Clinical review: a review and analysis of heart rate variability and the diagnosis and prognosis of infection

Evaluation of Machine Learning to Detect Influenza Using Wearable Sensor Data and Patient-Reported Symptoms: Cohort Study

BACKGROUND

Machine learning offers quantitative pattern recognition analysis of wearable device data and has the potential to detect illness onset and monitor influenza-like illness (ILI) in patients who are infected.

OBJECTIVE

This study aims to evaluate the ability of machine-learning algorithms to distinguish between participants who are influenza positive and influenza negative in a cohort of symptomatic patients with ILI using wearable sensor (activity) data and self-reported symptom data during the latent and early symptomatic periods of ILI.

METHODS

This prospective observational cohort study used the extreme gradient boosting (XGBoost) classifier to determine whether a participant was influenza positive or negative based on 3 models using symptom-only data, activity-only data, and combined symptom and activity data. Data were collected from the Home Testing of Respiratory Illness (HTRI) study and FluStudy2020, both conducted between December 2019 and October 2020. The model was developed using the FluStudy2020 data and tested on the HTRI data. Analyses included participants in these studies with an at-home influenza diagnostic test result. Fitbit (Google LLC) devices were used to measure participants' steps, heart rate, and sleep parameters. Participants detailed their ILI symptoms, health care-seeking behaviors, and quality of life. Model performance was assessed by area under the curve (AUC), balanced accuracy, recall (sensitivity), specificity, precision (positive predictive value), negative predictive value, and weighted harmonic mean of precision and recall (F2) score.

RESULTS

An influenza diagnostic test result was available for 953 and 925 participants in HTRI and FluStudy2020, respectively, of whom 848 (89%) and 840 (90.8%) had activity data. For the training and validation sets, the highest performing model was trained on the combined symptom and activity data (training AUC=0.77; validation AUC=0.74) versus symptom-only (training AUC=0.73; validation AUC=0.72) and activity-only (training AUC=0.68; validation AUC=0.65) data. For the FluStudy2020 test set, the performance of the model trained on combined symptom and activity data was closely aligned with that of the symptom-only model (combined symptom and activity test AUC=0.74; symptom-only test AUC=0.74). These results were validated using independent HTRI data (combined symptom and activity evaluation AUC=0.75; symptom-only evaluation AUC=0.74). The top features guiding influenza detection were cough; mean resting heart rate during main sleep; fever; total minutes in bed for the combined model; and fever, cough, and sore throat for the symptom-only model.

CONCLUSIONS

Machine-learning algorithms had moderate accuracy in detecting influenza, suggesting that previous findings from research-grade sensors tested in highly controlled experimental settings may not easily translate to scalable commercial-grade sensors. In the future, more advanced wearable sensors may improve their performance in the early detection and discrimination of viral respiratory infections.

Continuous Monitoring of Heart Rate Variability in Free-Living Conditions Using Wearable Sensors: Exploratory Observational Study

BACKGROUND

Wearable physiological monitoring devices are promising tools for remote monitoring and early detection of potential health changes of interest. The widespread adoption of such an approach across communities and over long periods of time will require an automated data platform for collecting, processing, and analyzing relevant health information.

OBJECTIVE

In this study, we explore prospective monitoring of individual health through an automated data collection, metrics extraction, and health anomaly analysis pipeline in free-living conditions over a continuous monitoring period of several months with a focus on viral respiratory infections, such as influenza or COVID-19.

METHODS

A total of 59 participants provided smartwatch data and health symptom and illness reports daily over an 8-month window. Physiological and activity data from photoplethysmography sensors, including high-resolution interbeat interval (IBI) and step counts, were uploaded directly from Garmin Fenix 6 smartwatches and processed automatically in the cloud using a stand-alone, open-source analytical engine. Health risk scores were computed based on a deviation in heart rate and heart rate variability metrics from each individual's activity-matched baseline values, and scores exceeding a predefined threshold were checked for corresponding symptoms or illness reports. Conversely, reports of viral respiratory illnesses in health survey responses were also checked for corresponding changes in health risk scores to qualitatively assess the risk score as an indicator of acute respiratory health anomalies.

RESULTS

The median average percentage of sensor data provided per day indicating smartwatch wear compliance was 70%, and survey responses indicating health reporting compliance was 46%. A total of 29 elevated health risk scores were detected, of which 12 (41%) had concurrent survey data and indicated a health symptom or illness. A total of 21 influenza or COVID-19 illnesses were reported by study participants; 9 (43%) of these reports had concurrent smartwatch data, of which 6 (67%) had an increase in health risk score.

CONCLUSIONS

We demonstrate a protocol for data collection, extraction of heart rate and heart rate variability metrics, and prospective analysis that is compatible with near real-time health assessment using wearable sensors for continuous monitoring. The modular platform for data collection and analysis allows for a choice of different wearable sensors and algorithms. Here, we demonstrate its implementation in the collection of high-fidelity IBI data from Garmin Fenix 6 smartwatches worn by individuals in free-living conditions, and the prospective, near real-time analysis of the data, culminating in the calculation of health risk scores. To our knowledge, this study demonstrates for the first time the feasibility of measuring high-resolution heart IBI and step count using smartwatches in near real time for respiratory illness detection over a long-term monitoring period in free-living conditions.

Cardiovascular Autonomic Dysfunction in Hospitalized Patients with a Bacterial Infection: A Longitudinal Observational Pilot Study in the UK

PURPOSE

A temporal reduction in the cardiovascular autonomic responses predisposes patients to cardiovascular instability after a viral infection and therefore increases the risk of associated complications. These findings have not been replicated in a bacterial infection. This pilot study will explore the prevalence of cardiovascular autonomic dysfunction (CAD) in hospitalized patients with a bacterial infection.

METHODS

A longitudinal observational pilot study was conducted. Fifty participants were included: 13 and 37 participants in the infection group and healthy group, respectively. Recruitment and data collection were carried out during a two-year period. Participants were followed up for 6 weeks: all participants' cardiovascular function was assessed at baseline (week 1) and reassessed subsequently at week 6 so that the progression of the autonomic function could be evaluated over that period of time. The collected data were thereafter analyzed using STATA/SE version 16.1 (StataCorp). The Fisher Exact test, McNemar exact test, Mann-Whitney test and Wilcoxon test were used for data analysis.

RESULTS

32.4% of the participants in the healthy group were males (n = 12) and 67.6% were females (n = 25). Participants' age ranged from 33 years old to 76 years old with the majority being 40-60 years of age (62.1%) (Mean age 52.4 SD = 11.4). Heart rate variability (HRV) in response to Valsalva Maneuver, metronome breathing, standing and sustained handgrip in the infection group was lower than in the healthy group throughout the weeks. Moreover, both the HRV in response to metronome breathing and standing up showed a statistically significant difference when the mean values were compared between both groups in week 1 (p = 0.03 and p = 0.013). The prevalence of CAD was significantly higher in the infection group compared to healthy volunteers, both at the beginning of the study (p = 0.018) and at the end of follow up (p = 0.057), when all patients had been discharged.

CONCLUSIONS

CAD, as assessed by the HRV, is a common finding during the recovery period of a bacterial infection, even after 6 weeks post-hospital admission. This may increase the risk of complications and cardiovascular instability. It may therefore be of value to conduct a wider scale study to further evaluate this aspect so recommendations can be made for the cardiovascular autonomic assessment of patients while they are recovering from a bacterial infectious process.

COVID-19 surveillance based on consumer wearable devices

Background

Consumer wearable devices such as wristbands and smartwatches have potential application value in communicable disease surveillance.

Objective

We investigated the ability of wearable devices to monitor COVID-19 patients of varying severity.

Methods

COVID-19 patients with mobile phones supporting wearable device applications were selected from Dalian Sixth People Hospital. Physiological parameters from the wearable devices and electronic questionnaires were collected from the device wearing until 14 days post-discharge. Clinical information during hospitalization was also recorded. Based on imaging data, the patients were categorized into the milder group without pneumonia and the more severe group with pneumonia. We plotted the curves of the physiological parameters of the two groups to compare the differences and changes.

Results

Ninety-eight patients were included in the analysis. The mean age was 39.6 ± 10.5 years, including 45 males (45.9%). There were 24 asymptomatic patients, 10 mild patients, 60 moderate patients, and 4 severe patients. Compared with the milder group, the more severe group had higher heart rate-related parameters, while the heart rate variability (HRV) was the opposite. In the more severe group, the heart rate-related parameters showed a downward trend from 0 to 7 days after the fever resolution. Among them, the resting heart rate and sleep heart rate decreased on the 25th day after the onset and were close to the milder group 1 week after discharge.

Conclusions

Consumer wearable devices have the potential to monitor respiratory infections. Heart rate-related parameters obtained from these devices can be sensitive indicators of COVID-19 severity and correlate with disease evolution.

Trial registration

ClinicalTrials.gov NCT04459637.

Machine learning-based clinical decision support for infection risk prediction

Background

Healthcare-associated infection (HAI) remains a significant risk for hospitalized patients and a challenging burden for the healthcare system. This study presents a clinical decision support tool that can be used in clinical workflows to proactively engage secondary assessments of pre-symptomatic and at-risk infection patients, thereby enabling earlier diagnosis and treatment.

Methods

This study applies machine learning, specifically ensemble-based boosted decision trees, on large retrospective hospital datasets to develop an infection risk score that predicts infection before obvious symptoms present. We extracted a stratified machine learning dataset of 36,782 healthcare-associated infection patients. The model leveraged vital signs, laboratory measurements and demographics to predict HAI before clinical suspicion, defined as the order of a microbiology test or administration of antibiotics.

Results

Our best performing infection risk model achieves a cross-validated AUC of 0.88 at 1 h before clinical suspicion and maintains an AUC >0.85 for 48 h before suspicion by aggregating information across demographics and a set of 163 vital signs and laboratory measurements. A second model trained on a reduced feature space comprising demographics and the 36 most frequently measured vital signs and laboratory measurements can still achieve an AUC of 0.86 at 1 h before clinical suspicion. These results compare favorably against using temperature alone and clinical rules such as the quick sequential organ failure assessment (qSOFA) score. Along with the performance results, we also provide an analysis of model interpretability via feature importance rankings.

Conclusion

The predictive model aggregates information from multiple physiological parameters such as vital signs and laboratory measurements to provide a continuous risk score of infection that can be deployed in hospitals to provide advance warning of patient deterioration.

Prognostic implications of ultra-short heart rate variability indices in hospitalized patients with infective endocarditis

BACKGROUND

Infective endocarditis (IE) is a disease that poses a serious health risk. It is important to identify high-risk patients early in the course of their treatment. In the current study, we evaluated the prognostic value of ultra-short heart-rate variability (HRV), an index of vagal nerve activity, in IE.

METHODS

Retrospective analysis was performed on adult patients admitted to a tertiary hospital due to IE. A logistic regression (LR) was used to determine whether clinical, laboratory, and HRV parameters were predictive of specific clinical features (valve type, staphylococcal infection) or severe short-term complications (cardiac, metastatic infection, and death). The accuracy of the model was evaluated through the measurement of the area under the curve (AUC) of the receiver operating characteristic curve (ROC). An analysis of survival was conducted using Cox regression. A number of HRV indices were calculated, including the standard deviation of normal heart-beat intervals (SDNN) and the root mean square of successive differences (RMSSD).

RESULTS

75 patients, aged 60.3(±18.6) years old, were examined. When compared with published age- and gender-adjusted HRV norms, SDNN and RMSSD were found to be relatively low in our cohort (75%-76% lower than the median; 33%-41% lower than the 2nd percentile). 26(34.6%) patients developed a metastatic infection, with RMSSD<7.03ms (adjusted odds ratio (aOR) 9.340, p = 0.002), incorporated in a multivariate LR model (AUC 0.833). Furthermore, 27(36.0%) patients were diagnosed with Staphylococcus IE, with SDNN<4.92ms (aOR 5.235, p = 0.004), a major component of the multivariate LR model (AUC 0.741). Multivariate Cox regression survival model, included RMSSD (HR 1.008, p = 0.012).

CONCLUSION

SDNN, and particularly RMSSD, derived from ultra-short ECG recordings, may provide prognostic information about patients presenting with IE.

THE ASSOCIATION BETWEEN SYSTOLIC BLOOD PRESSURE AND HEART RATE IN EMERGENCY DEPARTMENT PATIENTS: A MULTICENTER COHORT STUDY

BACKGROUND

Guidelines and textbooks assert that tachycardia is an early and reliable sign of hypotension, and an increased heart rate (HR) is believed to be an early warning sign for the development of shock, although this response may change by aging, pain, and stress.

OBJECTIVE

To assess the unadjusted and adjusted associations between systolic blood pressure (SBP) and HR in emergency department (ED) patients of different age categories (18-50 years; 50-80 years; > 80 years).

METHODS

A multicenter cohort study using the Netherlands Emergency department Evaluation Database (NEED) including all ED patients ≥ 18 years from three hospitals in whom HR and SBP were registered at arrival to the ED. Findings were validated in a Danish cohort including ED patients. In addition, a separate cohort was used including ED patients with a suspected infection who were hospitalized from whom measurement of SBP and HR were available prior to, during, and after ED treatment. Associations between SBP and HR were visualized and quantified with scatterplots and regression coefficients (95% confidence interval [CI]).

RESULTS

A total of 81,750 ED patients were included from the NEED, and a total of 2358 patients with a suspected infection. No associations were found between SBP and HR in any age category (18-50 years: -0.03 beats/min/10 mm Hg, 95% CI -0.13-0.07, 51-80 years: -0.43 beats/min/10 mm Hg, 95% CI -0.38 to -0.50, > 80 years: -0.61 beats/min/10 mm Hg, 95% CI -0.53 to -0.71), nor in different subgroups of ED patient. No increase in HR existed with a decreasing SBP during ED treatment in ED patients with a suspected infection.

CONCLUSION

No association between SBP and HR existed in ED patients of any age category, nor in ED patients who were hospitalized with a suspected infection, even during and after ED treatment. Emergency physicians may be misled by traditional concepts about HR disturbances because tachycardia may be absent in hypotension.

Enabling health potential: exploring nonlinear and complex results of osteopathic manual medicine through complex systems theory

Osteopathic medicine is a holistic, patient-specific approach. Explaining the impact of osteopathic manipulative medicine (OMM) has been problematic because many of its effects are nonlinear. Complex systems theory (CST) is explored as a mechanism of understanding the interplay of the body's anatomy and physiology, an illness process, and the effects of OMM. Tensegrity is discussed as an example of an emergent property of the body's systems that affects not only biomechanics but also pathophysiology. Previous explanations of osteopathic philosophy are reviewed. The Host + Disease=Illness paradigm is a way to think through the impact of host and disease factors on an illness state, and how targeted interventions may affect the illness. The Osteopathic 5 Models are another way to view the body's complexity. The area of greatest restriction (AGR) screen can be understood to direct OMM in a way that respects complexity and enables asymmetric and nonlocal results to realize health potential. The impact of this framework is in coherently explaining the impact of osteopathic philosophy and OMM and exploring new approaches to research.

Application of probability theory to neonatal cardiac evaluation

Based on probability theory, a methodology that allows diagnosing neonatal cardiac dynamics was previously developed; however, diagnostic applications of this method are required to validate it to the neonatal cardiac dynamics was conducted, allowing to differentiate normal from pathological dynamics. The hourly maximum and minimum heart rate values from 39 continuous and ambulatory electrocardiographic records with a minimum length of 21 hours were taken, from newborns between 0 and 10 days of life, 9 clinically within normality limits and 30 with cardiac pathologies. The probability of occurrence of heart rates in ranges of 5 beats/minute was calculated. The distributions of probability were analysed, and finally the diagnosis was determined by the physical-mathematical methodology. Then, a statistical validation of sensitivity, specificity, and diagnostic agreement was performed. Normal registries showed probability distributions with absent or minimal presence of heart rates of the ranges between 125 and 135 beats/minute, while the abnormal ones had values within these ranges, as well as absence or minimal presence of heart rates from 75 beats/minute to 85 beats/minute. The sensitivity and specificity were 100%, and the Kappa coefficient had a value of 1. Hereby, it is concluded that through an application of a physical-mathematical methodology of neonatal cardiac diagnosis, it is possible to differentiate normality from disease.

Prediction of intrapartum fever using continuously monitored vital signs and heart rate variability

Objectives

Neonatal early onset sepsis (EOS), bacterial infection during the first seven days of life, is difficult to diagnose because presenting signs are non-specific, but early diagnosis before birth can direct life-saving treatment for mother and baby. Specifically, maternal fever during labor from placental infection is the strongest predictor of EOS. Alterations in maternal heart rate variability (HRV) may precede development of intrapartum fever, enabling incipient EOS detection. The objective of this work was to build a predictive model for intrapartum fever.

Methods

Continuously measured temperature, heart rate, and beat-to-beat RR intervals were obtained from wireless sensors on women (n = 141) in labor; traditional manual vital signs were taken every 3-6 hours. Validated measures of HRV were calculated in moving 5-minute windows of RR intervals: standard deviation of normal-to-normal intervals (SDNN) and root mean square of successive differences (RMSSD) between normal heartbeats.

Results

Fever (>38.0 °C) was detected by manual or continuous measurements in 48 women. Compared to afebrile mothers, average SDNN and RMSSD in febrile mothers decreased significantly (p < 0.001) at 2 and 3 hours before fever onset, respectively. This observed HRV divergence and raw recorded vitals were applied to a logistic regression model at various time horizons, up to 4-5 hours before fever onset. Model performance increased with decreasing time horizons, and a model built using continuous vital signs as input variables consistently outperformed a model built from episodic vital signs.

Conclusions

HRV-based predictive models could identify mothers at risk for fever and infants at risk for EOS, guiding maternal antibiotic prophylaxis and neonatal monitoring.

Combination of Interleukin-6, C-Reactive Protein and Procalcitonin Values as Predictive Index of Sepsis in Course of Fever Episode in Adult Haematological Patients: Observational and Statistical Study

Haematological patients represent a vulnerable population to opportunistic infections, mainly due to the disease itself and chemotherapy-induced neutropenia. The level of immune suppression strongly increases the importance of timely antibiotic treatment in order to prevent sepsis-related mortality. During the initial fever episode, serum biomarkers are usually used to estimate the probability of blood stream infection prior to the results of microbial diagnosis. A new serum biomarker combination study on a febrile haematological population, including C-reactive protein (CRP), interleukin-6 (IL-6) and procalcitonin (PCT), is proposed in order to improve their predictive accuracy. In our prospective study, CRP, IL-6 and PCT were evaluated in 34 immunosuppressed haematological patients immediately after the onset of 51 fever episodes, either during the course of standard chemotherapy or high-dose chemotherapy and autologous stem cell transplant. The fever episodes were divided into documented infections and fever alone. Receiver operating characteristic analysis (ROC) was performed for each biomarker and a combination of all three biomarkers (multiROC) to define a new predictive index. Significant differences were evidenced between the two groups (documented infection and no infection) for both PCT and IL-6 (p = 0.03 and p = 0.035, respectively), but none for CRP (p = 0.1). The composite parameter is more reliable than any single biomarker alone, with an area under the curve (AUC) of 79% and with high sensitivity and specificity. IL-6 gave the closest response compared to the composite index. Composite parameters of serum biomarkers could be used for an early diagnosis of infection at fever onset in haematological patients.

Autonomic Dysfunction during Acute SARS-CoV-2 Infection: A Systematic Review

Although autonomic dysfunction (AD) after the recovery from Coronavirus disease 2019 (COVID-19) has been thoroughly described, few data are available regarding the involvement of the autonomic nervous system (ANS) during the acute phase of SARS-CoV-2 infection. The primary aim of this review was to summarize current knowledge regarding the AD occurring during acute COVID-19. Secondarily, we aimed to clarify the prognostic value of ANS involvement and the role of autonomic parameters in predicting SARS-CoV-2 infection. According to the PRISMA guidelines, we performed a systematic review across Scopus and PubMed databases, resulting in 1585 records. The records check and the analysis of included reports’ references allowed us to include 22 articles. The studies were widely heterogeneous for study population, dysautonomia assessment, and COVID-19 severity. Heart rate variability was the tool most frequently chosen to analyze autonomic parameters, followed by automated pupillometry. Most studies found ANS involvement during acute COVID-19, and AD was often related to a worse outcome. Further studies are needed to clarify the role of autonomic parameters in predicting SARS-CoV-2 infection. The evidence emerging from this review suggests that a complex autonomic nervous system imbalance is a prominent feature of acute COVID-19, often leading to a poor prognosis.

Improving the Accuracy of R-Peak Detection in a Wearable Armband Device for Daily Life Electrocardiogram Monitoring Using a Deep Convolutional Denoising Encoder-Decoder Network

Continuous long-term heart rate (HR) monitoring using wearable devices is desirable to aid in the diagnosis of many health-related conditions. Recently, we have developed an armband device that does not use obstructive leads, has dry electrodes which are convenient for long-term electrocardiogram (ECG) recording, and has been shown to be an effective alternate approach for continuous ECG monitoring. However, motion artifacts (MA) due to electromyogram (EMG) contractions are acknowledged as the major challenge of an armband. In this study, we used a deep convolutional neural network denoising encoder-decoder (CNNDED) to enhance the accuracy of R-peak detection in MA-corrupted ECG recordings obtained by an armband device. We collected simultaneous 24-hour ECG recordings using both the armband device and a Holter monitor on 10 subjects. Each 10-sec ECG segment was converted to a time-frequency representation and subsequently used as the input to CNNDED. During the training process, the model learned to accentuate the location of R peaks by amplifying their values in each ECG beat and suppressing the remaining waveforms. For the training output, the model used the R-peak location information from the simultaneously collected Holter ECG data, which were considered as the reference. The performance of CNNDED was evaluated on an independent test data set using the standard performance metrics. The mean relative error of the estimated HR with respect to the Holter data was 17.5 and 7.3 beats/min, pre- and post-CNNDED, respectively. The mean relative difference of the root mean square of successive difference values were 0.23 and 0.06 before and after applying CNNDED, respectively. Although further study is needed, the current preliminary results suggest that CNNDED can improve detection of R peaks even when they are completely buried in the presence of EMG artifacts.

Detection and Monitoring of Viral Infections via Wearable Devices and Biometric Data

Mounting clinical evidence suggests that viral infections can lead to detectable changes in an individual's normal physiologic and behavioral metrics, including heart and respiration rates, heart rate variability, temperature, activity, and sleep prior to symptom onset, potentially even in asymptomatic individuals. While the ability of wearable devices to detect viral infections in a real-world setting has yet to be proven, multiple recent studies have established that individual, continuous data from a range of biometric monitoring technologies can be easily acquired and that through the use of machine learning techniques, physiological signals and warning signs can be identified. In this review, we highlight the existing knowledge base supporting the potential for widespread implementation of biometric data to address existing gaps in the diagnosis and treatment of viral illnesses, with a particular focus on the many important lessons learned from the coronavirus disease 2019 pandemic.

The mechanistic and prognostic implications of heart rate variability analysis in patients with cirrhosis

Chronic liver damage leads to scarring of the liver tissue and ultimately a systemic illness known as cirrhosis. Patients with cirrhosis exhibit multi-organ dysfunction and high mortality. Reduced heart rate variability (HRV) is a hallmark of cirrhosis, reflecting a state of defective cardiovascular control and physiological network disruption. Several lines of evidence have revealed that decreased HRV holds prognostic information and can predict survival of patients independent of the severity of liver disease. Thus, the aim of this review is to shed light on the mechanistic and prognostic implications of HRV analysis in patients with cirrhosis. Notably, several studies have extensively highlighted the critical role systemic inflammation elicits in conferring the reduction in patients' HRV. It appears that IL-6 is likely to play a central mechanistic role, whereby its levels also correlate with manifestations, such as autonomic neuropathy and hence the partial uncoupling of the cardiac pacemaker from autonomic control. Reduced HRV has also been reported to be highly correlated with the severity of hepatic encephalopathy, potentially through systemic inflammation affecting specific brain regions, involved in both cognitive function and autonomic regulation. In general, the prognostic ability of HRV analysis holds immense potential in improving survival rates for patients with cirrhosis, as it may indeed be added to current prognostic indicators, to ultimately increase the accuracy of selecting the recipient most in need of liver transplantation. However, a network physiology approach in the future is critical to delineate the exact mechanistic basis by which decreased HRV confers poor prognosis.

Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study

Early detection of diseases such as COVID-19 could be a critical tool in reducing disease transmission by helping individuals recognize when they should self-isolate, seek testing, and obtain early medical intervention. Consumer wearable devices that continuously measure physiological metrics hold promise as tools for early illness detection. We gathered daily questionnaire data and physiological data using a consumer wearable (Oura Ring) from 63,153 participants, of whom 704 self-reported possible COVID-19 disease. We selected 73 of these 704 participants with reliable confirmation of COVID-19 by PCR testing and high-quality physiological data for algorithm training to identify onset of COVID-19 using machine learning classification. The algorithm identified COVID-19 an average of 2.75 days before participants sought diagnostic testing with a sensitivity of 82% and specificity of 63%. The receiving operating characteristic (ROC) area under the curve (AUC) was 0.819 (95% CI [0.809, 0.830]). Including continuous temperature yielded an AUC 4.9% higher than without this feature. For further validation, we obtained SARS CoV-2 antibody in a subset of participants and identified 10 additional participants who self-reported COVID-19 disease with antibody confirmation. The algorithm had an overall ROC AUC of 0.819 (95% CI [0.809, 0.830]), with a sensitivity of 90% and specificity of 80% in these additional participants. Finally, we observed substantial variation in accuracy based on age and biological sex. Findings highlight the importance of including temperature assessment, using continuous physiological features for alignment, and including diverse populations in algorithm development to optimize accuracy in COVID-19 detection from wearables.

Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder

This study proposes a contrastive convolutional auto-encoder (contrastive CAE), a combined architecture of an auto-encoder and contrastive loss, to identify individuals with suspected COVID-19 infection using heart-rate data from participants with multiple sclerosis (MS) in the ongoing RADAR-CNS mHealth research project. Heart-rate data was remotely collected using a Fitbit wristband. COVID-19 infection was either confirmed through a positive swab test, or inferred through a self-reported set of recognised symptoms of the virus. The contrastive CAE outperforms a conventional convolutional neural network (CNN), a long short-term memory (LSTM) model, and a convolutional auto-encoder without contrastive loss (CAE). On a test set of 19 participants with MS with reported symptoms of COVID-19, each one paired with a participant with MS with no COVID-19 symptoms, the contrastive CAE achieves an unweighted average recall of 95.3 % , a sensitivity of 100 % and a specificity of 90.6 % , an area under the receiver operating characteristic curve (AUC-ROC) of 0.944, indicating a maximum successful detection of symptoms in the given heart rate measurement period, whilst at the same time keeping a low false alarm rate.

Classification of Blood Volume Decompensation State via Machine Learning Analysis of Multi-Modal Wearable-Compatible Physiological Signals

This paper presents a novel computational algorithm to estimate blood volume decompensation state based on machine learning (ML) analysis of multi-modal wearable-compatible physiological signals. To the best of our knowledge, our algorithm may be the first of its kind which can not only discriminate normovolemia from hypovolemia but also classify hypovolemia into absolute hypovolemia and relative hypovolemia. We realized our blood volume classification algorithm by (i) extracting a multitude of features from multi-modal physiological signals including the electrocardiogram (ECG), the seismocardiogram (SCG), the ballistocardiogram (BCG), and the photoplethysmogram (PPG), (ii) constructing two ML classifiers using the features, one to classify normovolemia vs. hypovolemia and the other to classify hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) sequentially integrating the two to enable multi-class classification (normovolemia, absolute hypovolemia, and relative hypovolemia). We developed the blood volume decompensation state classification algorithm using the experimental data collected from six animals undergoing normovolemia, relative hypovolemia, and absolute hypovolemia challenges. Leave-one-subject-out analysis showed that our classification algorithm achieved an F1 score and accuracy of (i) 0.93 and 0.89 in classifying normovolemia vs. hypovolemia, (ii) 0.88 and 0.89 in classifying hypovolemia into absolute hypovolemia and relative hypovolemia, and (iii) 0.77 and 0.81 in classifying the overall blood volume decompensation state. The analysis of the features embedded in the ML classifiers indicated that many features are physiologically plausible, and that multi-modal SCG-BCG fusion may play an important role in achieving good blood volume classification efficacy. Our work may complement existing computational algorithms to estimate blood volume compensatory reserve as a potential decision-support tool to provide guidance on context-sensitive hypovolemia therapeutic strategy.

Alternation of the Autonomic Nervous System Is Associated With Pulmonary Sequelae in Patients With COVID-19 After Six Months of Discharge

Previous studies suggest that autonomic dysfunction is associated with disease severity in acute phase in patients with coronavirus disease 2019 (COVID-19). However, the association between autonomic dysfunction and pulmonary sequelae in patients with COVID-19 is unknown. We conducted a prospective study to investigate the association between autonomic dysfunction and pulmonary sequelae in patients with COVID-19 discharged for 6 months. We included 40 eligible participants and collected the following indicators: heart rate variability (HRV), pulmonary function tests (PFTs), lung X-ray computed tomography (CT), routine blood parameters, liver function parameters, and lymphocyte subsets. We found that at 6 months post-discharge, HRV still had a tight correlation with pulmonary fibrosis. There was a significant difference in HRV between patients with and without diffusion dysfunction, but HRV did not differ between patients with or without ventilatory dysfunction. Diffusion dysfunction and pulmonary fibrosis were tightly associated, and HRV index changes in patients with diffusion dysfunction had the same trend as that of patients with pulmonary fibrosis. They had a lower standard deviation of NN intervals (SDNN), the standard deviation of the average NN intervals (SDANN), and the triangular index, but a higher ratio between LF and HF power (LF/HF). In addition, WBC, neutrophils, and CD4/CD8 were correlated with pulmonary fibrosis and HRV. We concluded that autonomic dysfunction is closely associated with pulmonary fibrosis and diffusion dysfunction, and immune mechanisms may potentially contribute to this process.

Vital signs as physiomarkers of neonatal sepsis

Neonatal sepsis accounts for significant morbidity and mortality, particularly among premature infants in the Neonatal Intensive Care Unit. Abnormal vital sign patterns serve as physiomarkers of sepsis and provide early warning of illness before overt clinical decompensation. The systemic inflammatory response to pathogens signals the autonomic nervous system, leading to changes in temperature, respiratory rate, heart rate, and blood pressure. In infants with comorbidities of prematurity, vital sign abnormalities often occur in the absence of infection, which confounds sepsis diagnosis. This review will cover the mechanisms of vital sign changes in neonatal sepsis, including the cholinergic anti-inflammatory pathway mediated by the vagus nerve, which is critical to the host response to infectious and inflammatory insults. We will also review the clinical implications of vital sign changes in neonatal sepsis, including their use in early warning scores and systems to direct clinicians to the bedside of infants with physiologic changes that might be due to sepsis. IMPACT: This manuscript summarizes and reviews the relevant literature on the physiological manifestations of neonatal sepsis and how we monitor and analyze these through vital signs and advanced analytics.

cosinoRmixedeffects: an R package for mixed-effects cosinor models

Background

Wearable devices enable monitoring and measurement of physiological parameters over a 24-h period, and some of which exhibit circadian rhythm characteristics. However, the currently available R package cosinor could only analyze daily cross-sectional data and compare the parameters between groups with two levels. To evaluate longitudinal changes in the circadian patterns, we need to extend the model to a mixed-effect model framework, allowing for random effects and interaction between COSINOR parameters and time-varying covariates.

Results

We developed the cosinoRmixedeffects R package for modelling longitudinal periodic data using mixed-effects cosinor models. The model allows for covariates and interactions with the non-linear parameters MESOR, amplitude, and acrophase. To facilitate ease of use, the package utilizes the syntax and functions of the widely used emmeans package to obtain estimated marginal means and contrasts. Estimation and hypothesis testing involving the non-linear circadian parameters are carried out using bootstrapping. We illustrate the package functionality by modelling daily measurements of heart rate variability (HRV) collected among health care workers over several months. Differences in circadian patterns of HRV between genders, BMI, and during infection with SARS-CoV2 are evaluated to illustrate how to perform hypothesis testing.

Conclusion

cosinoRmixedeffects package provides the model fitting, estimation and hypothesis testing for the mixed-effects COSINOR model, for the linear and non-linear circadian parameters MESOR, amplitude and acrophase. The model accommodates factors with any number of categories, as well as complex interactions with circadian parameters and categorical factors.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04463-3.

Hepatic FGF21 preserves thermoregulation and cardiovascular function during bacterial inflammation

Sickness behaviors, including anorexia, are evolutionarily conserved responses to acute infections. Inflammation-induced anorexia causes dramatic metabolic changes, of which components critical to survival are unique depending on the type of inflammation. Glucose supplementation during the anorectic period induced by bacterial inflammation suppresses adaptive fasting metabolic pathways, including fibroblast growth factor 21 (FGF21), and decreases survival. Consistent with this observation, FGF21-deficient mice are more susceptible to mortality from endotoxemia and polybacterial peritonitis. Here, we report that increased circulating FGF21 during bacterial inflammation is hepatic derived and required for survival through the maintenance of thermogenesis, energy expenditure, and cardiac function. FGF21 signaling downstream of its obligate coreceptor, β-Klotho (KLB), is required in bacterial sepsis. However, FGF21 modulates thermogenesis and chronotropy independent of the adipose, forebrain, and hypothalamus, which are operative in cold adaptation, suggesting that in bacterial inflammation, either FGF21 signals through a novel, undescribed target tissue or concurrent signaling of multiple KLB-expressing tissues is required.

Assessment of the Feasibility of Using Noninvasive Wearable Biometric Monitoring Sensors to Detect Influenza and the Common Cold Before Symptom Onset

IMPORTANCE

Currently, there are no presymptomatic screening methods to identify individuals infected with a respiratory virus to prevent disease spread and to predict their trajectory for resource allocation.

OBJECTIVE

To evaluate the feasibility of using noninvasive, wrist-worn wearable biometric monitoring sensors to detect presymptomatic viral infection after exposure and predict infection severity in patients exposed to H1N1 influenza or human rhinovirus.

DESIGN, SETTING, AND PARTICIPANTS

The cohort H1N1 viral challenge study was conducted during 2018; data were collected from September 11, 2017, to May 4, 2018. The cohort rhinovirus challenge study was conducted during 2015; data were collected from September 14 to 21, 2015. A total of 39 adult participants were recruited for the H1N1 challenge study, and 24 adult participants were recruited for the rhinovirus challenge study. Exclusion criteria for both challenges included chronic respiratory illness and high levels of serum antibodies. Participants in the H1N1 challenge study were isolated in a clinic for a minimum of 8 days after inoculation. The rhinovirus challenge took place on a college campus, and participants were not isolated.

EXPOSURES

Participants in the H1N1 challenge study were inoculated via intranasal drops of diluted influenza A/California/03/09 (H1N1) virus with a mean count of 106 using the median tissue culture infectious dose (TCID50) assay. Participants in the rhinovirus challenge study were inoculated via intranasal drops of diluted human rhinovirus strain type 16 with a count of 100 using the TCID50 assay.

MAIN OUTCOMES AND MEASURES

The primary outcome measures included cross-validated performance metrics of random forest models to screen for presymptomatic infection and predict infection severity, including accuracy, precision, sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC).

RESULTS

A total of 31 participants with H1N1 (24 men [77.4%]; mean [SD] age, 34.7 [12.3] years) and 18 participants with rhinovirus (11 men [61.1%]; mean [SD] age, 21.7 [3.1] years) were included in the analysis after data preprocessing. Separate H1N1 and rhinovirus detection models, using only data on wearble devices as input, were able to distinguish between infection and noninfection with accuracies of up to 92% for H1N1 (90% precision, 90% sensitivity, 93% specificity, and 90% F1 score, 0.85 [95% CI, 0.70-1.00] AUC) and 88% for rhinovirus (100% precision, 78% sensitivity, 100% specificity, 88% F1 score, and 0.96 [95% CI, 0.85-1.00] AUC). The infection severity prediction model was able to distinguish between mild and moderate infection 24 hours prior to symptom onset with an accuracy of 90% for H1N1 (88% precision, 88% sensitivity, 92% specificity, 88% F1 score, and 0.88 [95% CI, 0.72-1.00] AUC) and 89% for rhinovirus (100% precision, 75% sensitivity, 100% specificity, 86% F1 score, and 0.95 [95% CI, 0.79-1.00] AUC).

CONCLUSIONS AND RELEVANCE

This cohort study suggests that the use of a noninvasive, wrist-worn wearable device to predict an individual's response to viral exposure prior to symptoms is feasible. Harnessing this technology would support early interventions to limit presymptomatic spread of viral respiratory infections, which is timely in the era of COVID-19.

Temporal Differential Expression of Physiomarkers Predicts Sepsis in Critically Ill Adults

BACKGROUND

Sepsis is a life-threatening condition with high mortality rates. Early detection and treatment are critical to improving outcomes. Our primary objective was to develop artificial intelligence capable of predicting sepsis earlier using a minimal set of streaming physiological data in real time.

METHODS AND FINDINGS

A total of 29,552 adult patients were admitted to the intensive care unit across five regional hospitals in Memphis, Tenn, over 18 months from January 2017 to July 2018. From these, 5,958 patients were selected after filtering for continuous (minute-by-minute) physiological data availability. A total of 617 (10.4%) patients were identified as sepsis cases, using the Third International Consensus Definitions for Sepsis and Septic Shock (Sepsis-3) criteria. Physiomarkers, a set of signal processing features, were derived from five physiological data streams including heart rate, respiratory rate, and blood pressure (systolic, diastolic, and mean), captured every minute from the bedside monitors. A support vector machine classifier was used for classification. The model accurately predicted sepsis up to a mean and 95% confidence interval of 17.4 ± 0.22 h before sepsis onset, with an average test accuracy of 83.0% (average sensitivity, specificity, and area under the receiver operating characteristics curve of 0.757, 0.902, and 0.781, respectively).

CONCLUSIONS

This study demonstrates that salient physiomarkers derived from continuous bedside monitoring are temporally and differentially expressed in septic patients. Using this information, minimalistic artificial intelligence models can be developed to predict sepsis earlier in critically ill patients.

Alteration of Autonomic Nervous System Is Associated With Severity and Outcomes in Patients With COVID-19

Background

Previous studies suggest that coronavirus disease 2019 (COVID-19) is a systemic infection involving multiple systems, and may cause autonomic dysfunction.

Objective

To assess autonomic function and relate the findings to the severity and outcomes in COVID-19 patients.

Methods

We included consecutive patients with COVID-19 admitted to the 21st COVID-19 Department of the east campus of Renmin Hospital of Wuhan University from February 6 to March 7, 2020. Clinical data were collected. Heart rate variability (HRV), N-terminal pro-B-type natriuretic peptide (NT-proBNP), D-dimer, and lymphocytes and subsets counts were analysed at two time points: nucleic-acid test positive and negative. Psychological symptoms were assessed after discharge.

Results

All patients were divided into a mild group (13) and a severe group (21). The latter was further divided into two categories according to the trend of HRV. Severe patients had a significantly lower standard deviation of the RR intervals (SDNN) (P < 0.001), standard deviation of the averages of NN intervals (SDANN) (P < 0.001), and a higher ratio of low- to high-frequency power (LF/HF) (P = 0.016). Linear correlations were shown among SDNN, SDANN, LF/HF, and laboratory indices (P < 0.05). Immune function, D-dimer, and NT-proBNP showed a consistent trend with HRV in severe patients (P < 0.05), and severe patients without improved HRV parameters needed a longer time to clear the virus and recover (P < 0.05).

Conclusion

HRV was associated with the severity of COVID-19. The changing trend of HRV was related to the prognosis, indicating that HRV measurements can be used as a non-invasive predictor for clinical outcome.

Early Warning of Infection in Patients Undergoing Hematopoietic Stem Cell Transplantation Using Heart Rate Variability and Serum Biomarkers

Early warning of infection is critical to reduce the risk of deterioration and mortality, especially in neutropenic patients following hematopoietic stem cell transplantation (HCT). Given that heart rate variability (HRV) is a sensitive and early marker for infection, and that serum inflammatory biomarkers can have high specificity for infection, we hypothesized their combination may be useful for accurate early warning of infection. In this study, we developed and evaluated a composite predictive model using continuous HRV with daily serum biomarker measurements to provide risk stratification of future deterioration in HCT recipients. A total of 116 ambulatory outpatients about to undergo HCT consented to collection of prospective demographic, clinical (daily vital signs), HRV (continuous electrocardiography [ECG] monitoring, laboratory [daily serum samples frozen at -80 °C]), and infection outcome variables (defined as the time of escalation of antibiotics), all from 24 hours pre-HCT to the onset of infection or 14 days post-HCT. Indications for antibiotic escalation were adjudicated as "true infection" or not by 2 blinded HCT clinicians. A composite time series of 8 HRV metrics was created for each patient, and the probability of deterioration within the next 72 hours was estimated using logistic regression modeling of composite HRV and serum biomarkers using a rule-based naïve Bayes model if the HRV-based probability exceeded a median threshold. Thirty-five patients (30%) withdrew within <24 hours owing to intolerability of ECG monitoring, leaving 81 patients, of whom 48 (59%) had antibiotic escalation adjudicated as true infection. The combined HRV and biomarker (TNF-α, IL-6, and IL-7) predictive model began increasing at ∼48 hours on average before the diagnosis of infection, could distinguish between high risk of impending infection (>90% incidence of subsequent infection within 72 hours), average risk (∼50%), and low risk (<10%), with an area under the receiver operating characteristic curve of 0.87. However, given that prophylactic predictive ECG monitoring and daily serum collection proved challenging for many patients, further refinement in measurement is necessary for further study.

Early Detection of Late Onset Sepsis in Premature Infants Using Visibility Graph Analysis of Heart Rate Variability

OBJECTIVE

This study was designed to test the diagnostic value of visibility graph features derived from the heart rate time series to predict late onset sepsis (LOS) in preterm infants using machine learning.

METHODS

The heart rate variability (HRV) data was acquired from 49 premature newborns hospitalized in neonatal intensive care units (NICU). The LOS group consisted of patients who received more than five days of antibiotics, at least 72 hours after birth. The control group consisted of infants who did not receive antibiotics. HRV features in the days prior to the start of antibiotics (LOS group) or in a randomly selected period (control group) were compared against a baseline value calculated during a calibration period. After automatic feature selection, four machine learning algorithms were trained. All the tests were done using two variants of the feature set: one only included traditional HRV features, and the other additionally included visibility graph features. Performance was studied using area under the receiver operating characteristics curve (AUROC).

RESULTS

The best performance for detecting LOS was obtained with logistic regression, using the feature set including visibility graph features, with AUROC of 87.7% during the six hours preceding the start of antibiotics, and with predictive potential (AUROC above 70%) as early as 42 h before start of antibiotics.

CONCLUSION

These results demonstrate the usefulness of introducing visibility graph indexes in HRV analysis for sepsis prediction in newborns.

SIGNIFICANCE

The method proposed the possibility of non-invasive, real-time monitoring of risk of LOS in a NICU setting.

Is the heart rate variability monitoring using the analgesia nociception index a predictor of illness severity and mortality in critically ill patients with COVID-19? A pilot study

Introduction

The analysis of heart rate variability (HRV) has proven to be an important tool for the management of autonomous nerve system in both surgical and critically ill patients. We conducted this study to show the different spectral frequency and time domain parameters of HRV as a prospective predictor for critically ill patients, and in particular for COVID-19 patients who are on mechanical ventilation. The hypothesis is that most severely ill COVID-19 patients have a depletion of the sympathetic nervous system and a predominance of parasympathetic activity reflecting the remaining compensatory anti-inflammatory response.

Materials and methods

A single-center, prospective, observational pilot study which included COVID-19 patients admitted to the Surgical Intensive Care Unit was conducted. The normalized high-frequency component (HFnu), i.e. ANIm, and the standard deviation of RR intervals (SDNN), i.e. Energy, were recorded using the analgesia nociception index monitor (ANI). To estimate the severity and mortality we used the SOFA score and the date of discharge or date of death.

Results

A total of fourteen patients were finally included in the study. ANIm were higher in the non-survivor group (p = 0.003) and were correlated with higher IL-6 levels (p = 0.020). Energy was inversely correlated with SOFA (p = 0.039) and fewer survival days (p = 0.046). A limit value at 80 of ANIm, predicted mortalities with a sensitivity of 100% and specificity of 85.7%. In the case of Energy, a limit value of 0.41 ms predicted mortality with all predictive values of 71.4%.

Conclusion

A low autonomic nervous system activity, i.e. low SDNN or Energy, and a predominance of the parasympathetic system, i.e. low HFnu or ANIm, due to the sympathetic depletion in COVID-19 patients are associated with a worse prognosis, higher mortality, and higher IL-6 levels.

Use of Physiological Data From a Wearable Device to Identify SARS-CoV-2 Infection and Symptoms and Predict COVID-19 Diagnosis: Observational Study

BACKGROUND

Changes in autonomic nervous system function, characterized by heart rate variability (HRV), have been associated with infection and observed prior to its clinical identification.

OBJECTIVE

We performed an evaluation of HRV collected by a wearable device to identify and predict COVID-19 and its related symptoms.

METHODS

Health care workers in the Mount Sinai Health System were prospectively followed in an ongoing observational study using the custom Warrior Watch Study app, which was downloaded to their smartphones. Participants wore an Apple Watch for the duration of the study, measuring HRV throughout the follow-up period. Surveys assessing infection and symptom-related questions were obtained daily.

RESULTS

Using a mixed-effect cosinor model, the mean amplitude of the circadian pattern of the standard deviation of the interbeat interval of normal sinus beats (SDNN), an HRV metric, differed between subjects with and without COVID-19 (P=.006). The mean amplitude of this circadian pattern differed between individuals during the 7 days before and the 7 days after a COVID-19 diagnosis compared to this metric during uninfected time periods (P=.01). Significant changes in the mean and amplitude of the circadian pattern of the SDNN was observed between the first day of reporting a COVID-19-related symptom compared to all other symptom-free days (P=.01).

CONCLUSIONS

Longitudinally collected HRV metrics from a commonly worn commercial wearable device (Apple Watch) can predict the diagnosis of COVID-19 and identify COVID-19-related symptoms. Prior to the diagnosis of COVID-19 by nasal swab polymerase chain reaction testing, significant changes in HRV were observed, demonstrating the predictive ability of this metric to identify COVID-19 infection.

Predicting Volume Responsiveness Among Sepsis Patients Using Clinical Data and Continuous Physiological Waveforms

The efficacy of early fluid treatment in patients with sepsis is unclear and may contribute to serious adverse events due to fluid non-responsiveness. The current method of deciding if patients are responsive to fluid administration is often subjective and requires manual intervention. This study utilizes MIMIC III and associated matched waveform datasets across the entire ICU stay duration of each patient to develop prediction models for assessing fluid responsiveness in sepsis patients. We developed a pipeline to extract high frequency continuous waveform data and included waveform features in the prediction models. Comparing across five machine learning models, random forest performed the best when no waveform information is added (AUC = 0.84), with mean arterial blood pressure and age identified as key factors. After incorporation of features from physiologic waveforms, logistic regression with L1 penalty provided consistent performance and high interpretability, achieving an accuracy of 0.89 and F1 score of 0.90.

Validation and Comparison of Six Risk Scores for Infection in Patients With ST-Segment Elevation Myocardial Infarction Undergoing Percutaneous Coronary Intervention

Aims: Very few of the risk scores to predict infection in ST-segment elevation myocardial infarction (STEMI) patients undergoing percutaneous coronary intervention (PCI) have been validated, and reports on their differences. We aimed to validate and compare the discriminatory value of different risk scores for infection.

Methods: A total of 2,260 eligible patients with STEMI undergoing PCI from January 2010 to May 2018 were enrolled. Six risk scores were investigated: age, serum creatinine, or glomerular filtration rate, and ejection fraction (ACEF or AGEF) score; Canada Acute Coronary Syndrome (CACS) risk score; CHADS₂ score; Global Registry for Acute Coronary Events (GRACE) score; and Mehran score conceived for contrast induced nephropathy. The primary endpoint was infection during hospitalization.

Results: Except CHADS₂ score (AUC, 0.682; 95%CI, 0.652–0.712), the other risk scores showed good discrimination for predicting infection. All risk scores but CACS risk score (calibration slope, 0.77; 95%CI, 0.18–1.35) showed best calibration for infection. The risks scores also showed good discrimination for in-hospital major adverse clinical events (MACE) (AUC range, 0.700–0.786), except for CHADS₂ score. All six risk scores showed best calibration for in-hospital MACE. Subgroup analysis demonstrated similar results.

Conclusions: The ACEF, AGEF, CACS, GRACE, and Mehran scores showed a good discrimination and calibration for predicting infection and MACE.

The Vagal Autonomic Pathway of COVID-19 at the Crossroad of Alzheimer's Disease and Aging: A Review of Knowledge

Coronavirus Disease 2019 (COVID-19) pandemic-triggered mortality is significantly higher in older than in younger populations worldwide. Alzheimer's disease (AD) is related to aging and was recently reported to be among the major risk factors for COVID-19 mortality in older people. The symptomatology of COVID-19 indicates that lethal outcomes of infection rely on neurogenic mechanisms. The present review compiles the available knowledge pointing to the convergence of COVID-19 complications with the mechanisms of autonomic dysfunctions in AD and aging. The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) is prone to neuroinvasion from the lung along the vagus nerve up to the brainstem autonomic nervous centers involved in the coupling of cardiovascular and respiratory rhythms. The brainstem autonomic network allows SARS-CoV-2 to trigger a neurogenic switch to hypertension and hypoventilation, which may act in synergy with aging- and AD-induced dysautonomias, along with an inflammatory "storm". The lethal outcomes of COVID-19, like in AD and unhealthy aging, likely rely on a critical hypoactivity of the efferent vagus nerve cholinergic pathway, which is involved in lowering cardiovascular pressure and systemic inflammation tone. We further discuss the emerging evidence supporting the use of 1) the non-invasive stimulation of vagus nerve as an additional therapeutic approach for severe COVID-19, and 2) the demonstrated vagal tone index, i.e., heart rate variability, via smartphone-based applications as a non-serological low-cost diagnostic of COVID-19. These two well-known medical approaches are already available and now deserve large-scale testing on human cohorts in the context of both AD and COVID-19.

Heart rate variability measures for prediction of severity of illness and poor outcome in ED patients with sepsis

INTRODUCTION

This study evaluates the utility of heart rate variability (HRV) for assessment of severity of illness and poor outcome in Emergency Department (ED) patients with sepsis. HRV measures evaluated included low frequency (LF) signal, high frequency (HF) signal, and deviations in LF and HF signal from age-adjusted reference values.

METHODS

This was a prospective, observational study. Seventy-two adult ED patients were assessed within 6 h of arrival.

RESULTS

Severity of illness as defined by sepsis subtype correlated with decreased LF signal (sepsis: 70.68 ± 22.95, severe sepsis: 54.00 ± 28.41, septic shock: 45.54 ± 23.31, p = 0.02), increased HF signal (sepsis: 27.87 ± 19.42, severe sepsis: 44.63 ± 27.29, septic shock: 47.66 ± 20.98, p = 0.01), increasingly negative deviations in LF signal (sepsis: 0.41 ± 24.53, severe sepsis: -21.43 ± 30.09, septic shock -30.39 ± 26.09, p = 0.005) and increasingly positive deviations in HF signal (sepsis: -1.86 ± 21.09, severe sepsis: 20.07 ± 29.03, septic shock: 23.6 ± 24.17, p = 0.004). Composite poor outcome correlated with decreased LF signal (p = 0.008), increased HF signal (p = 0.03), large negative deviations in LF signal (p = 0.004) and large positive deviations in HF signal (p = 0.02). Deviations in LF and HF signal from age-adjusted reference values correlated with individual measures of poor outcome with greater consistency than LF or HF signal.

DISCUSSION

Accounting for the influence of age on baseline HRV signal improves the predictive value of HRV measures in ED patients with sepsis.

Assessment of physiological signs associated with COVID-19 measured using wearable devices

Respiration rate, heart rate, and heart rate variability (HRV) are some health metrics that are easily measured by consumer devices, which can potentially provide early signs of illness. Furthermore, mobile applications that accompany wearable devices can be used to collect relevant self-reported symptoms and demographic data. This makes consumer devices a valuable tool in the fight against the COVID-19 pandemic. Data on 2745 subjects diagnosed with COVID-19 (active infection, PCR test) were collected from May 21 to September 11, 2020, consisting of PCR positive tests conducted between February 16 and September 9. Considering male (female) participants, 11.9% (11.2%) of the participants were asymptomatic, 48.3% (47.8%) recovered at home by themselves, 29.7% (33.7%) recovered at home with the help of someone else, 9.3% (6.6%) required hospitalization without ventilation, and 0.5% (0.4%) required ventilation. There were a total of 21 symptoms reported, and the prevalence of symptoms varies by sex. Fever was present in 59.4% of male subjects and in 52% of female subjects. Based on self-reported symptoms alone, we obtained an AUC of 0.82 ± 0.017 for the prediction of the need for hospitalization. Based on physiological signs, we obtained an AUC of 0.77 ± 0.018 for the prediction of illness on a specific day. Respiration rate and heart rate are typically elevated by illness, while HRV is decreased. Measuring these metrics, taken in conjunction with molecular-based diagnostics, may lead to better early detection and monitoring of COVID-19.

Potential Prognostic Markers in the Heart Rate Variability Features for Early Diagnosis of Sepsis in the Pediatric Intensive Care Unit using Convolutional Neural Network Classifiers

Blood infection due to different circumstances could immediately develop to an extreme body reaction that leads to a serious life-threatening condition, called Sepsis. Currently, therapeutic protocols through timely antibiotic resuscitation strategies play an important role to fight against the adverse conditions and improve survival. Therefore, timing, and more specifically early diagnosis of the illness, is crucially important for an effective treatment. Studies have indicated that vital signals such as heart rate variability (HRV) could provide potential prognostic biological markers that can help with early detection of sepsis before it is clinically diagnosed through its actual symptoms. Therefore, this study employs neonatal and pediatric electrocardiogram (ECG) to extract 52 hourly sets of linear and non-linear features from the HRV, starting from 24 hours prior to the clinical diagnosis of sepsis in patients with positive blood cultures (n=14). Similar sets of features were also obtained from a non-sepsis control group to create an evaluation benchmark (n=14).In particular, this study initially demonstrates how the variations within the 24 hours values of specific HRV featuresets could effectively reveal prognostic information about the evolution of sepsis, prior to the actual clinical diagnosis. Moreover, this study demonstrates that differences in the values of a particular set of features at 22 hours before the actual clinical diagnosis/symptoms can be reliably used to train a convolutional neural network for automatic classification between the individuals in the sepsis and non-sepsis groups with 88.89±7.86% accuracy.Clinical relevance- Results suggest potential early diagnosis of sepsis through real-time automatic classification of HRV features as prognostic indicators in clinical ECG recordings.

Potential Prognostic Markers in the Heart Rate Variability Features for Early Diagnosis of Sepsis in the Pediatric Intensive Care Unit using Convolutional Neural Network Classifiers

Blood infection due to different circumstances could immediately develop to an extreme body reaction that leads to a serious life-threatening condition, called Sepsis. Currently, therapeutic protocols through timely antibiotic resuscitation strategies play an important role to fight against the adverse conditions and improve survival. Therefore, timing, and more specifically early diagnosis of the illness, is crucially important for an effective treatment. Studies have indicated that vital signals such as heart rate variability (HRV) could provide potential prognostic biological markers that can help with early detection of sepsis before it is clinically diagnosed through its actual symptoms. Therefore, this study employs neonatal and pediatric electrocardiogram (ECG) to extract 52 hourly sets of linear and non-linear features from the HRV, starting from 24 hours prior to the clinical diagnosis of sepsis in patients with positive blood cultures (n=14). Similar sets of features were also obtained from a non-sepsis control group to create an evaluation benchmark (n=14).In particular, this study initially demonstrates how the variations within the 24 hours values of specific HRV feature-sets could effectively reveal prognostic information about the evolution of sepsis, prior to the actual clinical diagnosis. Moreover, this study demonstrates that differences in the values of a particular set of features at 22 hours before the actual clinical diagnosis/symptoms can be reliably used to train a convolutional neural network for automatic classification between the individuals in the sepsis and non-sepsis groups with 88.89±7.86% accuracy.

Bedside hyperspectral imaging for the evaluation of microcirculatory alterations in perioperative intensive care medicine: a study protocol for an observational clinical pilot study (HySpI-ICU)

INTRODUCTION

Normalisation of macrocirculatory parameters during resuscitation therapy does not guarantee the restoration of microcirculatory perfusion in critical illness due to haemodynamic incoherence. Persistent microcirculatory abnormalities are associated with severity of organ dysfunction and mandate the development of bedside microcirculatory monitoring. A novel hyperspectral imaging (HSI) system can visualise changes in skin perfusion, oxygenation and water content at the bedside. We aim to evaluate the effectiveness of HSI for bedside monitoring of skin microcirculation and the association of HSI parameters with organ dysfunction in patients with sepsis and major abdominal surgery.

METHODS AND ANALYSIS

Three independent groups will be assessed and separately analysed within a clinical prospective observational study: (1) 25 patients with sepsis or septic shock (according to sepsis-3 criteria), (2) 25 patients undergoing pancreatic surgery and (3) 25 healthy controls. Patients with sepsis and patients undergoing pancreatic surgery will receive standard therapy according to local protocols derived from international guidelines. In addition, cardiac output of perioperative patients and patients with sepsis will be measured. Healthy controls undergo one standardised evaluation. The TIVITA Tissue System is a novel HSI system that uses the visible and near-infrared spectral light region to determine tissue microcirculatory parameters. HSI analysis (hand/knee) will be done in parallel to haemodynamic monitoring within defined intervals during a 72-hour observation period. HSI data will be correlated with the Sequential Organ Failure Assessment score, global haemodynamics, inflammation and glycocalyx markers, surgical complications and 30-day outcome.

ETHICS AND DISSEMINATION

The protocol has been approved by the local ethics committee of the University of Heidelberg (S-148/2019). Study results will be submitted to peer-reviewed journals and medical conferences.

TRIAL REGISTRATION NUMBER

DRKS00017313; Pre-results.

Autonomic Rehabilitation: Adapting to Change

Adaption to changes of external environment or internal health, the body-mind connection, or autonomic nervous system must be flexible and healthy. Population health studies with wearable technology and remote monitoring will lead to paradigm shifts in how to approach the physiology of emotion. Heart rate variability as a whole health biomarker could emerge as a foundation for a process beginning with objective habits and skills of real-time modulation with focused breathing for healthier decision making and autonomic health trajectory change. Physical medicine and rehabilitation is uniquely poised to refine an autonomic rehabilitation process in an integrative manner to help individuals adapt.

Heart Rate Variability, Clinical and Laboratory Measures to Predict Future Deterioration in Patients Presenting With Sepsis

BACKGROUND

Risk stratification of patients presenting to the emergency department (ED) with sepsis can be challenging. We derived and evaluated performance of a predictive model containing clinical, laboratory, and heart rate variability (HRV) measures to quantify risk of deterioration in this population.

METHODS

ED patients aged 21 and older satisfying the 1992 consensus conference criteria for sepsis and able to consent (directly or through a surrogate) were enrolled (n = 1,247). Patients had clinical, laboratory, and HRV data recorded within 1 h of ED presentation, and were followed to identify deterioration within 72 h.

RESULTS

Eight hundred thirty-two patients had complete data, of whom 68 (8%) reached at least one endpoint. Optimal predictive performance was derived from a combination of laboratory values and HRV metrics with an area under the receiver-operating curve (AUROC) of 0.80 (95% CI, 0.65-0.92). This combination of variables was superior to clinical (AUROC = 0.69, 95% CI, 0.54-0.83), laboratory (AUROC = 0.77, 95% CI, 0.63-0.90), and HRV measures (AUROC = 0.76, 95% CI, 0.61-0.90) alone. The HRV+LAB model identified a high-risk cohort of patients (14% of all patients) with a 4.3-fold (95% CI, 3.2-5.4) increased risk of deterioration (incidence of deterioration: 35%), as well as a low-risk group (61% of all patients) with 0.2-fold (95% CI 0.1-0.4) risk of deterioration (incidence of deterioration: 2%).

CONCLUSIONS

A model that combines HRV and laboratory values may help ED physicians evaluate risk of deterioration in patients with sepsis and merits validation and further evaluation.

Serious infection may systemically increase noradrenergic signaling and produce psychological effects

Serious infection elicits inflammatory processes that act through a range of molecular pathways, including cytokine signaling. It is not established however that noradrenaline (NA), a widely distributed neurotransmitter in the brain that is also a principal output molecule of the sympathetic nervous system, can produce psychological effects associated with infection. This paper puts forth the hypothesis that through neural-immune crosstalk, serious infection increases noradrenergic signaling, both in the central nervous system and in peripheral organs. In this manner, elevated noradrenergic transmission may help produce basic symptoms of infection such as fever, fatigue, aches and pains (including headache), nausea, and loss of appetite. NA may also promote cognitive impairment, major depression, unipolar mania, and even epileptic seizures in some cases. The paper focuses on three major types of infection: influenza (viral), tuberculosis (bacterial), malaria (parasitic), while also summarizing the potential relationship between NA and human immunodeficiency virus (HIV) infection. Four lines of evidence are used to test association between NA and influenza, tuberculosis, and malaria: direct measures of NA and its metabolites; and incidence of hypertension, bipolar mania, and epileptic seizures, since the latter three conditions may be associated with elevated NA. In addition, heart rate variability data are examined with respect to a number of infectious diseases, since those data provide information on sympathetic nervous system activity. While the data do not unequivocally support elevated noradrenergic signaling promoting psychological symptomatology with infection, many studies are consistent with this view.

Identifying Optimal Features from Heart Rate Variability for Early Detection of Sepsis in Pediatric Intensive Care

Sepsis as bacterial infection is the most common and costly causes of mortality in critically ill patients. The early diagnosis of sepsis is significantly important for effective treatment. In this study, over a period of two years, the electrocardiogram of nearly 500 pediatric and neonate patients with heart diseases were collected in 24 hours before diagnosis. The collected data of 22 patients were studied including 11 sepsis patients with positive blood cultures and 11 non-sepsis patients. After extracting the HRV (Heart Rate Variability) signal, 28 linear and nonlinear features according to previous research were extracted. By using the relative entropy method as a feature selection technique, the extracted features were evaluated for their ability to discriminate the data in sepsis and non-sepsis groups, and the best features were entered into the classification process. Using the four classification models of SVM, LDA, KNN and Decision Tree, the accuracy of 86.36% was obtained with Decision Tree for discrimination of sepsis patients from other patients.

Serum amyloid A1 as a biomarker for radiation dose estimation and lethality prediction in irradiated mouse

Background

Fast and reliable biomarkers are needed to distinguish whether individuals were exposed or not to radiation and assess radiation dose, and to predict the severity of radiation damage in a large-scale radiation accident. Serum amyloid A1 (SAA1) is a protein induced by multiple factors including inflammatory. Therefore, this study aimed at exploring the role of SAA1 in the radiation dose estimation and lethality prediction after radiation.

Methods

C57BL/6J female mice were exposed to total body irradiation (TBI) at different doses and time points and amifostine, a drug used to reduce the side effects of radiotherapy, was injected before irradiation. Patients with nasopharyngeal carcinoma subjected to radiotherapy were used as the irradiation model in humans.

Results

A moderate SAA1 increase was observed at 6 hours in serum samples from irradiated mice at all doses used, with a peak at 12 hours, then decreased to day 3 after exposure. A second SAA1 increase was observed from day 5 to 7, which was associated to subsequent lethality. Treatment with amifostine before irradiation could prevent mice death and inhibit the second SAA1 increase. SAA1 increase after radiation was confirmed in human serum of nasopharyngeal carcinoma patients after radiotherapy.

Conclusions

Serum SAA1 levels could represent a biomarker for radiation dose estimation and its second increase might be a useful lethality indicator after radiation in a mouse model.

A healthy dose of chaos: Using fractal frameworks for engineering higher-fidelity biomedical systems

Optimal levels of chaos and fractality are distinctly associated with physiological health and function in natural systems. Chaos is a type of nonlinear dynamics that tends to exhibit seemingly random structures, whereas fractality is a measure of the extent of organization underlying such structures. Growing bodies of work are demonstrating both the importance of chaotic dynamics for proper function of natural systems, as well as the suitability of fractal mathematics for characterizing these systems. Here, we review how measures of fractality that quantify the dose of chaos may reflect the state of health across various biological systems, including: brain, skeletal muscle, eyes and vision, lungs, kidneys, tumours, cell regulation, skin and wound repair, bone, vasculature, and the heart. We compare how reports of either too little or too much chaos and fractal complexity can be damaging to normal biological function, and suggest that aiming for the healthy dose of chaos may be an effective strategy for various biomedical applications. We also discuss rising examples of the implementation of fractal theory in designing novel materials, biomedical devices, diagnostics, and clinical therapies. Finally, we explain important mathematical concepts of fractals and chaos, such as fractal dimension, criticality, bifurcation, and iteration, and how they are related to biology. Overall, we promote the effectiveness of fractals in characterizing natural systems, and suggest moving towards using fractal frameworks as a basis for the research and development of better tools for the future of biomedical engineering.

Early Postnatal Heart Rate Variability in Healthy Newborn Infants

Background

Despite the increasing interest in fetal and neonatal heart rate variability (HRV) analysis and its potential use as a tool for early disease stratification, no studies have previously described the normal trends of HRV in healthy babies during the first hours of postnatal life.

Methods

We prospectively recruited 150 healthy babies from the postnatal ward and continuously recorded their electrocardiogram during the first 24 h after birth. Babies were included if born in good condition and stayed with their mother. Babies requiring any medication or treatment were excluded. Five-minute segments of the electrocardiogram (non-overlapping time-windows) with more than 90% consecutive good quality beats were included in the calculation of hourly medians and interquartile ranges to describe HRV trends over the first 24 h. We used multilevel mixed effects regression with auto-regressive covariance structure for all repeated measures analysis and t-tests to compare group differences. Non-normally distributed variables were log-transformed.

Results

Nine out of 16 HRV metrics (including heart rate) changed significantly over the 24 h [Heart rate p < 0.01; Standard deviation of the NN intervals p = 0.01; Standard deviation of the Poincaré plot lengthwise p < 0.01; Cardiac sympathetic index (CSI) p < 0.01; Normalized high frequency power p = 0.03; Normalized low frequency power p < 0.01; Total power p < 0.01; HRV index p = 0.01; Parseval index p = 0.03], adjusted for relevant clinical variables. We observed an increase in several HRV metrics during the first 6 h followed by a gradual normalization by approximately 12 h of age. Between 6 and 12 h of age, only heart rate and the normalized low frequency power changed significantly, while between 12 and 18 h no metric, other than heart rate, changed significantly. Analysis with multilevel mixed effects regression analysis (multivariable) revealed that gestational age, reduced fetal movements, cardiotocography and maternal chronic or pregnancy induced illness were significant predictors of several HRV metrics.

Conclusion

Heart rate variability changes significantly during the first day of life, particularly during the first 6 h. The significant correlations between HRV and clinical risk variables support the hypothesis that HRV is a good indicator of overall wellbeing of a baby and is sensitive to detect birth-related stress and monitor its resolution over time.

Combining quick sequential organ failure assessment score with heart rate variability may improve predictive ability for mortality in septic patients at the emergency department

Background

Although the quick Sequential Organ Failure Assessment (qSOFA) score was recently introduced to identify patients with suspected infection/sepsis, it has limitations as a predictive tool for adverse outcomes. We hypothesized that combining qSOFA score with heart rate variability (HRV) variables improves predictive ability for mortality in septic patients at the emergency department (ED).

Methods

This was a retrospective study using the electronic medical record of a tertiary care hospital in Singapore between September 2014 and February 2017. All patients aged 21 years or older who were suspected with infection/sepsis in the ED and received electrocardiography monitoring with ZOLL X Series Monitor (ZOLL Medical Corporation, Chelmsford, MA) were included. We fitted a logistic regression model to predict the 30-day mortality using one of the HRV variables selected from one of each three domains those previously reported as strong association with mortality (i.e. standard deviation of NN [SDNN], ratio of low frequency to high frequency power [LF/HF], detrended fluctuation analysis α-2 [DFA α-2]) in addition to the qSOFA score. The predictive accuracy was assessed with other scoring systems (i.e. qSOFA alone, National Early Warning Score, and Modified Early Warning Score) using the area under the receiver operating characteristic curve.

Results

A total of 343 septic patients were included. Non-survivors were significantly older (survivors vs. non-survivors, 65.7 vs. 72.9, p <0.01) and had higher qSOFA (0.8 vs. 1.4, p <0.01) as compared to survivors. There were significant differences in HRV variables between survivors and non-survivors including SDNN (23.7s vs. 31.8s, p = 0.02), LF/HF (2.8 vs. 1.5, p = 0.02), DFA α-2 (1.0 vs. 0.7, P < 0.01). Our prediction model using DFA-α-2 had the highest c-statistic of 0.76 (95% CI, 0.70 to 0.82), followed by qSOFA of 0.68 (95% CI, 0.62 to 0.75), National Early Warning Score at 0.67 (95% CI, 0.61 to 0.74), and Modified Early Warning Score at 0.59 (95% CI, 0.53 to 0.67).

Conclusions

Adding DFA-α-2 to the qSOFA score may improve the accuracy of predicting in-hospital mortality in septic patients who present to the ED. Further multicenter prospective studies are required to confirm our results.