1
|
Ariza M, Béjar J, Barrué C, Cano N, Segura B, Cortés CU, Junqué C, Garolera M. Cognitive reserve, depressive symptoms, obesity, and change in employment status predict mental processing speed and executive function after COVID-19. Eur Arch Psychiatry Clin Neurosci 2024:10.1007/s00406-023-01748-x. [PMID: 38285245 DOI: 10.1007/s00406-023-01748-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/30/2023] [Accepted: 12/18/2023] [Indexed: 01/30/2024]
Abstract
The risk factors for post-COVID-19 cognitive impairment have been poorly described. This study aimed to identify the sociodemographic, clinical, and lifestyle characteristics that characterize a group of post-COVID-19 condition (PCC) participants with neuropsychological impairment. The study sample included 426 participants with PCC who underwent a neurobehavioral evaluation. We selected seven mental speed processing and executive function variables to obtain a data-driven partition. Clustering algorithms were applied, including K-means, bisecting K-means, and Gaussian mixture models. Different machine learning algorithms were then used to obtain a classifier able to separate the two clusters according to the demographic, clinical, emotional, and lifestyle variables, including logistic regression with least absolute shrinkage and selection operator (LASSO) (L1) and Ridge (L2) regularization, support vector machines (linear/quadratic/radial basis function kernels), and decision tree ensembles (random forest/gradient boosting trees). All clustering quality measures were in agreement in detecting only two clusters in the data based solely on cognitive performance. A model with four variables (cognitive reserve, depressive symptoms, obesity, and change in work situation) obtained with logistic regression with LASSO regularization was able to classify between good and poor cognitive performers with an accuracy and a weighted averaged precision of 72%, a recall of 73%, and an area under the curve of 0.72. PCC individuals with a lower cognitive reserve, more depressive symptoms, obesity, and a change in employment status were at greater risk for poor performance on tasks requiring mental processing speed and executive function. Study registration: www.ClinicalTrials.gov , identifier NCT05307575.
Collapse
Affiliation(s)
- Mar Ariza
- Grup de Recerca en Cervell, Cognició i Conducta, Consorci Sanitari de Terrassa (CST), Terrassa, Spain
- Unitat de Psicologia Mèdica, Departament de Medicina, Universitat de Barcelona (UB), Barcelona, Spain
| | - Javier Béjar
- Departament de Ciències de la Computació, Universitat Politècnica de Catalunya-BarcelonaTech, Barcelona, Spain.
| | - Cristian Barrué
- Departament de Ciències de la Computació, Universitat Politècnica de Catalunya-BarcelonaTech, Barcelona, Spain
| | - Neus Cano
- Grup de Recerca en Cervell, Cognició i Conducta, Consorci Sanitari de Terrassa (CST), Terrassa, Spain
- Departament de Ciències Bàsiques, Universitat Internacional de Catalunya (UIC), Sant Cugat del Vallès, Spain
| | - Bàrbara Segura
- Unitat de Psicologia Mèdica, Departament de Medicina, Universitat de Barcelona (UB), Barcelona, Spain
- Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain
- Institut de Neurociències, Universitat de Barcelona (UB), Barcelona, Spain
| | - Claudio Ulises Cortés
- Departament de Ciències de la Computació, Universitat Politècnica de Catalunya-BarcelonaTech, Barcelona, Spain
| | - Carme Junqué
- Unitat de Psicologia Mèdica, Departament de Medicina, Universitat de Barcelona (UB), Barcelona, Spain
- Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain
- Institut de Neurociències, Universitat de Barcelona (UB), Barcelona, Spain
| | - Maite Garolera
- Grup de Recerca en Cervell, Cognició i Conducta, Consorci Sanitari de Terrassa (CST), Terrassa, Spain.
- Neuropsychology Unit, Consorci Sanitari de Terrassa (CST), Terrassa, Spain.
| |
Collapse
|
2
|
Sekendiz Z, Clouston SAP, Morozova O, Carr MA, Fontana A, Mehta N, Ali A, Jiang E, Luft B. ASSESSMENT AND CHARACTERIZATION OF COVID-19 RELATED COGNITIVE DECLINE: RESULTS FROM A NATURAL EXPERIMENT. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.11.06.23298101. [PMID: 37986906 PMCID: PMC10659478 DOI: 10.1101/2023.11.06.23298101] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/22/2023]
Abstract
Background Cognitive impairment is the most common and disabling manifestation of post-acute sequelae of SARS-CoV-2. There is an urgent need for the application of more stringent methods for evaluating cognitive outcomes in research studies. Objective To determine whether cognitive decline emerges with the onset of COVID-19 and whether it is more pronounced in patients with Post-Acute Sequelae of SARS-CoV-2 or severe COVID-19. Methods This longitudinal cohort study compared the cognitive performance of 276 patients with COVID-19 to that of 217 controls across four neuroinflammation or vascular disease-sensitive domains of cognition using data collected both before and after the pandemic starting in 2015. Results The mean age of the COVID-19 group was 56.04±6.6 years, while that of the control group was 58.1±7.3 years. Longitudinal models indicated a significant decline in cognitive throughput ((β=-0.168, P=.001) following COVID-19, after adjustment for pre-COVID-19 functioning, demographics, and medical factors. The effect sizes were large; the observed changes in throughput were equivalent to 10.6 years of normal aging and a 59.8% increase in the burden of mild cognitive impairment. Cognitive decline worsened with coronavirus disease 2019 severity and was concentrated in participants reporting post-acute sequelae of SARS-CoV-2. Conclusion COVID-19 was most likely associated with the observed cognitive decline, which was worse among patients with PASC or severe COVID-19. Monitoring patients with post-acute sequelae of SARS-CoV-2 for declines in the domains of processing speed and visual working memory and determining the long-term prognosis of this decline are therefore warranted.
Collapse
Affiliation(s)
- Zennur Sekendiz
- Stony Brook University, Department of Medicine-World Trade Center Health Program
| | - Sean A P Clouston
- Stony Brook University, Family, Population and Preventive Medicine, Program in Public Health
| | - Olga Morozova
- The University of Chicago, Department of Public Health Sciences
| | - Melissa A Carr
- Stony Brook University, Department of Medicine-World Trade Center Health Program
| | - Ashley Fontana
- Stony Brook University, Department of Medicine-World Trade Center Health Program
| | - Nikhil Mehta
- Stony Brook University, Department of Medicine-World Trade Center Health Program
| | - Alina Ali
- Stony Brook University, Department of Medicine-World Trade Center Health Program
| | - Eugene Jiang
- Stony Brook University, Department of Medicine-World Trade Center Health Program
| | - Benjamin Luft
- Stony Brook University, Department of Medicine-World Trade Center Health Program
| |
Collapse
|