Predictive Alerting: Leveraging Novel AI Approaches For The Early Detection Of Patients With Rare Disease

By Jeremy Watkins, MS, Data Scientist; Ben Cerio, PhD, Staff Data Scientist; Wissam Siblini, PhD, Senior Machine Learning Engineer; Marc Carmichael, PhD, Clinical Advisor; Vijay Divi, PhD, Head of Data Science

We often liken the task of pinpointing a rare disease to the proverbial search for a needle in a haystack. This comparison has taken on an even greater significance in recent years, as a result of the exponential growth of healthcare data. While this expansion offers new avenues for detecting rare diseases, it also adds to the complexity of sifting through the noise.

Individuals afflicted with rare diseases frequently endure prolonged periods, sometimes spanning years, before receiving an accurate diagnosis. The inherent variability in how these diseases manifest complicates their identification through conventional means. To ensure timely and precise identification, our methods must be as diverse as the diseases themselves. While a uniform approach would be ideal, in reality, it often falls short when disease characteristics, treatment patterns, and patient experiences exhibit such wide-ranging diversity. This is why we are committed to developing comprehensive tools that address the unique challenges presented by rare diseases in healthcare data.

Uncover the ways that Komodo Health is constructing alert solutions for its clients, thus employing a blend of prescriptive and predictive machine learning techniques.