Differentiating mania/hypomania from happiness using a machine learning analytic approach.

JOURNAL OF AFFECTIVE DISORDERS

卷:281

Article

Parker, Gordon¹  Spoelma, Michael J.¹  Tavella, Gabriela¹  Alda, Martin²  Hajek, Tomas²  Dunner, David L.^3,4  O'Donovan, Claire²  Rybakowski, Janusz K.⁵  Goldberg, Joseph F.⁶  Bayes, Adam^1,7  Sharma, Verinder⁸  Boyce, Philip⁹  Manicavasagar, Vijaya^1,7 

[1] Univ New South Wales, Sch Psychiat, Sydney, NSW, Australia

[2] Dalhousie Univ, Dept Psychiat, Halifax, NS, Canada

[3] Ctr Anxiety & Depress, Mercer Isl, WA USA

[4] Univ Washington, Dept Psychiat & Behav Sci, Seattle, WA 98195 USA

[5] Poznan Univ Med Sci, Dept Adult Psychiat, Poznan, Poland

[6] Icahn Sch Med Mt Sinai, Dept Psychiat, New York, NY 10029 USA

[7] Black Dog Inst, Sydney, NSW, Australia

[8] Western Univ, Dept Psychiat, London, ON, Canada

[9] Univ Sydney, Sydney Med Sch, Discipline Psychiat, Sydney, NSW, Australia

关键词: Bipolar disorder;    Major depression;    Psychiatric diagnosis;    Mania;    Hypomania;    Machine learning;   

DOI  :  10.1016/j.jad.2020.12.058

来源: Elsevier

【 摘 要 】

Background: This study aimed to improve the accuracy of bipolar disorder diagnoses by identifying symptoms that help to distinguish mania/hypomania in bipolar disorders from general 'happiness' in those with unipolar depression. Methods: An international sample of 165 bipolar and 29 unipolar depression patients (as diagnosed by their clinician) were recruited. All participants were required to rate a set of 96 symptoms with regards to whether they typified their experiences of manic/hypomanic states (for bipolar patients) or when they were 'happy' (unipolar patients). A machine learning paradigm (prediction rule ensembles; PREs) was used to derive rule ensembles that identified which of the 94 non-psychotic symptoms and their combinations best predicted clinically-allocated diagnoses. Results: The PREs were highly accurate at predicting clinician bipolar and unipolar diagnoses (92% and 91% respectively). A total of 20 items were identified from the analyses, which were all highly discriminating across the two conditions. When compared to a classificatory approach insensitive to the weightings of the items, the ensembles were of comparable accuracy in their discriminatory capacity despite the unbalanced sample. This illustrates the potential for PREs to supersede traditional classificatory approaches. Limitations: There were considerably less unipolar than bipolar patients in the sample, which limited the overall accuracy of the PREs. Conclusions: The consideration of symptoms outlined in this study should assist clinicians in distinguishing between bipolar and unipolar disorders. Future research will seek to further refine and validate these symptoms in a larger and more balanced sample.

【 授权许可】

Free