A machine learning algorithm to differentiate bipolar disorder from major depressive disorder using an online mental health questionnaire and blood biomarker data

Download

s41398-020-01181-x.pdf

Date

2021-01-01

Author

Tomasik, Jakub
Han, Sung Yeon Sarah
Barton-Owen, Giles
Mirea, Dan-Mircea
Martin-Key, Nayra A.
Rustogi, Nitin
Lago, Santiago G.
Olmert, Tony
Cooper, Jason D.
Özcan Kabasakal, Süreyya
Eljasz, Pawel
Thomas, Gregoire
Tuytten, Robin
Metcalfe, Tim
Schei, Thea S.
Farrag, Lynn P.
Friend, Lauren V.
Bell, Emily
Cowell, Dan
Bahn, Sabine

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

135
views

27
downloads

The vast personal and economic burden of mood disorders is largely caused by their under- and misdiagnosis, which is associated with ineffective treatment and worsening of outcomes. Here, we aimed to develop a diagnostic algorithm, based on an online questionnaire and blood biomarker data, to reduce the misdiagnosis of bipolar disorder (BD) as major depressive disorder (MDD). Individuals with depressive symptoms (Patient Health Questionnaire-9 score >= 5) aged 18-45 years were recruited online. After completing a purpose-built online mental health questionnaire, eligible participants provided dried blood spot samples for biomarker analysis and underwent the World Health Organization World Mental Health Composite International Diagnostic Interview via telephone, to establish their mental health diagnosis. Extreme Gradient Boosting and nested cross-validation were used to train and validate diagnostic models differentiating BD from MDD in participants who self-reported a current MDD diagnosis. Mean test area under the receiver operating characteristic curve (AUROC) for separating participants with BD diagnosed as MDD (N = 126) from those with correct MDD diagnosis (N = 187) was 0.92 (95% CI: 0.86-0.97). Core predictors included elevated mood, grandiosity, talkativeness, recklessness and risky behaviour. Additional validation in participants with no previous mood disorder diagnosis showed AUROCs of 0.89 (0.86-0.91) and 0.90 (0.87-0.91) for separating newly diagnosed BD (N = 98) from MDD (N = 112) and subclinical low mood (N = 120), respectively. Validation in participants with a previous diagnosis of BD (N = 45) demonstrated sensitivity of 0.86 (0.57-0.96). The diagnostic algorithm accurately identified patients with BD in various clinical scenarios, and could help expedite accurate clinical diagnosis and treatment of BD.

URI

https://hdl.handle.net/11511/88826

Journal

TRANSLATIONAL PSYCHIATRY

DOI

https://doi.org/10.1038/s41398-020-01181-x

Collections

Department of Chemistry, Article

Suggestions

OpenMETU
Core

A Combined Digital and Biomarker Diagnostic Aid for Mood Disorders (the Delta Trial): Protocol for an Observational Study Olmert, Tony; Cooper, Jason D.; Han, Sung Yeon Sarah; Barton-Owen, Giles; Farrag, Lynn; Bell, Emily; Friend, Lauren V.; Özcan Kabasakal, Süreyya; Rustogi, Nitin; Preece, Rhian L.; Eljasz, Pawel; Tomasik, Jakub; Cowell, Daniel; Bahn, Sabine (2020-08-01) Background: Mood disorders affect hundreds of millions of people worldwide, imposing a substantial medical and economic burden. Existing diagnostic methods for mood disorders often result in a delay until accurate diagnosis, exacerbating the challenges of these disorders. Advances in digital tools for psychiatry and understanding the biological basis of mood disorders offer the potential for novel diagnostic methods that facilitate early and accurate diagnosis of patients.
Development of self-stigma inventory for patients with schizophrenia (SSI-P): reliability and validity study Yıldız, Mustafa; Kiras, Fatma; Incedere, Aysel; Abut, Fatma Betül (2019-10-01) OBJECTIVES: Internalizing the public stigma in patients with schizophrenia leads to self-stigmatization associated with a number of negative consequences such as depression, low self-esteem, hopelessness, impairment of social adaptation, unemployment, and treatment non-adherence. No instruments have been developed to assess the self-stigmatization for patients with schizophrenia living in Turkey. The purpose of this study was to develop a culturally-sensitive and easy-to-use instrument to measure self-stigm...
A signal transduction score flow algorithm for cyclic cellular pathway analysis, which combines transcriptome and ChIP-seq data Isik, Zerrin; Ersahin, Tulin; Atalay, Mehmet Volkan; AYKANAT, CEVDET; Atalay, Rengül (2012-01-01) Determination of cell signalling behaviour is crucial for understanding the physiological response to a specific stimulus or drug treatment. Current approaches for large-scale data analysis do not effectively incorporate critical topological information provided by the signalling network. We herein describe a novel model- and data-driven hybrid approach, or signal transduction score flow algorithm, which allows quantitative visualization of cyclic cell signalling pathways that lead to ultimate cell response...
A Phase-field Approach to Model Aortic Dissections Gültekin, Osman; Dal, Hüsnü; Holzapfel, Gerhard A. (null; 2018-07-06) Physiological and pathological aspects of aortic dissection are important issues in medical science , and undoubtedly require a deeper understanding of the respective mechanics that is behind these phenomenon. This has rendered computational mechanics very important to improve and even guide monitoring and preoperative planning [1]. In particular, the in silico estimation of the macro-scopic crack initiation and its propagation associated with aortic dissection purports valuable data for the clinics. The pr...
A Lab-on-a-chip system integrating dielectrophoretic detection and impedance counting units for chemotherapy guidance in leukemia Demircan Yalçın, Yağmur; Külah, Haluk; Department of Electrical and Electronics Engineering (2018) Precision medicine is defined as therapies, directed to the requirements of individual patients on the basis of genetic, biomarker, phenotypic, or psychosocial characteristics, discriminating a given patient from others with similar clinical states. Oncology is the foremost application area of precision medicine. Although the aim of precision medicine is very clear and simple, the clinical practice of it in cancer patients has some challenges, such as tumor heterogeneity. Tumor heterogeneity can be the most...

Citation Formats

J. Tomasik et al., “A machine learning algorithm to differentiate bipolar disorder from major depressive disorder using an online mental health questionnaire and blood biomarker data,” TRANSLATIONAL PSYCHIATRY, pp. 0–0, 2021, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/88826.