TY - JOUR
T1 - Clinical and neuroimaging predictors of benzodiazepine response in catatonia
T2 - A machine learning approach
AU - Badinier, Jane
AU - Lopes, Renaud
AU - Mastellari, Tomas
AU - Fovet, Thomas
AU - Williams, Steven C R
AU - Pruvo, Jean-Pierre
AU - Amad, Ali
N1 - Funding Information:
The authors gratefully acknowledge the contributions of Morgan Gautherot to this study. This work was supported by the University of Lille, the UFR3S and the CHU de Lille. We also acknowledge support from the GIRCI Nord-Ouest and extend our gratitude to the patients and the members of the clinical team, including physicians, nurses, and other members of staff who made this work possible through their expertise and dedication to patient care.
Funding Information:
The authors gratefully acknowledge the contributions of Morgan Gautherot to this study. This work was supported by the University of Lille , the UFR3S and the CHU de Lille . We also acknowledge support from the GIRCI Nord-Ouest and extend our gratitude to the patients and the members of the clinical team, including physicians, nurses, and other members of staff who made this work possible through their expertise and dedication to patient care.
Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/4
Y1 - 2024/4
N2 - Catatonia is a well characterized psychomotor syndrome combining motor, behavioural and neurovegetative signs. Benzodiazepines are the first-choice treatment, effective in 70 % of cases. Currently, the factors associated with benzodiazepine resistance remain unknown. We aimed to develop machine learning models using clinical and neuroimaging data to predict benzodiazepine response in catatonic patients. This study examined a cohort of catatonic patients who underwent standardized clinical evaluation, 3 T brain MRI, and benzodiazepine trial. Based on clinical response, patients were classified as benzodiazepine responders or non-responders. Cortical thickness and regional brain volumes were measured. Two machine learning models (linear model and gradient boosting tree model) were developed to identify predictors of treatment response using clinical, demographic, and neuroimaging data. The cohort included 65 catatonic patients, comprising 30 benzodiazepine responders and 35 non-responders. Using clinical data alone, the linear model achieved 63% precision, 51% recall, a specificity of 61%, and 58% AUC, while the gradient boosting tree (GBT) model attained 46% precision, 60% recall, a specificity of 62% and 64% AUC. Incorporating neuroimaging data improved model performance, with the linear model achieving 66% precision, 57% recall, a specificity of 67%, and 70% AUC, and the GBT model attaining 50% precision, 50% recall, a specificity of 62% and 70% AUC. The integration of imaging data with demographic and clinical information significantly enhanced the predictive performance of the models. The duration of the catatonic syndrome, along with the presence of mitgehen (passive obedience) and immobility/stupor, and the volume of the right medial orbito-frontal cortex emerged as important factors in predicting non-response to benzodiazepines.
AB - Catatonia is a well characterized psychomotor syndrome combining motor, behavioural and neurovegetative signs. Benzodiazepines are the first-choice treatment, effective in 70 % of cases. Currently, the factors associated with benzodiazepine resistance remain unknown. We aimed to develop machine learning models using clinical and neuroimaging data to predict benzodiazepine response in catatonic patients. This study examined a cohort of catatonic patients who underwent standardized clinical evaluation, 3 T brain MRI, and benzodiazepine trial. Based on clinical response, patients were classified as benzodiazepine responders or non-responders. Cortical thickness and regional brain volumes were measured. Two machine learning models (linear model and gradient boosting tree model) were developed to identify predictors of treatment response using clinical, demographic, and neuroimaging data. The cohort included 65 catatonic patients, comprising 30 benzodiazepine responders and 35 non-responders. Using clinical data alone, the linear model achieved 63% precision, 51% recall, a specificity of 61%, and 58% AUC, while the gradient boosting tree (GBT) model attained 46% precision, 60% recall, a specificity of 62% and 64% AUC. Incorporating neuroimaging data improved model performance, with the linear model achieving 66% precision, 57% recall, a specificity of 67%, and 70% AUC, and the GBT model attaining 50% precision, 50% recall, a specificity of 62% and 70% AUC. The integration of imaging data with demographic and clinical information significantly enhanced the predictive performance of the models. The duration of the catatonic syndrome, along with the presence of mitgehen (passive obedience) and immobility/stupor, and the volume of the right medial orbito-frontal cortex emerged as important factors in predicting non-response to benzodiazepines.
UR - http://www.scopus.com/inward/record.url?scp=85186954744&partnerID=8YFLogxK
U2 - 10.1016/j.jpsychires.2024.02.039
DO - 10.1016/j.jpsychires.2024.02.039
M3 - Article
C2 - 38430659
SN - 0022-3956
VL - 172
SP - 300
EP - 306
JO - Journal of psychiatric research
JF - Journal of psychiatric research
ER -