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

Abstract

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.

Performance and impact of a multiplex PCR in ICU patients with ventilator-associated pneumonia or ventilated hospital-acquired pneumonia

“…The design of our study does not allow to easily separate what is directly related to the M-PCR results from the impact of a multidisciplinary review of each le. As with other innovative tools, 39 clinical trials, preferably randomized and multicentric, should be conducted to evaluate clinical outcomes, including adverse outcomes, process improvement and ecological impact. Special attention should be paid to the integration and implementation of systems into clinical practice, and their adoption and utilisation by clinicians.…”

A Review of Predictive Analytics Solutions for Sepsis Patients

“…52 Schinkel et al performed a review similar to ours by searching only PubMed, but they excluded studies that did not have an AUROC statistic. 53 No search query is perfect; in fact, Salvador-Olivan et al found that almost 93% of search strategies in systematic reviews contained at least one error in their respective search queries. 54…”

Machine Learning and Multidrug-Resistant Gram-Negative Bacteria: An Interesting Combination for Current and Future Research

“…ML is a branch of artificial intelligence that consists of conferring on computers the ability to learn from data [14,15]. Differently from classical computer expert systems, which are explicitly programmed to do specific task/s (e.g., recognizing a patient to be at risk of MDR-GNB infection), ML algorithms have a notable advantage in term of flexibility, since they may be able to point out the association between patients' characteristics (the input) and the risk of MDR-GNB infection (the output) without being explicitly programmed to do so [16].…”