Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{167266,
        author = {MUNNURU PRATHYUSHA and N.Naveen Kumar},
        title = {DATA DRIVEN INSIGHTS INTO OPIOID PATIENTS POPULATIONS USING MACHINE LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {3},
        pages = {671-684},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=167266},
        abstract = {The project's primary focus is on using machine learning techniques to classify opioid patients, aiming to address the pressing issue of the opioid crisis and the escalating number of drug overdoses in recent years. By leveraging these techniques, the project seeks to contribute to a better understanding and management of opioid-related issues. Current approaches for predicting opioid prescription lack the desired level of accuracy. The project recognizes this limitation and emphasizes the need for improvement. Additionally, it underscores the importance of considering the association between mental health and opioid intake, an aspect often overlooked in previous studies. This consideration acknowledges the multifaceted nature of opioid dependencies. The project utilizes a comprehensive dataset from the MIMIC-III database, encompassing both structured and unstructured data. By doing so, it aims to identify intentional and unintentional opioid intake patterns, providing a holistic understanding of the factors influencing opioid use. This integrated data approach contributes to a more robust analysis and classification process. Ablation analysis is conducted as part of the project's methodology, offering a systematic breakdown of the model's components and parameters. This analysis provides valuable insights into the significance of different elements in the classification process, leading to a deeper understanding of opioid patients. The extraction of new insights contributes to the project's goal of refining and enhancing opioid patient classification methods. The project incorporates key other models to enhance classification accuracy. The inclusion of a Stacking Classifier, Voting Classifier, and the integration of CNN + LSTM models contribute to a robust ensemble system. Notably, both Stacking and Voting Classifiers achieve an exceptional 100% accuracy, underscoring the effectiveness of the ensemble approach in accurately classifying opioid patients.},
        keywords = {Opioid intake, mental illness, MIMIC-III database, machine learning, deep learning.},
        month = {August},
        }