use cases

Prediction of Antibiotic Resistance

Use clinical variables from the EMR of patients to predict antibiotic resistance


Antibiotic resistance bacteria are one of the world’s greatest health threats, causing severe problems in preventing and treating persistent disease (1)(2). Despite the various actions taken over the past decades to address this issue, trends in global antibiotic resistance show no signs of slowing (2). The effectiveness of antibiotics is endangered due to inadequate medical prescriptions, excessive use and misuse of these drugs, extensive agricultural use, the availability of few new antibiotics and regulatory barriers to the development of new medicines by the pharmaceutical industry. As a result, the rapid emergence of resistant bacteria is increasing to dangerously high levels around the world leading to the antibiotic resistance crisis (3).

Why it matters

  • 30-50% of treatment indication, agent choice or duration of antibiotic therapy on incorrect (3).
  • 30-60% of antibiotics prescribed in UCIs are unnecessary, inappropriate or suboptimal (3).
  • 80% of antibiotics sold in U.S. are used in animals to promote growth and prevent infections (3).
  • 27% of all drugs sold without prescription in urban areas, while this dropped to 8% in rural areas (4).
  • 51.7% of pharmacies dispense antibiotics freely without a prescription (4).

Antibiotic resistance increases morbidity and mortality associated with infections and contributes significantly to rising healthcare costs due to longer hospital stays, increased hospital admissions and the need for more costly second-line medications (1)(5). Indeed, resistance results from the interaction of microorganisms, patient and hospital environment, as well as the use of antibiotics and infection control practices (5). Antibiotic resistance is seen as a major threat as it compromises the ability of the human immune system to deal with infectious diseases and contributes to a variety of complications in vulnerable patients and patients suffering from chronic conditions (2).

Antibiotics are the second most self-medicated drugs after painkillers (3). Antibiotic self-medication predisposes patients to pharmacological interactions, the symptoms of an underlying disease can be ignored and as a result there is a high probability of the development of microbial resistance (6). Unbridled irrational use of antibiotics without prescription or medical guidance may increase the likelihood of inappropriate, incorrect or inappropriate therapy, misdiagnosis, delays in proper treatment, pathogen resistance and increased morbidity (7).


Predictive analytics and AI may assist clinicians in monitor trends in antimicrobial resistance to promote antibiotics’ sensible applications (8). AI-based models could recognize and predict the severity of infection, provide for appropriate antibiotic prescription including appropriate therapy selection, dose, and correct route of administration, classify and predict bacterial resistance to antibiotics by genomes (9). In addition, ML techniques can predict early antibiotic resistance or the probability of a microbial agent becoming resistant. Another application of AI to antibiotic resistance in the healthcare industry could be the discovery of new antibiotics that are structurally different from those already known (8).


  • Genomic data resource: Data extracted from accumulation of genomes in clinical laboratories that can be used to survey the evolution of pathogens.
  • Unstructured Clinical Registries: Data extracted from integrated patient EHR registries that contain different types of patient-level variables such as demographics, diagnoses, problem lists, medications, vital signs, and laboratory data.


  1. World. (2020, July 31). Antibiotic resistance.; World Health Organization: WHO. Retrieved February 23, 2023,
  2. Struelens M. J. (1998). The epidemiology of antimicrobial resistance in hospital acquired infections: problems and possible solutions. BMJ (Clinical research ed.), 317(7159), 652–654.
  3. Ventola C. L. (2015). The antibiotic resistance crisis: part 1: causes and threats. P & T : a peer-reviewed journal for formulary management, 40(4), 277–283.
  4. P. (2019). Antimicrobial Resistance: Implications and Costs. Infection and drug resistance, 12, 3903–3910.
  5. Bennadi D. (2013). Self-medication: A current challenge. Journal of basic and clinical pharmacy, 5(1), 19–23.
  6. Rabaan, A. A., Alhumaid, S., Mutair, A. A., Garout, M., Abulhamayel, Y., Halwani, M. A., Alestad, J. H., Bshabshe, A. A., Sulaiman, T., AlFonaisan, M. K., Almusawi, T., Albayat, H., Alsaeed, M., Alfaresi, M., Alotaibi, S., Alhashem, Y. N., Temsah, M. H., Ali, U., & Ahmed, N. (2022). Application of Artificial Intelligence in Combating High Antimicrobial Resistance Rates. Antibiotics (Basel, Switzerland), 11(6), 784.
  7. Nepal, G., & Bhatta, S. (2018). Self-medication with Antibiotics in WHO Southeast Asian Region: A Systematic Review. Cureus, 10(4), e2428.
  8. Ren, Y., Chakraborty, T., Doijad, S., Falgenhauer, L., Falgenhauer, J., Goesmann, A., Hauschild, A. C., Schwengers, O., & Heider, D. (2022). Prediction of antimicrobial resistance based on whole-genome sequencing and machine learning. Bioinformatics (Oxford, England), 38(2), 325–334.
  9. Su, M., Satola, S. W., & Read, T. D. (2019). Genome-Based Prediction of Bacterial Antibiotic Resistance. Journal of clinical microbiology, 57(3), e01405-18.

Book a Free Consultation

Trusted by the world's top healthcare institutions