A team of researchers from Duke University, Northwestern University and other universities has found that using Apple’s Apple Watch smartwatch can help predict pain in patients with sickle cell disease.
Sickle cell disease is an inherited red blood cell disorder that is often associated with complications such as chronic anemia, stroke and vaso-occlusive crisis (VOC), which is often “unpredictable, difficult to treat and a major cause of hospitalization.
With Apple’s Apple Watch, the research team analyzed monitoring data and used machine learning to help predict pain in patients with sickle cell disease and to predict trends in VOC-induced pain.
The researchers used three machine learning models, multinomial logistic regression, gradient boosting and random forest, as well as two Null models, to assess the accuracy of pain scores.
The research team recruited 20 patients with sickle cell disease, all of whom were black or African-American, including 12 ( 60% ) women and eight ( 40% ) men. 14 were diagnosed with hemoglobin SS (70%). The median age of the population was 35.5 (IQR 30-41) years.
Each person wore an Apple Watch for an average of 2 hours and 17 minutes, and a total of 15,683 data points were collected for the entire population. The best-performing model was the random forest model, which was able to predict pain scores with 84.5 percent accuracy and an RMSE of 0.84.
The researchers found that Apple Watch is a “novel and feasible approach and presents a low-cost method that could benefit clinicians and patients with sickle cell disease in the treatment of VOC.
