1
|
Badinier J, Lopes R, Mastellari T, Fovet T, Williams SCR, Pruvo JP, Amad A. Clinical and neuroimaging predictors of benzodiazepine response in catatonia: A machine learning approach. J Psychiatr Res 2024; 172:300-306. [PMID: 38430659 DOI: 10.1016/j.jpsychires.2024.02.039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Revised: 01/24/2024] [Accepted: 02/20/2024] [Indexed: 03/05/2024]
Abstract
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.
Collapse
Affiliation(s)
- Jane Badinier
- Univ. Lille, Inserm, CHU Lille, U1172, LilNCog, Lille Neuroscience & Cognition, F-59000, Lille, France
| | - Renaud Lopes
- Univ. Lille, Inserm, CHU Lille, U1172, LilNCog, Lille Neuroscience & Cognition, F-59000, Lille, France
| | - Tomas Mastellari
- Univ. Lille, Inserm, CHU Lille, U1172, LilNCog, Lille Neuroscience & Cognition, F-59000, Lille, France
| | - Thomas Fovet
- Univ. Lille, Inserm, CHU Lille, U1172, LilNCog, Lille Neuroscience & Cognition, F-59000, Lille, France
| | - Steven C R Williams
- Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
| | - Jean-Pierre Pruvo
- Univ. Lille, Inserm, CHU Lille, U1172, LilNCog, Lille Neuroscience & Cognition, F-59000, Lille, France
| | - Ali Amad
- Univ. Lille, Inserm, CHU Lille, U1172, LilNCog, Lille Neuroscience & Cognition, F-59000, Lille, France; Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
| |
Collapse
|
2
|
Mastellari T, Saint-Dizier C, Fovet T, Geoffroy PA, Rogers J, Lamer A, Amad A. Exploring seasonality in catatonia diagnosis: Evidence from a large-scale population study. Psychiatry Res 2024; 331:115652. [PMID: 38071881 DOI: 10.1016/j.psychres.2023.115652] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/29/2023] [Revised: 11/12/2023] [Accepted: 11/29/2023] [Indexed: 01/02/2024]
Abstract
Catatonia is a severe psychomotor syndrome mainly associated with psychiatric disorders, such as mood disorders and schizophrenia. Seasonal patterns have been described for these psychiatric disorders, and a previous study conducted in South London showed for the first time a seasonal pattern in the onset of catatonia. In this study, we aim to extend those findings to a larger national sample of patients admitted to French metropolitan hospitals, between 2015 and 2022, and to perform subgroup analyses by the main associated psychiatric disorder. A total of 6225 patients diagnosed with catatonia were included. A seasonal pattern for catatonia diagnosis was described, using cosinor models. Two peaks of diagnoses for catatonic cases were described in March and around September-October. Depending on the associated psychiatric disorder, the seasonality of catatonia diagnosis differed. In patients suffering with mood disorders, peaks of catatonia diagnosis were found in March and July. For patients suffering with schizophrenia, no seasonal pattern was found.
Collapse
Affiliation(s)
- Tomas Mastellari
- Univ. Lille, Inserm, CHU Lille, U1172 - LilNCog - Lille Neuroscience & Cognition, F-59000 Lille, France.
| | - Chloé Saint-Dizier
- Fédération Régionale de Recherche en Santé Mentale et Psychiatrie, Hauts-de-France, France; Univ. Lille, Faculté Ingénierie et Management de la Santé, Lille F-59000, France
| | - Thomas Fovet
- Univ. Lille, Inserm, CHU Lille, U1172 - LilNCog - Lille Neuroscience & Cognition, F-59000 Lille, France
| | - Pierre-Alexis Geoffroy
- Département de Psychiatrie et d'Addictologie, AP-HP, GHU Paris Nord, DMU Neurosciences, Hôpital Bichat - Claude Bernard, F-75018 Paris, France; Université Paris Cité, NeuroDiderot, Inserm, FHU I2-D2, F-75019 Paris, France; GHU Paris - Psychiatry & Neurosciences, 1 rue Cabanis, 75014 Paris, France
| | - Jonathan Rogers
- Division of Psychiatry, University College London, London, UK; South London and Maudsley NHS Foundation Trust, London, UK
| | - Antoine Lamer
- Fédération Régionale de Recherche en Santé Mentale et Psychiatrie, Hauts-de-France, France; Univ. Lille, Faculté Ingénierie et Management de la Santé, Lille F-59000, France; Univ. Lille, CHU Lille, ULR 2694 - METRICS: Évaluation des Technologies de Santé et des Pratiques Médicales, Lille F-59000, France
| | - Ali Amad
- Univ. Lille, Inserm, CHU Lille, U1172 - LilNCog - Lille Neuroscience & Cognition, F-59000 Lille, France
| |
Collapse
|