Background: Patients undergoing major surgery are at risk of complications, so‐called serious adverse events (SAE). Continuous monitoring may detect deteriorating patients by recording abnormal vital signs. We aimed to assess the association between abnormal vital signs inspired by Early Warning Score thresholds and subsequent SAEs in patients undergoing major abdominal surgery.Methods: Prospective observational cohort study continuously monitoring heart rate, respiratory rate, peripheral oxygen saturation, and blood pressure for up to 96 h in 500 postoperative patients admitted to the general ward. Exposure variables were vital sign abnormalities, primary outcome was any serious adverse event occurring within 30 postoperative days. The primary analysis investigated the association between exposure variables per 24 h and subsequent serious adverse events.Results: Serious adverse events occurred in 37% of patients, with 38% occurring during monitoring. Among patients with SAE during monitoring, the median duration of vital sign abnormalities was 272 min (IQR 110–447), compared to 259 min (IQR 153–394) in patients with SAE after monitoring and 261 min (IQR 132–468) in the patients without any SAE (p = .62 for all three group comparisons). Episodes of heart rate ≥110 bpm occurred in 16%, 7.1%, and 3.9% of patients in the time before SAE during monitoring, after monitoring, and without SAE, respectively (p < .002). Patients with SAE after monitoring experienced more episodes of hypotension ≤90 mm Hg/24 h (p = .001).Conclusion: Overall duration of vital sign abnormalities at current thresholds were not significantly associated with subsequent serious adverse events, but more patients with tachycardia and hypotension had subsequent serious adverse events.Trial registration: Clinicaltrials.gov, identifier NCT03491137.

Continuous monitoring of high-risk patients and early prediction of severe outcomes is crucial to prevent avoidable deaths. Current clinical monitoring is primarily based on intermittent observation of vital signs and the early warning scores (EWS). The drawback is lack of time series dynamics and correlations among vital signs. This study presents an approach to real-time outcome prediction based on machine learning from continuous recording of vital signs. Systolic blood pressure, diastolic blood pressure, heart rate, pulse rate, respiration rate and peripheral blood oxygen saturation were continuously acquired by wearable devices from 292 post-operative high-risk patients. The outcomes from serious complications were evaluated based on review of patients' medical record. The descriptive statistics of vital signs and patient demographic information were used as features. Four machine learning models K-Nearest-Neighbors (KNN), Decision Trees (DT), Random Forest (RF), and Boosted Ensemble (BE) were trained and tested. In static evaluation, all four models had comparable prediction performance to that of the state of the art. In dynamic evaluation, the models trained from the static evaluation were tested with continuous data. RF and BE obtained the lower false positive rate (FPR) of 0.073 and 0.055 on no-outcome patients respectively. The four models KNN, DT, RF and BE had area under receiver operating characteristic curve (AUROC) of 0.62, 0.64, 0.65 and 0.64 respectively on outcome patients. RF was found to be optimal model with lower FPR on no-outcome patients and a higher AUROC on outcome patients. These findings are encouraging and indicate that additional investigations must focus on validating performance in a clinical setting before deployment of the real-time outcome prediction.

Objective. Wireless sensors for continuous monitoring of vital signs have potential to improve patient care by earlier detection of deterioration in general ward patients. We aimed to assess agreement between wireless and standard (wired) monitoring devices in patients hospitalized with acute exacerbation of chronic obstructive pulmonary disease (AECOPD). Approach. Paired measurements of vital signs were recorded with 15 min intervals for two hours. The primary outcome was agreement between wireless and standard monitor measurements using the Bland and Altman method to calculate bias with 95% limits of agreement (LoA). We considered LoA of less than ±5 beats min ⁻¹ (bpm) acceptable for heart rate (HR), whereas agreement of peripheral oxygen saturation (SpO ₂ ), respiratory rate (RR), and blood pressure (BP) were acceptable if within ±3%-points, ±3 breaths min ⁻¹ (brpm), and ±10 mmHg, respectively. Main results. 180 sample-pairs of vital signs from 20 with AECOPD patients were recorded for comparison. The wireless versus standard monitor bias was 0.03 (LoA −3.2 to 3.3) bpm for HR measurements, 1.4% (LoA −0.7% to 3.6%) for SpO ₂ , −7.8 (LoA −22.3 to 6.8) mmHg for systolic BP and −6.2 (LoA −16.8 to 4.5) mmHg for diastolic BP. The wireless versus standard monitor bias for RR measurements was 0.75 (LoA −6.1 to 7.6) brpm. Significance. Commercially available wireless monitors could accurately measure HR in patients admitted with AECOPD compared to standard wired monitoring. Agreement for SpO ₂ were borderline acceptable while agreement for RR and BP should be interpreted with caution.

Continuous vital sign monitoring at the general hospital ward has major potential advantages over intermittent monitoring but generates many alerts with risk of alert fatigue. We hypothesized that the number of alerts would be decreased using different filters. This study was an exploratory analysis of the alert reducing effect from adding two different filters to continuously collected vital sign data (peripheral oxygen saturation, blood pressure, heart rate and respiratory rate) in patients admitted after major surgery or severe medical disease. Filtered data were compared to data without artifact removal. Filter one consisted of artifact removal, filter two consisted of artifact removal plus duration criteria adjusted for severity of vital sign deviation. Alert thresholds were based on National Early Warning Score (NEWS) threshold. A population of 716 patients admitted for severe medical disease or major surgery with continous wireless vital sign monitoring at the generel ward with a mean monitoring time of 75.8 hours, were included for the analysis. Without artifact removal we found a median of 137 [IQR: 87-188] alerts per patient/day, artifact removal resulted in a median of 101 [IQR: 56-160] alerts per patient/day and with artifact removal combined with a duration-severity criterion we found a median of 19 [IQR: 9-34] alerts per patient/day. Reduction of alerts was 86.4% (p < 0.001) for values without artifact removal (137 alerts) vs. the duration criteria and a reduction (19 alerts) of 81.5% (p < 0.001) for the criteria with artifact removal (101 alerts) vs. the duration criteria (19 alerts). We conclude that a combination of artifact removal and duration-severity criteria approach substantially reduces alerts generated by continuous vital sign monitoring.