Hostname: page-component-848d4c4894-75dct Total loading time: 0 Render date: 2024-05-18T09:02:12.472Z Has data issue: false hasContentIssue false
  • English
  • Français

Hospital-acquired infections surveillance: The machine-learning algorithm mirrors National Healthcare Safety Network definitions

Published online by Cambridge University Press:  11 January 2024

Stephani Amanda Lukasewicz Ferreira Open the ORCID record for Stephani Amanda Lukasewicz Ferreira [Opens in a new window] ,
Arateus Crysham Franco Meneses ,
Tiago Andres Vaz Open the ORCID record for Tiago Andres Vaz [Opens in a new window] ,
Otavio Luiz da Fontoura Carvalho ,
Camila Hubner Dalmora ,
Daiane Pressotto Vanni ,
Isabele Ribeiro Berti  and
Rodrigo Pires dos Santos
Stephani Amanda Lukasewicz Ferreira*
Affiliation:
Qualis, Porto Alegre, Rio Grande do Sul, Brazil
Arateus Crysham Franco Meneses
Affiliation:
Qualis, Porto Alegre, Rio Grande do Sul, Brazil
Tiago Andres Vaz
Affiliation:
Qualis, Porto Alegre, Rio Grande do Sul, Brazil
Otavio Luiz da Fontoura Carvalho
Affiliation:
Qualis, Porto Alegre, Rio Grande do Sul, Brazil
Camila Hubner Dalmora
Affiliation:
Qualis, Porto Alegre, Rio Grande do Sul, Brazil
Daiane Pressotto Vanni
Affiliation:
Tacchini Hospital, Bento Gonçalves, Rio Grande do Sul, Brazil
Isabele Ribeiro Berti
Affiliation:
Tacchini Hospital, Bento Gonçalves, Rio Grande do Sul, Brazil
Rodrigo Pires dos Santos
Affiliation:
Qualis, Porto Alegre, Rio Grande do Sul, Brazil
*
Corresponding author: Stephani Amanda Lukasewicz Ferreira, RN, MSc, Qualis, 1022 Osvaldo Aranha Ave, Room 1101, Porto Alegre, RS, 90035-191, Brazil. E-mail: stephani@portalqualis.com.br
Get access Rights & Permissions [Opens in a new window]

Abstract

Background:

Surveillance of hospital-acquired infections (HAIs) is the foundation of infection control. Machine learning (ML) has been demonstrated to be a valuable tool for HAI surveillance. We compared manual surveillance with a supervised, semiautomated, ML method, and we explored the types of infection and features of importance depicted by the model.

Methods:

From July 2021 to December 2021, a semiautomated surveillance method based on the ML random forest algorithm, was implemented in a Brazilian hospital. Inpatient records were independently manually searched by the local team, and a panel of independent experts reviewed the ML semiautomated results for confirmation of HAI.

Results:

Among 6,296 patients, manual surveillance classified 183 HAI cases (2.9%), and a semiautomated method found 299 HAI cases (4.7%). The semiautomated method added 77 respiratory infections, which comprised 93.9% of the additional HAIs. The ML model considered 447 features for HAI classification. Among them, 148 features (33.1%) were related to infection signs and symptoms; 101 (22.6%) were related to patient severity status, 51 features (11.4%) were related to bacterial laboratory results; 40 features (8.9%) were related to invasive procedures; 34 (7.6%) were related to antibiotic use; and 31 features (6.9%) were related to patient comorbidities. Among these 447 features, 229 (51.2%) were similar to those proposed by NHSN as criteria for HAI classification.

Conclusion:

The ML algorithm, which included most NHSN criteria and >200 features, augmented the human capacity for HAI classification. Well-documented algorithm performances may facilitate the incorporation of AI tools in clinical or epidemiological practice and overcome the drawbacks of traditional HAI surveillance.

Type
Original Article
Information
Infection Control & Hospital Epidemiology , Volume 45 , Issue 5 , May 2024 , pp. 604 - 608
Check for updates
Copyright
© The Author(s), 2024. Published by Cambridge University Press on behalf of The Society for Healthcare Epidemiology of America

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Magill, SS, O’Leary, E, Janelle, SJ, et al. Changes in prevalence of healthcare-associated infections in US hospitals. N Engl J Med 2018;379:1732–1744.CrossRefGoogle Scholar
Weiner-Lastinger, LM, Pattabiraman, V, Konnor, RY, et al. The impact of coronavirus disease 2019 (COVID-19) on healthcare-associated infections in 2020: a summary of data reported to the National Healthcare Safety Network. Infect Control Hosp Epidemiol 2022;43:12–25.CrossRefGoogle Scholar
National Healthcare Safety Network. HAI checklists. Centers for Disease Control and Prevention website. https://www.cdc.gov/nhsn/hai-checklists/index.html. Accessed June 27, 2023.Google Scholar
Agência Nacional de Vigilância Sanitária. Critérios Diagnósticos de Infecções Relacionadas à Assistência à Saúde, 2017.Google Scholar
Mitchell, BG, Hall, L, Halton, K, MacBeth, D, Gardner, A. Time spent by infection control professionals undertaking healthcare-associated infection surveillance: a multicentered cross-sectional study. Infect Dis Health 2016;21:36e40.Google Scholar
Shenoy, ES, Branch-Elliman, W. Automating surveillance for healthcare-associated infections: rationale and current realities (part I/III). Antimicrob Steward Healthc Epidemiol 2023;3:e25.CrossRefGoogle ScholarPubMed
Russo, PL, Shaban, RZ, Macbeth, D, Carter, A, Mitchell, BG. Impact of electronic healthcare-associated infection surveillance software on infection prevention resources: a systematic review of the literature. J Hosp Infect 2018;99:1–7.CrossRefGoogle ScholarPubMed
Scardoni, A, Balzarini, F, Signorelli, C, Cabitza, F, Odone, A. Artificial intelligence-based tools to control healthcare associated infections: a systematic review of the literature. J Infect Public Health 2020;13:1061–1077.CrossRefGoogle ScholarPubMed
Ferreira, SAL, Meneses, ACF, Vaz, TA, et al. An effective infection surveillance assistant robot impacts care delivery by reducing burden on infection control professional staff. N Engl J Catalyst 2022;3(8):1–17.Google Scholar
Dos Santos, RP, Silva, D, Menezes, A, et al. Automated healthcare-associated infection surveillance using an artificial intelligence algorithm. Infect Prev Pract 2021;3:100167.CrossRefGoogle ScholarPubMed
Deo, RC. Machine learning in medicine. Circulation 2015;132:1920–1930.CrossRefGoogle ScholarPubMed
Fernández-Delgado, M, Cernadas, E, Barro, S, Amorim, D, Fernández-Delgado, A. Do we need hundreds of classifiers to solve real-world classification problems? J Mach Learn Res 2014;15:3133–3181.Google Scholar
Magill, SS, Hellinger, W, Cohen, J, et al. Prevalence of healthcare-associated infections in acute-care hospitals in Jacksonville, Florida. Infect Control Hosp Epidemiol 2012;33:283–291.CrossRefGoogle ScholarPubMed
Glenister, HM, Taylor, LJ, Bartlett, CL, Cooke, EM, Sedgwick, JA, Mackintosh, CA. An evaluation of surveillance methods for detecting infections in hospital inpatients. J Hosp Infect 1993;23:229–242.CrossRefGoogle ScholarPubMed
Wundavalli, L, Agrawal, US, Satpathy, S, Debnath, BR, Agnes, TA. How much is adequate staffing for infection control? A deterministic approach through the lens of workload indicators of staffing need. Am J Infect Control 2020;48:609–614.CrossRefGoogle ScholarPubMed
Bartles, R, Dickson, A, Babade, O. A systematic approach to quantifying infection prevention staffing and coverage needs. J Infect Control 2018;46:487–491.CrossRefGoogle ScholarPubMed
Ehrentraut, C, Ekholm, M, Tanushi, H, Tiedemann, J, Dalianis, H. Detecting hospital-acquired infections: a document classification approach using support vector machines and gradient tree boosting. Health Informatics J 2018;24:24–42.CrossRefGoogle ScholarPubMed
Cohen, G, Hilario, M, Sax, H, Hugonnet, S, Pellegrini, C, Geissbuhler, A. An application of one-class support vector machine to nosocomial infection detection. Stud Health Technol Inform 2004;107:716–720.Google ScholarPubMed
Cohen, G, Sax, H, Geissbuhler, A. Novelty detection using one-class Parzen density estimator. An application to surveillance of nosocomial infections. Stud Health Technol Inform 2008;136:21–26.Google ScholarPubMed
Cohen, G, Hilario, M, Sax, H, Hugonnet, S, Geissbuhler, A. Learning from imbalanced data in surveillance of nosocomial infection. Artif Intell Med 2006;37:7–18.CrossRefGoogle ScholarPubMed