Comparing Continuous with Periodic Vital Sign Scoring for Clinical Deterioration Using a Patient Data Model

Abstract

To evaluate a minute-by-minute monitoring algorithm against a periodic early warning score (EWS) in detecting clinical deterioration and workload. Periodic EWSs suffer from large measurement intervals, causing late detection of deterioration. This might be prevented by continuous vital sign monitoring with a real-time algorithm such as the Visensia Safety Index (VSI). This prospective comparative data modeling cohort study (NCT04189653) compares continuous algorithmic alerts against periodic EWS in continuous monitored medical and surgical inpatients. We evaluated sensitivity, frequency, number of warnings needed to evaluate (NNE) and time of initial alert till escalation of care (EOC): Rapid Response Team activation, unplanned ICU admission, emergency surgery, or death. Also, the percentage of VSI alerting minutes was compared between patients with or without EOC. In 1529 admissions continuous VSI warned for 55% of EOC (95% CI: 45-64%) versus 51% (95% CI: 41-61%) by periodic EWS. NNE for VSI was 152 alerts per detected EOC (95% CI: 114-190) compared to 21 (95% CI: 17-28). It generated 0.99 warnings per day per patient compared to 0.13. Time from detection score till escalation was 8.3 hours (IQR: 2.6-24.8) with VSI versus 5.2 (IQR: 2.7-12.3) hours with EWS (P=0.074). The percentage of warning VSI minutes was higher in patients with EOC than in stable patients (2.36% vs 0.81%, P<0.001). Although sensitivity of detection was not significantly improved continuous vital sign monitoring shows potential for earlier alerts for deterioration compared to periodic EWS. A higher percentage of alerting minutes may indicate risk for deterioration.

The future of postoperative vital sign monitoring in general wards: improving patient safety through continuous artificial intelligence-enabled alert formation and reduction

“…Barriers were technological and related to device design and internet connectivity [33 ▪ ]. The benefit of CVSM on reducing nurses workload is further supported by a descriptive analysis documenting a 10 minute per patient per day time saving with CVSM as compared with NEWS [34], and also in a case control study in 249 patients of CSVM vs manual monitoring that also found decreased time to rapid response team activation [35], similar to other aforementioned studies [6,19].…”

“…AI applications for continuous monitoring is already reported to have benefit within alert reduction [8 ▪ ], early detection (sometimes termed prediction) [6,18], pattern recognition by combining multisensor and additional sources of information (i.e., blood-samples, demographics etc.) [18,19], and will undoubtedly venture into new areas.…”

“…Table 1 summarizes more recent AI-enabled systems. Using the ViSi mobile multisensory system (BP, P, temp, RR, sat) [6] for risk calculation (Visensia Safety Index, VSI) the study compared the continuous VSI system vs. intermittent manual assessments for escalation of care, number of alerts and accuracy for true alert detection etc. in 1529 admissions.…”

“…In addition to a large workload associated with manual collection of all these variables, the manual monitoring also inherits inaccuracies such as preference for specific numbers (such as those below thresholds for escalation and those dividable by 4 due to per-minute measurements only being performed for 15 s etc.). Replacing spot measurements with continuous monitoring has for decades been shown to results in detection of more deviating vital signs for obvious reasons [6,7] (Figs. 1 and 2).…”