Intelligent anti-microbial system (i.A.M.S)
AI prediction of microbial resistance, personalized antibiogram, antibiotics decision support system, risk of sepsis and mortality AI prediction
Sepsis impacts and causes millions of deaths annually worldwide, including Taiwan. The mortality could be up to 29.2%.2 Failure to detect and diagnose sepsis early is an important factor for high mortality rate. Per hour of delay in appropriate antibiotic administration, mortality rate increases by 7.6%.3 Additionally, the extended- and pan-drug resistant bacteria known as “superbug,” spreads rapidly globally. The World Health Organization (WHO) reported that approximately 700 000 individuals died from infectious disease caused by resistant bacteria, and approximately 10 000 000 individuals would die due to “superbug” infection in 2050, which impacts more than that of COVID-19. “Optimizing antibiotics usage and developing rapid tests” are important issue in antimicrobial stewardship. The microbial diagnosis in the Center of Laboratory Medicine is the beginning of all our effort. However, the critical condition changed more rapidly than that of the traditional method to identify pathogens and antimicrobial susceptibilities.
Resolving the problems, our team produced the first and most complete “comprehensive anti-microbial system” that focuses on patients with infection and sepsis. The team is composed of the infectious disease and critical care medicine-specialized physicians, laboratory medicine department, pharmacy department, information technology department, big data center, and artificial intelligence center. We organize the big data and information and use the AI prediction to help clinicians diagnose more rapidly and perform precise therapy.
The “prediction of sepsis risks and mortality” alerts clinicians to implement measures for patients with high-risk. Clinicians could obtain information from previous pathogens and antimicrobial susceptibility tests for targeted patients by “personized antibiograms,” and the locally common pathogens with antimicrobial susceptibility by “intelligent antibiotic clinical decision support systems.” Furthermore, the systems also help physicians prescribe empirical antibiotics with adequate dosage based on the weight, liver, and renal function. “AI prediction of antimicrobial susceptibility test (AST)” could text physicians the antimicrobial resistance prediction results earlier than that of the traditional method and allow them adjust antibiotics.
We integrated the scattered data over time, AI prediction of sepsis, and AST in a friendly platform to achieve early sepsis detection, more rapid pathogen and antimicrobial susceptibility identification, and appropriate antibiotics use. Based on the “comprehensive anti-microbial system,” our team would offer more personalized precision medicine timely with higher quality combined with gene information.
The near-miss of medication dosage error was quite reduced from 2.95% to 0.79%. The report of resistance prediction was 1.4 days earlier than traditional culture report, and the mortality rate of delayed prescription of appropriate antibiotics for CRKP and MRSA infection with sepsis were reduced from 40% to 28%.
AI System for Sepsis Detection and Mortality
- 《新聞思想啟》第28 集(壹電視)
- 敗血症致死率高達3 成！「智抗菌」助預測感染並快檢菌種(健康醫療網)
- 智抗菌決策輔助系統感染源鑑定1 小時出爐-大台中新聞(台灣生活新聞)
- 抗敗血症! "智抗菌"感染源鑑定1 小時出爐｜華視台語新聞2022.03.04(華視)