Prediction of lithium response using clinical data.
Saved in:
| Title: | Prediction of lithium response using clinical data. |
|---|---|
| Authors: | Nunes, A. (AUTHOR), Ardau, R. (AUTHOR), Berghöfer, A. (AUTHOR), Bocchetta, A. (AUTHOR), Chillotti, C. (AUTHOR), Deiana, V. (AUTHOR), Garnham, J. (AUTHOR), Grof, E. (AUTHOR), Hajek, T. (AUTHOR), Manchia, M. (AUTHOR), Müller‐Oerlinghausen, B. (AUTHOR), Pinna, M. (AUTHOR), Pisanu, C. (AUTHOR), O'Donovan, C. (AUTHOR), Severino, G. (AUTHOR), Slaney, C. (AUTHOR), Suwalska, A. (AUTHOR), Zvolsky, P. (AUTHOR), Cervantes, P. (AUTHOR), Zompo, M. (AUTHOR) |
| Source: | Acta Psychiatrica Scandinavica. Feb2020, Vol. 141 Issue 2, p131-141. 11p. 1 Diagram, 3 Charts, 1 Graph. |
| Subjects: | Machine learning, Receiver operating characteristic curves, Therapeutic use of lithium, Biomarkers |
| Abstract: | 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. [ABSTRACT FROM AUTHOR] |
| Copyright of Acta Psychiatrica Scandinavica is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Psychology and Behavioral Sciences Collection |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | 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. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 0001690X |
| DOI: | 10.1111/acps.13122 |
