Background: Schizophrenia can be interpreted as a pathology involving the neocortex whose cognitive dysfunctions represent a central and persistent characteristic of the disease, as well as one of the more important symptoms in relation to the impairment of psychosocial functioning and the resulting disabilities. Given the implication of cognitive functions in everyday life, they can better predict the degree of schizophrenia. The study proposes to use Machine Learning techniques to identify the specific cognitive deficits of schizophrenia that mostly characterize the disorder, as well as to develop a predictive system that can diagnose the presence of schizophrenia based on neurocognitive tests.
Background: The study employs a dataset of neurocognitive assessments carried out on 201 people (86 schizophrenic patients and 115 healthy patients) recruited by the Neuroscience Group of the University of Bari "A. Moro". A data analysis process has been carried out, with the aim of selecting the most relevant features as well as to prepare data for training a number of "off-the-shelf" machine learning methods (Decision Tree, Random Forest, Logistic Regression, k-Nearest Neighbor, Neural Network, Support Vector Machine), which have been evaluated in terms of classification accuracy according to stratified 20-fold cross-validation.
Results: Among all variables, 14 were selected as the most influential for the classification problem. The variables with greater influence are related to working memory, executive functions, attention, verbal fluency, memory. The best algorithms turned out to be Support Vector Machine (SVM) and Neural Network, showing an accuracy of 87.8% and 84.8% on a test set.
Conclusions: Machine Learning provides "cheap" and non-invasive methods that potentially enable early intervention with specific rehabilitation interventions. The results suggest the need to integrate a thorough neuropsychological evaluation into the more general diagnostic evaluation of patients with schizophrenia disorder.