Costs, benefits and the prevention of patient deterioration

Real-Time Machine Learning Alerts to Prevent Escalation of Care: A Nonrandomized Clustered Pragmatic Clinical Trial

OBJECTIVES

Machine learning algorithms can outperform older methods in predicting clinical deterioration, but rigorous prospective data on their real-world efficacy are limited. We hypothesized that real-time machine learning generated alerts sent directly to front-line providers would reduce escalations.

DESIGN

Single-center prospective pragmatic nonrandomized clustered clinical trial.

SETTING

Academic tertiary care medical center.

PATIENTS

Adult patients admitted to four medical-surgical units. Assignment to intervention or control arms was determined by initial unit admission.

INTERVENTIONS

Real-time alerts stratified according to predicted likelihood of deterioration sent either to the primary team or directly to the rapid response team (RRT). Clinical care and interventions were at the providers' discretion. For the control units, alerts were generated but not sent, and standard RRT activation criteria were used.

MEASUREMENTS AND MAIN RESULTS

The primary outcome was the rate of escalation per 1000 patient bed days. Secondary outcomes included the frequency of orders for fluids, medications, and diagnostic tests, and combined in-hospital and 30-day mortality. Propensity score modeling with stabilized inverse probability of treatment weight (IPTW) was used to account for differences between groups. Data from 2740 patients enrolled between July 2019 and March 2020 were analyzed (1488 intervention, 1252 control). Average age was 66.3 years and 1428 participants (52%) were female. The rate of escalation was 12.3 vs. 11.3 per 1000 patient bed days (difference, 1.0; 95% CI, -2.8 to 4.7) and IPTW adjusted incidence rate ratio 1.43 (95% CI, 1.16-1.78; p < 0.001). Patients in the intervention group were more likely to receive cardiovascular medication orders (16.1% vs. 11.3%; 4.7%; 95% CI, 2.1-7.4%) and IPTW adjusted relative risk (RR) (1.74; 95% CI, 1.39-2.18; p < 0.001). Combined in-hospital and 30-day-mortality was lower in the intervention group (7% vs. 9.3%; -2.4%; 95% CI, -4.5% to -0.2%) and IPTW adjusted RR (0.76; 95% CI, 0.58-0.99; p = 0.045).

CONCLUSIONS

Real-time machine learning alerts do not reduce the rate of escalation but may reduce mortality.

The impact of continuous wireless monitoring on adverse device effects in medical and surgical wards: a review of current evidence

Novel technologies allow continuous wireless monitoring systems (CWMS) to measure vital signs and these systems might be favorable compared to intermittent monitoring regarding improving outcomes. However, device safety needs to be validated because uncertain evidence challenges the clinical implementation of CWMS. This review investigates the frequency of device-related adverse events in patients monitored with CWMS in general hospital wards. Systematic literature searches were conducted in PubMed and Embase. We included trials of adult patients in general hospital wards monitored with CWMS. Our primary outcome was the frequency of unanticipated serious adverse device effects (USADEs). Secondary outcomes were adverse device effects (ADEs) and serious adverse device effects (SADE). Data were extracted from eligible studies and descriptive statistics were applied to analyze the data. Seven studies were eligible for inclusion with a total of 1485 patients monitored by CWMS. Of these patients, 54 patients experienced ADEs (3.6%, 95% CI 2.8-4.7%) and no USADEs or SADEs were reported (0%, 95% CI 0-0.31%). The studies of the SensiumVitals® patch, the iThermonitor, and the ViSi Mobile® device reported 28 (9%), 25 (5%), and 1 (3%) ADEs, respectively. No ADEs were reported using the HealthPatch, WARD 24/7 system, or Coviden Alarm Management. Current evidence suggests that CWMS are safe to use but systematic reporting of all adverse device effects is warranted.