• btc = $69 503.00 - 244.45 (-0.35 %)

  • eth = $3 782.11 26.98 (0.72 %)

  • ton = $6.42 0.10 (1.58 %)

  • btc = $69 503.00 - 244.45 (-0.35 %)

  • eth = $3 782.11 26.98 (0.72 %)

  • ton = $6.42 0.10 (1.58 %)

17 Mar, 2023
1 min time to read

Duke and Northwestern University researchers have published a study on the Apple Watch's ability to predict pain in people with sickle cell disease.

A group of researchers conducted a study to explore the potential of using Apple Watch data and machine learning to predict pain from vaso-occlusive crises (VOCs) in patients with sickle cell disease, a genetic red blood cell disorder associated with severe complications such as chronic anemia, stroke, and VOCs. The study was conducted at Duke University's SCD Day Hospital, where patients with sickle cell disease admitted for a VOC were approached to participate in the study by wearing an Apple Watch Series 3 for the duration of their visit.

The data collected by the Apple Watches included heart rate, heart rate variability, and calories. Pain scores and vital signs were also recorded from the electronic medical record. The researchers then applied multiple machine learning models to analyze the data and predict pain scores. The results showed that all models outperformed the null models, and the random forest model was the best-performing model, predicting pain scores with an accuracy of 84.5% and a root-mean-square error of 0.84.

According to the researchers, the study demonstrates the feasibility of using a noninvasive device such as the Apple Watch to predict pain scores during VOCs in patients with sickle cell disease. The study's findings indicate that the use of Apple Watch and machine learning could be a low-cost and novel approach that could benefit both patients and clinicians in the treatment of VOCs.