder, in order to provide references for related researches and clinical treatment.
Research methods: The literature on the application of machine learning in the field of bipolar disorder in recent years was searched through literature navigation. The aspects of prevention, diagnosis and treatment interventions in bipolar disorder were analyzed.
Research conclusion: In recent years, researches on the clinical diagnosis and treatment of bipolar disorder by machine learning have been increasing. However, there are still some limitations and it still needs to be cautious in clinical application. As mental health practitioners, we should actively adapt to and promote the further development of machine learning in the field of bipolar disorder.
- Laksshman S, Bhat R R, Viswanath V, DeepBipolar: Identifying genomic mutations for bipolar disorder via deep learning [J]. HUMAN MUTATION, 2017, 38(9):1217-1224.Google ScholarCross Ref
- Grande I, Berk M, Birmaher B, Bipolar disorder [J]. LANCET, 2016, 387(10027):1561-1572.Google ScholarCross Ref
- Nunes A, Schnack H G, Ching C R, Using structural MRI to identify bipolar disorders–13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group [J]. Molecular psychiatry, 2020, 25(9):2130-2143.Google ScholarCross Ref
- Ma Y, Ji J, Huang Y, Implementing machine learning in bipolar diagnosis in China [J]. Translational psychiatry, 2019, 9(1):305.Google ScholarCross Ref
- World H O. The ICD-10 classification of mental and behavioural disorders: diagnostic criteria for research [M]. World Health Organization, 1993.Google Scholar
- American Psychiatric Association D, American P A. Diagnostic and statistical manual of mental disorders: DSM-5 [M]. American psychiatric association Washington, DC, 2013.Google Scholar
- Navarro Mateu F, Alonso J, Lim C C, The association between psychotic experiences and disability: results from the WHO World Mental Health Surveys [J]. Acta Psychiatrica Scandinavica, 2017, 136(1):74-84.Google ScholarCross Ref
- Marrie R A, Walld R, Bolton J M, Increased incidence of psychiatric disorders in immune-mediated inflammatory disease [J]. Journal of psychosomatic research, 2017, 101:17-23.Google Scholar
- Fagiolini A, Coluccia A, Maina G, Diagnosis, epidemiology and management of mixed states in bipolar disorder [J]. CNS drugs, 2015, 29:725-740.Google ScholarCross Ref
- Lichtenstein P, Yip B H, Björk C, Common genetic determinants of schizophrenia and bipolar disorder in Swedish families: a population-based study [J]. The Lancet, 2009, 373(9659):234-239.Google ScholarCross Ref
- Paterniti S, Bisserbe J. Pharmacotherapy for bipolar disorder and concordance with treatment guidelines: survey of a general population sample referred to a tertiary care service [J]. BMC psychiatry, 2013, 13:1-12.Google ScholarCross Ref
- Chen G, Chen P, Gong J, Shared and specific patterns of dynamic functional connectivity variability of striato-cortical circuitry in unmedicated bipolar and major depressive disorders [J]. Psychological Medicine, 2022, 52(4):747-756.Google ScholarCross Ref
- Squarcina L, Dagnew T M, Rivolta M W, Automated cortical thickness and skewness feature selection in bipolar disorder using a semi-supervised learning method [J]. Journal of affective disorders, 2019, 256:416-423.Google Scholar
- Mwangi B, Wu M J, Bauer I E, Predictive classification of pediatric bipolar disorder using atlas-based diffusion weighted imaging and support vector machines [J]. PSYCHIATRY RESEARCH-NEUROIMAGING, 2015, 234(2):265-271.Google ScholarCross Ref
- Huang Y, Wang Y U, Wang H, Prevalence of mental disorders in China: a cross-sectional epidemiological study [J]. The Lancet Psychiatry, 2019, 6(3):211-224.Google ScholarCross Ref
- Matsuo K, Harada K, Fujita Y, Distinctive neuroanatomical substrates for depression in bipolar disorder versus major depressive disorder [J]. Cerebral Cortex, 2019, 29(1):202-214.Google ScholarCross Ref
- Rive M M, Redlich R, Schmaal L, Distinguishing medication‐free subjects with unipolar disorder from subjects with bipolar disorder: state matters [J]. Bipolar disorders, 2016, 18(7):612-623.Google ScholarCross Ref
- Erguzel T T, Sayar G H, Tarhan N. Artificial intelligence approach to classify unipolar and bipolar depressive disorders [J]. Neural Computing and Applications, 2016, 27(6):1607-1616.Google ScholarDigital Library
- Johannesen J K, O Donnell B F, Shekhar A, Diagnostic specificity of neurophysiological endophenotypes in schizophrenia and bipolar disorder [J]. Schizophrenia bulletin, 2013, 39(6):1219-1229.Google ScholarCross Ref
- Pirooznia M, Seifuddin F, Judy J, Data mining approaches for genome-wide association of mood disorders [J]. Psychiatric genetics, 2012, 22(2):55.Google ScholarCross Ref
- Dmitrzak-Weglarz M P, Pawlak J M, Maciukiewicz M, Clock gene variants differentiate mood disorders [J]. Molecular biology reports, 2015, 42:277-288.Google Scholar
- Laksshman S, Bhat R R, Viswanath V, DeepBipolar: Identifying genomic mutations for bipolar disorder via deep learning [J]. Human mutation, 2017, 38(9):1217-1224.Google ScholarCross Ref
- Malhi G S, Outhred T, Das P, Modeling suicide in bipolar disorders [J]. Bipolar disorders, 2018, 20(4):334-348.Google ScholarCross Ref
- Hansson C, Joas E, Pålsson E, Risk factors for suicide in bipolar disorder: A cohort study of 12, 850 patients [J]. European Neuropsychopharmacology, 2019, 29(S1).Google ScholarCross Ref
- Franklin J C, Ribeiro J D, Fox K R, Risk factors for suicidal thoughts and behaviors: A meta-analysis of 50 years of research. [J]. Psychological bulletin, 2017, 143(2):187.Google ScholarCross Ref
- Eugene A R, Masiak J, Eugene B. Predicting lithium treatment response in bipolar patients using gender-specific gene expression biomarkers and machine learning [J]. F1000Research, 2018, 7.Google Scholar
- Fleck D E, Ernest N, Adler C M, Prediction of lithium response in first‐episode mania using the LITHium Intelligent Agent (LITHIA): pilot data and proof‐of‐concept [J]. Bipolar disorders, 2017, 19(4):259-272.Google ScholarCross Ref
Index Terms
- Application of machine learning in bipolar disorder
Recommendations
Internet gaming disorder
Online role-playing video games provide opportunities to connect socially and can enhance self-esteem. For some players, however, overuse fosters dependency leading to negative psychosocial and health consequences. Per the American Psychiatric ...
A Machine Learning-Based Method to Identify Bipolar Disorder Patients
AbstractBipolar disorder is a serious psychiatric disorder characterized by periodic episodes of manic and depressive symptomatology. Due to the high percentage of people suffering from severe bipolar and depressive disorders, the modelling, ...
Comments