Algorithms for Prediction of Clinical Deterioration on the General Wards: A Scoping Review

Abstract

OBJECTIVE: The primary objective of this scoping review was to identify and describe state-of-the-art models that use vital sign monitoring to predict clinical deterioration on the general ward. The secondary objective was to identify facilitators, barriers, and effects of implementing these models. DATA SOURCES: PubMed, Embase, and CINAHL databases until November 2020. STUDY SELECTION: We selected studies that compared vital signs–based automated real-time predictive algorithms to current track-and-trace protocols in regard to the outcome of clinical deterioration in a general ward population. DATA EXTRACTION: Study characteristics, predictive characteristics and barriers, facilitators, and effects. RESULTS: We identified 1,741 publications, 21 of which were included in our review. Two of the these were clinical trials, 2 were prospective observational studies, and the remaining 17 were retrospective studies. All of the studies focused on hospitalized adult patients. The reported area under the receiver operating characteristic curves ranged between 0.65 and 0.95 for the outcome of clinical deterioration. Positive predictive value and sensitivity ranged between 0.223 and 0.773 and 7.2% to 84.0%, respectively. Input variables differed widely, and predicted endpoints were inconsistently defined. We identified 57 facilitators and 48 barriers to the implementation of these models. We found 68 reported effects, 57 of which were positive. CONCLUSION: Predictive algorithms can detect clinical deterioration on the general ward earlier and more accurately than conventional protocols, which in one recent study led to lower mortality. Consensus is needed on input variables, predictive time horizons, and definitions of endpoints to better facilitate comparative research.

Sodium fluctuation as a parameter in predicting mortality in general hospitalized patients

“…The optimal cut-off point was 7.5 mmol/L with a sensitivity of 76.5% and a specificity of 84.2%. The single parameter system using sodium fluctuation level as the marker performed better than previously reported single parameter systems and multiple parameter weighting systems ( 24 , 25 ). Our results suggested that the clinical significance of sodium fluctuation should be emphasized in clinical practice.…”

Early Prediction of All-Cause Clinical Deterioration in General Wards Patients: Development and Validation of a Biomarker-Based Machine Learning Model Derived From Rapid Response Team Activations

“…Furthermore, almost all of the deterioration models in the literature, which include laboratory variables (such as, for example, those of the LAPS-2 score 12 ) use the absolute form of the exam values. To the best of our knowledge, 21 our model is among a few (if not the only one) that use differential (or δ) biomarker variables in deterioration prediction models. It is known, however, that changes in biomarker values (δ) within a specific timeframe can indicate certain underlying pathophysiological changes, such as, for example, in case of bleeding (δ in hemoglobin values) or acute kidney injury (δ in creatinine values).…”

“…Moreover, most of the prediction models were trained according to cases with the following outcome variables: cardiorespiratory arrest/death/unexpected transfer to ICU. Only few studies 20,21 have adopted the activation of the RRT as an outcome for the training and validation of the predictive model, 22,23 although such an outcome encompasses a broader and richer perspective of clinical deteriorations. In fact, a significant percentage (almost half ) of RRT deterioration cases end with stabilization of patients on wards, 24,25 a clinical scenario otherwise not used by most systems.…”

Effectiveness of an Artificial Intelligence–Enabled Intervention for Detecting Clinical Deterioration

“…2 Despite widespread adoption of EWSs, few methodologically rigorous studies have evaluated their impact on patient outcomes. A recent systematic review identified only 1 patientlevel randomized clinical trial, 3 with that study finding no significant difference with the use of an EWS in the primary outcome of transfer to the intensive care unit (ICU). 4 Most studies, including one of the largest studies to date (N = 43 949), 5 have reported associations or pre-post comparisons that are vulnerable to inherent biases.…”