Gordon Parker1, Michael J Spoelma2, Gabriela Tavella2, Martin Alda3, Tomas Hajek3, David L Dunner4, Claire O'Donovan3, Janusz K Rybakowski5, Joseph F Goldberg6, Adam Bayes7, Verinder Sharma8, Philip Boyce9, Vijaya Manicavasagar7. 1. School of Psychiatry, University of New South Wales, Sydney, Australia. Electronic address: g.parker@unsw.edu.au. 2. School of Psychiatry, University of New South Wales, Sydney, Australia. 3. Department of Psychiatry, Dalhousie University, Halifax, Nova Scotia, Canada. 4. Center for Anxiety and Depression, Mercer Island, Washington, United States; Department of Psychiatry and Behavioral Sciences, University of Washington, Seattle, Washington, United States. 5. Department of Adult Psychiatry, Poznan University of Medical Sciences, Poznan, Poland. 6. Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, United States. 7. School of Psychiatry, University of New South Wales, Sydney, Australia; Black Dog Institute, Sydney, Australia. 8. Department of Psychiatry, Western University, London, Ontario, Canada. 9. Discipline of Psychiatry, Sydney Medical School, University of Sydney, Sydney, Australia.
Abstract
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.
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 depressionpatients (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.