Ijraset Journal For Research in Applied Science and Engineering Technology
Interpretable Machine Leaning Models for Healthcare Decision Support
Authors: Ankita Bhide, Ms. Rohini Tambe, Buddhabhushan Tikte, Hemant Gaikwad
DOI Link: https://doi.org/10.22214/ijraset.2025.70118
Certificate: View Certificate
Abstract
The proposed Interpretable Machine Learning-based Decision Support System (DSS) addresses the critical challenge of balancing accuracy and interpretability in healthcare decision-making. By utilizing the Random Forest algorithm, the system provides reliable predictions while offering feature importance visualization, enhancing trust among clinicians. The integration of Natural Language Processing (NLP) further improves the analysis of unstructured medical data, ensuring comprehensive decision support. The model is validated using real-world clinical datasets and evaluated through accuracy, F1-score, and AUC-ROC, demonstrating its effectiveness. Additionally, seamless integration with Hospital Information Systems (HIS) via REST APIs ensures real-time usability. This research contributes to the development of trustworthy AI-driven healthcare solutions, empowering healthcare professionals with transparent, data-driven insights for improved patient care and clinical outcomes. Future enhancements include optimizing real-time processing and integrating domain-specific NLP models for further accuracy improvements. In conclusion, the project highlights the transformative potential of IoT in healthcare, demonstrating that innovative technologies can significantly enhance patient monitoring, improve healthcare outcomes, and bridge gaps in access to medical services.
Introduction
The proposed interpretable machine learning-based Decision Support System (DSS) uses the Random Forest algorithm to balance predictive accuracy with transparency through feature importance visualization, fostering clinician trust. It incorporates Natural Language Processing (NLP) to effectively analyze unstructured medical data, providing comprehensive decision support. Validated on real clinical data and evaluated using accuracy, F1-score, and AUC-ROC, the system demonstrates strong performance. Integration with Hospital Information Systems (HIS) via REST APIs enables real-time clinical use. This research advances trustworthy AI healthcare solutions, empowering clinicians with transparent, data-driven insights to improve patient care. Future plans include enhancing real-time processing and applying specialized NLP models.
Conclusion
The proposed Interpretable Machine Learning-based Decision Support System (DSS) addresses the critical challenge of balancing accuracy and interpretability in healthcare decision-making. By utilizing the Random Forest algorithm, the system provides reliable predictions while offering feature importance visualization, enhancing trust among clinicians. The integration of Natural Language Processing (NLP) further improves the analysis of unstructured medical data, ensuring comprehensive decision support. The model is validated using real-world clinical datasets and evaluated through accuracy, F1-score, and AUC-ROC, demonstrating its effectiveness. Additionally, seamless integration with Hospital Information Systems (HIS) via REST APIs ensures real-time usability. This research contributes to the development of trustworthy AI-driven healthcare solutions, empowering healthcare professionals with transparent, data-driven insights for improved patient care and clinical outcomes. Future enhancements include optimizing real-time processing and integrating domain-specific NLP models for further accuracy improvements. In conclusion, the project highlights the transformative potential of IoT in healthcare, demonstrating that innovative technologies can significantly enhance patient monitoring, improve healthcare outcomes, and bridge gaps in access to medical services.
References
[1] A New Real Time Clinical Decision Support System Using Machine Learning for Critical Care Unit at Mar 2022 | IRJET [2] Overview on the Advancements of Support Vector Machine Models in Healthcare Applications at 2024 | MDPI [3] Bayesian Networks in Healthcare: Distribution by Medical Condition at 2020 | Elsevier [4] LASSO Regression Modeling on Prediction of Medical Terms among Seafarers’ Health Documents at 2022 | MDPI [5] Classification of Heart Disease Using K-Nearest Neighbor and Genetic Algorithm at 2020 | ScienceDirect [6] Chinmay Chakraborty; Amit Kishor, \"Real-Time Cloud-Based PatientCentric Monitoring Using Computational Health Systems\", IEEE Transactions on Computational Social Systems, India, 2022. [7] Rakhi Bhardwaj; Shiv Narain Gupta; Manish Gupta; Priyesh Tiwari, “IoT based Healthware and Healthcare Monitoring System in India” 2021 International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), April 2021. 23 [8] Mahmood. K. Awsaj; Yousif Al Mashhadany; Lamia Chaari Fourati ,“RealTime Healthcare Monitoring and Treatment System Based Microcontroller with IoT” 2023 15th International Conference on Developments in eSystems Engineering (DeSE), India, 2023. [9] Ahmed Dridi; Salma Sassi; Sami Faiz ,“A Smart IoT platform for personalized healthcare monitoring using semantic technologies” ,2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI), 2018. [10] K. Vijaipriya; C. Priya; Siji Sivanandan; R. Krishnaswamy, “ECG Monitoring System using IoT for Health Care Applications” ,2023 Second International Conference on Augmented Intelligence and Sustainable Systems
Copyright
Copyright © 2025 Ankita Bhide, Ms. Rohini Tambe, Buddhabhushan Tikte, Hemant Gaikwad. This 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.
Download Paper
Paper Id : IJRASET70118
Publish Date : 2025-04-30
ISSN : 2321-9653
Publisher Name : IJRASET
DOI Link : Click Here
Submit Paper Online