Machine Learning for Disease Event Detection

For people with asthma, developing a viral respiratory tract infection, such as from the common cold or flu, can have a profound effect on the expression of disease resulting in the need for acute care and possibly, death. One of the challenges in asthma research and treatment is that there is no standard definition or test to diagnose asthma or acute asthma events. Our client wanted to define asthma, and identify asthma sufferers who are ill and at risk for major respiratory complications. Elder Research was hired to:

1. Find a molecular signature that could be developed as a diagnostic tool
2. Develop a predictive model that could be turned into an app and incorporated into a wearable device.

The client developed a controlled environment to collect clinical samples and data from volunteers inoculated with a virus or placebo. Elder Research data scientists collaborated with doctors and staff to develop indexes that identified volunteers who were sick and volunteers who experienced an acute asthma attack during the course of the study. Data from analytes extracted from daily blood and nasal wick samples collected from the volunteers (shown in the chart below) in addition to other clinical data were investigated.

In two months Elder Research developed two indexes and applied them as a standard definition to characterize volunteers who fell ill and those who experienced acute asthma worsening. Our methodology identified four predictive biomarkers (three analytes and one clinical measurement). We also developed an algorithm that can be incorporated into an application such as a wearable device.

Download This Case Study