Biomedicine

AI - enhanced Safety of Prescription and clinical application

Principal Investigator:Yu-Chuan (Jack) Li

Abstract

MedGuard is based on >1.3B prescription big data, unsupervised learning and reinforcement learning, to simulate real-world physicians’ behaviors by the treatment patterns. Now, it is applied for more than 250 doctors and 400,000 prescription. Averagely we save 300-600M NTD for each hospital every year based on implemented real record analysis.

1learn more
Team Introduction

Our team consist of physicians, pharmacists, computer scientists, data scientists and marketing specialists.

Goals and Plan

Based on this project, we are expected to upgrade our system (Protection&prevention, Proactive Recommendations), develop reinforcement learning model, create hospitals report、start clinical trial in US medical institutions, and promote startup business. Then, it can build brand products, increase entry barriers to, expand the market, and potentially be the first AI medical unicorn from Taiwan.

Entry Barrier

MedGuard every year, with >60% user acceptance rate and >85% by expert review, based on reinforced learning for physician behavior resulted in 3% alert rate.The MedGuard is patent and FDA pended.

Market Scope

 According to the WHO report, the cost associated with medication errors has been estimated at $42 billion USD annually.This product is mainly applicable to medium and large hospitals. The market is estimated to generate revenues of more than $4 billion USD per year.