EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3039. AI-powered lab-on-a-chip platform for rapid bacterial detection
Invited abstract in session TD-20: Advancements in AI and Genomics: Bridging Technology and Biology for Future Healthcare Solutions, stream Computational Biology, Bioinformatics and Medicine.
Tuesday, 14:30-16:00Room: 45 (building: 116)
Authors (first author is the speaker)
1. | Felipe Tetsuo Yamada
|
INESC TEC, Faculdade de Engenharia, Universidade do Porto | |
2. | Flávia Barbosa
|
Porto, INESC TEC | |
3. | Luis Guimarães
|
INESC TEC, Faculadade de Engenharia, Universidade do Porto |
Abstract
Antimicrobial resistance (AMR) presents a serious threat to public health by undermining the efficacy of antibiotic treatments, leading to prolonged illness and heightened healthcare costs. Nearly 5 million deaths occur annually due to drug-resistant infections, with the European Union recording over 33,000 fatalities yearly, coupled with an economic impact exceeding €1.5 billion annually in healthcare expenses and productivity loss. The widespread misuse of antibiotics across various sectors, including human medicine, animal husbandry, and agriculture, coupled with inadequate infection prevention and control measures, fuels the proliferation of resistant bacteria, driving the AMR crisis. Addressing AMR in bacteria requires concerted actions to promote judicious antibiotic usage, enhance infection prevention and control protocols, develop new antibiotics, and bolster surveillance systems to monitor resistance trends effectively.
Utilizing molecular detection techniques, this study employs a microfluidic lab-on-a-chip device with DNA and bacteriophage proteins as bio-recognition molecules. The device generates unique signals for different fluid compositions. The aim is to develop a machine learning model capable of analyzing these signals, thereby aiding in the detection and monitoring of bacteria and AMR genes during infections. Ultimately, this will improve antibiotic prescribing decisions in both human and animal healthcare.
Keywords
- Artificial Intelligence
- Analytics and Data Science
- Computational Biology, Bioinformatics and Medicine
Status: accepted
Back to the list of papers