Jordanian Journal of Informatics and Computing

ISSN: 3080-6828 (Online)

A Confidence-Aware and Safety-Constrained AI Framework for Antimicrobial Resistance Decision Support

by 

Hussein Ali Hussein Al Naffakh

PDF logoPDF

Published: 2026/06/16

Abstract

The issue of antimicrobial resistance (AMR) poses a significant threat to clinical decision-making because of dissimilar laboratory practices, incomplete antimicrobial susceptibility testing (AST) results, and patient-specific safety limitations. The majority of current artificial intelligence (AI)-based AMR tools focus on predictive accuracy in ideal situations and only offer few mechanisms to deal with uncertainty or avoid unsafe advice. This paper suggests a confidence-sensitive and safety-constrained AI-based decision support model that can work in practice when faced with incomplete data in the real world. The framework combines calibration prediction of resistance, ability to abstain with confidence, patient tailored filtering of safety, and aligning of guidelines with interpretation to control when to issue or withhold a recommendation. A strength test was conducted by scenario-based data availability configuration which emulates typical laboratory constraints. The findings show that the suggested framework consistently performs reliably on accepted cases and abstains correctly in the case of uncertainty and produces safer alternative recommendations in the case of contraindication. The proposed approach can make AMR prediction a patient-safe, trans-ogram, and reliability-focused decision support system that enables the use of antimicrobial stewardship in everyday practice.

Keywords

Antimicrobial resistanceClinical decision supportConfidence-aware AISafety constraintsData incompletenessand Machine learning.

A Confidence-Aware and Safety-Constrained AI Framework for Antimicrobial Resistance Decision Support is licensed under CC BY 4.0CCBY

References

  1. C. J. L. Murray et al., “Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis,” The Lancet, vol. 399, no. 10325, pp. 629–655, 2022.
  2. World Health Organization, “Global Antimicrobial Resistance and Use Surveillance System (GLASS) Report 2023,” 2023. [Online]. Available: https://www.who.int/publications/i/item/9789240078740
  3. Clinical and L. S. Institute, “Performance Standards for Antimicrobial Susceptibility Testing (M100), 34th Edition,” 2024.
  4. G. Kahlmeter, C. G. Giske, T. J. Kirn, and S. E. Sharp, “European Committee on Antimicrobial Susceptibility Testing (EUCAST): Technical Notes on Antimicrobial Susceptibility Testing,” Clinical Microbiology and Infection, vol. 26, no. 5, pp. 511–514, 2020, doi: 10.1016/j.cmi.2020.02.002.
  5. S. Lepuschitz et al., “Machine learning for antimicrobial resistance prediction: current status, limitations, and future perspectives,” Clin. Microbiol. Rev., vol. 36, no. 1, pp. e00059–22, 2023.
  6. G. Feretzakis et al., “Machine learning for antibiotic resistance prediction: a step towards improved clinical decision support,” J. Clin. Med., vol. 9, no. 11, p. 3517, 2020.
  7. B. Kompa, J. Snoek, and A. L. Beam, “Second opinion needed: communicating uncertainty in medical machine learning,” NPJ Digit. Med., vol. 4, no. 1, p. 4, 2021.
  8. E. Begoli, T. Bhattacharya, and D. Kusnezov, “The need for uncertainty quantification in machine-assisted medical decision making,” Nat. Mach. Intell., vol. 1, no. 1, pp. 20–23, 2019.
  9. M. S. Pulia et al., “The emergency department as a steward of antibiotic use in the era of COVID-19 and beyond,” Academic Emergency Medicine, vol. 27, no. 10, pp. 1047–1052, 2020.
  10. T. F. Barlam et al., “Implementing an Antibiotic Stewardship Program: Guidelines by the Infectious Diseases Society of America and the Society for Healthcare Epidemiology of America,” Clinical Infectious Diseases, vol. 62, no. 10, pp. e51–e77, 2016, doi: 10.1093/cid/ciw118.
  11. European Committee on Antimicrobial Susceptibility Testing, “Breakpoint tables for interpretation of MICs and zone diameters, Version 14.0,” 2024.
  12. R. T. Sutton, D. Pincock, D. C. Baumgart, D. C. Sadowski, R. N. Fedorak, and K. I. Kroeker, “An overview of clinical decision support systems: benefits, risks, and strategies for success,” NPJ Digit. Med., vol. 3, no. 1, p. 17, 2020.
  13. R. Ibrahim et al., “Handling missing values in healthcare data: a systematic review,” Journal of the American Medical Informatics Association, vol. 28, no. 12, pp. 2750–2760, 2021.
  14. G. Varoquaux and V. Cheplygina, “Machine learning for medical imaging: methodological failures and recommendations for the future,” NPJ Digit. Med., vol. 5, no. 1, p. 48, 2022.
  15. A. L. Beam and I. S. Kohane, “Big data and machine learning in health care,” JAMA, 2018.
  16. E. W. Steyerberg, Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating, 2nd ed. Cham, Switzerland: Springer, 2019. doi: 10.1007/978-3-030-16399-0.
  17. C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger, “On calibration of modern neural networks,” in Proceedings of the International Conference on Machine Learning (ICML), PMLR, 2017, pp. 1321–1330.
  18. World Health Organization, Ethics and governance of artificial intelligence for health. World Health Organization, 2021.