Related Experiment Video
Updated: Aug 26, 2025
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
Disorganization domain as a putative predictor of Treatment Resistant Schizophrenia (TRS) diagnosis: A machine
Annarita Barone1, Michele De Prisco1, Benedetta Altavilla1
1Unit of Treatment Resistant Psychosis and Laboratory of Molecular and Translational Psychiatry, Section of Psychiatry, Department of Neuroscience, Reproductive Science and Odontostomatology, University School of Medicine "Federico II", Naples, Italy.
Background:
Treatment Resistant Schizophrenia (TRS) is the persistence of significant symptoms despite adequate antipsychotic treatment. Although consensus guidelines are available, this condition remains often unrecognized and an average delay of 4-9 years in the initiation of clozapine, the gold standard for the pharmacological treatment of TRS, has been reported. We aimed to determine through a machine learning approach which domain of the Positive and Negative Syndrome Scale (PANSS) 5-factor model was most associated with TRS.
Methods:
In a cross-sectional design, 128 schizophrenia patients were classified as TRS (n = 58) or non-TRS (n = 60) after a structured retrospective-prospective analysis of treatment response. The random forest algorithm (RF) was trained to analyze the relationship between the presence/absence of TRS and PANSS-based psychopathological factor scores (positive, negative, disorganization, excitement, and emotional distress). As a complementary strategy to identify the variables most associated with the diagnosis of TRS, we included the variables selected by the RF algorithm in a multivariate logistic regression model.
Results:
according to the RF model, patients with higher disorganization, positive, and excitement symptom scores were more likely to be classified as TRS. The model showed an accuracy of 67.19%, a sensitivity of 62.07%, and a specificity of 71.43%, with an area under the curve (AUC) of 76.56%. The multivariate model including disorganization, positive, and excitement factors showed that disorganization was the only factor significantly associated with TRS. Therefore, the disorganization factor was the variable most consistently associated with the diagnosis of TRS in our sample.
Insights
Disorganization symptoms in schizophrenia are strongly linked to treatment resistance. Machine learning identified this factor as key for diagnosing Treatment Resistant Schizophrenia (TRS), potentially speeding up clozapine initiation.
Area of Science:
- Psychiatry
- Machine Learning
- Clinical Psychology
Background:
- Treatment Resistant Schizophrenia (TRS) is characterized by persistent symptoms despite adequate antipsychotic treatment.
- A significant delay in initiating clozapine, the gold standard for TRS, is common due to delayed recognition.
- Current diagnostic approaches may not fully capture the nuances of TRS.
Purpose of the Study:
- To identify which domain of the Positive and Negative Syndrome Scale (PANSS) 5-factor model is most associated with Treatment Resistant Schizophrenia (TRS).
- To leverage machine learning for a more accurate and timely identification of TRS.
- To reduce diagnostic delays and improve patient outcomes by pinpointing key symptom clusters.
Main Methods:
- A cross-sectional study of 128 schizophrenia patients, classified as TRS or non-TRS.
- The random forest algorithm (RF) was employed to analyze the relationship between PANSS factors and TRS.
- A multivariate logistic regression model was used to validate findings from the RF algorithm.
Main Results:
- The RF model indicated that higher scores in disorganization, positive, and excitement symptoms were associated with TRS.
- The model achieved 67.19% accuracy, 62.07% sensitivity, and 71.43% specificity, with an AUC of 76.56%.
- Disorganization emerged as the single factor significantly associated with TRS in the multivariate analysis, highlighting its diagnostic importance.
Conclusions:
- The disorganization factor of the PANSS is the most consistent predictor of Treatment Resistant Schizophrenia (TRS).
- Machine learning approaches can effectively identify key symptom domains associated with complex psychiatric conditions.
- Early identification of TRS, particularly focusing on disorganization symptoms, can facilitate timely treatment with clozapine.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Related Concept Videos
01:17Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
01:29Psychological and Sociocultural Causes of Schizophrenia
01:17Schizophrenia
01:28Psychosis and Antipsychotic Drugs: Overview
01:26Classification of Systems-I
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
01:28Drug Therapy
Antianxiety Medications