BACKGROUND Predicting recurrent Clostridium difficile infection (rCDI) remains difficult. METHODS: We employed a retrospective cohort design. Granular electronic medical record (EMR) data had been collected from patients hospitalized at 21 Kaiser Permanente Northern California hospitals. The derivation dataset (2007-2013) included data from 9,386 patients who experienced incident CDI (iCDI) and 1,311 who experienced their first CDI recurrences (rCDI). The validation dataset (2014) included data from 1,865 patients who experienced incident CDI and 144 who experienced rCDI. Using multiple techniques, including machine learning, we evaluated more than 150 potential predictors. Our final analyses evaluated 3 models with varying degrees of complexity and 1 previously published model. RESULTS Despite having a large multicenter cohort and access to granular EMR data (eg, vital signs, and laboratory test results), none of the models discriminated well (c statistics, 0.591-0.605), had good calibration, or had good explanatory power. CONCLUSIONS Our ability to predict rCDI remains limited. Given currently available EMR technology, improvements in prediction will require incorporating new variables because currently available data elements lack adequate explanatory power. Infect Control Hosp Epidemiol 2017;38:1196-1203.
BACKGROUND Predicting recurrent Clostridium difficileinfection (rCDI) remains difficult. METHODS: We employed a retrospective cohort design. Granular electronic medical record (EMR) data had been collected from patients hospitalized at 21 Kaiser Permanente Northern California hospitals. The derivation dataset (2007-2013) included data from 9,386 patients who experienced incident CDI (iCDI) and 1,311 who experienced their first CDI recurrences (rCDI). The validation dataset (2014) included data from 1,865 patients who experienced incident CDI and 144 who experienced rCDI. Using multiple techniques, including machine learning, we evaluated more than 150 potential predictors. Our final analyses evaluated 3 models with varying degrees of complexity and 1 previously published model. RESULTS Despite having a large multicenter cohort and access to granular EMR data (eg, vital signs, and laboratory test results), none of the models discriminated well (c statistics, 0.591-0.605), had good calibration, or had good explanatory power. CONCLUSIONS Our ability to predict rCDI remains limited. Given currently available EMR technology, improvements in prediction will require incorporating new variables because currently available data elements lack adequate explanatory power. Infect Control Hosp Epidemiol 2017;38:1196-1203.
Authors: Mary Y Hu; Kianoosh Katchar; Lorraine Kyne; Seema Maroo; Sanjeev Tummala; Valley Dreisbach; Hua Xu; Daniel A Leffler; Ciarán P Kelly Journal: Gastroenterology Date: 2008-12-13 Impact factor: 22.682
Authors: Erik R Dubberke; Kimberly A Reske; Yan Yan; Margaret A Olsen; L Clifford McDonald; Victoria J Fraser Journal: Clin Infect Dis Date: 2007-12-15 Impact factor: 9.079
Authors: David W Eyre; A Sarah Walker; David Wyllie; Kate E Dingle; David Griffiths; John Finney; Lily O'Connor; Alison Vaughan; Derrick W Crook; Mark H Wilcox; Timothy E A Peto Journal: Clin Infect Dis Date: 2012-08 Impact factor: 9.079
Authors: Kerrie Davies; Jody Lawrence; Claire Berry; Georgina Davis; Holly Yu; Bing Cai; Elisa Gonzalez; Ida Prantner; Andrea Kurcz; Ioana Macovei; Hanna Pituch; Elena Nováková; Otakar Nyč; Barbara Gärtner; Fabian K Berger; Monica Oleastro; Oliver A Cornely; Maria J G T Vehreschild; Louise Pedneault; Mark Wilcox Journal: Front Public Health Date: 2020-07-17
Authors: E Bouza; J M Aguado; L Alcalá; B Almirante; P Alonso-Fernández; M Borges; J Cobo; J Guardiola; J P Horcajada; E Maseda; J Mensa; N Merchante; P Muñoz; J L Pérez Sáenz; M Pujol; E Reigadas; M Salavert; J Barberán Journal: Rev Esp Quimioter Date: 2020-02-20 Impact factor: 1.553