Hidden Markov models for monitoring circadian rhythmicity in telemetric activity data

Molecular characterization of the circadian clock in patients with Parkinson's disease-CLOCK4PD Study protocol

INTRODUCTION

Circadian rhythms (CRs) orchestrate intrinsic 24-hour oscillations which synchronize an organism's physiology and behaviour with respect to daily cycles. CR disruptions have been linked to Parkinson's Disease (PD), the second most prevalent neurodegenerative disorder globally, and are associated to several PD-symptoms such as sleep disturbances. Studying molecular changes of CR offers a potential avenue for unravelling novel insights into the PD progression, symptoms, and can be further used for optimization of treatment strategies. Yet, a comprehensive characterization of the alterations at the molecular expression level for core-clock and clock-controlled genes in PD is still missing.

METHODS AND ANALYSIS

The proposed study protocol will be used to characterize expression profiles of circadian genes obtained from saliva samples in PD patients and controls. For this purpose, 20 healthy controls and 70 PD patients will be recruited. Data from clinical assessment, questionnaires, actigraphy tracking and polysomnography will be collected and clinical evaluations will be repeated as a follow-up in one-year time. We plan to carry out sub-group analyses considering several clinical factors (e.g., biological sex, treatment dosages, or fluctuation of symptoms), and to correlate reflected changes in CR of measured genes with distinct PD phenotypes (diffuse malignant and mild/motor-predominant). Additionally, using NanoStringⓇ multiplex technology on a subset of samples, we aim to further explore potential CR alterations in hundreds of genes involved in neuropathology pathways.

DISCUSSION

CLOCK4PD is a mono-centric, non-interventional observational study aiming at the molecular characterization of CR alterations in PD. We further plan to determine physiological modifications in sleep and activity patterns, and clinical factors correlating with the observed CR changes. Our study may provide valuable insights into the intricate interplay between CR and PD with a potential to be used as a predictor of circadian alterations reflecting distinct disease phenotypes, symptoms, and progression outcomes.

Validating CircaCP: a generic sleep-wake cycle detection algorithm for unlabelled actigraphy data

Sleep-wake (SW) cycle detection is a key step for extracting temporal sleep metrics from actigraphy. Various supervised learning algorithms have been developed, yet their generalizability from sensor to sensor or study to study is questionable. In this paper, we detail and validate an unsupervised algorithm-CircaCP-for detecting SW cycles from actigraphy. It first uses a robust cosinor model to estimate circadian rhythm, then searches for a single change point (CP) within each circadian cycle. Using CircaCP, we estimated sleep/wake onset times (S/WOTs) from 2125 individuals' data in the MESA sleep study and compared the estimated S/WOTs against self-reported S/WOT event markers, using Bland-Altman analysis as well as variance component analysis. On average, SOTs estimated by CircaCP were 3.6 min behind those reported by event markers, and WOTs by CircaCP were less than 1 min behind those reported by markers. These differences accounted for less than 0.2% variability in S/WOTs, considering other sources of between-subject variations. Rooted in first principles of human circadian rhythms, our algorithm transferred seamlessly from children's hip-worn ActiGraph data to ageing adults' wrist-worn Actiwatch data. The generalizability of our algorithm suggests that it can be widely applied to actigraphy collected by other sensors and studies.

Digital Remote Monitoring Using an mHealth Solution for Survivors of Cancer: Protocol for a Pilot Observational Study

BACKGROUND

Healthy lifestyle interventions have a positive impact on multiple disease trajectories, including cancer-related outcomes. Specifically, appropriate habitual physical activity, adequate sleep, and a regular wholesome diet are of paramount importance for the wellness and supportive care of survivors of cancer. Mobile health (mHealth) apps have the potential to support novel tailored lifestyle interventions.

OBJECTIVE

This observational pilot study aims to assess the feasibility of mHealth multidimensional longitudinal monitoring in survivors of cancer. The primary objective is to test the compliance (user engagement) with the monitoring solution. Secondary objectives include recording clinically relevant subjective and objective measures collected through the digital solution.

METHODS

This is a monocentric pilot study taking place in Bangor, Wales, United Kingdom. We plan to enroll up to 100 adult survivors of cancer not receiving toxic anticancer treatment, who will provide self-reported behavioral data recorded via a dedicated app and validated questionnaires and objective data automatically collected by a paired smartwatch over 16 weeks. The participants will continue with their normal routine surveillance care for their cancer. The primary end point is feasibility (eg, mHealth monitoring acceptability). Composite secondary end points include clinically relevant patient-reported outcome measures (eg, the Edmonton Symptom Assessment System score) and objective physiological measures (eg, step counts). This trial received a favorable ethical review in May 2023 (Integrated Research Application System 301068).

RESULTS

This study is part of an array of pilots within a European Union funded project, entitled "GATEKEEPER," conducted at different sites across Europe and covering various chronic diseases. Study accrual is anticipated to commence in January 2024 and continue until June 2024. It is hypothesized that mHealth monitoring will be feasible in survivors of cancer; specifically, at least 50% (50/100) of the participants will engage with the app at least once a week in 8 of the 16 study weeks.

CONCLUSIONS

In a population with potentially complex clinical needs, this pilot study will test the feasibility of multidimensional remote monitoring of patient-reported outcomes and physiological parameters. Satisfactory compliance with the use of the app and smartwatch, whether confirmed or infirmed through this study, will be propaedeutic to the development of innovative mHealth interventions in survivors of cancer.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/52957.

Dimensionality reduction and features visual representation based on conditional probabilities applied to activity classification

A large part of the information emitted by contemporary technological devices comes in the form of time series. The massive commercialization of these kinds of devices has made the study of time series feature extraction techniques acquire a vital relevance in last years. Two main things are essential when applying feature extraction techniques to time series: to reduce the dimensionality so it occupies the least amount of storage memory possible, and to make features that contain the relevant information regarding the nature of the data set and the goals to be achieved. For this purpose, we propose in this work a brand new technique called the State Changes Representation for Time Series (SCRTS), which relies on the relevant data associated with the conditional probabilities of the time series (also known in the literature as Markov model's features), and the distribution of its values. This method is length-independent, which means that we can apply it to time series of different dimensions obtaining the same number of features for each one. Also, it provides a visual representation of the input data, so it is possible to interpret what makes a certain time series different from the other. After explaining how it works, we apply it to 3 different wearable accelerometer data sets. This algorithm reduces the original dimension of the time series considerably (in the best case from 5499 values to 31), having a good performance in the classification results (in the best chance with an accuracy of 98%).

Efficient assessment of real-world dynamics of circadian rhythms in heart rate and body temperature from wearable data

Laboratory studies have made unprecedented progress in understanding circadian physiology. Quantifying circadian rhythms outside of laboratory settings is necessary to translate these findings into real-world clinical practice. Wearables have been considered promising way to measure these rhythms. However, their limited validation remains an open problem. One major barrier to implementing large-scale validation studies is the lack of reliable and efficient methods for circadian assessment from wearable data. Here, we propose an approximation-based least-squares method to extract underlying circadian rhythms from wearable measurements. Its computational cost is ∼ 300-fold lower than that of previous work, enabling its implementation in smartphones with low computing power. We test it on two large-scale real-world wearable datasets: [Formula: see text] of body temperature data from cancer patients and ∼ 184 000 days of heart rate and activity data collected from the 'Social Rhythms' mobile application. This shows successful extraction of real-world dynamics of circadian rhythms. We also identify a reasonable harmonic model to analyse wearable data. Lastly, we show our method has broad applicability in circadian studies by embedding it into a Kalman filter that infers the state space of the molecular clocks in tissues. Our approach facilitates the translation of scientific advances in circadian fields into actual improvements in health.

Human Activity Recognition with an HMM-Based Generative Model

Human activity recognition (HAR) has become an interesting topic in healthcare. This application is important in various domains, such as health monitoring, supporting elders, and disease diagnosis. Considering the increasing improvements in smart devices, large amounts of data are generated in our daily lives. In this work, we propose unsupervised, scaled, Dirichlet-based hidden Markov models to analyze human activities. Our motivation is that human activities have sequential patterns and hidden Markov models (HMMs) are some of the strongest statistical models used for modeling data with continuous flow. In this paper, we assume that emission probabilities in HMM follow a bounded-scaled Dirichlet distribution, which is a proper choice in modeling proportional data. To learn our model, we applied the variational inference approach. We used a publicly available dataset to evaluate the performance of our proposed model.

A hidden Markov modeling approach combining objective measure of activity and subjective measure of self-reported sleep to estimate the sleep-wake cycle

Characterizing the sleep-wake cycle in adolescents is an important prerequisite to better understand the association of abnormal sleep patterns with subsequent clinical and behavioral outcomes. The aim of this research was to develop hidden Markov models (HMM) that incorporate both objective (actigraphy) and subjective (sleep log) measures to estimate the sleep-wake cycle using data from the NEXT longitudinal study, a large population-based cohort study. The model was estimated with a negative binomial distribution for the activity counts (1-minute epochs) to account for overdispersion relative to a Poisson process. Furthermore, self-reported measures were dichotomized (for each one-minute interval) and subject to misclassification. We assumed that the unobserved sleep-wake cycle follows a two-state Markov chain with transitional probabilities varying according to a circadian rhythm. Maximum-likelihood estimation using a backward-forward algorithm was applied to fit the longitudinal data on a subject by subject basis. The algorithm was used to reconstruct the sleep-wake cycle from sequences of self-reported sleep and activity data. Furthermore, we conduct simulations to examine the properties of this approach under different observational patterns including both complete and partially observed measurements on each individual.

Circadian disruption and cancer- and treatment-related symptoms

Cancer patients experience a number of co-occurring side- and late-effects due to cancer and its treatment including fatigue, sleep difficulties, depressive symptoms, and cognitive impairment. These symptoms can impair quality of life and may persist long after treatment completion. Furthermore, they may exacerbate each other's intensity and development over time. The co-occurrence and interdependent nature of these symptoms suggests a possible shared underlying mechanism. Thus far, hypothesized mechanisms that have been purported to underlie these symptoms include disruptions to the immune and endocrine systems. Recently circadian rhythm disruption has emerged as a related pathophysiological mechanism underlying cancer- and cancer-treatment related symptoms. Circadian rhythms are endogenous biobehavioral cycles lasting approximately 24 hours in humans and generated by the circadian master clock - the hypothalamic suprachiasmatic nucleus. The suprachiasmatic nucleus orchestrates rhythmicity in a wide range of bodily functions including hormone levels, body temperature, immune response, and rest-activity behaviors. In this review, we describe four common approaches to the measurement of circadian rhythms, highlight key research findings on the presence of circadian disruption in cancer patients, and provide a review of the literature on associations between circadian rhythm disruption and cancer- and treatment-related symptoms. Implications for future research and interventions will be discussed.

Measuring Daily Activity Rhythms in Young Adults at Risk of Affective Instability Using Passively Collected Smartphone Data: Observational Study

BACKGROUND

Irregularities in circadian rhythms have been associated with adverse health outcomes. The regularity of rhythms can be quantified using passively collected smartphone data to provide clinically relevant biomarkers of routine.

OBJECTIVE

This study aims to develop a metric to quantify the regularity of activity rhythms and explore the relationship between routine and mood, as well as demographic covariates, in an outpatient psychiatric cohort.

METHODS

Passively sensed smartphone data from a cohort of 38 young adults from the Penn or Children's Hospital of Philadelphia Lifespan Brain Institute and Outpatient Psychiatry Clinic at the University of Pennsylvania were fitted with 2-state continuous-time hidden Markov models representing active and resting states. The regularity of routine was modeled as the hour-of-the-day random effects on the probability of state transition (ie, the association between the hour-of-the-day and state membership). A regularity score, Activity Rhythm Metric, was calculated from the continuous-time hidden Markov models and regressed on clinical and demographic covariates.

RESULTS

Regular activity rhythms were associated with longer sleep durations (P=.009), older age (P=.001), and mood (P=.049).

CONCLUSIONS

Passively sensed Activity Rhythm Metrics are an alternative to existing metrics but do not require burdensome survey-based assessments. Low-burden, passively sensed metrics based on smartphone data are promising and scalable alternatives to traditional measurements.

Digital circadian and sleep health in individual hospital shift workers: A cross sectional telemonitoring study

BACKGROUND

Telemonitoring of circadian and sleep cycles could identify shift workers at increased risk of poor health, including cancer and cardiovascular diseases, thus supporting personalized prevention.

METHODS

The Circadiem cross-sectional study aimed at determining early warning signals of risk of health alteration in hospital nightshifters (NS) versus dayshifters (DS, alternating morning and afternoon shifts). Circadian rhythmicity in activity, sleep, and temperature was telemonitored on work and free days for one week. Participants wore a bluetooth low energy thoracic accelerometry and temperature sensor that was wirelessly connected to a GPRS gateway and a health data hub server. Hidden Markov modelling of activity quantified Rhythm Index, rest quality (probability, p1-1, of remaining at rest), and rest duration. Spectral analyses determined periods in body surface temperature and accelerometry. Parameters were compared and predictors of circadian and sleep disruption were identified by multivariate analyses using information criteria-based model selection. Clusters of individual shift work response profiles were recognized.

FINDINGS

Of 140 per-protocol participants (133 females), there were 63 NS and 77 DS. Both groups had similar median rest amount, yet NS had significantly worse median rest-activity Rhythm Index (0·38 [IQR, 0·29-0·47] vs. 0·69 [0·60-0·77], p<0·0001) and rest quality p1-1 (0·94 [0·94-0·95] vs 0·96 [0·94-0·97], p<0·0001) over the whole study week. Only 48% of the NS displayed a circadian period in temperature, as compared to 70% of the DS (p=0·026). Poor p1-1 was associated with nightshift work on both work (p<0·0001) and free days (p=0·0098). The number of years of past night work exposure predicted poor rest-activity Rhythm Index jointly with shift type, age and chronotype on workdays (p= 0·0074), and singly on free days (p=0·0005).

INTERPRETATION

A dedicated analysis toolbox of streamed data from a wearable device identified circadian and sleep rhythm markers, that constitute surrogate candidate endpoints of poor health risk in shift-workers.

FUNDING

French Agency for Food, Environmental and Occupational Health & Safety (EST-2014/1/064), University of Warwick, Medical Research Council (United Kingdom, MR/M013170), Cancer Research UK(C53561/A19933).

Artificial intelligence and machine learning in precision and genomic medicine

The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.

Artificial intelligence and machine learning in precision and genomic medicine

The advancement of precision medicine in medical care has led behind the conventional symptom-driven treatment process by allowing early risk prediction of disease through improved diagnostics and customization of more effective treatments. It is necessary to scrutinize overall patient data alongside broad factors to observe and differentiate between ill and relatively healthy people to take the most appropriate path toward precision medicine, resulting in an improved vision of biological indicators that can signal health changes. Precision and genomic medicine combined with artificial intelligence have the potential to improve patient healthcare. Patients with less common therapeutic responses or unique healthcare demands are using genomic medicine technologies. AI provides insights through advanced computation and inference, enabling the system to reason and learn while enhancing physician decision making. Many cell characteristics, including gene up-regulation, proteins binding to nucleic acids, and splicing, can be measured at high throughput and used as training objectives for predictive models. Researchers can create a new era of effective genomic medicine with the improved availability of a broad range of datasets and modern computer techniques such as machine learning. This review article has elucidated the contributions of ML algorithms in precision and genome medicine.

Holistic Needs Assessment of Cancer Survivors-Supporting the Process Through Digital Monitoring of Circadian Physiology

The year 2022 could represent a significant juncture in the incorporation of mHealth solutions in routine cancer care. With the recent global COVID-19 pandemic leading a surge in both observation- and intervention-based studies predominantly aimed at remote monitoring there has been huge intellectual investment in developing platforms able to provide real time analytics that are readily usable. Another fallout from the pandemic has seen record waiting times and delayed access to cancer therapies leading to exhausting pressures on global healthcare providers. It seems an opportune time to utilize this boom in platforms to offer more efficient “at home” clinical assessments and less “in department” time for patients. Here, we will focus specifically on the role of digital tools around cancer survivorship, a relevant aspect of the cancer journey, particularly benefiting from integrative approaches. Within that context a further concept will be introduced and that is of the likely upsurge in circadian-based interpretation of continuous monitoring and the engendered therapeutic modifications. Chronobiology across the 24-hour span has long been understood to control key bodily aspects and circadian dysregulation plays a significant role in the risk of cancer and also the response to therapy and therefore progressive outcome. The rapid improvement in minimally invasive monitoring devices is, in the opinion of the authors, likely to advance introducing chronobiological amendments to routine clinical practices with positive impact on cancer survivors.

circadian rhythms are not captured equal: Exploring Circadian metrics extracted by differentcomputational methods from smartphone accelerometer and GPS sensors in daily life tracking

Objective

To identify the differences between circadian rhythm (CR) metrics characterized by different mobile sensors and computational methods.

Methods

We used smartphone tracking and daily survey data from 225 college student participants, applied four methods (survey construct automation, cosinor regression, non-parametric method, Fourier analysis) on two types of smartphone sensor data (GPS, accelerometer) to characterize CR. We explored the inter-relations among the extracted circadian metrics as well as between the circadian metrics and participants’ self-reported mood and sleep outcomes.

Results

Compared to GPS signals, smartphone accelerometer activity follows an intradaily distribution that starts earlier in the day, winds down later, reaches half cumulative activity about the same time, conforms less to a sinusoidal wave, and exhibits more intradaily fragmentation but higher CR strength and lower interdaily disruption. We found a notable negative correlation between intradaily variability and CR strength especially pronounced in GPS activity. Self-reported sleep and mood outcomes showed significant correlations with particular CR metrics.

Conclusions

We revealed significant inter-relations and discrepancies in the circadian metrics discovered from two smartphone sensors and four CR algorithms and their bearings on wellbeing indicators such as sleep quality and loneliness.

Circadian and chemotherapy-related changes in urinary modified nucleosides excretion in patients with metastatic colorectal cancer

Urinary levels of modified nucleosides reflect nucleic acids turnover and can serve as non-invasive biomarkers for monitoring tumour circadian dynamics, and treatment responses in patients with metastatic colorectal cancer. In 39 patients, median overnight urinary excretion of LC-HRMS determinations of pseudouridine, was ~ tenfold as large as those of 1-methylguanosine, 1-methyladenosine, or 4-acetylcytidine, and ~ 100-fold as large as those of adenosine and cytidine. An increase in any nucleoside excretion after chemotherapy anticipated plasma carcinoembryonic antigen progression 1–2 months later and was associated with poor survival. Ten fractionated urines were collected over 2-days in 29 patients. The median value of the rhythm-adjusted mean of urinary nucleoside excretion varied from 64.3 for pseudouridine down to 0.61 for cytidine. The rhythm amplitudes relative to the 24-h mean of 6 nucleoside excretions were associated with rest duration, supporting a tight link between nucleosides turnover and the rest-activity rhythm. Moreover, the amplitude of the 1-methylguanosine rhythm was correlated with the rest-activity dichotomy index, a significant predictor of survival outcome in prior studies. In conclusion, urinary excretion dynamics of modified nucleosides appeared useful for the characterization of the circadian control of cellular proliferation and for tracking early responses to treatments in colorectal cancer patients.

Identifying the Recurrence of Sleep Apnea Using A Harmonic Hidden Markov Model

We propose to model time-varying periodic and oscillatory processes by means of a hidden Markov model where the states are defined through the spectral properties of a periodic regime. The number of states is unknown along with the relevant periodicities, the role and number of which may vary across states. We address this inference problem by a Bayesian nonparametric hidden Markov model assuming a sticky hierarchical Dirichlet process for the switching dynamics between different states while the periodicities characterizing each state are explored by means of a trans-dimensional Markov chain Monte Carlo sampling step. We develop the full Bayesian inference algorithm and illustrate the use of our proposed methodology for different simulation studies as well as an application related to respiratory research which focuses on the detection of apnea instances in human breathing traces.

Telemonitored Human Circadian Temperature Dynamics During Daily Routine

BACKGROUND

Circadian rhythms in body temperature coordinate peripheral molecular clocks, hence they could potentially predict optimal treatment timing (chronotherapy) in individual patients. Circadian parameters in chest surface body temperature (Chesttemp) were recorded remotely and in real time through the use of wearable sensors.

METHODS

The dynamics of circadian oscillations in Chesttemp and core body temperature (Coretemp) and their moderation by sex and age were analysed in 38 men and 50 women, aged 21-78 years. In two studies (ST1 and ST2), Chesttemp was measured every minute and teletransmitted using a BLE-connected sensor for 3.6-28.3 days. Additionally, in ST2, Coretemp was recorded per minute in 33 age- and sex-stratified subjects using electronic ingestible pills with radio-frequency transmissions. Circadian parameters were computed using spectral analysis and cosinor modelling. The temporal relations between Chesttemp and Coretemp cosinor parameters were summarised with principal component (PC) analysis. The effect of sex and age was analysed through multivariate regression.

RESULTS

Using spectral analysis, a dominant period of 24- or 12-h was identified in 93.2% of the Chesttemp and in 100% of the Coretemp time series. The circadian parameters varied largely between-subjects both for Chesttemp (ranges: mesors, 33.2-36.6°C; amplitudes, 0.2-2.5°C; acrophases, 14:05-7:40), and Coretemp (mesors, 36.6-37.5°C; amplitudes, 0.2-0.7°C; bathyphases, 23:50-6:50). Higher PC loadings mainly corresponded to (i) large Chesttemp amplitudes, and phase advance of both temperature rhythms for the first PC (PC1, 27.2% of variance var.), (ii) high mesors in both temperature rhythms for PC2 (22.4% var.), and (iii) large Coretemp amplitudes for PC3 (12.9% var.). Chesttemp and Coretemp mesors and PC2 loadings decreased in females, while remaining quite stable in males as a function of age. In contrast, Coretemp amplitude and PC3 loadings increased with age in females, but decreased in males. Finally, older subjects, both female and male, displayed a reduction in ultradian variabilities, and an increase in both Chesttemp circadian amplitude and PC1 loadings.

INTERPRETATION

The dynamics relations between Chesttemp and Coretemp rhythms were largely moderated by age and sex, with results suggesting that treatment timing could be most critical for therapeutic index in women and in order people.

Novel approach to modeling high-frequency activity data to assess therapeutic effects of analgesics in chronic pain conditions

Osteoarthritis (OA) is a chronic condition often associated with pain, affecting approximately fourteen percent of the population, and increasing in prevalence. A globally aging population have made treating OA-associated pain as well as maintaining mobility and activity a public health priority. OA affects all mammals, and the use of spontaneous animal models is one promising approach for improving translational pain research and the development of effective treatment strategies. Accelerometers are a common tool for collecting high-frequency activity data on animals to study the effects of treatment on pain related activity patterns. There has recently been increasing interest in their use to understand treatment effects in human pain conditions. However, activity patterns vary widely across subjects; furthermore, the effects of treatment may manifest in higher or lower activity counts or in subtler ways like changes in the frequency of certain types of activities. We use a zero inflated Poisson hidden semi-Markov model to characterize activity patterns and subsequently derive estimators of the treatment effect in terms of changes in activity levels or frequency of activity type. We demonstrate the application of our model, and its advance over traditional analysis methods, using data from a naturally occurring feline OA-associated pain model.

Biological Rhythm and Chronotype: New Perspectives in Health

The circadian rhythm plays a fundamental role in regulating biological functions, including sleep–wake preference, body temperature, hormonal secretion, food intake, and cognitive and physical performance. Alterations in circadian rhythm can lead to chronic disease and impaired sleep. The circadian rhythmicity in human beings is represented by a complex phenotype. Indeed, over a 24-h period, a person’s preferred time to be more active or to sleep can be expressed in the concept of morningness–eveningness. Three chronotypes are distinguished: Morning, Neither, and Evening-types. Interindividual differences in chronotypes need to be considered to reduce the negative effects of circadian disruptions on health. In the present review, we examine the bi-directional influences of the rest–activity circadian rhythm and sleep–wake cycle in chronic pathologies and disorders. We analyze the concept and the main characteristics of the three chronotypes.

Disrupted Circadian Rest-Activity Cycles in Inflammatory Bowel Disease Are Associated With Aggressive Disease Phenotype, Subclinical Inflammation, and Dysbiosis

Patients with inflammatory bowel disease (IBD)-Crohn's disease (CD), and ulcerative colitis (UC), have poor sleep quality. Sleep and multiple immunologic and gastrointestinal processes in the body are orchestrated by the circadian clock, and we recently reported that a later category or chronotype of the circadian clock was associated with worse IBD specific outcomes. The goal of this study was to determine if circadian misalignment by rest-activity cycles is associated with markers of aggressive disease, subclinical inflammation, and dysbiosis in IBD. A total of 42 patients with inactive but biopsy-proven CD or UC and 10 healthy controls participated in this prospective cohort study. Subjects were defined as having an aggressive IBD disease history (steroid dependence, use of biologic or immunomodulator, and/or surgery) or non-aggressive history. All participants did two weeks of wrist actigraphy, followed by measurement of intestinal permeability and stool microbiota. Wrist actigraphy was used to calculate circadian markers of rest-activity- interdaily stability (IS), intradaily variability (IV), and relative amplitude (RA). Aggressive IBD history was associated with decrease rest-activity stability (IS) and increased fragmentation compared to non-aggressive IBD and health controls at 0.39 ±.15 vs. 0.51 ± 0.10 vs. 0.55 ± 0.09 (P < 0.05) and 0.83 ± 0.20 vs. 0.72 ± 0.14 (P < 0.05) but not HC at 0.72 ± 0.14 (P = 0.08); respectively. There was not a significant difference in RA by IBD disease history. Increased intestinal permeability and increased TNF-α levels correlated with an increased rest activity fragmentation (IV) at R = 0.35, P < 0.05 and R = 0.37, P < 0.05, respectively; and decreased rest-activity amplitude (RA) was associated with increased stool calprotectin at R = 0.40, P < 0.05. Analysis of intestinal microbiota showed a significant decrease in commensal butyrate producing taxa and increased pro-inflammatory bacteria with disrupted rest-activity cycles. In this study, different components of circadian misalignment by rest-activity cycles were associated with a more aggressive IBD disease history, increased intestinal permeability, stool calprotectin, increased pro-inflammatory cytokines, and dysbiosis. Wrist activity allows for an easy non-invasive assessment of circadian activity which may be an important biomarker of inflammation in IB.

Wearable Device Heart Rate and Activity Data in an Unsupervised Approach to Personalized Sleep Monitoring: Algorithm Validation

Background

The proliferation of wearable devices that collect activity and heart rate data has facilitated new ways to measure sleeping and waking durations unobtrusively and longitudinally. Most existing sleep/wake identification algorithms are based on activity only and are trained on expensive and laboriously annotated polysomnography (PSG). Heart rate can also be reflective of sleep/wake transitions, which has motivated its investigation herein in an unsupervised algorithm. Moreover, it is necessary to develop a personalized approach to deal with interindividual variance in sleep/wake patterns.

Objective

We aimed to develop an unsupervised personalized sleep/wake identification algorithm using multifaceted data to explore the benefits of incorporating both heart rate and activity level in these types of algorithms and to compare this approach’s output with that of an existing commercial wearable device’s algorithms.

Methods

In this study, a total of 14 community-dwelling older adults wore wearable devices (Fitbit Alta; Fitbit Inc) 24 hours a day and 7 days a week over period of 3 months during which their heart rate and activity data were collected. After preprocessing the data, a model was developed to distinguish sleep/wake states based on each individual’s data. We proposed the use of hidden Markov models and compared different modeling schemes. With the best model selected, sleep/wake patterns were characterized by estimated parameters in hidden Markov models, and sleep/wake states were identified.

Results

When applying our proposed algorithm on a daily basis, we found there were significant differences in estimated parameters between weekday models and weekend models for some participants.

Conclusions

Our unsupervised approach can be effectively implemented based on an individual’s multifaceted sleep-related data from a commercial wearable device. A personalized model is shown to be necessary given the interindividual variability in estimated parameters.

Tele-Monitoring of Cancer Patients' Rhythms during Daily Life Identifies Actionable Determinants of Circadian and Sleep Disruption

The dichotomy index (I < O), a quantitative estimate of the circadian regulation of daytime activity and sleep, predicted overall cancer survival and emergency hospitalization, supporting its integration in a mHealth platform. Modifiable causes of I < O deterioration below 97.5%—(I < O)_low—were sought in 25 gastrointestinal cancer patients and 33 age- and sex-stratified controls. Rest-activity and temperature were tele-monitored with a wireless chest sensor, while daily activities, meals, and sleep were self-reported for one week. Salivary cortisol rhythm and dim light melatonin onset (DLMO) were determined. Circadian parameters were estimated using Hidden Markov modelling, and spectral analysis. Actionable predictors of (I < O)_low were identified through correlation and regression analyses. Median compliance with protocol exceeded 95%. Circadian disruption—(I < O)_low—was identified in 13 (52%) patients and four (12%) controls (p = 0.002). Cancer patients with (I < O)_low had lower median activity counts, worse fragmented sleep, and an abnormal or no circadian temperature rhythm compared to patients with I < O exceeding 97.5%—(I < O)_high—(p < 0.012). Six (I < O)_low patients had newly-diagnosed sleep conditions. Altered circadian coordination of rest-activity and chest surface temperature, physical inactivity, and irregular sleep were identified as modifiable determinants of (I < O)_low. Circadian rhythm and sleep tele-monitoring results support the design of specific interventions to improve outcomes within a patient-centered systems approach to health care.

Disrupted diurnal oscillation of gut-derived Short chain fatty acids in shift workers drinking alcohol: Possible mechanism for loss of resiliency of intestinal barrier in disrupted circadian host

Microbiota derived short chain fatty acids (SCFAs) are produced by fermentation of nondigestible fiber, and are a key component in intestinal barrier homeostasis. Since the microbiome has diurnal fluctuations, we hypothesized that SCFAs in humans have a diurnal rhythm and their rhythmicity would be impacted by the host central circadian misalignment (night shift work) which would make intestinal barrier more susceptible to disruption by alcohol. To test this hypothesis, we studied 3 groups of subjects: patients with alcohol use disorder, but no liver disease (AD), healthy day workers (DW), and night workers (NW). All subjects were studied at baseline and then in DW and NW subjects after moderate daily alcohol (0.5 g/kg) for 7 days. Gut-derived plasma SCFAs showed a significant circadian oscillation by cosinor analysis in DW; however, SCFA in the AD and NW subjects lost 24-hour rhythmicity. Decrease in SCFA correlated with increased colonic permeability. Both chronic and moderate alcohol consumption for 1 week caused circadian disruption based on wrist actigraphy and urinary melatonin. Our study shows that (1) gut-derived plasma SCFAs have a diurnal rhythm in humans that is impacted by the central clock of the host; (2) moderate alcohol suppresses SCFAs which was associated with increased colonic permeability; and (3) less invasive urinary 6-SM correlated and rest-activity actigraphy correlated with plasma melatonin. Future studies are needed to examine the role circadian misalignment on gut derived SCFAs as possible mechanism for loss of intestinal barrier resiliency to injurious agents like alcohol.

Review of GPS collar deployments and performance on nonhuman primates

Over the past 20 years, GPS collars have emerged as powerful tools for the study of nonhuman primate (hereafter, "primate") movement ecology. As the size and cost of GPS collars have decreased and performance has improved, it is timely to review the use and success of GPS collar deployments on primates to date. Here we compile data on deployments and performance of GPS collars by brand and examine how these relate to characteristics of the primate species and field contexts in which they were deployed. The compiled results of 179 GPS collar deployments across 17 species by 16 research teams show these technologies can provide advantages, particularly in adding to the quality, quantity, and temporal span of data collection. However, aspects of this technology still require substantial improvement in order to make deployment on many primate species pragmatic economically. In particular, current limitations regarding battery lifespan relative to collar weight, the efficacy of remote drop-off mechanisms, and the ability to remotely retrieve data need to be addressed before the technology is likely to be widely adopted. Moreover, despite the increasing utility of GPS collars in the field, they remain substantially more expensive than VHF collars and tracking via handheld GPS units, and cost considerations of GPS collars may limit sample sizes and thereby the strength of inferences. Still, the overall high quality and quantity of data obtained, combined with the reduced need for on-the-ground tracking by field personnel, may help defray the high equipment cost. We argue that primatologists armed with the information in this review have much to gain from the recent, substantial improvements in GPS collar technology.

Influence of sleep-wake cycle on body mass index in female shift-working nurses with sleep quality as mediating variable

This study investigated the relationship between the sleep-wake cycle and body mass index (BMI) of female shift-working nurses and examine the mediating effect of sleep quality on this relationship. We recruited a total of 147 female nurses working monthly rotating shifts at a teaching hospital in Taiwan from the day (n=63), evening (n=50), and night (n=34) shifts. Our research instruments utilized a questionnaire to collect demographic and work-related information, the Pittsburgh Sleep Quality Index (PSQI), and actigraphs to record sleep patterns for seven consecutive days. The sleep-wake cycles were then estimated using the dichotomy index (I<O). The I<O values were negatively associated with both BMI (β=-0.28, p=0.001) and PSQI scores (β=-0.29, p<0.001), the bootstrapping results indicated that the estimate of the indirect effect was -0.28, and the 95% confidence interval ranged from -0.68 to -0.05. For female shift-working nurses, sleep quality mediates the influence of the sleep-wake cycle on BMI, indicating that the maintenance of a regular sleep-wake cycle and good sleep quality could be important for female shift-working nurses.

The future of sleep health: a data-driven revolution in sleep science and medicine

In recent years, there has been a significant expansion in the development and use of multi-modal sensors and technologies to monitor physical activity, sleep and circadian rhythms. These developments make accurate sleep monitoring at scale a possibility for the first time. Vast amounts of multi-sensor data are being generated with potential applications ranging from large-scale epidemiological research linking sleep patterns to disease, to wellness applications, including the sleep coaching of individuals with chronic conditions. However, in order to realise the full potential of these technologies for individuals, medicine and research, several significant challenges must be overcome. There are important outstanding questions regarding performance evaluation, as well as data storage, curation, processing, integration, modelling and interpretation. Here, we leverage expertise across neuroscience, clinical medicine, bioengineering, electrical engineering, epidemiology, computer science, mHealth and human-computer interaction to discuss the digitisation of sleep from a inter-disciplinary perspective. We introduce the state-of-the-art in sleep-monitoring technologies, and discuss the opportunities and challenges from data acquisition to the eventual application of insights in clinical and consumer settings. Further, we explore the strengths and limitations of current and emerging sensing methods with a particular focus on novel data-driven technologies, such as Artificial Intelligence.

Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine

Precision medicine is one of the recent and powerful developments in medical care, which has the potential to improve the traditional symptom-driven practice of medicine, allowing earlier interventions using advanced diagnostics and tailoring better and economically personalized treatments. Identifying the best pathway to personalized and population medicine involves the ability to analyze comprehensive patient information together with broader aspects to monitor and distinguish between sick and relatively healthy people, which will lead to a better understanding of biological indicators that can signal shifts in health. While the complexities of disease at the individual level have made it difficult to utilize healthcare information in clinical decision-making, some of the existing constraints have been greatly minimized by technological advancements. To implement effective precision medicine with enhanced ability to positively impact patient outcomes and provide real-time decision support, it is important to harness the power of electronic health records by integrating disparate data sources and discovering patient-specific patterns of disease progression. Useful analytic tools, technologies, databases, and approaches are required to augment networking and interoperability of clinical, laboratory and public health systems, as well as addressing ethical and social issues related to the privacy and protection of healthcare data with effective balance. Developing multifunctional machine learning platforms for clinical data extraction, aggregation, management and analysis can support clinicians by efficiently stratifying subjects to understand specific scenarios and optimize decision-making. Implementation of artificial intelligence in healthcare is a compelling vision that has the potential in leading to the significant improvements for achieving the goals of providing real-time, better personalized and population medicine at lower costs. In this study, we focused on analyzing and discussing various published artificial intelligence and machine learning solutions, approaches and perspectives, aiming to advance academic solutions in paving the way for a new data-centric era of discovery in healthcare.

Predictability of individual circadian phase during daily routine for medical applications of circadian clocks

BACKGROUNDCircadian timing of treatments can largely improve tolerability and efficacy in patients. Thus, drug metabolism and cell cycle are controlled by molecular clocks in each cell and coordinated by the core body temperature 24-hour rhythm, which is generated by the hypothalamic pacemaker. Individual circadian phase is currently estimated with questionnaire-based chronotype, center-of-rest time, dim light melatonin onset (DLMO), or timing of core body temperature (CBT) maximum (acrophase) or minimum (bathyphase).METHODSWe aimed at circadian phase determination and readout during daily routines in volunteers stratified by sex and age. We measured (a) chronotype, (b) every minute (q1min) CBT using 2 electronic pills swallowed 24 hours apart, (c) DLMO through hourly salivary samples from 1800 hours to bedtime, and (d) q1min accelerations and surface temperature at anterior chest level for 7 days, using a teletransmitting sensor. Circadian phases were computed using cosinor and hidden Markov modeling. Multivariate regression identified the combination of biomarkers that best predicted core temperature circadian bathyphase.RESULTSAmong the 33 participants, individual circadian phases were spread over 5 hours, 10 minutes (DLMO); 7 hours (CBT bathyphase); and 9 hours, 10 minutes (surface temperature acrophase). CBT bathyphase was accurately predicted, i.e., with an error less than 1 hour for 78.8% of the subjects, using a new digital health algorithm (INTime), combining time-invariant sex and chronotype score with computed center-of-rest time and surface temperature bathyphase (adjusted R2 = 0.637).CONCLUSIONINTime provided a continuous and reliable circadian phase estimate in real time. This model helps integrate circadian clocks into precision medicine and will enable treatment timing personalization following further validation.FUNDINGMedical Research Council, United Kingdom; AP-HP Foundation; and INSERM.

Bayesian Model Search for Nonstationary Periodic Time Series

We propose a novel Bayesian methodology for analyzing nonstationary time series that exhibit oscillatory behavior. We approximate the time series using a piecewise oscillatory model with unknown periodicities, where our goal is to estimate the change-points while simultaneously identifying the potentially changing periodicities in the data. Our proposed methodology is based on a trans-dimensional Markov chain Monte Carlo algorithm that simultaneously updates the change-points and the periodicities relevant to any segment between them. We show that the proposed methodology successfully identifies time changing oscillatory behavior in two applications which are relevant to e-Health and sleep research, namely the occurrence of ultradian oscillations in human skin temperature during the time of night rest, and the detection of instances of sleep apnea in plethysmographic respiratory traces. Supplementary materials for this article are available online.

Modelling reassurances of clinicians with hidden Markov models

BACKGROUND

A key element in the interaction between clinicians and patients with cancer is reassurance giving. Learning about the stochastic nature of reassurances as well as making inferential statements about the influence of covariates such as patient response and time spent on previous reassurances are of particular importance.

METHODS

We fit Hidden Markov Models (HMMs) to reassurance type from multiple time series of clinicians' reassurances, decoded from audio files of review consultations between patients with breast cancer and their therapeutic radiographer. Assuming a latent state process driving the observations process, HMMs naturally accommodate serial dependence in the data. Extensions to the baseline model such as including covariates as well as allowing for fixed effects for the different clinicians are straightforward to implement.

RESULTS

We found that clinicians undergo different states, in which they are more or less inclined to provide a particular type of reassurance. The states are very persistent, however switches occasionally occur. The lengthier the previous reassurance, the more likely the clinician is to stay in the current state.

CONCLUSIONS

HMMs prove to be a valuable tool and provide important insights for practitioners.

TRIAL REGISTRATION

Trial Registration number: ClinicalTrials.gov: NCT02599506. Prospectively registered on 11th March 2015.