In this prospective, interventional, international study, we investigate continuous monitoring of hospitalised patients’ vital signs using wearable technology as a basis for real-time early warning scores (EWS) estimation and vital signs time-series prediction. The collected continuous monitored vital signs are heart rate, blood pressure, respiration rate, and oxygen saturation of a heterogeneous patient population hospitalised in cardiology, postsurgical, and dialysis wards. Two aspects are elaborated in this study. The first is the high-rate (every minute) estimation of the statistical values (e.g., minimum and mean) of the vital signs components of the EWS for one-minute segments in contrast with the conventional routine of 2 to 3 times per day. The second aspect explores the use of a hybrid machine learning algorithm of kNN-LS-SVM for predicting future values of monitored vital signs. It is demonstrated that a real-time implementation of EWS in clinical practice is possible. Furthermore, we showed a promising prediction performance of vital signs compared to the most recent state of the art of a boosted approach of LSTM. The reported mean absolute percentage errors of predicting one-hour averaged heart rate are 4.1, 4.5, and 5% for the upcoming one, two, and three hours respectively for cardiology patients. The obtained results in this study show the potential of using wearable technology to continuously monitor the vital signs of hospitalised patients as the real-time estimation of EWS in addition to a reliable prediction of the future values of these vital signs is presented. Ultimately, both approaches of high-rate EWS computation and vital signs time-series prediction is promising to provide efficient cost-utility, ease of mobility and portability, streaming analytics, and early warning for vital signs deterioration.

Photoplethysmography- (PPG) based smartphone applications facilitate heart rate and rhythm monitoring in patients with paroxysmal and persistent atrial fibrillation (AF). Despite an endorsement from the European Heart Rhythm Association, validation studies in this setting are lacking. Therefore, we evaluated the accuracy of PPG-derived heart rate and rhythm classification in subjects with an established diagnosis of AF in unsupervised real-world conditions. Fifty consecutive patients were enrolled, 4 weeks before undergoing AF ablation. Patients used a handheld single-lead electrocardiography (ECG) device and a fingertip PPG smartphone application to record 3907 heart rhythm measurements twice daily during 8 weeks. The ECG was performed immediately before and after each PPG recording and was given a diagnosis by the majority of three blinded cardiologists. A consistent ECG diagnosis was exhibited along with PPG data of sufficient quality in 3407 measurements. A single measurement exhibited good quality more often with ECG (93.2%) compared to PPG (89.5%; P < 0.001). However, PPG signal quality improved to 96.6% with repeated measurements. Photoplethysmography-based detection of AF demonstrated excellent sensitivity [98.3%; confidence interval (CI): 96.7–99.9%], specificity (99.9%; CI: 99.8–100.0%), positive predictive value (99.6%; CI: 99.1–100.0%), and negative predictive value (99.6%; CI: 99.0–100.0%). Photoplethysmography underestimated the heart rate in AF with 6.6 b.p.m. (95% CI: 5.8 b.p.m. to 7.4 b.p.m.). Bland–Altman analysis revealed increased underestimation in high heart rates. The root mean square error was 11.8 b.p.m. Smartphone applications using PPG can be used to monitor patients with AF in unsupervised real-world conditions. The accuracy of AF detection algorithms in this setting is excellent, but PPG-derived heart rate may tend to underestimate higher heart rates.

Background: Consumer-oriented wearable devices (CWDs) such as smartphones and smartwatches have gained prominence for their ability to detect atrial fibrillation (AF) through proprietary algorithms using electrocardiography or photoplethysmography (PPG)–based digital recordings. Despite numerous individual validation studies, a direct comparison of interdevice performance is lacking. Objective: This study aimed to evaluate and compare the ability of CWDs to distinguish between sinus rhythm and AF. Methods: Patients exhibiting sinus rhythm or AF were enrolled through a cardiology outpatient clinic. The participants were instructed to perform heart rhythm measurements using a handheld 6-lead electrocardiogram (ECG) device (KardiaMobile 6L), a smartwatch-derived single-lead ECG (Apple Watch), and two PPG-based smartphone apps (FibriCheck and Preventicus) in a random sequence, with simultaneous 12-lead reference ECG as the gold standard. Results: A total of 122 participants were included in the study: median age 69 (IQR 61-77) years, 63.9% (n=78) men, 25% (n=30) with AF, 9.8% (n=12) without prior smartphone experience, and 73% (n=89) without experience in using a smartwatch. The sensitivity to detect AF was 100% for all devices. The specificity to detect sinus rhythm was 96.4% (95% CI 89.5%-98.8%) for KardiaMobile 6L, 97.8% (95% CI 91.6%‐99.5%) for Apple Watch, 98.9% (95% CI 92.5%‐99.8%) for FibriCheck, and 97.8% (95% CI 91.5%‐99.4%) for Preventicus (P=.50). Insufficient quality measurements were observed in 10.7% (95% CI 6.3%-17.5%) of cases for both KardiaMobile 6L and Apple Watch, 7.4% (95% CI 3.9%‐13.6%) for FibriCheck, and 14.8% (95% CI 9.5%‐22.2%) for Preventicus (P=.21). Participants preferred Apple Watch over the other devices to monitor their heart rhythm. Conclusions: In this study population, the discrimination between sinus rhythm and AF using CWDs based on ECG or PPG was highly accurate, with no significant variations in performance across the examined devices.

This study introduces machine learning predictive models to predict the future values of the monitored vital signs of COVID-19 ICU patients. The main vital sign predictors include heart rate, respiration rate, and oxygen saturation. We investigated the performances of the developed predictive models by considering different approaches. The first predictive model was developed by considering the following vital signs: heart rate, blood pressure (systolic, diastolic and mean arterial, pulse pressure), respiration rate, and oxygen saturation. Similar to the first approach, the second model was developed using the same vital signs, but it was trained and tested based on a leave-one-subject-out approach. The third predictive model was developed by considering three vital signs: heart rate (HR), respiration rate (RR), and oxygen saturation (SpO${}_2$). The fourth model was a leave-one-subject-out model for the three vital signs. Finally, the fifth predictive model was developed based on the same three vital signs, but with a five-minute observation rate, in contrast with the aforementioned four models, where the observation rate was hourly to bi-hourly. For the five models, the predicted measurements were those of the three upcoming observations (on average, three hours ahead). Based on the obtained results, we observed that by limiting the number of vital sign predictors (i.e., three vital signs), the prediction performance was still acceptable, with the average mean absolute percentage error (MAPE) being $12\%,5\%$, and $21.4\%$ for heart rate, oxygen saturation, and respiration rate, respectively. Moreover, increasing the observation rate could enhance the prediction performance to be, on average, $8\%,4.8\%$, and $17.8\%$ for heart rate, oxygen saturation, and respiration rate, respectively. It is envisioned that such models could be integrated with monitoring systems that could, using a limited number of vital signs, predict the health conditions of COVID-19 ICU patients in real-time.

Mortality prediction for intensive care unit (ICU) patients is a challenging problem that requires extracting discriminative and informative features. This study presents a proof of concept for exploring features that can provide clinical insight. Through a feature engineering approach, it is attempted to improve ICU mortality prediction in field conditions with low frequently measured data (i.e., hourly to bi-hourly). Features are explored by investigating the vital signs measurements of ICU patients, labelled with mortality or survival at discharge. The vital signs of interest in this study are heart and respiration rate, oxygen saturation and blood pressure. The latter comprises systolic, diastolic and mean arterial pressure. In the feature exploration process, it is aimed to extract simple and interpretable features that can provide clinical insight. For this purpose, a classifier is required that maximises the margin between the two classes (i.e., survival and mortality) with minimum tolerance to misclassification errors. Moreover, it preferably has to provide a linear decision surface in the original feature space without mapping to an unlimited dimensionality feature space. Therefore, a linear hard margin support vector machine (SVM) classifier is suggested. The extracted features are grouped in three categories: statistical, dynamic and physiological. Each category plays an important role in enhancing classification error performance. After extracting several features within the three categories, a manual feature fine-tuning is applied to consider only the most efficient features. The final classification, considering mortality as the positive class, resulted in an accuracy of $91.56\%$ , sensitivity of $90.59\%$ , precision of $86.52\%$ and F ${}_1$ -score of $88.50\%$ . The obtained results show that the proposed feature engineering approach and the extracted features are valid to be considered and further enhanced for the mortality prediction purpose. Moreover, the proposed feature engineering approach moved the modelling methodology from black-box modelling to grey-box modelling in combination with the powerful classifier of SVMs.

Aim: This paper presents the preliminary results from the ongoing REMOTE trial. It aims to explore the opportunities and hurdles of using insertable cardiac monitors (ICMs) and photoplethysmography-based mobile health (PPG-based mHealth) using a smartphone or smartwatch to detect atrial fibrillation (AF) in cryptogenic stroke and transient ischemic attack (TIA) patients.Methods and Results: Cryptogenic stroke or TIA patients (n = 39) received an ICM to search for AF and were asked to use a blinded PPG-based mHealth application for 6 months simultaneously. They were randomized to smartphone or smartwatch monitoring. In total, 68,748 1-min recordings were performed using PPG-based mHealth. The number of mHealth recordings decreased significantly over time in both smartphone and smartwatch groups (p < 0.001 and p = 0.002, respectively). Insufficient signal quality was more frequently observed in smartwatch (43.3%) compared to smartphone recordings (17.8%, p < 0.001). However, when looking at the labeling of the mHealth recordings on a patient level, there was no significant difference in signal quality between both groups. Moreover, the use of a smartwatch resulted in significantly more 12-h periods (91.4%) that were clinically useful compared to smartphone users (84.8%) as they had at least one recording of sufficient signal quality. Simultaneously, continuous data was collected from the ICMs, resulting in approximately 6,660,000 min of data (i.e., almost a 100-fold increase compared to mHealth). The ICM algorithm detected AF and other cardiac arrhythmias in 10 and 19 patients, respectively. However, these were only confirmed after adjudication by the remote monitoring team in 1 (10%) and 5 (26.3%) patients, respectively. The confirmed AF was also detected by PPG-based mHealth.Conclusion: Based on the preliminary observations, our paper illustrates the potential as well as the limitations of PPG-based mHealth and ICMs to detect AF in cryptogenic stroke and TIA patients in four elements: (i) mHealth was able to detect AF in a patient in which AF was confirmed on the ICM; (ii) Even state-of-the-art ICMs yielded many false-positive AF registrations; (iii) Both mHealth and ICM still require physician revision; and (iv) Blinding of the mHealth results impairs compliance and motivation.