1
|
van der Meijden SL, van Boekel AM, van Goor H, Nelissen RG, Schoones JW, Steyerberg EW, Geerts BF, de Boer MG, Arbous MS. Automated Identification of Postoperative Infections to Allow Prediction and Surveillance Based on Electronic Health Record Data: Scoping Review. JMIR Med Inform 2024; 12:e57195. [PMID: 39255011 PMCID: PMC11422734 DOI: 10.2196/57195] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2024] [Revised: 07/12/2024] [Accepted: 07/16/2024] [Indexed: 09/11/2024] Open
Abstract
BACKGROUND Postoperative infections remain a crucial challenge in health care, resulting in high morbidity, mortality, and costs. Accurate identification and labeling of patients with postoperative bacterial infections is crucial for developing prediction models, validating biomarkers, and implementing surveillance systems in clinical practice. OBJECTIVE This scoping review aimed to explore methods for identifying patients with postoperative infections using electronic health record (EHR) data to go beyond the reference standard of manual chart review. METHODS We performed a systematic search strategy across PubMed, Embase, Web of Science (Core Collection), the Cochrane Library, and Emcare (Ovid), targeting studies addressing the prediction and fully automated surveillance (ie, without manual check) of diverse bacterial infections in the postoperative setting. For prediction modeling studies, we assessed the labeling methods used, categorizing them as either manual or automated. We evaluated the different types of EHR data needed for the surveillance and labeling of postoperative infections, as well as the performance of fully automated surveillance systems compared with manual chart review. RESULTS We identified 75 different methods and definitions used to identify patients with postoperative infections in studies published between 2003 and 2023. Manual labeling was the predominant method in prediction modeling research, 65% (49/75) of the identified methods use structured data, and 45% (34/75) use free text and clinical notes as one of their data sources. Fully automated surveillance systems should be used with caution because the reported positive predictive values are between 0.31 and 0.76. CONCLUSIONS There is currently no evidence to support fully automated labeling and identification of patients with infections based solely on structured EHR data. Future research should focus on defining uniform definitions, as well as prioritizing the development of more scalable, automated methods for infection detection using structured EHR data.
Collapse
Affiliation(s)
- Siri Lise van der Meijden
- Intensive Care Unit, Leiden University Medical Center, Leiden, Netherlands
- Healthplus.ai BV, Amsterdam, Netherlands
| | - Anna M van Boekel
- Intensive Care Unit, Leiden University Medical Center, Leiden, Netherlands
| | - Harry van Goor
- General Surgery Department, Radboud University Medical Center, Nijmegen, Netherlands
| | - Rob Ghh Nelissen
- Department of Orthopedics, Leiden University Medical Center, Leiden, Netherlands
| | - Jan W Schoones
- Directorate of Research Policy, Leiden University Medical Center, Leiden, Netherlands
| | - Ewout W Steyerberg
- Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, Netherlands
| | | | - Mark Gj de Boer
- Department of Infectious Diseases, Leiden University Medical Center, Leiden, Netherlands
| | - M Sesmu Arbous
- Intensive Care Unit, Leiden University Medical Center, Leiden, Netherlands
| |
Collapse
|
2
|
Colborn KL, Zhuang Y, Dyas AR, Henderson WG, Madsen HJ, Bronsert MR, Matheny ME, Lambert-Kerzner A, Myers QWO, Meguid RA. Development and validation of models for detection of postoperative infections using structured electronic health records data and machine learning. Surgery 2023; 173:464-471. [PMID: 36470694 PMCID: PMC10204069 DOI: 10.1016/j.surg.2022.10.026] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/05/2022] [Revised: 10/18/2022] [Accepted: 10/26/2022] [Indexed: 12/04/2022]
Abstract
BACKGROUND Postoperative infections constitute more than half of all postoperative complications. Surveillance of these complications is primarily done through manual chart review, which is time consuming, expensive, and typically only covers 10% to 15% of all operations. Automated surveillance would permit the timely evaluation of and reporting of all operations. METHODS The goal of this study was to develop and validate parsimonious, interpretable models for conducting surveillance of postoperative infections using structured electronic health records data. This was a retrospective study using 30,639 unique operations from 5 major hospitals between 2013 and 2019. Structured electronic health records data were linked to postoperative outcomes data from the American College of Surgeons National Surgical Quality Improvement Program. Predictors from the electronic health records included diagnoses, procedures, and medications. Infectious complications included surgical site infection, urinary tract infection, sepsis, and pneumonia within 30 days of surgery. The knockoff filter, a penalized regression technique that controls type I error, was applied for variable selection. Models were validated in a chronological held-out dataset. RESULTS Seven percent of patients experienced at least one type of postoperative infection. Models selected contained between 4 and 8 variables and achieved >0.91 area under the receiver operating characteristic curve, >81% specificity, >87% sensitivity, >99% negative predictive value, and 10% to 15% positive predictive value in a held-out test dataset. CONCLUSION Surveillance and reporting of postoperative infection rates can be implemented for all operations with high accuracy using electronic health records data and simple linear regression models.
Collapse
Affiliation(s)
- Kathryn L Colborn
- Department of Surgery, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO; Department of Biostatistics and Informatics, Colorado School of Public Health, Aurora, CO; Adult and Child Consortium for Health Outcomes Research and Delivery Science, University of Colorado Anschutz Medical Campus, Aurora, CO.
| | - Yaxu Zhuang
- Department of Biostatistics and Informatics, Colorado School of Public Health, Aurora, CO
| | - Adam R Dyas
- Department of Surgery, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO
| | - William G Henderson
- Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO; Department of Biostatistics and Informatics, Colorado School of Public Health, Aurora, CO
| | - Helen J Madsen
- Department of Surgery, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO
| | - Michael R Bronsert
- Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO; Adult and Child Consortium for Health Outcomes Research and Delivery Science, University of Colorado Anschutz Medical Campus, Aurora, CO
| | - Michael E Matheny
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN; Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN; Division of General Internal Medicine, Vanderbilt University Medical Center, Nashville, TN
| | - Anne Lambert-Kerzner
- Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO
| | - Quintin W O Myers
- Department of Surgery, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO
| | - Robert A Meguid
- Department of Surgery, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado Anschutz Medical Campus, Aurora, CO; Adult and Child Consortium for Health Outcomes Research and Delivery Science, University of Colorado Anschutz Medical Campus, Aurora, CO
| |
Collapse
|
3
|
Shen Y, Cui H. Diagnostic accuracy of electronic surveillance tool for catheter-associated urinary tract infections in tertiary care hospitals: A meta-analysis. Medicine (Baltimore) 2021; 100:e27363. [PMID: 34596149 PMCID: PMC8483878 DOI: 10.1097/md.0000000000027363] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/03/2021] [Accepted: 09/09/2021] [Indexed: 01/05/2023] Open
Abstract
BACKGROUND Automated systems have been developed to reduce labor-intensive manual recordings during nosocomial infection surveillance. The diagnostic accuracies of these systems have differed in various settings. METHODS We designed this meta-analysis to evaluate the diagnostic accuracy of an electronic surveillance tool for catheter-associated urinary tract infections (CAUTIs) in tertiary care hospitals. We systematically searched databases such as Medline, Scopus, Cochrane library and Embase (from inception until November 2019) for relevant studies. We assessed the quality of trials using the diagnostic accuracy studies-2 tool, and performed a meta-analysis to obtain a pooled sensitivity and specificity for electronic surveillance. We included 6 studies with 16,492 patients in the analysis. RESULTS We found a pooled sensitivity of electronic diagnostic surveillance for CAUTIs of 97.5% (95% confidence interval [CI], 67.6-99.9%) and a pooled specificity of 92.6% (95% CI, 55.2-99.2%). The diagnostic odds ratio was 494 (95% CI, 89-2747). The positive likelihood ratio was 13.1 (95% CI, 1.63-105.8) and the negative likelihood ratio 0.02 (95% CI, 0.001-0.40). A bivariate box plot indicated the possibility of heterogeneity between the included studies. CONCLUSION Our review suggests that electronic surveillance is useful for diagnosing CAUTIs among hospitalized patients in tertiary care hospitals due to its high sensitivity and specificity.
Collapse
|
4
|
Streefkerk HRA, Verkooijen RP, Bramer WM, Verbrugh HA. Electronically assisted surveillance systems of healthcare-associated infections: a systematic review. ACTA ACUST UNITED AC 2020; 25. [PMID: 31964462 PMCID: PMC6976884 DOI: 10.2807/1560-7917.es.2020.25.2.1900321] [Citation(s) in RCA: 22] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/26/2023]
Abstract
Background Surveillance of healthcare-associated infections (HAI) is the basis of each infection control programme and, in case of acute care hospitals, should ideally include all hospital wards, medical specialties as well as all types of HAI. Traditional surveillance is labour intensive and electronically assisted surveillance systems (EASS) hold the promise to increase efficiency. Objectives To give insight in the performance characteristics of different approaches to EASS and the quality of the studies designed to evaluate them. Methods In this systematic review, online databases were searched and studies that compared an EASS with a traditional surveillance method were included. Two different indicators were extracted from each study, one regarding the quality of design (including reporting efficiency) and one based on the performance (e.g. specificity and sensitivity) of the EASS presented. Results A total of 78 studies were included. The majority of EASS (n = 72) consisted of an algorithm-based selection step followed by confirmatory assessment. The algorithms used different sets of variables. Only a minority (n = 7) of EASS were hospital-wide and designed to detect all types of HAI. Sensitivity of EASS was generally high (> 0.8), but specificity varied (0.37–1). Less than 20% (n = 14) of the studies presented data on the efficiency gains achieved. Conclusions Electronically assisted surveillance of HAI has yet to reach a mature stage and to be used routinely in healthcare settings. We recommend that future studies on the development and implementation of EASS of HAI focus on thorough validation, reproducibility, standardised datasets and detailed information on efficiency.
Collapse
Affiliation(s)
- H Roel A Streefkerk
- Albert Schweitzer Hospital/Rivas group Beatrix hospital/Regionaal Laboratorium medische Microbiologie, Dordrecht/Gorinchem, the Netherlands.,Erasmus University Medical Center (Erasmus MC), Rotterdam, the Netherlands
| | - Roel Paj Verkooijen
- Department of Medical Microbiology, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - Wichor M Bramer
- Medical Library, Erasmus MC University Medical Center Rotterdam, Rotterdam, the Netherlands
| | - Henri A Verbrugh
- Erasmus University Medical Center (Erasmus MC), Rotterdam, the Netherlands
| |
Collapse
|
5
|
Bronsert M, Singh AB, Henderson WG, Hammermeister K, Meguid RA, Colborn KL. Identification of postoperative complications using electronic health record data and machine learning. Am J Surg 2020; 220:114-119. [PMID: 31635792 PMCID: PMC7183252 DOI: 10.1016/j.amjsurg.2019.10.009] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2019] [Revised: 09/13/2019] [Accepted: 10/01/2019] [Indexed: 12/23/2022]
Abstract
BACKGROUND Using the American College of Surgeons National Surgical Quality Improvement Program (NSQIP) complication status of patients who underwent an operation at the University of Colorado Hospital, we developed a machine learning algorithm for identifying patients with one or more complications using data from the electronic health record (EHR). METHODS We used an elastic-net model to estimate regression coefficients and carry out variable selection. International classification of disease codes (ICD-9), common procedural terminology (CPT) codes, medications, and CPT-specific complication event rate were included as predictors. RESULTS Of 6840 patients, 922 (13.5%) had at least one of the 18 complications tracked by NSQIP. The model achieved 88% specificity, 83% sensitivity, 97% negative predictive value, 52% positive predictive value, and an area under the curve of 0.93. CONCLUSIONS Using machine learning on EHR postoperative data linked to NSQIP outcomes data, a model with 163 predictors from the EHR identified complications well at our institution.
Collapse
Affiliation(s)
- Michael Bronsert
- University of Colorado Anschutz Medical Campus, Adult and Child Consortium for Health Outcomes Research and Delivery Science, Aurora, CO, USA; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado School of Medicine, Aurora, CO, USA.
| | - Abhinav B Singh
- Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado School of Medicine, Aurora, CO, USA.
| | - William G Henderson
- University of Colorado Anschutz Medical Campus, Adult and Child Consortium for Health Outcomes Research and Delivery Science, Aurora, CO, USA; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado School of Medicine, Aurora, CO, USA; University of Colorado Anschutz Medical Campus, Colorado School of Public Health, Department of Biostatistics and Informatics, Aurora, CO, USA.
| | - Karl Hammermeister
- University of Colorado Anschutz Medical Campus, Adult and Child Consortium for Health Outcomes Research and Delivery Science, Aurora, CO, USA; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado School of Medicine, Aurora, CO, USA; University of Colorado Anschutz Medical Campus, School of Medicine, Department of Cardiology, Aurora, CO, USA.
| | - Robert A Meguid
- University of Colorado Anschutz Medical Campus, Adult and Child Consortium for Health Outcomes Research and Delivery Science, Aurora, CO, USA; Surgical Outcomes and Applied Research Program, Department of Surgery, University of Colorado School of Medicine, Aurora, CO, USA.
| | - Kathryn L Colborn
- University of Colorado Anschutz Medical Campus, Colorado School of Public Health, Department of Biostatistics and Informatics, Aurora, CO, USA.
| |
Collapse
|
6
|
Colborn KL, Bronsert M, Hammermeister K, Henderson WG, Singh AB, Meguid RA. Identification of urinary tract infections using electronic health record data. Am J Infect Control 2019; 47:371-375. [PMID: 30522837 DOI: 10.1016/j.ajic.2018.10.009] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2018] [Revised: 10/13/2018] [Accepted: 10/14/2018] [Indexed: 12/23/2022]
Abstract
BACKGROUND Population ascertainment of postoperative urinary tract infections (UTIs) is time-consuming and expensive, as it often requires manual chart review. Using the American College of Surgeons National Surgical Quality Improvement Program UTI status of patients who underwent an operation at the University of Colorado Hospital, we sought to develop an algorithm for identifying UTIs using data from the electronic health record. METHODS Data were split into training (operations occurring between 2013-2015) and test (operations in 2016) sets. A binomial generalized linear model with an elastic-net penalty was used to fit the model and carry out variables selection. International classification of disease codes, common procedural terminology codes, antibiotics, catheterization, and common procedural terminology-specific UTI event rates were included as predictors. The Youden's J statistic was used to determine the optimal classification threshold. RESULTS Of 6,840 patients, 134 (2.0%) had a UTI. The model achieved 92% specificity, 80% sensitivity, 100% negative predictive value, 16% positive predictive value, and an area under the curve of 0.94 using a decision threshold of 0.03. CONCLUSIONS A model with 14 predictors from the electronic health record identifies UTIs well, and it could be used to scale up UTI surveillance or to estimate the impact of large-scale interventions on UTI rates.
Collapse
Affiliation(s)
- Kathryn L Colborn
- Department of Biostatistics and Informatics, Colorado School of Public Health, University of Colorado Anschutz Medical Campus, Aurora, CO.
| | - Michael Bronsert
- Adult and Child Consortium for Health Outcomes Research and Delivery Science, University of Colorado Anschutz Medical Campus, Aurora, CO; Department of Surgery, Surgical Outcomes and Applied Research Program, School of Medicine, University of Colorado Anschutz Medical Campus, University of Colorado, Aurora, CO
| | - Karl Hammermeister
- Adult and Child Consortium for Health Outcomes Research and Delivery Science, University of Colorado Anschutz Medical Campus, Aurora, CO; Department of Surgery, Surgical Outcomes and Applied Research Program, School of Medicine, University of Colorado Anschutz Medical Campus, University of Colorado, Aurora, CO; Department of Cardiology, School of Medicine, University of Colorado Anschutz Medical Campus, Aurora, CO
| | - William G Henderson
- Department of Biostatistics and Informatics, Colorado School of Public Health, University of Colorado Anschutz Medical Campus, Aurora, CO; Adult and Child Consortium for Health Outcomes Research and Delivery Science, University of Colorado Anschutz Medical Campus, Aurora, CO; Department of Surgery, Surgical Outcomes and Applied Research Program, School of Medicine, University of Colorado Anschutz Medical Campus, University of Colorado, Aurora, CO
| | - Abhinav B Singh
- Department of Surgery, Surgical Outcomes and Applied Research Program, School of Medicine, University of Colorado Anschutz Medical Campus, University of Colorado, Aurora, CO
| | - Robert A Meguid
- Adult and Child Consortium for Health Outcomes Research and Delivery Science, University of Colorado Anschutz Medical Campus, Aurora, CO; Department of Surgery, Surgical Outcomes and Applied Research Program, School of Medicine, University of Colorado Anschutz Medical Campus, University of Colorado, Aurora, CO
| |
Collapse
|
7
|
Sanger PC, Granich M, Olsen-Scribner R, Jain R, Lober WB, Stapleton A, Pottinger PS. Electronic Surveillance For Catheter-Associated Urinary Tract Infection Using Natural Language Processing. AMIA ... ANNUAL SYMPOSIUM PROCEEDINGS. AMIA SYMPOSIUM 2018; 2017:1507-1516. [PMID: 29854220 PMCID: PMC5977673] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
Catheter-associated urinary tract infection (CAUTI) is a common and costly healthcare-associated infection, yet measuring it accurately is challenging and resource-intensive. Electronic surveillance promises to make this task more objective and efficient in an era of new financial and regulatory imperatives, but previous surveillance approaches have used a simplified version of the definition. We applied a complete definition, including subjective elements identified through natural language processing of clinical notes. Through examination of documentation practices, we defined a set of rules that identified positively and negatively asserted symptoms of CAUTI. Our algorithm was developed on a training set of 1421 catheterizedpatients and prospectively validated on 1567 catheterizedpatients. Compared to gold standard chart review, our tool had a sensitivity of 97.1%, specificity of 94.5% PPV of 66.7% and NPV of 99.6% for identifying CAUTI. We discuss sources of error and suggestions for more computable future definitions.
Collapse
|
8
|
Zachariah P, Whittier S, Reed C, LaRussa P, Larson EL, Vargas CY, Saiman L, Stockwell MS. Community -and hospital laboratory-based surveillance for respiratory viruses. Influenza Other Respir Viruses 2016; 10:361-6. [PMID: 26987664 PMCID: PMC4947942 DOI: 10.1111/irv.12387] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/29/2016] [Indexed: 11/25/2022] Open
Abstract
Traditional surveillance for respiratory viruses relies on symptom detection and laboratory detection during medically attended encounters for acute respiratory infection/influenza-like illness (ARI/ILI). Ecological momentary reporting using text messages is a novel method for surveillance. This study compares respiratory viral activity detected through longitudinal community-based surveillance using text message responses for sample acquisition and testing to respiratory viral activity obtained from hospital laboratory data from the same community. We demonstrate a significant correlation between community- and hospital laboratory-based surveillance for most respiratory viruses, although the relative proportions of viruses detected in the community and hospital differed significantly.
Collapse
Affiliation(s)
| | - Susan Whittier
- Columbia University Medical Center, New York, NY, USA.,New York-Presbyterian Hospital, New York, NY, USA
| | - Carrie Reed
- Centers for Disease Control and Prevention, Atlanta, GA, USA
| | | | | | | | - Lisa Saiman
- Columbia University Medical Center, New York, NY, USA.,New York-Presbyterian Hospital, New York, NY, USA
| | - Melissa S Stockwell
- Columbia University Medical Center, New York, NY, USA.,New York-Presbyterian Hospital, New York, NY, USA
| |
Collapse
|
9
|
Data elements and validation methods used for electronic surveillance of health care-associated infections: a systematic review. Am J Infect Control 2015; 43:600-5. [PMID: 26042848 DOI: 10.1016/j.ajic.2015.02.006] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2015] [Accepted: 02/04/2015] [Indexed: 11/22/2022]
Abstract
BACKGROUND We describe the primary data sources, data elements, and validation methods currently used in electronic surveillance systems (ESS) for identification and surveillance of health care-associated infections (HAIs), and compares these data elements and validation methods with recommended standards. METHODS Using Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, a PubMed and manual search was conducted to identify research articles describing ESS for identification and surveillance of HAIs published January 1, 2009-August 31, 2014. Selected articles were evaluated to determine what data elements and validation methods were included. RESULTS Among the 509 articles identified in the original literature search, 30 met the inclusion criteria. Whereas the majority of studies (83%) used recommended data sources and validated the numerator (80%), only 10% of studies performed external and internal validation. In addition, there was variation in the ESS data formats used. CONCLUSIONS Our findings suggest that the majority of ESS for HAI surveillance use standard definitions, but the lack of widespread internal data, denominator, and external validation in these systems reduces the reliability of their findings. Additionally, advanced programming skills are required to create, implement, and maintain these systems and to reduce the variability in data formats.
Collapse
|