Machine learning predicts osteoporosis in patients with rheumatoid arthritis
Click Here to Manage Email Alerts
Key takeaways:
- A machine learning model was effective at predicting osteoporosis among patients with RA.
- The model highlighted monthly income, education, surgical history and marital status as predictive factors.
Machine learning algorithms can be effective in predicting osteoporosis among patients with rheumatoid arthritis, as well as identifying new predictive factors, according to data published in Nature Scientific Reports.
“Recently, machine learning (ML) algorithms have been extensively applied to various clinical practices, including disease classification, risk prediction, and treatment response,” Chaewon Lee, of Kangwon National University, in Chuncheon, South Korea, and colleagues wrote. “Although studies on the prediction of osteoporosis or fractures using ML models in the general population have been conducted, those on patients with RA are lacking.”
To develop a machine learning model to predict osteoporosis in patients with RA using clinical data, Lee and colleagues evaluated four representative algorithms — logistic regression, random forest, XGBoost and LightGBM — each with different trade-offs of speed, resource-intensiveness and overfitting. Model underwent fivefold cross-validation measuring accuracy, F1 score and area under the receiver operating characteristic (AUC) curve.
The F1 score was “the harmonic mean of precision and recall,” while the AUC measure “was primarily used to compensate for the limitations of the accuracy when class distributions were different,” the researchers wrote. Data for 2,374 adult patients with RA, recruited between July 2009 and March 2012, were included from the Korean Observational Study Network for Arthritis.
According to the researchers, the osteoporosis predictive accuracy among the four algorithms ranged from .0678 to 0.682, and was highest for the XGBoost algorithm. Meanwhile, the random forest algorithm had the highest F1 score: 0.705. AUC measures were 0.75 (95% CI; 0.717-0.783) in the logistic regression algorithm, 0.747 (95% CI; 0.715-0.781) for random forest, 0.749 (95% CI; 0.72-0.779) for XGBoost, and 0.744 (95% CI; 0.715-0.772) for LightGBM.
The logistic regression model was shown to have the “best” performance, while the predictive capabilities of the other models were “similar,” the researchers wrote. Results from the machine learning model indicated predictive factors for osteoporosis include monthly income, education, surgical history and marital status, in addition to conventional factors like age and BMI.
“We applied representative ML algorithms to predict osteoporosis using clinical data from patients with RA,” Lee and colleagues wrote. “By comparing with previous studies, we observed a comparable performance. ML methods have the potential to support practitioners in the detection of osteoporosis in patients with RA.”
Perspective
Back to Top
David A. McLain, MD, MACR, FACP, FRCP
Several research studies indicate that artificial intelligence (AI) has the potential to match or even surpass human performance in critical health care tasks, including disease diagnosis. Presently, algorithms excel in detecting malignant tumors, outperforming radiologists, and assisting researchers in constructing cohorts for expensive clinical trials. AI encompasses a diverse array of technologies, each with immediate relevance to health care, though their applications vary widely.
Machine learning, a statistical technique for modeling data and learning through training, stands out as one of the most prevalent forms of AI. In a 2018 Deloitte survey of 1,100 U.S. managers engaged in AI, 63% of companies were already employing machine learning. This broad technique underpins many AI approaches, with various iterations. In health care, traditional machine learning finds common application in precision medicine, predicting successful treatment protocols based on patient attributes and treatment context.
The convergence of AI and precision medicine holds the promise of transforming health care. Precision medicine methods identify patient phenotypes with unique responses to treatment or specific health care needs. AI uses advanced computation and inference for generating insights, enabling reasoning and learning, and enhancing clinician decision-making through augmented intelligence.
The determinants of individual health, influenced by lifestyle, nutrition, environment, and access to care, can now be tracked and measured by wearables and medical devices. These factors, encompassing behavioral, socio-economic, physiological, and psychological data, constitute about 60% of health determinants, while genes contribute around 30%, and medical history only 10%.
Integrated into health care, precision medicine has the potential to deliver more accurate diagnoses, predict disease risk before symptoms manifest, and formulate tailored treatment plans for optimal safety and efficiency.
Collapse
Read more about
Click Here to Manage Email Alerts