Share This Article
New research has highlighted the potential for the Apple Watch to predict pain scores in people with sickle cell disease. A study led by researchers from Duke University and Northwestern University aimed to use machine learning to analyze data collected by the smartwatch to predict pain associated with vaso-occlusive crises (VOCs) in sickle cell disease patients.
The study found that Apple Watch was a “novel and feasible approach” that could benefit clinicians and individuals with sickle cell disease.
Sickle cell disease is a genetic red blood cell disorder that can lead to chronic anemia, stroke, and VOCs. These VOCs are difficult to predict and treat and are the leading cause of hospitalization. Researchers set out to use Apple Watch data, including heart rate, heart rate variability, and calories, to help better understand the pain experience and find trends to predict pain from VOCs.
To collect data, researchers approached 20 sickle cell disease patients admitted for a VOC at Duke University’s SCD Day Hospital between July and September 2021. Each patient was given an Apple Watch Series 3 to wear for the duration of their visit, collecting data that was combined with pain scores and vital signs from electronic medical records. The study used multiple machine learning models to analyze the data.
The evaluation metrics considered were accuracy, area under the receiving operating characteristic curve, and root-mean-square error. All models outperformed the null models, with the best-performing model being the random forest model, which predicted pain scores with an accuracy of 84.5% and a root-mean-square error of 0.84.
Related articles
- British Writer’s Life Saved by Apple Watch’s Atrial Fibrillation Detection
- New Study Reveals Shocking Lack of Sleep Among Apple Watch Users
The study demonstrates the potential for the Apple Watch to provide a low-cost method that could benefit clinicians and individuals with sickle cell disease in the treatment of VOCs.
The researchers note that “the strong performance of the model in all metrics validates feasibility and the ability to use data collected from a noninvasive device, the Apple Watch, to predict the pain scores during VOCs”. The study’s findings could prove to be a significant step forward in healthcare, with the Apple Watch becoming a useful tool for both patients and physicians.
