Using digital phenotyping to classify bipolar disorder and unipolar disorder – exploratory findings using machine learning models

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Using digital phenotyping to classify bipolar disorder and unipolar disorder – exploratory findings using machine learning models. / Faurholt-Jepsen, Maria; Rohani, Darius Adam; Busk, Jonas; Tønning, Morten Lindberg; Frost, Mads; Bardram, Jakob Eyvind; Kessing, Lars Vedel.

I: European Neuropsychopharmacology, Bind 81, 2024, s. 12-19.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Faurholt-Jepsen, M, Rohani, DA, Busk, J, Tønning, ML, Frost, M, Bardram, JE & Kessing, LV 2024, 'Using digital phenotyping to classify bipolar disorder and unipolar disorder – exploratory findings using machine learning models', European Neuropsychopharmacology, bind 81, s. 12-19. https://doi.org/10.1016/j.euroneuro.2024.01.003

APA

Faurholt-Jepsen, M., Rohani, D. A., Busk, J., Tønning, M. L., Frost, M., Bardram, J. E., & Kessing, L. V. (2024). Using digital phenotyping to classify bipolar disorder and unipolar disorder – exploratory findings using machine learning models. European Neuropsychopharmacology, 81, 12-19. https://doi.org/10.1016/j.euroneuro.2024.01.003

Vancouver

Faurholt-Jepsen M, Rohani DA, Busk J, Tønning ML, Frost M, Bardram JE o.a. Using digital phenotyping to classify bipolar disorder and unipolar disorder – exploratory findings using machine learning models. European Neuropsychopharmacology. 2024;81:12-19. https://doi.org/10.1016/j.euroneuro.2024.01.003

Author

Faurholt-Jepsen, Maria ; Rohani, Darius Adam ; Busk, Jonas ; Tønning, Morten Lindberg ; Frost, Mads ; Bardram, Jakob Eyvind ; Kessing, Lars Vedel. / Using digital phenotyping to classify bipolar disorder and unipolar disorder – exploratory findings using machine learning models. I: European Neuropsychopharmacology. 2024 ; Bind 81. s. 12-19.

Bibtex

@article{79ada8c9abcf4bbc8ddd2053b740bde5,

title = "Using digital phenotyping to classify bipolar disorder and unipolar disorder – exploratory findings using machine learning models",

abstract = "The aims were to investigate 1) differences in smartphone-based data on phone usage between bipolar disorder (BD) and unipolar disorder (UD) and 2) by using machine learning models, the sensitivity, specificity, and AUC of the combined smartphone data in classifying BD and UD. Daily smartphone-based self-assessments of mood and same-time passively collected smartphone data on smartphone usage was available for six months. A total of 64 patients with BD and 74 patients with UD were included. Patients with BD during euthymic states compared with UD in euthymic states had a lower number of incoming phone calls/ day (B: -0.70, 95%CI: -1.37; -0.70, p = 0.040). Patients with BD during depressive states had a lower number of incoming and outgoing phone calls/ day as compared with patients with UD in depressive states. In classification by using machine learning models, 1) overall (regardless of the affective state), patients with BD were classified with an AUC of 0.84, which reduced to 0.48 when using a leave-one-patient-out crossvalidation (LOOCV) approach; similarly 2) during a depressive state, patients with BD were classified with an AUC of 0.86, which reduced to 0.42 with LOOCV; 3) during a euthymic state, patients with BD were classified with an AUC of 0.87, which reduced to 0.46 with LOOCV. While digital phenotyping shows promise in differentiating between patients with BD and UD, it highlights the challenge of generalizing to unseen individuals. It should serve as an complement to comprehensive clinical evaluation by clinicians.",

keywords = "Bipolar disorder, Digital phenotyping, Smartphone, Unipolar disorder",

author = "Maria Faurholt-Jepsen and Rohani, {Darius Adam} and Jonas Busk and T{\o}nning, {Morten Lindberg} and Mads Frost and Bardram, {Jakob Eyvind} and Kessing, {Lars Vedel}",

note = "Publisher Copyright: {\textcopyright} 2024 Elsevier B.V. and ECNP",

year = "2024",

doi = "10.1016/j.euroneuro.2024.01.003",

language = "English",

volume = "81",

pages = "12--19",

journal = "European Neuropsychopharmacology",

issn = "0924-977X",

publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Using digital phenotyping to classify bipolar disorder and unipolar disorder – exploratory findings using machine learning models

AU - Faurholt-Jepsen, Maria

AU - Rohani, Darius Adam

AU - Busk, Jonas

AU - Tønning, Morten Lindberg

AU - Frost, Mads

AU - Bardram, Jakob Eyvind

AU - Kessing, Lars Vedel

PY - 2024

Y1 - 2024

N2 - The aims were to investigate 1) differences in smartphone-based data on phone usage between bipolar disorder (BD) and unipolar disorder (UD) and 2) by using machine learning models, the sensitivity, specificity, and AUC of the combined smartphone data in classifying BD and UD. Daily smartphone-based self-assessments of mood and same-time passively collected smartphone data on smartphone usage was available for six months. A total of 64 patients with BD and 74 patients with UD were included. Patients with BD during euthymic states compared with UD in euthymic states had a lower number of incoming phone calls/ day (B: -0.70, 95%CI: -1.37; -0.70, p = 0.040). Patients with BD during depressive states had a lower number of incoming and outgoing phone calls/ day as compared with patients with UD in depressive states. In classification by using machine learning models, 1) overall (regardless of the affective state), patients with BD were classified with an AUC of 0.84, which reduced to 0.48 when using a leave-one-patient-out crossvalidation (LOOCV) approach; similarly 2) during a depressive state, patients with BD were classified with an AUC of 0.86, which reduced to 0.42 with LOOCV; 3) during a euthymic state, patients with BD were classified with an AUC of 0.87, which reduced to 0.46 with LOOCV. While digital phenotyping shows promise in differentiating between patients with BD and UD, it highlights the challenge of generalizing to unseen individuals. It should serve as an complement to comprehensive clinical evaluation by clinicians.

AB - The aims were to investigate 1) differences in smartphone-based data on phone usage between bipolar disorder (BD) and unipolar disorder (UD) and 2) by using machine learning models, the sensitivity, specificity, and AUC of the combined smartphone data in classifying BD and UD. Daily smartphone-based self-assessments of mood and same-time passively collected smartphone data on smartphone usage was available for six months. A total of 64 patients with BD and 74 patients with UD were included. Patients with BD during euthymic states compared with UD in euthymic states had a lower number of incoming phone calls/ day (B: -0.70, 95%CI: -1.37; -0.70, p = 0.040). Patients with BD during depressive states had a lower number of incoming and outgoing phone calls/ day as compared with patients with UD in depressive states. In classification by using machine learning models, 1) overall (regardless of the affective state), patients with BD were classified with an AUC of 0.84, which reduced to 0.48 when using a leave-one-patient-out crossvalidation (LOOCV) approach; similarly 2) during a depressive state, patients with BD were classified with an AUC of 0.86, which reduced to 0.42 with LOOCV; 3) during a euthymic state, patients with BD were classified with an AUC of 0.87, which reduced to 0.46 with LOOCV. While digital phenotyping shows promise in differentiating between patients with BD and UD, it highlights the challenge of generalizing to unseen individuals. It should serve as an complement to comprehensive clinical evaluation by clinicians.

KW - Bipolar disorder

KW - Digital phenotyping

KW - Smartphone

KW - Unipolar disorder

U2 - 10.1016/j.euroneuro.2024.01.003

DO - 10.1016/j.euroneuro.2024.01.003

M3 - Journal article

C2 - 38310716

AN - SCOPUS:85183940279

VL - 81

SP - 12

EP - 19

JO - European Neuropsychopharmacology

JF - European Neuropsychopharmacology

SN - 0924-977X

ER -

ID: 382433361