Prediction of lithium response using clinical data

A. Nunes, R. Ardau, A. Berghöfer, A. Bocchetta, C. Chillotti, V. Deiana, J. Garnham, E. Grof, T. Hajek, M. Manchia, B. Müller-Oerlinghausen, M. Pinna, C. Pisanu, C. O’Donovan, G. Severino, C. Slaney, A. Suwalska, P. Zvolsky, P. Cervantes, M. del ZompoP. Grof, J. Rybakowski, L. Tondo, T. Trappenberg, M. Alda

Producción científica: Contribución a una revistaArtículorevisión exhaustiva

59 Citas (Scopus)

Resumen

Objective: Promptly establishing maintenance therapy could reduce morbidity and mortality in patients with bipolar disorder. Using a machine learning approach, we sought to evaluate whether lithium responsiveness (LR) is predictable using clinical markers. Method: Our data are the largest existing sample of direct interview-based clinical data from lithium-treated patients (n = 1266, 34.7% responders), collected across seven sites, internationally. We trained a random forest model to classify LR—as defined by the previously validated Alda scale—against 180 clinical predictors. Results: Under appropriate cross-validation procedures, LR was predictable in the pooled sample with an area under the receiver operating characteristic curve of 0.80 (95% CI 0.78–0.82) and a Cohen kappa of 0.46 (0.4–0.51). The model demonstrated a particularly low false-positive rate (specificity 0.91 [0.88–0.92]). Features related to clinical course and the absence of rapid cycling appeared consistently informative. Conclusion: Clinical data can inform out-of-sample LR prediction to a potentially clinically relevant degree. Despite the relevance of clinical course and the absence of rapid cycling, there was substantial between-site heterogeneity with respect to feature importance. Future work must focus on improving classification of true positives, better characterizing between- and within-site heterogeneity, and further testing such models on new external datasets.

Idioma originalEnglish
Páginas (desde-hasta)131-141
Número de páginas11
PublicaciónActa Psychiatrica Scandinavica
Volumen141
N.º2
DOI
EstadoPublished - feb. 1 2020

Nota bibliográfica

Funding Information:
Genome Canada (MA, AN), Dalhousie Department of Psychiatry Research Fund (MA, AN), Canadian Institutes of Health Research #64410 (MA), Nova Scotia Health Research Foundation Scotia Scholars Graduate Scholarship (AN), Killam Postgraduate Scholarship (AN).

Publisher Copyright:
© 2019 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd

ASJC Scopus Subject Areas

  • Psychiatry and Mental health

Huella

Profundice en los temas de investigación de 'Prediction of lithium response using clinical data'. En conjunto forman una huella única.

Citar esto

Nunes, A., Ardau, R., Berghöfer, A., Bocchetta, A., Chillotti, C., Deiana, V., Garnham, J., Grof, E., Hajek, T., Manchia, M., Müller-Oerlinghausen, B., Pinna, M., Pisanu, C., O’Donovan, C., Severino, G., Slaney, C., Suwalska, A., Zvolsky, P., Cervantes, P., ... Alda, M. (2020). Prediction of lithium response using clinical data. Acta Psychiatrica Scandinavica, 141(2), 131-141. https://doi.org/10.1111/acps.13122