BACKGROUND: Traditional methods of outbreak investigations utilize reactive whole genome sequencing (WGS) to confirm or refute the outbreak. We have implemented WGS surveillance and a machine learning (ML) algorithm for the electronic health record (EHR) to retrospectively detect previously unidentified outbreaks and to determine the responsible transmission routes. METHODS: We performed WGS surveillance to identify and characterize clusters of genetically-related Pseudomonas aeruginosa infections during a 24-month period. ML of the EHR was used to identify potential transmission routes. A manual review of the EHR was performed by an infection preventionist to determine the most likely route and results were compared to the ML algorithm. RESULTS: We identified a cluster of 6 genetically related P. aeruginosa cases that occurred during a 7-month period. The ML algorithm identified gastroscopy as a potential transmission route for 4 of the 6 patients. Manual EHR review confirmed gastroscopy as the most likely route for 5 patients. This transmission route was confirmed by identification of a genetically-related P. aeruginosa incidentally cultured from a gastroscope used on 4of the 5 patients. Three infections, 2 of which were blood stream infections, could have been prevented if the ML algorithm had been running in real-time. CONCLUSIONS: WGS surveillance combined with a ML algorithm of the EHR identified a previously undetected outbreak of gastroscope-associated P. aeruginosa infections. These results underscore the value of WGS surveillance and ML of the EHR for enhancing outbreak detection in hospitals and preventing serious infections.
BACKGROUND: Traditional methods of outbreak investigations utilize reactive whole genome sequencing (WGS) to confirm or refute the outbreak. We have implemented WGS surveillance and a machine learning (ML) algorithm for the electronic health record (EHR) to retrospectively detect previously unidentified outbreaks and to determine the responsible transmission routes. METHODS: We performed WGS surveillance to identify and characterize clusters of genetically-related Pseudomonas aeruginosa infections during a 24-month period. ML of the EHR was used to identify potential transmission routes. A manual review of the EHR was performed by an infection preventionist to determine the most likely route and results were compared to the ML algorithm. RESULTS: We identified a cluster of 6 genetically related P. aeruginosa cases that occurred during a 7-month period. The ML algorithm identified gastroscopy as a potential transmission route for 4 of the 6 patients. Manual EHR review confirmed gastroscopy as the most likely route for 5 patients. This transmission route was confirmed by identification of a genetically-related P. aeruginosa incidentally cultured from a gastroscope used on 4of the 5 patients. Three infections, 2 of which were blood stream infections, could have been prevented if the ML algorithm had been running in real-time. CONCLUSIONS: WGS surveillance combined with a ML algorithm of the EHR identified a previously undetected outbreak of gastroscope-associated P. aeruginosa infections. These results underscore the value of WGS surveillance and ML of the EHR for enhancing outbreak detection in hospitals and preventing serious infections.
Authors: Anton Bankevich; Sergey Nurk; Dmitry Antipov; Alexey A Gurevich; Mikhail Dvorkin; Alexander S Kulikov; Valery M Lesin; Sergey I Nikolenko; Son Pham; Andrey D Prjibelski; Alexey V Pyshkin; Alexander V Sirotkin; Nikolay Vyahhi; Glenn Tesler; Max A Alekseyev; Pavel A Pevzner Journal: J Comput Biol Date: 2012-04-16 Impact factor: 1.479
Authors: O Bajolet; D Ciocan; C Vallet; C de Champs; V Vernet-Garnier; T Guillard; L Brasme; G Thiefin; G Cadiot; F Bureau-Chalot Journal: J Hosp Infect Date: 2013-01-20 Impact factor: 3.926
Authors: Alexander J Sundermann; Ahmed Babiker; Jane W Marsh; Kathleen A Shutt; Mustapha M Mustapha; Anthony W Pasculle; Chinelo Ezeonwuka; Melissa I Saul; Marissa P Pacey; Daria Van Tyne; Ashley M Ayres; Vaughn S Cooper; Graham M Snyder; Lee H Harrison Journal: Clin Infect Dis Date: 2020-05-23 Impact factor: 9.079
Authors: Alison L Galdys; Jane W Marsh; Edgar Delgado; A William Pasculle; Marissa Pacey; Ashley M Ayres; Amy Metzger; Lee H Harrison; Carlene A Muto Journal: Infect Control Hosp Epidemiol Date: 2018-11-19 Impact factor: 3.254
Authors: Elizabeth Robilotti; Weihua Huang; N Esther Babady; Donald Chen; Mini Kamboj Journal: Infect Control Hosp Epidemiol Date: 2020-02 Impact factor: 3.254
Authors: Shelley S Magill; Jonathan R Edwards; Wendy Bamberg; Zintars G Beldavs; Ghinwa Dumyati; Marion A Kainer; Ruth Lynfield; Meghan Maloney; Laura McAllister-Hollod; Joelle Nadle; Susan M Ray; Deborah L Thompson; Lucy E Wilson; Scott K Fridkin Journal: N Engl J Med Date: 2014-03-27 Impact factor: 91.245
Authors: Mustapha M Mustapha; Jane W Marsh; Chinelo D Ezeonwuka; Anthony W Pasculle; Marissa P Pacey; Ashley M Querry; Carlene A Muto; Lee H Harrison Journal: Genome Announc Date: 2016-09-29
Authors: Mustapha M Mustapha; Vatsala R Srinivasa; Marissa P Griffith; Shu-Ting Cho; Daniel R Evans; Kady Waggle; Chinelo Ezeonwuka; Daniel J Snyder; Jane W Marsh; Lee H Harrison; Vaughn S Cooper; Daria Van Tyne Journal: mSystems Date: 2022-06-13 Impact factor: 7.324
Authors: Alexander J Sundermann; Jieshi Chen; Praveen Kumar; Ashley M Ayres; Shu Ting Cho; Chinelo Ezeonwuka; Marissa P Griffith; James K Miller; Mustapha M Mustapha; A William Pasculle; Melissa I Saul; Kathleen A Shutt; Vatsala Srinivasa; Kady Waggle; Daniel J Snyder; Vaughn S Cooper; Daria Van Tyne; Graham M Snyder; Jane W Marsh; Artur Dubrawski; Mark S Roberts; Lee H Harrison Journal: Clin Infect Dis Date: 2022-08-31 Impact factor: 20.999
Authors: Hemant Goyal; Sara Larsen; Abhilash Perisetti; Nikolaj Birk Larsen; Lotte Klinten Ockert; Sven Adamsen; Benjamin Tharian; Nirav Thosani Journal: Endosc Int Open Date: 2022-06-10