Infection Control & Hospital Epidemiology (2019), 40,314–319 doi:10.1017/ice.2018.343
Original Article
Automated data mining of the electronic health record for investigation of healthcare-associated outbreaks
Alexander J. SundermannMPH,CIC1,2, JamesK. MillerPhD3, Jane
W.MarshPhD1,Melissa I. SaulMS4,Kathleen A. ShuttMS1, Marissa Pacey1, Mustapha M. Mustapha MBBS, PhD1,Ashley Ayres BS,CIC2, A. William Pasculle ScD5,Jieshi ChenMS3,
Graham M. Snyder MD, SM2,Artur W.DubrawskiPhD3 and Lee H. Harrison MD1 1The Microbial Genomic Epidemiology Laboratory, Infectious Diseases Epidemiology Research Unit, University of Pittsburgh School of Medicine and Graduate School of Public Health, Pittsburgh, Pennsylvania, 2Department of Infection Prevention and Control, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania, 3Anton Laboratory, Carnegie Mellon University, Pittsburgh, Pennsylvania, 4Department of Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania and 5Department of Pathology, University of Pittsburgh, Pittsburgh, Pennsylvania
Abstract
Background: Identifying routes of transmission among hospitalized patients during a healthcare-associated outbreak can be tedious, particu- larly among patients with complex hospital stays and multiple exposures. Data mining of the electronic health record (EHR) has the potential to rapidly identify common exposures among patients suspected of being part of an outbreak.
Methods: We retrospectively analyzed 9 hospital outbreaks that occurred during 2011–2016 and that had previously been characterized both according to transmission route and by molecular characterization of the bacterial
isolates.Wedetermined (1) the ability of data mining of the EHR to identify the correct route of transmission, (2) how early the correct route was identified during the timeline of the outbreak, and (3) how many cases in the outbreaks could have been prevented had the system been running in real time.
Results: Correct routes were identified for all outbreaks at the second patient, except for one outbreak involving>1 transmission route that was detected at the eighth patient.Upto 40 or 34 infections (78% or 66% of possible preventable infections, respectively) could have been prevented if data mining had been implemented in real time, assuming the initiation of an effective intervention within 7 or 14 days of identification of the transmission route, respectively.
Conclusions: Data mining of the EHR was accurate for identifying routes of transmission among patients who were part of the outbreak. Prospective validation of this approach using routine whole-genome sequencing and data mining of the EHR for both outbreak detection and route attribution is ongoing.
(Received 16 September 2018; accepted 3 December 2018)
Healthcare-associated outbreaks caused by serious bacterial pathogens cause substantial morbidity and mortality and add to healthcare costs.1,2 Detection of outbreaks can be difficult in large hospitals where bacterial transmission may go unnoticed for prolonged periods.3 Investigation and control of a hospital outbreak requires the identification of the route of transmission among patients suspected of being part of the outbreak so that intervention measures can be implemented. This task can be labor intensive for outbreaks that involve complex patients who have long stays, multiple transfers within the hospital, and multiple procedures. Multiple transmission routes respon- sible for hospital outbreaks have included transmission from environmental contamination; colonized healthcare personnel;
Author for correspondence: Lee H. Harrison, Email:
lharriso@pitt.edu *The affiliations have been updated since original publication. An erratum notice
detailing this change was also published (DOI: 10.1017/ice.2019.84). Cite this article: Sundermann AJ, et al. (2019). Automated data mining of the electronic
health record for investigation of healthcare-associated outbreaks. Infection Control & Hospital Epidemiology, 40: 314–319,
https://doi.org/10.1017/ice.2018.343
© 2019 by The Society for Healthcare Epidemiology of America. All rights reserved.
medical procedures using contaminated devices; and contami- nated medications, solutions, or other medical therapies.4,5 Widespread availability of the electronic health record (EHR)
offers the potential to use automated data mining tools to find common exposures among hospitalized patients during outbreak investigations. Many epidemiologically relevant variables are readily available in the EHR, including patient location in the hospital, procedures performed, therapies received, and contact with individual healthcare personnel. Data mining, the process of identifying patterns in large data sets, has the potential to be useful for identifying common exposures in the EHR during hospital outbreak investigations. Furthermore, whole- genome sequencing (WGS) has become increasingly available; this method discriminates pathogens at the genetic level.6–8 Genomic data from patient bacterial isolates have the potential to aid in the data mining and outbreak investigation process.9 We are developing a surveillance system called Enhanced Detection System for Healthcare-Associated Transmission (EDS-HAT); it will combine prospective WGS surveillance of clinical isolates of key hospital-associated bacterial pathogens
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124 |
Page 125 |
Page 126 |
Page 127 |
Page 128 |
Page 129 |
Page 130 |
Page 131 |
Page 132
