Evidence-based Clinical Decision Support Systems for the prediction and detection of three disease states in critical care: A systematic literature review

Abstract

Background: Clinical decision support (CDS) systems have emerged as tools providing intelligent decision making to address challenges of critical care. CDS systems can be based on existing guidelines or best practices; and can also utilize machine learning to provide a diagnosis, recommendation, or therapy course. Methods: This research aimed to identify evidence-based study designs and outcome measures to determine the clinical effectiveness of clinical decision support systems in the detection and prediction of hemodynamic instability, respiratory distress, and infection within critical care settings. PubMed, ClinicalTrials.gov and Cochrane Database of Systematic Reviews were systematically searched to identify primary research published in English between 2013 and 2018. Studies conducted in the USA, Canada, UK, Germany and France with more than 10 participants per arm were included. Results: In studies on hemodynamic instability, the prediction and management of septic shock were the most researched topics followed by the early prediction of heart failure. For respiratory distress, the most popular topics were pneumonia detection and prediction followed by pulmonary embolisms. Given the importance of imaging and clinical notes, this area combined Machine Learning with image analysis and natural language processing. In studies on infection, the most researched areas were the detection, prediction, and management of sepsis, surgical site infections, as well as acute kidney injury. Overall, a variety of Machine Learning algorithms were utilized frequently, particularly support vector machines, boosting techniques, random forest classifiers and neural networks. Sensitivity, specificity, and ROC AUC were the most frequently reported performance measures. Conclusion: This review showed an increasing use of Machine Learning for CDS in all three areas. Large datasets are required for training these algorithms; making it imperative to appropriately address, challenges such as class imbalance, correct labelling of data and missing data. Recommendations are formulated for the development and successful adoption of CDS systems.

Evidence-based Clinical Decision Support Systems for the prediction and detection of three disease states in critical care: A systematic literature review

“…Study protocols identified from bibliographic databases were, however, excluded assuming that final study results would be available and identified elsewhere. The strategy employed in PubMed is provided as Extended data , Table 1–Table 3 25– 27 .…”

“…Extended data - Table 2-Search strategy for respiratory distress or respiratory failure in MEDLINE.docx. https://doi.org/10.6084/m9.figshare.9892112.v1 26 .…”

“…Figshare: PRISMA checklist for ‘Evidence-based Clinical Decision Support Systems for the prediction and detection of three disease states in critical care: A systematic literature review’. https://doi.org/10.6084/m9.figshare.9894107.v1 107 .…”

This is your toolkit in hemodynamic monitoring

“…The physician can be made aware of their thinking process and can be trained to use or leave out specific values obtained with the clinical examination, or the physician can be trained to reconsider their conclusion when new information is presented. Additionally, machine learning algorithms are increasingly applied in studies to diagnose and predict outcomes of circulatory shock [87]. These types of techniques may be applied to improve the clinical examination as a first step for the evaluation of circulatory shock.…”

Ambiguous definitions for baseline serum creatinine affect acute kidney diagnosis at the emergency department

“…Growing use of electronic health records (EHR) and machine learning have provided a possibility to study large collections of real-world data and develop early detection systems for AKI [10]. Indeed, clinical decision support systems (CDS) have emerged as tools for initial assessment and identification of AKI patients in different settings [11]. These CDS make recommendations and risk stratifications based on the existing guidelines and best practices for AKI [12].…”