Arrow
use cases

Predicting and Preventing Urinary Tract Infections with Artificial Intelligence | Arkangel AI

Urinary tract infections (UTIs) impose significant health and financial burdens, AI allows providers to intervene accordingly.

Problem

Urinary tract infections (UTIs) are the most common infections treated in outpatient settings in the United States (1). They are also the fifth most common type of hospital-acquired infection, with an estimated 62,000 infections occurring annually in acute care hospitals (2). Each year, UTIs lead to approximately 400,000 hospitalizations, seven million office visits, and one million emergency department visits, resulting in roughly $10 billion in expenditures related to UTI care (3). This significant financial burden is compounded by the 13,000 deaths associated with healthcare-acquired UTIs annually (2), of which 69% of catheter-associated UTIs (CAUTIs) are considered avoidable (6).

Why it matters

  • UTIs result in approximately $10 billion in healthcare expenditures annually in the U.S., reflecting a significant financial burden.
  • Healthcare-acquired UTIs are associated with 13,000 deaths each year, highlighting a critical patient safety issue.
  • Sixty-nine percent of catheter-associated UTIs (CAUTIs) are considered avoidable, indicating substantial potential for improvement in prevention measures.

Solution

"UTIForecast AI" is a predictive model designed to identify the risk of urinary tract infections in patients. Analyzes clinical factors and patient history to provide insight into UTIs, allowing healthcare professionals to preventively implement protective measures and improve patient outcomes, while aiming to reduce costs health care partners.

Discover more and interact with our AI!

Datasources

The synthetic data set used for this model was aligned with clinical research findings to accurately reflect the patient's risk factors for UTIs. Research includes epidemiological studies by Medina and Castillo-Pino (1), CDC guidelines on UTI events (2), hospitalization trends analyzed by Simmering et al. (3),  patient education provided by the Cleveland Clinic (4), and intervention evaluations by Meddings et al. (5). These studies informed the choice of variables and their importance, equipping the model to provide reliable risk predictions.

Citations

  1. Medina, Martha, and Edgardo Castillo-Pino. “An Introduction to the Epidemiology and Burden of Urinary Tract Infections” Therapeutic Advances in Urology, vol. 11, 1 Jan. 2019, doi:10.1177/1756287219832172. Accessed 5 Mar. 2021.
  2. Centers for Disease Control and Prevention. “Urinary Tract Infection (Catheter-Associated Urinary Tract Infection [CAUTI] and Non- Catheter-Associated Urinary Tract Infection [UTI] Events.” National Healthcare Safety Network, Jan. 2021. Accessed 5 Mar. 2021.
  3. Simmering, Jacob E., et al. The Increase in Hospitalizations for Urinary Tract Infections and the Associated Costs in the United States, 1998-2011. Open Forum Infectious Diseases, vol. 4, no. 1, 1 Jan. 2017, doi:10.1093/ofid/ofw281. Accessed 8 Mar. 2021.
  4. Family Health Team. “6 Things You Should Know about UTIs in Older Adults.” Health Essentials from Cleveland Clinic, Health Essentials from Cleveland Clinic, 4 May 2018, health.clevelandclinic.org/6-things-you-should-know-about-utis-in-older-adults/. Accessed 23 Feb. 2021.
  5. Meddings, Jennifer, et al. “Systematic Review of Interventions to Reduce Urinary Tract Infection in Nursing Home Residents” Journal of Hospital Medicine, vol. 12, no. 5, 1 May 2017, pp. 356-368, doi:10.12788/jhm.2724. Accessed 8 Mar. 2021.

Book a Free Consultation

Trusted by the world's top healthcare institutions