Case Number 114057 - Predicting Disease with Weather

Contact: Geoffrey Pinski
Email: pinskig@ucmail.uc.edu
Phone: 513-558-5696

Description:  Our patent pending method for creating customizable weather-disease attack risk models for a range of common diseases will usher in a new phase of disease risk prediction. Created by a collaboration between Dr. Vincent Martin, MD of the University of Cincinnati, Dr. Robert Nicholson, PhD of Mercy Research and Albert Peterlin, of ERREx, Inc, our models can help optimize population management risk modeling and/or intelligent digital/mobile health (or mHealth) personalized health solution apps that engage patients during high-risk periods for attacks of disease to reduce preventable medical costs while improving care outcomes and quality.

Clinical experience along with well over a hundred published research findings implicate weather as a risk factor for an array of diseases that drive medical care costs. This includes hospital readmission disease drivers such as heart (e.g., congestive heart failure, heart attack) and respiratory (e.g., asthma, chronic obstructive pulmonary disease/emphysema) diseases as well as those diseases with high ambulatory/ER presentation rates (e.g., migraine, asthma, and depression). Whether to avoid financial penalties for hospital readmissions, or as part of an ACO model where preventing medical care costs are rewarded, reducing preventable medical costs while maintaining care quality and improving patient outcomes is rapidly becoming a primary focus of health care systems and digital/mHealth personal health solutions.

To achieve these aims, health systems population managers and personalized health solution app developers employ algorithmically driven disease risk models ranging from broad based population management to personalized medicine to predict disease attack risk. However, these models do not account for the unseen, ever-present, fluctuating weather conditions that can influence disease attack risk. Our interdisciplinary team of doctors, healthcare researchers, statisticians, and meteorologists has created mathematical models that use dynamic, seasonally and normatively adjusted real-time weather conditions to create accurate daily and near-term weather-disease attack risk models. Our models can help optimize population management strategies that engage patients during disease attack high-risk periods and can also seamlessly integrate into digital/mHealth platforms that engage the patient when weather conditions (alone or in conjunction with other risk factors) place them at increased risk for a disease attack and then provide them actionable options to prevent or mitigate the attack.

We have tested, validated, and produced a market-ready version of our weather-disease attack risk model for migraine. Our models showed population attack risk prediction superior to anything else published or in use for migraine. Moreover, we created stratified individual-level risk models. The result is a migraine early warning system that is ideally suited for a digital/mHealth personal health solution in conjunction with a healthcare system or within a smart device application.

By using our models, healthcare systems will realize greater financial gain by reducing preventable medical care costs while improving care quality and outcomes. Personalized health solution providers will be able to add our models to their digital/mHealth platforms to create an even more intelligent personalized health solution. Finally, and most importantly, patients will be alerted to when they are at heightened risk for a disease attack and take action to prevent or mitigate the attack. This will result in lower health care costs for the patient, not missing work or other life responsibilities, and will ultimately allow them improved quality of life. In addition, they will develop brand loyalty to the system and/or digital/mHealth solution that provides them with life enhancing, or even lifesaving, solutions.



Please see our additional technology summary: Predicting Disease with Weather.