New study explores how Apple Watch could be used to predict pain

New research on Apple Watch Health Features emerges at a rapid pace. Researchers from a coalition including Duke University and Northwestern University have published the results of a study to determine if an Apple Watch could be used to predict pain in people with sickle cell disease.

Use Apple Watch to predict pain

As the researchers explained, sickle cell disease is a genetic disease of red blood cells associated with a number of serious complications. This includes things like chronic anemia, strokes, and vaso-occlusive crises (VOCs). In particular, VOCs are “unpredictable, difficult to treat, and the leading cause of hospitalization.”

With this study, the researchers decided to use Apple Watch data and machine learning to “help us better understand pain experience and find patterns to predict VOC pain.” .

  1. To determine the feasibility of using the Apple Watch to predict pain scores in people with sickle cell disease admitted to Duke University SCD Day Hospital, called Day Hospital.
  2. Build and evaluate machine learning algorithms to predict VOC pain scores with the Apple Watch.

    To collect data for the study, researchers at Duke University Day Hospital approached patients with sickle cell disease who had been admitted with a VOC and asked if they were interested in participating in the study. This data collection took place between July 2021 and September 2021.

    Those who agreed to participate in the study received an Apple Watch Series 3 which they wore for the duration of their visit. Each Apple Watch collected data including “heart rate, heart rate variability (calculated), and calories.”

    Pain scores and vital signs were collected from the electronic medical record. The researchers then combined the data and applied several machine learning models to analyze whether these techniques can help patients and physicians better understand the pain experience and find patterns to predict VOC pain.

    Data were analyzed using 3 different machine learning models: multinomial logistic regression, gradient boosting and random forest, and 2 null models, to assess the accuracy of pain scores. The evaluation parameters taken into account were the accuracy (F1 score), the area under the reception operating characteristic curve and the root mean square error (RMSE).

    We recruited 20 patients with sickle cell disease, all identified as black or African American and comprised of 12 (60%) women and 8 (40%) men. There were 14 people diagnosed with hemoglobin-like SS (70%). The median age of the population was 35.5 (IQR 30-41) years. The median time each individual spent wearing the Apple Watch was 2 hours and 17 minutes and a total of 15,683 data points were collected from the population. All models outperformed null models, and the best performing model was the random forest model, which was able to predict pain scores with an accuracy of 84.5% and an RMSE of 0.84.

    As pointed out MyHealthyApple, the study shows that the Apple Watch can be “very useful for both patients and the doctors who care for them”. The researchers found that Apple Watch is a “novel and feasible approach and presents an inexpensive method that could benefit clinicians and people with sickle cell disease in the treatment of VOCs.”

    “The good performance of the model in all measures validates the feasibility and ability to use data collected from a non-invasive device, the Apple Watch, to predict pain scores during VOCs,” the researchers explain. .

    You can find more details about the study on the National Library of Medicine website.

    Follow Chance: Twitter, instagramAnd Mastodon

    FTC: We use revenue-generating automatic affiliate links. More.

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top