PRO TALK (AI): How Logical Neural Networks Are Transforming Healthcare

Rado Kotorov
Trendalyze, Founder & CEO

Rado Korotov has 20+ years experience the data management, business intelligence (BI), and AI. He got attracted to the field during his Ph.D. studies in Decision and Game Theory at the Department of Applied Philosophy at Bowling Green State University. After graduating in 2000, he joined a rapidly growing startup that pioneered web portals, digital loyalty programs, and the first big data analytics system. In 2006, Rado joined Information Builders Inc. and collaborated closely with founder and CEO Gerry Cohen on numerous products and patented technologies. They introduced the first self-service BI tools; co-invented the first mobile BI apps; developed the first BI search product in collaboration with Google; and the first autoML in collaboration with R-project. He currently manages Trendlayze Inc., a fast-growing platform for time series and IoT real-time monitoring.

He has written numerous articles and three books: “Organizational Intelligence: How Smart Companies Use Information to Become More Competitive and Profitable”, “Data-Driven Business Models for the Digital Economy,” and “97 Things about Ethics Everyone in Data Science Should Know.”

The quest for a practical AI solution for automated ECG diagnostic is motivated by desire to reduce the human and financial resources required for patient monitoring and to enable more ubiquitous remote outpatient monitoring. Today, Deep Neural Networks (DNN) are considered the building blocks of all AI solutions.  Yet, DNNs are not widely adopted in hospitals for automatic diagnostic for the following reasons. First, doctors do not have the time nor the desire to be “mechanical Turks” who label row-by-row millions of ECG patient records for model training. Second, doctors do not trust black box diagnostic predictions as humans need reasons to support deliberate actions. Third, “the right-to-know” regulation included in GDPR requires organizations to provide to stakeholders explanations for any automatic decision making. We overcomes these challenges with an innovative, patent-pending variant of the Neural Networks. The LNN by Trendalyze in cooperation with LaTrobe University (Australia) and St. Ekaterina University Hospital (Bulgaria). It achieved the best performance of 100% within-patient accuracy in recognizing atrial fibrillation in 12-lead ECG recordings and showed robustness with respect to the wide variations of ECG patterns among different patients.