Smartphone-based biomarkers, woman talking on the phone

Smartphone-based biomarkers in patients with bipolar disorder, unaffected relatives, and control individuals

Smartphone-based self-reported and automatically collected data may represent a potential diagnostic marker in patients with bipolar disorder.

Background

Bipolar disorder is a severe mental illness affecting 2% of the population that is characterized by recurrent changes in mood with depressive and (hypo)manic episodes (1). Accurate diagnosis of bipolar disorder is a challenge, and patients often experience symptoms for years before correct diagnosis and treatment is initiated (2). Because of the progressive nature of bipolar disorder, including increased risk of new episodes, longer duration of episodes, and more intense symptom severity during episodes, delayed diagnosis can have consequences (3).

Bipolar disorder is characterized by changes in behavioral activities (e.g. physical activity, speech) during depression and (hypo)mania. Currently bipolar disorder diagnosis and assessment of illness severity are based on clinical evaluation and self-reports. Self-reported measures of depressive and manic symptoms are often influenced by decreased illness insight and recall bias, when mood is monitored retrospectively.
Electronic devices, such as smartphones, offers a platform capable of monitoring and collecting objective data on behavioral activities in an unobtrusive manner and to monitor self-reported symptom severity more continuously, fine-grained and in real time settings. Today smartphone-based self-report of symptoms has been demonstrated feasible in several studies (4).

The present study is part of a large longitudinal cohort study in patients with bipolar disorder (the Bipolar Illness Onset study, the BIO study) (5).

Project objectives

In this study we aim to investigate whether smartphone-based self-reported and automatically generated data can:

1. Discriminate between patients with a newly diagnoses of bipolar
    disorder, their unaffected relatives and control individuals
2. Discriminate between manic states, depressive states and euthymia

All participants in the study will use a smartphone application on a daily basis. The application can collect automatically generated objective- and self-reported data. Self-reported data include daily registering of mood, sleep, activity level and medicine intake. Automatically generated objective data include phone usage, social activity, physical activity, mobility and voice features.
Potentially this study can help improve accurate diagnosis of bipolar disorder, leading to improved quality of life for patients with bipolar disorder.

References

1. Merikangas KR, Akiskal HS, Angst J, Greenberg PE, Hirschfeld RM, Petukhova M, et al. Lifetime and 12-month prevalence of bipolar spectrum disorder in the National Comorbidity Survey replication. Archives of general psychiatry. 2007;64(5):543-52.
2. Kessing LV. Diagnostic stability in bipolar disorder in clinical practise as according to ICD-10. Journal of affective disorders. 2005;85(3):293-9.
3. Kessing LV, Andersen PK. Evidence for clinical progression of unipolar and bipolar disorders. Acta Psychiatr Scand. 2017;135(1):51-64.
4. Faurholt-Jepsen M, Munkholm K, Frost M, Bardram JE, Kessing LV. Electronic self-monitoring of mood using IT platforms in adult patients with bipolar disorder: A systematic review of the validity and evidence. BMC Psychiatry. 2016;16:7.
5. Kessing LV, Munkholm K, Faurholt-Jepsen M, Miskowiak KW, Nielsen LB, Frikke-Schmidt R, et al. The Bipolar Illness Onset study: research protocol for the BIO cohort study. BMJ Open. 2017;7(6):e015462.

FUNDING

CACHET icon
This project is funded by CACHET and Region Hovedstadens Psykiatri.

PARTNERS

Contact

Sharleny Stanislaus
PhD student
Psychiatric Center Copenhagen

Contact

Maria Faurholt-Jepsen
Postdoc
Psychiatric Center Copenhagen
+45 38 64 70 73

Contact

Jakob Eyvind Bardram
Professor
DTU Compute
+45 45 25 53 11

Contact

Lars Vedel Kessing
Professor
Psychiatric Center Copenhagen, Rigshospitalet
+45 38 64 70 81
http://www.cachet.dk/research/phd-projects/smartphone-based-biomarkers
17 DECEMBER 2018