Smart Innovation
Antimicrobial resistance (AMR)
AMR develops when bacteria, fungi or viruses are exposed to antibiotics, antifungals or antivirals. As a result, the antimicrobials become ineffective and infections may persist. In addition, medical interventions including surgery, chemotherapy and stem cell therapy may become impossible.
AMR is considered the biggest global threat of Health and Food Safety.
AMR Insights
For Researchers and Entrepreneurs who wish to investigate, develop and commercialize novel vaccines, diagnostics and antimicrobials to prevent Antimicrobial resistance, AMR Insights offers selected, global information and data, specific education and extensive networking and partnering opportunities.
AMR Insights is for:
- Researchers at Universities and University Medical Centers
- Researchers at Research Institutes
- R&D professionals in Pharma, Biopharma and Diagnostics companies
- Entrepreneurs in start-up’s and spin off companies
- Innovators, Venture Capitalists.
Latest Topics
-
27 August 2025Towards an Interpretable Machine Learning Model for Predicting Antimicrobial Resistance
This paper explores how interpretable machine learning (ML) can improve the prediction of antimicrobial resistance (AMR) by integrating phenotype–genotype synergy. While ML methods already achieve high accuracy in predicting resistance from genomic data, most overlook complex, nonlinear interactions between genes and mutations. By accounting for these synergistic effects, models can better capture biological realities, improve […]
Read more... -
25 August 2025Gamified interventions to educate healthcare professionals on the rational use of antimicrobials
A prospective interventional study with 50 clinical practitioners, medical students, and pharmacy students tested an innovative gamified training approach on antimicrobial use, based on ICMR (2022) and IDSA guidelines. Pre- and post-tests showed significant improvements: correct differentiation between bacterial and viral infections rose from 48% to 94%, rational empirical prescribing from 34% to 82%, appropriate […]
Read more... -
22 August 2025Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning
This study explored the use of machine learning to predict bacterial antibiotic resistance using the large-scale Pfizer ATLAS dataset (917,049 isolates). Two data subsets were analyzed: Phenotype-Only and Phenotype + Genotype. Among the models tested, XGBoost performed best, reaching AUC values of 0.96 and 0.95. Data balancing improved recall, and the antibiotic used was the most important […]
Read more...
More news related to Smart innovation
