Continuous Glucose Monitoring Reveals Perioperative Hypoglycemia in Most Patients With Diabetes Undergoing Major Surgery: A Prospective Cohort Study.

OBJECTIVE: To investigate the frequency and duration of hypo- and hyperglycemia, assessed by continuous glucose monitoring (CGM) during and after major surgery, in departments with implemented diabetes care protocols. SUMMARY BACKGROUND DATA: Inadequate glycemic control in the perioperative period is associated with serious adverse events, but monitoring currently relies on point blood glucose measurements, which may underreport glucose excursions. METHODS: Adult patients without (A) or with diabetes [non-insulin-treated type 2 (B), insulin-treated type 2 (C) or type 1 (D)] undergoing major surgery were monitored using CGM (Dexcom G6), with an electrochemical sensor in the interstitial fluid, during surgery and for up to 10 days postoperatively. Patients and health care staff were blinded to CGM values, and glucose management adhered to the standard diabetes care protocol. Thirty-day postoperative serious adverse events were recorded. The primary outcome was duration of hypoglycemia (glucose <70 mg/dL). Clinicaltrials.gov: NCT04473001. RESULTS: Seventy patients were included, with a median observation time of 4.0 days. CGM was recorded in median 96% of the observation time. The median daily duration of hypoglycemia was 2.5 minutes without significant difference between the 4 groups (A-D). Hypoglycemic events lasting ≥15 minutes occurred in 43% of all patients and 70% of patients with type 1 diabetes. Patients with type 1 diabetes spent a median of 40% of the monitoring time in the normoglycemic range 70 to 180 mg/dL and 27% in the hyperglycemic range >250 mg/dL. Duration of preceding hypo- and hyperglycemia tended to be longer in patients with serious adverse events, compared with patients without events, but these were exploratory analyses. CONCLUSIONS: Significant duration of both hypo- and hyperglycemia was detected in high proportions of patients, particularly in patients with diabetes, despite protocolized perioperative diabetes management.

Ambulatory Detection of Isolated Rapid-Eye-Movement Sleep Behavior Disorder Combining Actigraphy and Questionnaire.

BACKGROUND: Isolated rapid-eye-movement sleep behavior disorder (iRBD) is in most cases a prodrome of neurodegenerative synucleinopathies, affecting 1% to 2% of middle-aged and older adults; however, accurate ambulatory diagnostic methods are not available. Questionnaires lack specificity in nonclinical populations. Wrist actigraphy can detect characteristic features in individuals with RBD; however, high-frequency actigraphy has been rarely used. OBJECTIVE: The aim was to develop a machine learning classifier using high-frequency (1-second resolution) actigraphy and a short patient survey for detecting iRBD with high accuracy and precision. METHODS: The method involved analysis of home actigraphy data (for seven nights and more) and a nine-item questionnaire (RBD Innsbruck inventory and three synucleinopathy prodromes of subjective hyposmia, constipation, and orthostatic dizziness) in a data set comprising 42 patients with iRBD, 21 sleep clinic patients with other sleep disorders, and 21 community controls. RESULTS: The actigraphy classifier achieved 95.2% (95% confidence interval [CI]: 88.3-98.7) sensitivity and 90.9% (95% CI: 82.1-95.8) precision. The questionnaire classifier achieved 90.6% accuracy and 92.7% precision, exceeding the performance of the Innsbruck RBD Inventory and prodromal questionnaire alone. Concordant predictions between actigraphy and questionnaire reached a specificity and precision of 100% (95% CI: 95.7-100.0) with 88.1% sensitivity (95% CI: 79.2-94.1) and outperformed any combination of actigraphy and a single question on RBD or prodromal symptoms. CONCLUSIONS: Actigraphy detected iRBD with high accuracy in a mixed clinical and community cohort. This cost-effective fully remote procedure can be used to diagnose iRBD in specialty outpatient settings and has potential for large-scale screening of iRBD in the general population. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Continuous monitoring is superior to manual measurements in detecting vital sign deviations in patients with COVID-19.

BACKGROUND: Patients admitted to the emergency care setting with COVID-19-infection can suffer from sudden clinical deterioration, but the extent of deviating vital signs in this group is still unclear. Wireless technology monitors patient vital signs continuously and might detect deviations earlier than intermittent measurements. The aim of this study was to determine frequency and duration of vital sign deviations using continuous monitoring compared to manual measurements. A secondary analysis was to compare deviations in patients admitted to ICU or having fatal outcome vs. those that were not. METHODS: Two wireless sensors continuously monitored (CM) respiratory rate (RR), heart rate (HR), and peripheral arterial oxygen saturation (SpO2 ). Frequency and duration of vital sign deviations were compared with point measurements performed by clinical staff according to regional guidelines, the National Early Warning Score (NEWS). RESULTS: SpO2 < 92% for more than 60 min was detected in 92% of the patients with CM vs. 40% with NEWS (p < .00001). RR > 24 breaths per minute for more than 5 min were detected in 70% with CM vs. 33% using NEWS (p = .0001). HR ≥ 111 for more than 60 min was seen in 51% with CM and 22% with NEWS (p = .0002). Patients admitted to ICU or having fatal outcome had longer durations of RR > 24 brpm (p = .01), RR > 21 brpm (p = .01), SpO2 < 80% (p = .01), and SpO2 < 85% (p = .02) compared to patients that were not. CONCLUSION: Episodes of desaturation and tachypnea in hospitalized patients with COVID-19 infection are common and often not detected by routine measurements.

Wireless Single-Lead versus Standard 12-Lead ECG, for ST-Segment Deviation during Adenosine Cardiac Stress Scintigraphy.

Wearable wireless electrocardiographic (ECG) monitoring is well-proven for arrythmia detection, but ischemia detection accuracy is not well-described. We aimed to assess the agreement of ST-segment deviation from single- versus 12-lead ECG and their accuracy for the detection of reversible ischemia. Bias and limits of agreement (LoA) were calculated between maximum deviations in ST segments from single- and 12-lead ECG during 82Rb PET-myocardial cardiac stress scintigraphy. Sensitivity and specificity for reversible anterior-lateral myocardial ischemia detection were assessed for both ECG methods, using perfusion imaging results as a reference. Out of 110 patients included, 93 were analyzed. The maximum difference between single- and 12-lead ECG was seen in II (-0.019 mV). The widest LoA was seen in V5, with an upper LoA of 0.145 mV (0.118 to 0.172) and a lower LoA of -0.155 mV (-0.182 to -0.128). Ischemia was seen in 24 patients. Single-lead and 12-lead ECG both had poor accuracy for the detection of reversible anterolateral ischemia during the test: single-lead ECG had a sensitivity of 8.3% (1.0-27.0%) and specificity of 89.9% (80.2-95.8%), and 12-lead ECG a sensitivity of 12.5% (3.0-34.4%) and a specificity of 91.3% (82.0-96.7%). In conclusion, agreement was within predefined acceptable criteria for ST deviations, and both methods had high specificity but poor sensitivity for the detection of anterolateral reversible ischemia. Additional studies must confirm these results and their clinical relevance, especially in the light of the poor sensitivity for detecting reversible anterolateral cardiac ischemia.

Quantifying physiological stability in the general ward using continuous vital signs monitoring: the circadian kernel density estimator.

Technological advances seen in recent years have introduced the possibility of changing the way hospitalized patients are monitored by abolishing the traditional track-and-trigger systems and implementing continuous monitoring using wearable biosensors. However, this new monitoring paradigm raise demand for novel ways of analyzing the data streams in real time. The aim of this study was to design a stability index using kernel density estimation (KDE) fitted to observations of physiological stability incorporating the patients' circadian rhythm. Continuous vital sign data was obtained from two observational studies with 491 postoperative patients and 200 patients with acute exacerbation of chronic obstructive pulmonary disease. We defined physiological stability as the last 24 h prior to discharge. We evaluated the model against periods of eight hours prior to events defined either as severe adverse events (SAE) or as a total score in the early warning score (EWS) protocol of ≥ 6, ≥ 8, or ≥ 10. The results found good discriminative properties between stable physiology and EWS-events (area under the receiver operating characteristics curve (AUROC): 0.772-0.993), but lower for the SAEs (AUROC: 0.594-0.611). The time of early warning for the EWS events were 2.8-5.5 h and 2.5 h for the SAEs. The results showed that for severe deviations in the vital signs, the circadian KDE model can alert multiple hours prior to deviations being noticed by the staff. Furthermore, the model shows good generalizability to another cohort and could be a simple way of continuously assessing patient deterioration in the general ward.

Deviations in continuously monitored electrodermal activity before severe clinical complications: a clinical prospective observational explorative cohort study.

Monitoring of high-risk patients in hospital wards is crucial in identifying and preventing clinical deterioration. Sympathetic nervous system activity measured continuously and non-invasively by Electrodermal activity (EDA) may relate to complications, but the clinical use remains untested. The aim of this study was to explore associations between deviations of EDA and subsequent serious adverse events (SAE). Patients admitted to general wards after major abdominal cancer surgery or with acute exacerbation of chronic obstructive pulmonary disease were continuously EDA-monitored for up to 5 days. We used time-perspectives consisting of 1, 3, 6, and 12 h of data prior to first SAE or from start of monitoring. We constructed 648 different EDA-derived features to assess EDA. The primary outcome was any SAE and secondary outcomes were respiratory, infectious, and cardiovascular SAEs. Associations were evaluated using logistic regressions with adjustment for relevant confounders. We included 714 patients and found a total of 192 statistically significant associations between EDA-derived features and clinical outcomes. 79% of these associations were EDA-derived features of absolute and relative increases in EDA and 14% were EDA-derived features with normalized EDA above a threshold. The highest F1-scores for primary outcome with the four time-perspectives were 20.7-32.8%, with precision ranging 34.9-38.6%, recall 14.7-29.4%, and specificity 83.1-91.4%. We identified statistically significant associations between specific deviations of EDA and subsequent SAE, and patterns of EDA may be developed to be considered indicators of upcoming clinical deterioration in high-risk patients.

Wireless Single-Lead ECG Monitoring to Detect New-Onset Postoperative Atrial Fibrillation in Patients After Major Noncardiac Surgery: A Prospective Observational Study.

BACKGROUND: New-onset postoperative atrial fibrillation (POAF) is associated with several cardiovascular complications and higher mortality. Several pathophysiological processes such as hypoxia can trigger POAF, but these are sparsely elucidated, and POAF is often asymptomatic. In patients undergoing major gastrointestinal cancer surgery, we aimed to describe the frequency of POAF as automatically estimated and detected via wireless repeated sampling monitoring and secondarily to describe the association between preceding vital sign deviations and POAF. METHOD: Patients ≥60 years of age undergoing major gastrointestinal cancer surgery were continuously monitored for up to 4 days postoperatively. Electrocardiograms were obtained every minute throughout the monitoring period. Clinical staff were blinded to all measurements. As for the primary outcome, POAF was defined as 30 consecutive minutes or more detected by a purpose-built computerized algorithm and validated by cardiologists. The primary exposure variable was any episode of peripheral oxygen saturation (Spo2) <85% for >5 consecutive minutes before POAF. RESULTS: A total of 30,145 hours of monitoring was performed in 398 patients, with a median of 92 hours per patient (interquartile range [IQR], 54-96). POAF was detected in 26 patients (6.5%; 95% confidence interval [CI], 4.5-9.4) compared with 14 (3.5%; 95% CI, 1.94-5.83) discovered by clinical staff in the monitoring period. POAF was followed by 9.4 days hospitalization (IQR, 6.5-16) versus 6.5 days (IQR, 2.5-11) in patients without POAF. Preceding episodes of Spo2 <85% for >5 minutes (OR, 1.02; 95% CI, 0.24-4.00; P = .98) or other vital sign deviations were not significantly associated with POAF. CONCLUSIONS: New-onset POAF occurred in 6.5% (95% CI, 4.5-9.4) of patients after major gastrointestinal cancer surgery, and 1 in 3 cases was not detected by the clinical staff (35%; 95% CI, 17-56). POAF was not preceded by vital sign deviations.

Continuously monitored vital signs for detection of myocardial injury in high-risk patients - An observational study.

BACKGROUND: Patients are at risk of myocardial injury after major non-cardiac surgery and during acute illness. Myocardial injury is associated with mortality, but often asymptomatic and currently detected through intermittent cardiac biomarker screening. This delays diagnosis, where vital signs deviations may serve as a proxy for early signs of myocardial injury. This study aimed to assess the association between continuous monitored vital sign deviations and subsequent myocardial injury following major abdominal cancer surgery and during acute exacerbation of chronic obstructive pulmonary disease. METHODS: Patients undergoing major abdominal cancer surgery or admitted with acute exacerbation of chronic obstructive pulmonary disease had daily troponin measurements. Continuous wireless monitoring of several vital signs was performed for up to 96 h after admission or surgery. The primary exposure was cumulative duration of peripheral oxygen saturation (SpO2 ) below 85% in the 24 h before the primary outcome of myocardial injury, defined as a new onset ischaemic troponin elevation assessed daily. If no myocardial injury occurred, the primary exposure was based on the first 24 h of measurement. RESULTS: A total of 662 patients were continuously monitored and 113 (17%) had a myocardial injury. Cumulative duration of SpO2  < 85% was significantly associated with myocardial injury (mean difference 14.2 min [95% confidence interval -4.7 to 33.1 min]; p = .005). Durations of hypoxaemia (SpO2  < 88% and SpO2  < 80%), tachycardia (HR > 110 bpm and HR > 130 bpm) and tachypnoea (RR > 24 min-1 and RR > 30 min-1 ) were also significantly associated with myocardial injury (p < .04, for all). CONCLUSION: Duration of severely low SpO2 detected by continuous wireless monitoring is significantly associated with myocardial injury in high-risk patients admitted to hospital wards. The effect of early detection and interventions should be assessed next.

Continuous monitoring of vital sign abnormalities; association to clinical complications in 500 postoperative patients.

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.

Machine learning classifiers do not improve prediction of hospitalization > 2 days after fast-track hip and knee arthroplasty compared with a classical statistical risk model.

Background and purpose: Prediction of postoperative outcomes and length of hospital stay (LOS) of patients is vital for allocation of healthcare resources. We investigated the performance of prediction models based on machinelearning algorithms compared with a previous risk stratification model using traditional multiple logistic regression, for predicting the risk of a LOS of > 2 days after fast-track total hip and knee replacement. Patients and methods: 3 different machine learning classifiers were trained on data from the Lundbeck Centre for Fast-track Hip and Knee Replacement Database (LCDB) collected from 9,512 patients between 2016 and 2017. The chosen classifiers were a random forest classifier (RF), a support vector machine classifier with a polynomial kernel (SVM), and a multinomial Naïve-Bayes classifier (NB). Results: Comparing performance measures of the classifiers with the traditional model revealed that all the models had a similar performance in terms of F1 score, accuracy, sensitivity, specificity, area under the receiver operating curve (AUC), and area under the precision-recall curve (AUPRC). A feature importance analysis of the RF classifier found hospital, age, use of walking aid, living alone, and joint operated on to be the most relevant input features. None of the classifiers reached a clinically relevant performance with the input data from the LCDB. Interpretation: Despite the promising prospects of machine-learning practices for disease and risk prediction, none of the machine learning models tested outperformed the traditional multiple regression model in predicting which patients in this cohort had a LOS > 2 days.

Continuous peripheral perfusion index in patients admitted to hospital wards - An observational study.

INTRODUCTION: Risk patients admitted to hospital wards may quickly develop haemodynamic deterioration and early recognition has high priority to allow preventive intervention. The peripheral perfusion index (PPI) may be an indicator of circulatory distress by assessing peripheral perfusion non-invasively from photoplethysmography. We aimed to describe the characteristics of PPI in hospitalized patients since this is not well-studied. MATERIALS AND METHODS: Patients admitted due to either acute exacerbation of chronic obstructive pulmonary disease (AECOPD) or after major abdominal cancer surgery were included in this study. Patients were monitored continuously up to 96 hours with a pulse oximeter. Comparisons between median PPI each day, time of day and admission type were described with mean difference (MD) and were analysed using Wilcoxon rank sum test and related to morbidity and mortality. RESULTS: PPI data from 291 patients were recorded for a total of 9279 hours. Median PPI fell from 1.4 (inter quartile range, IQR 0.9-2.3) on day 1 to 1.0 (IQR 0.6-1.6) on day 4. Significant differences occurred between PPI day vs evening (MD = 0.18, 95% CI 0.16-0.20, P = .028), day vs night (MD = 0.56, 95% CI 0.49-0.62, P < .0001) and evening vs night (MD = 0.38, 95% CI 0.33-0.42, P = .002). No significant difference in median PPI between AECOPD and surgical patients was found (MD = 0.15, 95% CI -0.08-0.38, P = .62). CONCLUSION: Lower PPI during daytime vs evening and night-time were seen for both populations. The highest frequency of serious adverse events and mortality was seen among patients with low median PPI. The clinical impact of PPI monitoring needs further confirmation.

Physiological abnormalities in patients admitted with acute exacerbation of COPD: an observational study with continuous monitoring.

Acute exacerbations of chronic obstructive pulmonary disease (AECOPD) may rapidly require intensive care treatment. Evaluation of vital signs is necessary to detect physiological abnormalities (micro events), but patients may deteriorate between measurements. We aimed to assess if continuous monitoring of vital signs in patients admitted with AECOPD detects micro events more often than routine ward rounds. In this observational pilot study (NCT03467815), 30 adult patients admitted with AECOPD were included. Patients were continuously monitored with peripheral oxygen saturation (SpO2), heart rate, and respiratory rate during the first 4 days after admission. Hypoxaemic events were defined as decreased SpO2 for at least 60 s. Non-invasive blood pressure was also measured every 15-60 min. Clinical ward staff measured vital signs as part of Early Warning Score (EWS). Data were analysed using Fisher's exact test or Wilcoxon rank sum test. Continuous monitoring detected episodes of SpO2 < 92% in 97% versus 43% detected by conventional EWS (p < 0.0001). Events of SpO2 < 88% was detected in 90% with continuous monitoring compared with 13% with EWS (p < 0.0001). Sixty-three percent of patients had episodes of SpO2 < 80% recorded by continuous monitoring and 17% had events lasting longer than 10 min. No events of SpO2 < 80% was detected by EWS. Micro events of tachycardia, tachypnoea, and bradypnoea were also more frequently detected by continuous monitoring (p < 0.02 for all). Moderate and severe episodes of desaturation and other cardiopulmonary micro events during hospitalization for AECOPD are common and most often not detected by EWS.

Pharmaco-electroencephalographic responses in the rat differ between active and inactive locomotor states.

Quantitative electroencephalography from freely moving rats is commonly used as a translational tool for predicting drug-effects in humans. We hypothesized that drug-effects may be expressed differently depending on whether the rat is in active locomotion or sitting still during recording sessions, and proposed automatic state-detection as a viable tool for estimating drug-effects free of hypo-/hyperlocomotion-induced effects. We aimed at developing a fully automatic and validated method for detecting two behavioural states: active and inactive, in one-second intervals and to use the method for evaluating ketamine, DOI, d-cycloserine, d-amphetamine, and diazepam effects specifically within each state. The developed state-detector attained high precision with more than 90% of the detected time correctly classified, and multiple differences between the two detected states were discovered. Ketamine-induced delta activity was found specifically related to locomotion. Ketamine and DOI suppressed theta and beta oscillations exclusively during inactivity. Characteristic gamma and high-frequency oscillations (HFO) enhancements of the NMDAR and 5HT2A modulators, speculated associated with locomotion, were profound and often largest during the inactive state. State-specific analyses, theoretically eliminating biases from altered occurrence of locomotion, revealed only few effects of d-amphetamine and diazepam. Overall, drug-effects were most abundant in the inactive state. In conclusion, this new validated and automatic locomotion state-detection method enables fast and reliable state-specific analysis facilitating discovery of state-dependent drug-effects and control for altered occurrence of locomotion. This may ultimately lead to better cross-species translation of electrophysiological effects of pharmacological modulations.

Sleep efficiency and neurophysiological patterns in middle-aged men are associated with cognitive change over their adult life course.

Disrupted sleep is a contributing factor to cognitive ageing, while also being associated with neurodegenerative disorders. Little is known, however, about the relation of sleep and the gradual cognitive changes over the adult life course. Sleep electroencephalogram (EEG) patterns are potential markers of the cognitive progress. To test this hypothesis, we assessed sleep architecture and EEG of 167 men born in the Copenhagen Metropolitan Area in 1953, who, based on individual cognitive testing from early (~18 years) to late adulthood (~58 years), were divided into 85 subjects with negative and 82 with positive cognitive change over their adult life. Participants underwent standard polysomnography, including manual sleep scoring at age ~58 years. Features of sleep macrostructure were combined with a number of EEG features to distinguish between the two groups. EEG rhythmicity was assessed by spectral power analysis in frontal, central and occipital sites. Functional connectivity was measured by inter-hemispheric EEG coherence. Group differences were assessed by analysis of covariance (p < 0.05), including education and severity of depression as potential covariates. Subjects with cognitive decline exhibited lower sleep efficiency, reduced inter-hemispheric connectivity during rapid eye movement (REM) sleep, and slower EEG rhythms during stage 2 non-REM sleep. Individually, none of these tendencies remained significant after multiple test correction; however, by combining them in a machine learning approach, the groups were separated with 72% accuracy (75% sensitivity, 67% specificity). Ongoing medical screenings are required to confirm the potential of sleep efficiency and sleep EEG patterns as signs of individual cognitive progress.

External validation of a data-driven algorithm for muscular activity identification during sleep.

Several automated methods for scoring periodic limb movements during sleep (PLMS) and rapid eye movement (REM) sleep without atonia (RSWA) have been proposed, but most of them were developed and validated on data recorded in the same clinic, thus they may be biased. This work aims to validate our data-driven algorithm for muscular activity detection during sleep, originally developed based on data recorded and manually scored at the Danish Center for Sleep Medicine. The validation was carried out on a cohort of 240 participants, including de novo Parkinson's disease (PD) patients and neurologically healthy controls, whose sleep data were recorded and manually evaluated at Paracelsus-Elena Klinik, Kassel, Germany. In the German cohort, the algorithm showed generally good agreement between manual and automated PLMS indices, and identified with 88.75% accuracy participants with PLMS index above 15 PLMS per hour of sleep, and with 84.17% accuracy patients suffering from REM sleep behaviour disorder (RBD) showing RSWA. By comparing the algorithm performances in the Danish and German cohorts, we hypothesized that inter-clinical differences may exist in the way limb movements are manually scored and how healthy controls are defined. Finally, the algorithm performed worse in PD patients, probably as a result of increased artefacts caused by abnormal motor events related to neurodegeneration. Our algorithm can identify, with reasonable performance, participants with RBD and increased PLMS index from data recorded in different centres, and its application may reveal inter clinical differences, which can be overcome in the future by applying automated methods.

Sleep-spindle detection: crowdsourcing and evaluating performance of experts, non-experts and automated methods.

Sleep spindles are discrete, intermittent patterns of brain activity observed in human electroencephalographic data. Increasingly, these oscillations are of biological and clinical interest because of their role in development, learning and neurological disorders. We used an Internet interface to crowdsource spindle identification by human experts and non-experts, and we compared their performance with that of automated detection algorithms in data from middle- to older-aged subjects from the general population. We also refined methods for forming group consensus and evaluating the performance of event detectors in physiological data such as electroencephalographic recordings from polysomnography. Compared to the expert group consensus gold standard, the highest performance was by individual experts and the non-expert group consensus, followed by automated spindle detectors. This analysis showed that crowdsourcing the scoring of sleep data is an efficient method to collect large data sets, even for difficult tasks such as spindle identification. Further refinements to spindle detection algorithms are needed for middle- to older-aged subjects.

A deep transfer learning approach for sleep stage classification and sleep apnea detection using wrist-worn consumer sleep technologies.

Obstructive sleep apnea (OSA) is a common, underdiagnosed sleep-related breathing disorder with serious health implications Objective - We propose a deep transfer learning approach for sleep stage classification and sleep apnea (SA) detection using wrist-worn consumer sleep technologies (CST). Methods - Our model is based on a deep convolutional neural network (DNN) utilizing accelerometers and photo-plethysmography signals from nocturnal recordings. The DNN was trained and tested on internal datasets that include raw data from clinical and wrist-worn devices; external validation was performed on a hold-out test dataset containing raw data from a wrist-worn CST. Results - Training on clinical data improves performance significantly, and feature enrichment through a sleep stage stream gives only minor improvements. Raw data input outperforms feature-based input in CST datasets. The system generalizes well but performs slightly worse on wearable device data compared to clinical data. However, it excels in detecting events during REM sleep and is associated with arousal and oxygen desaturation. We found; cases that were significantly underestimated were characterized by fewer of such event associations. Conclusion - This study showcases the potential of using CSTs as alternate screening solution for undiagnosed cases of OSA. Significance - This work is significant for its development of a deep transfer learning approach using wrist-worn consumer sleep technologies, offering comprehensive validation for data utilization, and learning techniques, ultimately improving sleep apnea detection across diverse devices.

MSED: A Multi-Modal Sleep Event Detection Model for Clinical Sleep Analysis.

Clinical sleep analysis require manual analysis of sleep patterns for correct diagnosis of sleep disorders. However, several studies have shown significant variability in manual scoring of clinically relevant discrete sleep events, such as arousals, leg movements, and sleep disordered breathing (apneas and hypopneas). We investigated whether an automatic method could be used for event detection and if a model trained on all events (joint model) performed better than corresponding event-specific models (single-event models). We trained a deep neural network event detection model on 1653 individual recordings and tested the optimized model on 1000 separate hold-out recordings. F1 scores for the optimized joint detection model were 0.70, 0.63, and 0.62 for arousals, leg movements, and sleep disordered breathing, respectively, compared to 0.65, 0.61, and 0.60 for the optimized single-event models. Index values computed from detected events correlated positively with manual annotations (r2 = 0.73, r2 = 0.77, r2 = 0.78, respectively). We furthermore quantified model accuracy based on temporal difference metrics, which improved overall by using the joint model compared to single-event models. Our automatic model jointly detects arousals, leg movements and sleep disordered breathing events with high correlation with human annotations. Finally, we benchmark against previous state-of-the-art multi-event detection models and found an overall increase in F1 score with our proposed model despite a 97.5% reduction in model size.

Remote Estimation of Peripheral Oxygen Saturation and Pulse Rate From Facial Analysis Using a Smartphone Camera.

Vital sign monitoring is an invaluable tool for healthcare professionals, both in the hospital and at home. Traditional measurement devices provide accurate readings but require physical contact with the patient which often is unsuitable, furthermore contact-based devices have been reported to fail by loosing contact due to movement as severe events occur, therefore, a contactless method is necessary.We hypothesize that, in ideal scenarios, it is possible to estimate both SpO2 and pulse rate using only facial video recorded with a smartphone's front-facing camera. To test this hypothesis, a dataset of 10 healthy subjects performing various breathing patterns while being recorded with a smartphone camera was collected during ideal lighting conditions.Using advanced image and signal processing methods to acquire remote photoplethysmography (rPPG) estimates from a patient's forehead, our proposed method can achieve SpO2 estimation results with Arms = 1.34% (accuracy RMS) and MAE ± STD = 1.26 ± 0.68% (mean average error) across a SpO2 range of 92% to 99% (percentage point SpO2) and pulse rate estimation results with Arms = 3.91 bpm (beats per minute) and MAE ± STD = 3.24±2.11 bpm across a pulse rate range of 60 bpm to 90 bpm. We conclude from these results, that remote vital sign estimation using facial videos recorded entirely with a smartphone camera is possible.

SViT: A Spectral Vision Transformer for the Detection of REM Sleep Behavior Disorder.

REM sleep behavior disorder (RBD) is a parasomnia with dream enactment and presence of REM sleep without atonia (RSWA). RBD diagnosed manually via polysomnography (PSG) scoring, which is time intensive. Isolated RBD (iRBD) is also associated with a high probability of conversion to Parkinson's disease. Diagnosis of iRBD is largely based on clinical evaluation and subjective PSG ratings of REM sleep without atonia. Here we show the first application of a novel spectral vision transformer (SViT) to PSG signals for detection of RBD and compare the results to the more conventional convolutional neural network architecture. The vision-based deep learning models were applied to scalograms (30 or 300 s windows) of the PSG data (EEG, EMG and EOG) and the predictions interpreted. A total of 153 RBD (96 iRBD and 57 RBD with PD) and 190 controls were included in the study and 5-fold bagged ensemble was used. Model outputs were analyzed per-patient (averaged), with regards to sleep stage, and the SViT was interpreted using integrated gradients. Models had a similar per-epoch test F1 score. However, the vision transformer had the best per-patient performance, with an F1 score 0.87. Training the SViT on channel subsets, it achieved an F1 score of 0.93 on a combination of EEG and EOG. EMG is thought to have the highest diagnostic yield, but interpretation of our model showed that high relevance was placed on EEG and EOG, indicating these channels could be included for diagnosing RBD.