Implementation of AI for predicting antibiotic resistance patterns: A hospital-based study
The use of Artificial Intelligence (AI) to predict antibiotic resistance patterns in a hospital setting is of interest. By leveraging machine learning (ML) models, including Random Forest, Logistic Regression and Support Vector Machines, the study aimed to predict resistance based on patient demographics, microbial species and clinical data. The Random Forest model outperformed other models in terms of accuracy, precision and recall. Data shows the importance of integrating AI-driven tools into clinical workflows for improved antibiotic stewardship and patient outcomes. Despite challenges, AI presents a promising approach for combating antibiotic resistance in healthcare.
Authors
- Piyush Jani
- Mohammed Mustafa (ORCID: https://orcid.org/0009-0007-6494-910X)
- Shailesh Tripathi (ORCID: https://orcid.org/0000-0002-3263-8928)
- Anshuman Srivastava (ORCID: https://orcid.org/0000-0001-8598-6427)
- Amrit Podder (ORCID: https://orcid.org/0000-0002-9816-3347)
- Mukul Singh (ORCID: https://orcid.org/0000-0003-3865-7916)
- R Ravikant
- Mukesh Kumar Patwa
Institutions
- Prince Sattam Bin Abdulaziz University (SA)
- Patna Medical College and Hospital (IN)
- Goa Medical College (IN)
- Central University of Tibetan Studies (IN)
- Teerthanker Mahaveer Medical College & Research Centre (IN)
- All India Institute of Medical Sciences (IN)
- Central Institute of Psychiatry (IN)
Publication Details
- Journal
- Bioinformation
- Published
- 2025-10-31
- DOI
- https://doi.org/10.6026/973206300213636
- Primary Topic
- Bacterial Identification and Susceptibility Testing
- Type
- article
- Field-Weighted Citation Impact
- 0.00