A decision support system for osteoporosis risk prediction using machine learning and explainable artificial intelligence

Varada Vivek Khanna, Krishnaraj Chadaga, Niranjana Sampathila, Rajagopala Chadaga, Srikanth Prabhu, Swathi K S, Aditya S. Jagdale, Devadas Bhat

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Osteoporosis is a metabolic bone condition that occurs when bone mineral density and mass decrease. This makes the bones weak and brittle. The disorder is often undiagnosed and untreated due to its asymptomatic nature until the manifestation of a fracture. Machine Learning (ML) is extensively used in diverse healthcare domains to analyze precise outcomes, provide timely risk scores, and allocate resources. Hence, we have designed multiple heterogeneous machine-learning frameworks to predict the risk of Osteoporosis. An open-source dataset of 1493 patients containing bone density, blood, and physical tests is utilized. Thirteen distinct feature selection techniques were leveraged to extract the most salient parameters. The best-performing pipeline consisted of a Forward Feature Selection algorithm followed by a custom multi-level ensemble learning-based stack, which achieved an accuracy of 89 %. Deploying a layer of explainable artificial intelligence using tools such as SHAP (SHapley Additive Values), LIME (Local Interpretable Model Explainer), ELI5, Qlattice, and feature importance provided interpretability and rationale behind classifier prediction. With this study, we aim to provide the holistic risk prediction of Osteoporosis and concurrently present a system for automated screening to assist physicians in making diagnostic decisions.

Original languageEnglish
Article numbere22456
JournalHeliyon
Volume9
Issue number12
DOIs
Publication statusPublished - 12-2023

All Science Journal Classification (ASJC) codes

  • General

Fingerprint

Dive into the research topics of 'A decision support system for osteoporosis risk prediction using machine learning and explainable artificial intelligence'. Together they form a unique fingerprint.

Cite this