EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Predicting remission after acute phase pharmacotherapy in patients with bipolar I depression: A machine learning approach with cross‐trial and cross‐drug replication

Jean Marrero-Polanco iD, Jeremiah B Joyce, Caroline W Grant, Paul E Croarkin, Arjun P Athreya iD, William V Bobo iD

Bipolar Disorders · 2025

DOI: 10.1111/bdi.13506 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bipolar Disorders, 2025. Verfasst von Jean Marrero-Polanco und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, Minnesota, USA. Hauptthemen laut MEDLINE: Bipolar Disorder, Olanzapine, Machine Learning, Antipsychotic Agents. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science Foundation, The Blue Gator Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Interpatient variability in bipolar I depression (BP‐D) symptoms challenges the ability to predict pharmacotherapeutic outcomes. A machine learning workflow was developed to predict remission after 8 weeks of pharmacotherapy (total score of ≤8 on the Montgomery Åsberg Depression Rating Scale [MADRS]).

Methods

Supervised machine learning models were trained on data from BP‐D patients treated with olanzapine ( N = 168) and were externally validated on patients treated with olanzapine/fluoxetine combination (OFC; N = 131) and lamotrigine (LTG; N = 126). Top predictors were used to develop a prognosis rule informing how many symptoms should change and by how much within 4 weeks to increase the odds of achieving remission.

Results

An AUC of 0.76 (NIR:0.59; p = 0.17) was established to predict remission in olanzapine‐treated subjects. These trained models achieved AUCs of 0.70 with OFC (NIR:0.52; p < 0.03) and 0.73 with LTG (NIR:0.52; p < 0.003), demonstrating external replication of prediction performance. Week‐4 changes in four MADRS symptoms (reported sadness, reduced sleep, reduced appetite, and concentration difficulties) were top predictors of remission. Across all pharmacotherapies, three or more of these symptoms needed to improve by ≥2 points at Week‐4 to have a 65% chance of achieving remission at 8 weeks (OR: 3.74, 95% CI: 2.45–5.76; p < 9.3E‐11).

Conclusion

Machine learning strategies achieved cross‐trial and cross‐drug replication in predicting remission after 8 weeks of pharmacotherapy for BP‐D. Interpretable prognoses rules required only a limited number of depressive symptoms, providing a promising foundation for developing simple quantitative decision aids that may, in the future, serve as companions to clinical judgment at the point of care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bipolar DisorderOlanzapineMachine LearningAntipsychotic AgentsLamotrigineFluoxetineHumansMaleFemaleAdultMiddle AgedRemission InductionDrug CombinationsPsychiatric Status Rating ScalesTreatment OutcomeYoung AdultBenzodiazepines

Stichwörter der Autor:innen

antipsychoticsbipolar depressionbipolar disorder type 1machine learningmood stabilizers

Substanzen

OlanzapineAntipsychotic AgentsLamotrigineFluoxetineolanzapine-fluoxetine combinationDrug CombinationsBenzodiazepines

Autor:innen und Institutionen

  • Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, Minnesota, USA.
  • Department of Psychiatry and Psychology, Mayo Clinic, Rochester, Minnesota, USA.
  • Center for Individualized Medicine, Mayo Clinic, Rochester, Minnesota, USA.
  • Department of Behavioral Science and Social Medicine, Florida State University College of Medicine, Tallahassee, Florida, USA.

ORCID-Profile: Jean Marrero-Polanco, Arjun P Athreya, William V Bobo

Förderung

  • National Science Foundation
  • The Blue Gator Foundation

Zitieren

APA

Marrero-Polanco, J., Joyce, J. B., Grant, C. W., Croarkin, P. E., Athreya, A. P., & Bobo, W. V. (2025). Predicting remission after acute phase pharmacotherapy in patients with bipolar I depression: A machine learning approach with cross‐trial and cross‐drug replication. Bipolar Disorders. https://doi.org/10.1111/bdi.13506

Vancouver

Marrero-Polanco J, Joyce JB, Grant CW, Croarkin PE, Athreya AP, Bobo WV. Predicting remission after acute phase pharmacotherapy in patients with bipolar I depression: A machine learning approach with cross‐trial and cross‐drug replication. Bipolar Disorders. 2025. doi:10.1111/bdi.13506

BibTeX
@article{MarreroPolanco2025,
  author = {Marrero-Polanco, Jean and Joyce, Jeremiah B and Grant, Caroline W and Croarkin, Paul E and Athreya, Arjun P and Bobo, William V},
  title = {Predicting remission after acute phase pharmacotherapy in patients with bipolar I depression: A machine learning approach with cross‐trial and cross‐drug replication},
  journal = {Bipolar Disorders},
  year = {2025},
  doi = {10.1111/bdi.13506}
}
Kostenlos starten →