Supervised machine learning for the prediction of infection on admission to hospital: a prospective observational cohort study

Rawson, Timothy M; Hernandez, Bernard; Moore, Luke; Blandy, Oliver; Herrero, Pau; Gilchrist, Mark; Gordon, Anthony; Toumazou, C.; Sriskandan, Shiranee; Georgiou, Pantelis; Holmes, Alison

doi:10.1093/jac/dky514

Cited by 33 publications

(14 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One study described a ML-CDSS trained to diagnose bacterial infection using six routinely available blood parameters with data from 160 203 individuals and its use in a prospective observational cohort. Among 104 patients included, the ML-CDSS predicted a bacterial infection in three individuals who were not identified by clinicians as having an infection on admission but were diagnosed later with a bacterial infection [58].…”

Section: Diagnosis Of Infectionmentioning

confidence: 99%

Machine learning for clinical decision support in infectious diseases: a narrative review of current applications

Peiffer-Smadja

Rawson

Ahmad

et al. 2020

Clinical Microbiology and Infection

306

174

View full text Add to dashboard Cite

Background: Machine learning (ML) is a growing field in medicine. This narrative review describes the current body of literature on ML for clinical decision support in infectious diseases (ID). Objectives: We aim to inform clinicians about the use of ML for diagnosis, classification, outcome prediction and antimicrobial management in ID. Sources: References for this review were identified through searches of MEDLINE/PubMed, EMBASE, Google Scholar, biorXiv, ACM Digital Library, arXiV and IEEE Xplore Digital Library up to July 2019. Content: We found 60 unique ML-clinical decision support systems (ML-CDSS) aiming to assist ID clinicians. Overall, 37 (62%) focused on bacterial infections, 10 (17%) on viral infections, nine (15%) on tuberculosis and four (7%) on any kind of infection. Among them, 20 (33%) addressed the diagnosis of infection, 18 (30%) the prediction, early detection or stratification of sepsis, 13 (22%) the prediction of treatment response, four (7%) the prediction of antibiotic resistance, three (5%) the choice of antibiotic regimen and two (3%) the choice of a combination antiretroviral therapy. The ML-CDSS were developed for intensive care units (n ¼ 24, 40%), ID consultation (n ¼ 15, 25%), medical or surgical wards (n ¼ 13, 20%), emergency department (n ¼ 4, 7%), primary care (n ¼ 3, 5%) and antimicrobial stewardship (n ¼ 1, 2%). Fifty-three ML-CDSS (88%) were developed using data from high-income countries and seven (12%) with data from low-and middle-income countries (LMIC). The evaluation of ML-CDSS was limited to measures of performance (e.g. sensitivity, specificity) for 57 ML-CDSS (95%) and included data in clinical practice for three (5%). Implications: Considering comprehensive patient data from socioeconomically diverse healthcare settings, including primary care and LMICs, may improve the ability of ML-CDSS to suggest decisions adapted to various clinical contexts. Currents gaps identified in the evaluation of ML-CDSS must also be addressed in order to know the potential impact of such tools for clinicians and patients.

show abstract

Section: Diagnosis Of Infectionmentioning

confidence: 99%

Machine learning for clinical decision support in infectious diseases: a narrative review of current applications

Peiffer-Smadja

Rawson

Ahmad

et al. 2020

Clinical Microbiology and Infection

306

174

View full text Add to dashboard Cite

show abstract

“…The data analysis driven by ML is a quite new approach in medical care and complementary diagnosis (Heinrichs and Eickhoff 2020 ; Sidey-Gibbons and Sidey-Gibbons 2019 ; Watson et al 2019 ); however, in the last years, several studies have reported the use of ML with image data or clinical specimens (blood, stool, urine) to help in diagnose cancer (Kourou et al 2015 ; Podnar et al 2019 ; Salod and Singh 2019 ; Wu et al 2019 ), diabetes and cardiovascular disease (Dinh et al 2019 ; Kavakiotis et al 2017 ; Shameer et al 2018 ) among other conditions (Ayling et al 2019 ; Gunčar et al 2018 ; Poostchi et al 2018 ; Ullah et al 2019 ). Considering the infective diseases, ML techniques were used to identify dengue (Hair et al 2019 ), bacterial infections (Rawson et al 2019 ) and, more recently, COVID-19 (Banerjee et al 2020 ; Brinati et al 2020 ). These studies employed mostly Random Forest, Logistic Regression, Naïve Bayes and SVM as learners and included basic blood sample data in their analysis (hematologic data, CRP, alanine and aspartate aminotransferases, among others).…”

Section: Discussionmentioning

confidence: 99%

Diagnostic significance of C-reactive protein and hematological parameters in acute toxoplasmosis

et al. 2020

View full text Add to dashboard Cite

Toxoplasmosis is a zoonosis caused by Toxoplasma gondii, which can be acquired by oral contact and may cause severe health problems especially for pregnant (congenital toxoplasmosis) and immunocompromised patients. This study aimed to verify the diagnostic significance of hematological parameters and C-reactive protein (CRP) for toxoplasmosis acute detection. A case-control study was carried out between December 2017 and May 2018, in samples of convenience independent of age and sex. The case group was formed by 25 patients with positive anti-Toxoplasma gondii IgG/IgM antibody and the control group was formed by 21 patients with non-positive anti-Toxoplasma gondii IgG/IgM antibody. The results of the hematological parameters and CRP were analyzed in these patients. The patients with Toxoplasma gondii IgM antibody reagent showed higher lymphocytes counting and lower neutrophils counting than the control group. C-reactive protein levels were not different between the groups case and control. ROC curve analysis highlighted that the cutoff value of [ 32.00% for lymphocytes and \ 57.50% for neutrophils were able to produce specificity higher than 90% for IgM antibody detection. The Naïve Bayes classifier was considered suitable (AUC & 0.700) to separate both groups according to their white cell counting. Changes in lymphocytes and neutrophils may be useful parameters for toxoplasmosis identification and may be used as a tool in the complementary diagnosis of toxoplasmosis.

show abstract

“…transformation to binary variables indicating missingness [22], carryforward of last observation [12,14,20,23e26], including complete cases only [18,27e30], or applying multiple imputation [11,17,31e35]. Two studies assessed the effect of missing data on model performance through a stepwise introduction of missing variables [36,37]. Class imbalance of the labelled outcome variable was explicitly mentioned if applicable in 39% (n ¼ 18) of the studies.…”

Section: Data Underlying Identified Machine Learning Studiesmentioning

confidence: 99%

“…This is particularly worrisome not only because of the debate on reproducibility [70] but also as ML tools are often being criticized as black boxes. The maintainers of the public MIMIC data repository lead the way in providing open source code "Pre-determined clinical case definition" (original quote from the authors) [36] "Any type of infection"; positive microbiological culture (original quote from the authors)…”

Section: Reporting Standardsmentioning

confidence: 99%

Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies

Luz

Vollmer

Decruyenaere

et al. 2020

Clinical Microbiology and Infection

View full text Add to dashboard Cite

Background: Machine learning (ML) is increasingly being used in many areas of health care. Its use in infection management is catching up as identified in a recent review in this journal. We present here a complementary review to this work. Objectives: To support clinicians and researchers in navigating through the methodological aspects of ML approaches in the field of infection management. Sources: A Medline search was performed with the keywords artificial intelligence, machine learning, infection*, and infectious disease* for the years 2014e2019. Studies using routinely available electronic hospital record data from an inpatient setting with a focus on bacterial and fungal infections were included. Content: Fifty-two studies were included and divided into six groups based on their focus. These studies covered detection/prediction of sepsis (n ¼ 19), hospital-acquired infections (n ¼ 11), surgical site infections and other postoperative infections (n ¼ 11), microbiological test results (n ¼ 4), infections in general (n ¼ 2), musculoskeletal infections (n ¼ 2), and other topics (urinary tract infections, deep fungal infections, antimicrobial prescriptions; n ¼ 1 each). In total, 35 different ML techniques were used. Logistic regression was applied in 18 studies followed by random forest, support vector machines, and artificial neural networks in 18, 12, and seven studies, respectively. Overall, the studies were very heterogeneous in their approach and their reporting. Detailed information on data handling and software code was often missing. Validation on new datasets and/or in other institutions was rarely done. Clinical studies on the impact of ML in infection management were lacking. Implications: Promising approaches for ML use in infectious diseases were identified. But building trust in these new technologies will require improved reporting. Explainability and interpretability of the models used were rarely addressed and should be further explored. Independent model validation and clinical studies evaluating the added value of ML approaches are needed.

show abstract

Supervised machine learning for the prediction of infection on admission to hospital: a prospective observational cohort study

Cited by 33 publications

References 41 publications

Machine learning for clinical decision support in infectious diseases: a narrative review of current applications

Machine learning for clinical decision support in infectious diseases: a narrative review of current applications

Diagnostic significance of C-reactive protein and hematological parameters in acute toxoplasmosis

Machine learning in infection management using routine electronic health records: tools, techniques, and reporting of future technologies

Contact Info

Product

Resources

About