SBIR-STTR Award

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is the development of an intuitive, easy-to-use, Smart Respiratory Health Management System for respiratory patients and their physicians. This system includes (1) lab-quality lung function data produced by the proposed mobile spirometer and paired smartphone application, (2) the interpretation and contextualization of this lung function data based on local environmental and physiological risk factors, and (3) the delivery of these insights to physicians and patients. By leveraging this software platform, this technology is expected to enable physicians to make timely interventions with their at-risk patients, thereby preventing acute respiratory exacerbations (e.g., asthma attacks) and any associated hospitalizations or visits to the emergency department. Currently, respiratory diseases are poorly managed, and the proposed predictive technology can help reduce the 1.6 million annual asthma-related visits to the emergency department. By enabling preventative patient interventions, the proposed technology is expected to reduce the high cost of asthma-related emergency department visits and hospitalizations. The proposed system-level solution will empower asthma patients to participate in their own health and treatment, while simultaneously improving health-related behaviors, patient-physician communication, and preventative care coordination.The proposed project focuses on the development of a software platform that connects chronic respiratory disease patients to physicians, to alert physicians of declining lung health. With this preemptive alert, physicians can intervene with patients before an acute respiratory exacerbation, thereby reducing hospitalizations and their associated costs. There are three steps required to implement this proposed system. The first is to facilitate the affordable collection of daily lab-quality lung function data. This step has already been completed via a mobile spirometer and pair smartphone application. The second step is to interpret and contextualize the collected data. This step requires the development of a predictive algorithm that incorporates risk factors from a physical activity and local environment. The third step is to deliver this data and their interpretation to the physician in a manner that is seamlessly incorporated into the existing electronic health records infrastructure and the physician's workflow. The second and third steps will be undertaken as part of this Phase I grant.

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project will be the redefinition of the care of asthma patients. Asthma is highly prevalent in the US, with 25 million patients currently suffering symptoms, and was the cause of 1.7 million emergency room visits in 2015, resulting in a huge societal cost. A predictive platform that can identify when a patient is at risk of an asthma attack would serve to reduce such costs by allowing intervention in a timely manner, thereby reducing the number of emergency room visits by asthma patients. Through the combination of remote monitoring of patient lung function, local environmental sensing, and data analytics, asthma can be understood at a personalized scale, a dramatic shift in the standard of care for this chronic and complex condition. Additionally, the platform developed in this project can be expanded to other conditions, such as chronic obstructive pulmonary disorder or cystic fibrosis, broadening its impact. Ultimately, it is envisioned that this project will result in a world without asthma attacks. This Small Business Innovation Research (SBIR) Phase II project will result in the development of a machine learning-based data analytics platform to identify in advance when asthma patients are at risk of an asthma attack, thereby enabling physicians to alter a patient's care plan and avoid hospitalization. To date, there is no integrated system to gather and analyze high-quality lung function and environmental data for asthma patients on a daily basis in order to truly analyze and predict a patient's health. As a result, asthma care is often reactive, requiring emergency treatment and resulting in poor clinical outcomes. The objectives of this Phase II research include the development and validation of a machine-learning based analytics model to generate new insights into the health of asthma patients; the development and implementation of a physician portal to translate such insights into clinical outcomes; and the development of new datasets to create a more robust and accurate platform. The result will be a live prediction platform to assist physicians in keeping asthma patients out of the emergency room. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.