Psychiatric Disorder Classification with Random Forest

This project was inspired by the need for better diagnostic tools in psychiatry, where identifying disorders based on patterns in patient data is often challenging due to complex, overlapping symptoms and data limitations. The goal was to classify seven psychiatric disorders using a dataset that presented significant challenges, including imbalanced classes and missing data. Through this project, we aimed to explore the applicability of machine learning models in this field, evaluate the impact of preprocessing and feature engineering, and tackle the challenges associated with small, imbalanced datasets.

Built With

• python
• scipy