Predominant polarity classification and associated clinical variables in bipolar disorder: A machine learning approach
Carregando...
Citações na Scopus
19
Tipo de produção
article
Data de publicação
2019
Título da Revista
ISSN da Revista
Título do Volume
Editora
ELSEVIER SCIENCE BV
Autores
BORGES JUNIOR, Renato Gomes
SALVINI, Rogerio
Citação
JOURNAL OF AFFECTIVE DISORDERS, v.245, p.279-282, 2019
Resumo
Background: Bipolar disorder (BD) is a severe psychiatric disorder characterized by periodic episodes of manic and depressive symptomatology. Predominant polarity (PP) appears to be an important specifier of BD. The present study employed machine learning (ML) algorithms to accurately determine a patient ' s PP without the inclusion of number and polarity of past episodes, while exploring associations between PP and demographic and clinical variables. Methods: From a cohort of 148 BD patients, demographic and clinical variables were collected using a customized questionnaire and the SCID-CV. The algorithm employed was the Random-Forest method. The algorithm was programed to classify patients into either depressive or manic predominant polarities and to reveal which variables were associated to the specifier. Results: The algorithm attained an AUC ROC of 74.72% (95% CI = 72.29-77.15%) in classifying patients into either manic or depressive PP. The variables selected by the algorithm were: (1) age at first depressive episode; (2) number of hospitalizations; (3) BD Type II; (4) manic onset; (5) delusions; (6) psychotic features at onset; (7) tobacco addiction; (8) family history of BD; (9) hallucinations; and (10) comorbid anxiety disorders, (11) alcohol dependence, (12) eating disorders and (13) substance dependence. Limitations: The study is limited due to the small sample size, the inclusion of only self-reported and clinician-observed clinical variables and its cross-sectional design. Discussion: The results suggest that the ML approach could be effective in determining a patient ' s PP. Furthermore, although not previously reported, some variables, such as tobacco use and comorbid eating disorders, appear to be closely associated with PP.
Palavras-chave
Bipolar disorder, Predominant polarity, Classifier, Machine Learning
Referências
- American Psychiatric Association (APA), 2013, DIAGN STAT MAN MENT
- Azorin JM, 2015, J AFFECT DISORDERS, V182, P57, DOI 10.1016/j.jad.2015.04.037
- Baldessarini RJ, 2012, ACTA PSYCHIAT SCAND, V125, P293, DOI 10.1111/j.1600-0447.2011.01818.x
- Belizario GO, 2017, INT J BIPOLAR DISORD, V5, DOI 10.1186/s40345-017-0085-5
- Bzdok Danilo, 2018, Biol Psychiatry Cogn Neurosci Neuroimaging, V3, P223, DOI 10.1016/j.bpsc.2017.11.007
- Carvalho AF, 2015, INT J NEUROPSYCHOPH, V18, DOI 10.1093/ijnp/pyu079
- Colom F, 2006, J AFFECT DISORDERS, V93, P13, DOI 10.1016/j.jad.2006.01.032
- Fayyad Usama M., 1996, ADV KNOWLEDGE DISCOV, P1, DOI 10.1609/AIMAG.V17I3.1230
- Ferrari AJ, 2016, BIPOLAR DISORD, V18, P440, DOI 10.1111/bdi.12423
- First M. B, 1996, STRUCTURED CLIN INTE
- Galatzer-Levy I., 2018, DATA SCI RES DOMAIN
- Garcia-Jimenez J., 2017, REV PSIQUIATR SALUD, V286
- Janiri D, 2017, CURR NEUROPHARMACOL, V15, P409, DOI 10.2174/1570159X14666160607101400
- Kohavi Ron, 1995, P INT JOINT C ART IN, P14
- Liaw A., 2002, R NEWS, V2, P18, DOI 10.1177/154405910408300516
- Librenza-Garcia D, 2017, NEUROSCI BIOBEHAV R, V80, P538, DOI 10.1016/j.neubiorev.2017.07.004
- Merikangas KR, 2011, ARCH GEN PSYCHIAT, V68, P241, DOI 10.1001/archgenpsychiatry.2011.12
- Mwangi Benson, 2016, Biol Psychiatry Cogn Neurosci Neuroimaging, V1, P186
- Mwangi B, 2015, PSYCHIAT RES-NEUROIM, V234, P265, DOI 10.1016/j.pscychresns.2015.10.002
- Popovic D, 2014, ACTA PSYCHIAT SCAND, V129, P366, DOI 10.1111/acps.12179
- Salvini R, 2015, STUD HEALTH TECHNOL, V216, P741, DOI 10.3233/978-1-61499-564-7-741
- Vieta E, 2009, J AFFECT DISORDERS, V119, P22, DOI 10.1016/j.jad.2009.02.028