Timothy M Rawson1,2,3, Bernard Hernandez4, Richard C Wilson1,2,3, Damien Ming1,2,3, Pau Herrero4, Nisha Ranganathan3, Keira Skolimowska3, Mark Gilchrist1,3, Giovanni Satta3, Pantelis Georgiou4, Alison H Holmes1,2,3. 1. National Institute for Health Research Health Protection Research Unit in Healthcare Associated Infections and Antimicrobial Resistance, Imperial College London, Hammersmith Campus, Du Cane Road, London W12 0NN, UK. 2. Centre for Antimicrobial Optimisation, Hammersmith Hospital, Imperial College London, Du Cane Road, London W12 0NN, UK. 3. Imperial College Healthcare NHS Trust, Hammersmith Hospital, Du Cane Road, London W12 0HS, UK. 4. Centre for Bio-inspired Technology, Department of Electrical and Electronic Engineering, Imperial College London, South Kensington Campus, London SW7 2AZ, UK.
Abstract
BACKGROUND: Bacterial infection has been challenging to diagnose in patients with COVID-19. We developed and evaluated supervised machine learning algorithms to support the diagnosis of secondary bacterial infection in hospitalized patients during the COVID-19 pandemic. METHODS: Inpatient data at three London hospitals for the first COVD-19 wave in March and April 2020 were extracted. Demographic, blood test and microbiology data for individuals with and without SARS-CoV-2-positive PCR were obtained. A Gaussian Naive Bayes, Support Vector Machine (SVM) and Artificial Neural Network were trained and compared using the area under the receiver operating characteristic curve (AUCROC). The best performing algorithm (SVM with 21 blood test variables) was prospectively piloted in July 2020. AUCROC was calculated for the prediction of a positive microbiological sample within 48 h of admission. RESULTS: A total of 15 599 daily blood profiles for 1186 individual patients were identified to train the algorithms; 771/1186 (65%) individuals were SARS-CoV-2 PCR positive. Clinically significant microbiology results were present for 166/1186 (14%) patients during admission. An SVM algorithm trained with 21 routine blood test variables and over 8000 individual profiles had the best performance. AUCROC was 0.913, sensitivity 0.801 and specificity 0.890. Prospective testing on 54 patients on admission (28/54, 52% SARS-CoV-2 PCR positive) demonstrated an AUCROC of 0.960 (95% CI: 0.90-1.00). CONCLUSIONS: An SVM using 21 routine blood test variables had excellent performance at inferring the likelihood of positive microbiology. Further prospective evaluation of the algorithms ability to support decision making for the diagnosis of bacterial infection in COVID-19 cohorts is underway.
BACKGROUND: Bacterial infection has been challenging to diagnose in patients with COVID-19. We developed and evaluated supervised machine learning algorithms to support the diagnosis of secondary bacterial infection in hospitalized patients during the COVID-19 pandemic. METHODS: Inpatient data at three London hospitals for the first COVD-19 wave in March and April 2020 were extracted. Demographic, blood test and microbiology data for individuals with and without SARS-CoV-2-positive PCR were obtained. A Gaussian Naive Bayes, Support Vector Machine (SVM) and Artificial Neural Network were trained and compared using the area under the receiver operating characteristic curve (AUCROC). The best performing algorithm (SVM with 21 blood test variables) was prospectively piloted in July 2020. AUCROC was calculated for the prediction of a positive microbiological sample within 48 h of admission. RESULTS: A total of 15 599 daily blood profiles for 1186 individual patients were identified to train the algorithms; 771/1186 (65%) individuals were SARS-CoV-2 PCR positive. Clinically significant microbiology results were present for 166/1186 (14%) patients during admission. An SVM algorithm trained with 21 routine blood test variables and over 8000 individual profiles had the best performance. AUCROC was 0.913, sensitivity 0.801 and specificity 0.890. Prospective testing on 54 patients on admission (28/54, 52% SARS-CoV-2 PCR positive) demonstrated an AUCROC of 0.960 (95% CI: 0.90-1.00). CONCLUSIONS: An SVM using 21 routine blood test variables had excellent performance at inferring the likelihood of positive microbiology. Further prospective evaluation of the algorithms ability to support decision making for the diagnosis of bacterial infection in COVID-19 cohorts is underway.
Authors: Timothy M Rawson; Luke S P Moore; Nina Zhu; Nishanthy Ranganathan; Keira Skolimowska; Mark Gilchrist; Giovanni Satta; Graham Cooke; Alison Holmes Journal: Clin Infect Dis Date: 2020-12-03 Impact factor: 9.079
Authors: T M Rawson; B Hernandez; L S P Moore; O Blandy; P Herrero; M Gilchrist; A Gordon; C Toumazou; S Sriskandan; P Georgiou; A H Holmes Journal: J Antimicrob Chemother Date: 2019-04-01 Impact factor: 5.790
Authors: N Peiffer-Smadja; T M Rawson; R Ahmad; A Buchard; P Georgiou; F-X Lescure; G Birgand; A H Holmes Journal: Clin Microbiol Infect Date: 2019-09-17 Impact factor: 8.067
Authors: T M Rawson; L S P Moore; B Hernandez; E Charani; E Castro-Sanchez; P Herrero; B Hayhoe; W Hope; P Georgiou; A H Holmes Journal: Clin Microbiol Infect Date: 2017-03-06 Impact factor: 8.067
Authors: Bernard Hernandez; Pau Herrero; Timothy Miles Rawson; Luke S P Moore; Benjamin Evans; Christofer Toumazou; Alison H Holmes; Pantelis Georgiou Journal: BMC Med Inform Decis Mak Date: 2017-12-08 Impact factor: 2.796
Authors: Timothy M Rawson; Luke S P Moore; Enrique Castro-Sanchez; Esmita Charani; Frances Davies; Giovanni Satta; Matthew J Ellington; Alison H Holmes Journal: J Antimicrob Chemother Date: 2020-07-01 Impact factor: 5.790