Sharecare develops new crowdsourced machine learning model to predict allergy symptom burden

Rhea-AI Summary

Sharecare has developed a machine-learning model to predict allergic rhinitis symptoms, aiming to improve allergy management. The research, involving over 2,000 participants across the U.S., achieved over 80% accuracy in forecasting allergy-related symptoms using environmental and physical activity data. Allergic rhinitis costs the U.S. approximately $24.8 billion annually in direct expenses. Sharecare plans to integrate the findings into consumer offerings, providing personalized symptom management recommendations and enhancing preventive care.

Positive

• Achieved over 80% accuracy in predicting allergy symptoms with machine learning.
• Potential to reduce $24.8 billion annual costs related to allergic rhinitis in the U.S.
• Plans to offer personalized recommendations for allergy sufferers through future consumer products.

Negative

• None.

ATLANTA and PALO ALTO, Calif., March 23, 2021 /PRNewswire/ -- What if you could develop a forecast for your allergies, just as you check the weather on your phone before heading out the door? While there may not be an app for that yet, new research from Sharecare, the digital health company that helps people manage all their health in one place, lays the groundwork for future efforts to map when allergies might flare up so individuals can live happier, more productive lives. The study, originated by doc.ai prior to its acquisition by Sharecare, was recently published in the Journal of Asthma and Allergy.

Using Omix, a proprietary digital clinical research platform powering mobile research studies, the Sharecare team developed and trained a machine-learning algorithm to predict the emergence and severity of symptoms related to allergic rhinitis. Commonly known as environmental allergies, allergic rhinitis is responsible for nearly 15 million clinic visits, 3.5 million days of missed work, and $24.8 billion in direct costs incurred in the U.S. every year.^1,2

Sharecare's study enrolled more than 2,000 participants from across the U.S. to gather real-world symptom and environmental data, such as geo-coded pollen counts. Smartphone sensor data including daily physical activity and geolocation were collected, and participants logged their symptoms in an e-diary. Using these inputs, the researchers' machine-learning algorithm was able to predict participants' allergy burden with greater than 80% accuracy. The study findings augment traditional allergy treatment regimens, which focus on avoiding triggers and can add tailored actionable insights that are meaningful to an individual in their unique environment.    

"To date, machine learning models in healthcare have focused on clinicians with decision support or administrators with forecasting, rather than emphasizing patient-facing direct care models," said Nirav R. Shah, MD, MPH, chief medical officer of Sharecare. "When predictive models like those in our study are capable of real-time personalized predictors and offer a strategy for tailored clinical care and prevention, they will be integrated into care delivery."

"Today, anyone with a smartphone can be a meaningful contributor to important research," said Sam De Brouwer, chief strategy officer at Sharecare. "Sharecare's Omix allergy study has opened up a secure way to contribute to preventive relief for high-risk allergic rhinitis patients. Following additional clinical external validation, this model could be packaged into consumer offerings providing allergy sufferers with real-time personalized recommendations for their symptoms that are refined on an ongoing basis as more people opt in to sharing their data."

Digital health studies conducted through Omix use all smartphone capabilities – including voice, photos, video, and text – to capture health data seamlessly with user permission. The participant-centric approach of Omix empowers individuals by providing easy data capture and tracking, points redeemable in the Omix marketplace, and an individualized end-of-study report.

The self-service version of the Omix study builder is currently in beta. Those interested in signing up to create their own mobile-based studies can do so now by joining the waitlist. More information can be found by visiting sharecare.com/omix.

About Sharecare
Sharecare is the leading digital health company that helps people – no matter where they are in their health journey – unify and manage all their health in one place. Our comprehensive and data-driven virtual health platform is designed to help people, providers, employers, health plans, government organizations, and communities optimize individual and population-wide well-being by driving positive behavior change. Driven by our philosophy that we are all together better, at Sharecare, we are committed to supporting each individual through the lens of their personal health and making high-quality care more accessible and affordable for everyone. To learn more, visit www.sharecare.com.

1Burton WN, Conti DJ, Chen C-Y, Schultz AB, Edington DW. The impact of allergies and allergy treatment on worker productivity. J Occup Environ Med. 2001;43(1):64–71. doi:10.1097/00043764- 200101000-000132. Mudarri DH. Valuing the economic costs of allergic rhinitis, acute bronchitis, and asthma from exposure to indoor dampness and mold in the US. J Environ Public Health. 2016;2016:1–12. doi:10.1155/2016/ 23865963. Sur DKC, Plesa
2Mudarri DH. Valuing the economic costs of allergic rhinitis, acute bronchitis, and asthma from exposure to indoor dampness and mold in the US. J Environ Public Health. 2016;2016:1–12. doi:10.1155/2016/ 23865963

 

View original content:http://www.prnewswire.com/news-releases/sharecare-develops-new-crowdsourced-machine-learning-model-to-predict-allergy-symptom-burden-301253261.html

SOURCE Sharecare

FAQ

What is the new allergy prediction model developed by Sharecare?

Sharecare's new model uses machine learning to forecast allergic rhinitis symptoms, improving allergy management.

How accurate is Sharecare's allergy prediction model?

The model has demonstrated over 80% accuracy in predicting allergy symptoms based on environmental data.

What is the economic impact of allergic rhinitis in the U.S.?

Allergic rhinitis incurs approximately $24.8 billion in direct costs annually in the U.S.

How can users participate in Sharecare's Omix study?

Individuals can join the waitlist for the self-service version of the Omix study builder to create mobile-based studies.