Using MRI and Machine Learning to Diagnose Schizophrenia
Author Information
Author(s): Hosna Tavakoli, Reza Rostami, Reza Shalbaf, Mohammad-Reza Nazem-Zadeh
Primary Institution: Institute of Cognitive Science Studies, Tehran, Iran
Hypothesis
Can MRI and machine learning improve the classification of schizophrenia and its subtypes?
Conclusion
MRI and machine learning algorithms can enhance the diagnostic process for schizophrenia and help identify brain-related abnormalities and cognitive impairments.
Supporting Evidence
- The classification accuracy reached as high as 79% in distinguishing schizophrenia patients from healthy individuals.
- The model demonstrated effectiveness with 72% accuracy in estimating the patient's label for a new dataset.
- Using a linear support vector machine, patients with schizophrenic subtypes were classified with an accuracy of 64%.
- The highest Spearman correlation coefficient was observed between the degree of the postcentral gyrus and mean reaction time in a verbal capacity task.
Takeaway
Doctors can use special brain scans and computer programs to better understand and diagnose schizophrenia, which is a mental health condition.
Methodology
The study used MRI data from 50 schizophrenia patients and 50 healthy individuals, applying machine learning algorithms to classify the data.
Potential Biases
Potential biases due to the small sample size and the reliance on specific datasets.
Limitations
The study had a relatively small sample size and limited data on schizophrenia subtypes.
Participant Demographics
50 schizophrenia patients and 50 age- and gender-matched healthy individuals.
Statistical Information
P-Value
0.001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website