Longitudinal Digital Phenotyping of Multiple Sclerosis Severity Using Passively Sensed Behaviors and Ecological Momentary Assessments

BackgroundLongitudinal tracking of multiple sclerosis (MS) symptoms in an individual’s environment may improve self-monitoring and clinical management for people with MS. Conventional symptom tracking methods rely on self-reports and clinical visits, which can be infrequent, subjective, and burdensome. Digital phenotyping using passively collected sensor data from smartphones and fitness trackers offers a promising alternative for continuous, real-time symptom monitoring with minimal patient burden.ObjectiveWe aimed to develop and evaluate a machine learning (ML)–based digital phenotyping approach to monitor the severity of clinically-relevant MS symptoms. We used passive sensing data to predict short-term fluctuations in patient-reported symptoms, including depressive symptoms, global MS symptom burden, severe fatigue, and poor sleep quality. Further, we examined the impact of incorporating behavioral context features and ecological momentary assessments on prediction performance.MethodsWe conducted a 12- to 24-week longitudinal study involving 104 people with MS, collecting passive sensor and behavioral health data. Smartphone sensors recorded call activity, location, and screen use, while fitness trackers captured heart rate, sleep patterns, and step count. We extracted patient-level behavioral features and categorized them into 2 feature sets: one from the prediction period (called action) and one from the preceding period (called context). Using an ML pipeline based on support vector machines and AdaBoost, we evaluated the predictive performance of sensor-based models, both with and without ecological momentary assessment inputs.ResultsBetween November 16, 2019, and January 24, 2021, overall, 104 people with MS (women: n=88, 84.6%; non-Hispanic White: n=97, 93.3%; mean age 44, SD 11.8 years) from a clinic-based cohort completed 12 weeks of data collection, including a subset of 44 participants (women: n=39, 89%; non-Hispanic White: n=42, 95%; mean age 45.7, SD 11.2 years) who completed 24 weeks of data collection. In total, we collected approximately 12,500 days of passive sensor and behavioral health data from the participants. Among the best-performing models with the least sensor data requirement, the ML algorithm predicted depressive symptoms with an accuracy of 80.6% (F1-score=0.76), high global MS symptom burden with an accuracy of 77.3% (F1-score=0.78), severe fatigue with an accuracy of 73.8% (F1-score=0.74), and poor sleep quality with an accuracy of 72.0% (F1-score=0.70). Further, sensor data were largely sufficient for predicting symptom severity, while the prediction of depressive symptoms benefited from minimal active patient input in the form of responses to 2 brief questions on the day before the prediction point.ConclusionsOur digital phenotyping approach using passive sensors on smartphones and fitness trackers may help patients with real-world, continuous self-monitoring of common symptoms in their own environment and assist clinicians with better triage of patient needs for timely interventions in MS and potentially other chronic neurological disorders.

BackgroundThe COVID-19 pandemic has broad negative impact on the physical and mental health of people with chronic neurological disorders such as multiple sclerosis (MS).ObjectiveWe presented a machine learning approach leveraging passive sensor data from smartphones and fitness trackers of people with MS to predict their health outcomes in a natural experiment during a state-mandated stay-at-home period due to a global pandemic.MethodsFirst, we extracted features that capture behavior changes due to the stay-at-home order. Then, we adapted and applied an existing algorithm to these behavior-change features to predict the presence of depression, high global MS symptom burden, severe fatigue, and poor sleep quality during the stay-at-home period.ResultsUsing data collected between November 2019 and May 2020, the algorithm detected depression with an accuracy of 82.5% (65% improvement over baseline; F1-score: 0.84), high global MS symptom burden with an accuracy of 90% (39% improvement over baseline; F1-score: 0.93), severe fatigue with an accuracy of 75.5% (22% improvement over baseline; F1-score: 0.80), and poor sleep quality with an accuracy of 84% (28% improvement over baseline; F1-score: 0.84).ConclusionsOur approach could help clinicians better triage patients with MS and potentially other chronic neurological disorders for interventions and aid patient self-monitoring in their own environment, particularly during extraordinarily stressful circumstances such as pandemics, which would cause drastic behavior changes.

Background:Sensors within smartphones, such as accelerometer and location, can describe longitudinal markers of behavior as represented through devices in a method called digital phenotyping. This study aimed to assess the feasibility of digital phenotyping for patients with alcohol-associated liver disease and alcohol use disorder, determine correlations between smartphone data and alcohol craving, and establish power assessment for future studies to prognosticate clinical outcomes.Methods:A total of 24 individuals with alcohol-associated liver disease and alcohol use disorder were instructed to download the AWARE application to collect continuous sensor data and complete daily ecological momentary assessments on alcohol craving and mood for up to 30 days. Data from sensor streams were processed into features like accelerometer magnitude, number of calls, and location entropy, which were used for statistical analysis. We used repeated measures correlation for longitudinal data to evaluate associations between sensors and ecological momentary assessments and standard Pearson correlation to evaluate within-individual relationships between sensors and craving.Results:Alcohol craving significantly correlated with mood obtained from ecological momentary assessments. Across all sensors, features associated with craving were also significantly correlated with all moods (eg, loneliness and stress) except boredom. Individual-level analysis revealed significant relationships between craving and features of location entropy and average accelerometer magnitude.Conclusions:Smartphone sensors may serve as markers for alcohol craving and mood in alcohol-associated liver disease and alcohol use disorder. Findings suggest that location-based and accelerometer-based features may be associated with alcohol craving. However, data missingness and low participant retention remain challenges. Future studies are needed for further digital phenotyping of relapse risk and progression of liver disease.

Quality of Life, Self-Reported Cognitive Difficulties, and Performance-Based Cognitive Problems in Multiple Sclerosis: What's Sleep Got to Do With It?

Multiple sclerosis (MS) is a chronic neurological disease that progresses with crisis and remission and causes significant psychosocial problems. Fatigue and sleep disorders are reported to be the most frequent problems that could change by gender and potentially affect daily living activities. This study aimed to examine the effects of pain, fatigue, and sleep quality on the activities of daily living in patients with multiple sclerosis by gender. This cross-sectional study involved 188 patients with MS. G*Power 3.4.9 was used in the study sample estimation, and it was found that at least 111 women and 45 men individuals should be reached with 0.5 (medium) effect size, 80% power, 5% type I error, and 2.5 allocation ratio. Considering 10% data loss, the study was completed with 188 multiple sclerosis patients, 134 women and 54 men. PwMS's pain, fatigue, sleep, and daily living activities were compared according to gender; it was found that the difference in the mean scores of women's PSQI subdimension "habitual sleep efficiency" was statistically significantly higher than that of men's (P < 0.05). A negative correlation was found between FIS scores and NEADL total scores and subdimension scores in men and women with MS (P < 0.05). In women with MS, the degree of fatigue being "important" (9.184 units) and "very important" (7.893 units) reduces daily living activities. In men with MS, "poor sleep quality" reduces activities of daily living (11.559 units). According to gender, women's DLA was negatively affected by fatigue, while men's DLA was negatively affected by poor sleep quality. Therefore, increased sleep disorders in men and fatigue in women may cause a decrease in daily life activities.

Advancements in technology, including mobile-based ecological momentary assessments (EMAs) and passive sensing, have immense potential to identify short-term suicide risk. However, the extent to which EMA and passive data, particularly in combination, have utility in detecting short-term risk in everyday life remains poorly understood. To examine whether and what combinations of self-reported EMA and sensor-based assessments identify next-day suicidal ideation. In this intensive longitudinal prognostic study, participants completed EMAs 4 times daily and wore a sensor wristband (Fitbit Charge 3) for 8 weeks. Multilevel machine learning methods, including penalized generalized estimating equations and classification and regression trees (CARTs) with repeated 5-fold cross-validation, were used to optimize prediction of next-day suicidal ideation based on time-varying features from EMAs (affective, cognitive, behavioral risk factors) and sensor data (sleep, activity, heart rate). Young adult patients who visited an emergency department with recent suicidal ideation and/or suicide attempt were recruited. Identified via electronic health record screening, eligible individuals were contacted remotely to complete enrollment procedures. Participants (aged 18 to 25 years) completed 14 708 EMA observations (64.4% adherence) and wore a sensor wristband approximately half the time (55.6% adherence). Data were collected between June 2020 and July 2021. Statistical analysis was performed from January to March 2023. The outcome was presence of next-day suicidal ideation. Among 102 enrolled participants, 83 (81.4%) were female; 6 (5.9%) were Asian, 5 (4.9%) were Black or African American, 9 (8.8%) were more than 1 race, and 76 (74.5%) were White; mean (SD) age was 20.9 (2.1) years. The best-performing model incorporated features from EMAs and showed good predictive accuracy (mean [SE] cross-validated area under the receiver operating characteristic curve [AUC], 0.84 [0.02]), whereas the model that incorporated features from sensor data alone showed poor prediction (mean [SE] cross-validated AUC, 0.56 [0.02]). Sensor-based features did not improve prediction when combined with EMAs. Suicidal ideation-related features were the strongest predictors of next-day ideation. When suicidal ideation features were excluded, an alternative EMA model had acceptable predictive accuracy (mean [SE] cross-validated AUC, 0.76 [0.02]). Both EMA models included features at different timescales reflecting within-day, end-of-day, and time-varying cumulative effects. In this prognostic study, self-reported risk factors showed utility in identifying near-term suicidal thoughts. Best-performing models required self-reported information, derived from EMAs, whereas sensor-based data had negligible predictive accuracy. These results may have implications for developing decision algorithms identifying near-term suicidal thoughts to guide risk monitoring and intervention delivery in everyday life.

Low-Burden Detection of Clinical Worsening in Body Dysmorphic Disorder Using Smartphone Sensor and Demographic Data.

Products and services based on digital wellbeing technologies typically include mobile device apps as well as browser-based apps to a lesser extent, and can include telephony-based services, text-based chatbots and voice activated chatbots. Many of these digital products and services are simultaneously available across many channels in order to maximize availability for users. Digital wellbeing technologies offer useful methods for real time data capture of the interactions of users with the products and services. We can design what data are recorded, how and where it may be stored, and crucially, how it can be analyzed to reveal individual or collective usage patterns. Digital phenotyping is the term given to the capturing and use of user log data from health and wellbeing technologies used in apps and cloud-based services. Digital phenotyping was originally proposed to correlate a person’s mental state by using their metadata and even sensor data on their smartphone. In some cases, the data is physiological, for example pulse or movement-related, and it is collected automatically. In other cases, the data is actually metadata, for example, when a call is made and the call duration rather than the content of the call. Oftentimes, as would be expected from a personal device located on the body of the user, rich data pertaining to geo-location, social media use and interaction is gathered. Health and wellbeing-related, scientifically validated assessment scales may also generate digital phenotype data. Another form of digital phenotype data is Ecological Momentary Assessment (EMA), which originally made use of paper-diary techniques to enable people to record their observations or answers to specific questions and combined the ecological validity with the rigorous measurement techniques of psychometric research. EMA secures data about both behavioural and intrapsychic aspects of individuals' daily activities, and it obtains reports about the experience as it occurs, thereby minimizing the effects of reliance on memory and reconstruction which can often be impaired by hindsight bias or recall bias. The use of digital phenotyping data and its analysis using machine learning and artificial intelligence is important since many national public health organizations are exploring how to use digital technologies such as health apps and cloud-based services for the self-management of diseases and thus logging user interactions allows for greater insight into user needs and provides ideas for improving these digital interventions, for example through enhanced personalization. Public health services benefit since the data can be automatically and hence cost-effectively collected. Such data may facilitate new ways for digital epidemiological analyses and provide data to inform health policies. If the public health organizations promote health apps and digital phenotyping analysis using machine learning and artificial intelligence is taken up by these organizations, then there is clear need for guidelines on the ethical application of these ‘democratized’ algorithms and techniques. My keynote talk begins by reviewing the evolution of the use of technology to support peoples’ health and wellbeing, from telecare and telehealth through to personalised healthcare, the growth of the idea of ‘quantified self’ and ultimately, self-managed care. I then discuss the growing use of commercially available digital devices and software for selfcare, and the explosion in the data arising from their use in society. The opportunities for the application of machine learning to the data, including EMA data are explored and the implications are discussed, across such areas as big data for research study design, ethics, the ‘servitization’ of machine learning, bias, surveillance, and health and wellbeing services. In order to illustrate my work, I will draw upon case studies from digital health and wellbeing, including maternal mental health, crisis helplines and apps for people living with dementia.

Effective management of symptoms in cancer patients requires early intervention. This study assessed whether the timing of referral to the Supportive Care Center (SCC) and symptom burden outcome varied by race or ethnicity in lung cancer patients who had been seen at a tertiary cancer center. Non-Hispanic white (n = 752), Hispanic (n = 111), and non-Hispanic black (n = 117) patients with nonsmall cell lung cancer comprised this sample. Data on sociodemographic factors, stage of disease, comorbid conditions, and symptom severity (pain, depressed mood, fatigue) served as potential predictor variables. Whereas the mean time (15 months; median = 7 months) from initial presentation at the cancer center to referral to the SCC did not vary by race or ethnicity, we found that Hispanics and non-Hispanic blacks had higher symptom burden when they first presented at the cancer center than non-Hispanic whites. Severe pain, depressed mood, and fatigue were significant predictors for early referral (<7 months) of non-Hispanic whites, but only severe fatigue (P <.05) was predictive of early referral for Hispanics and non-Hispanic blacks. Furthermore, while the proportion of non-Hispanic white patients reporting severe pain, depressed mood, and fatigue significantly decreased (P <.001) at first follow-up visit after referral to the SCC; among Hispanics, improvement was only observed for depressed mood. No improvement in any of these symptoms was observed for non-Hispanic blacks. Whereas the timing of referral to supportive services did not vary by race, disparities in symptom burden outcomes persisted. Additional studies are needed to validate our findings.

Several studies have reported on increasing psychosocial stress in academia due to work environment risk factors like job insecurity, work-family conflict, research grant applications, and high workload. The STRAW project adds novel aspects to occupational stress research among academic staff by measuring day-to-day stress in their real-world work environments over 15 working days. Work environment risk factors, stress outcomes, health-related behaviors, and work activities were measured repeatedly via an ecological momentary assessment (EMA), specially developed for this project. These results were combined with continuously tracked physiological stress responses using wearable devices and smartphone sensor and usage data. These data provide information on workplace context using our self-developed Android smartphone app. The data were analyzed using two approaches: 1) multilevel statistical modelling for repeated data to analyze relations between work environment risk factors and stress outcomes on a within- and between-person level, based on EMA results and a baseline screening, and 2) machine-learning focusing on building prediction models to develop and evaluate acute stress detection models, based on physiological data and smartphone sensor and usage data. Linking these data collection and analysis approaches enabled us to disentangle and model sources, outcomes, and contexts of occupational stress in academia.

BackgroundWe present a digital phenotyping protocol designed to continuously and objectively measure behavioral, physiological, and contextual data during pregnancy and the postpartum period using passive sensing from Garmin smartwatches and smartphones, along with active ecological momentary assessments (EMAs). This novel protocol uniquely adapts to the unpredictable timing of childbirth, spanning from the third trimester through 6 weeks post partum, to accurately capture critical temporal changes and maternal-infant outcomes. By providing high-frequency real-time data, this methodology offers comprehensive insights into pregnancy-related behaviors and physiological processes, overcoming the limitations of traditional retrospective self-report methods.ObjectiveWe aim to develop a protocol for longitudinal data collection supporting digital phenotyping that is optimized for pregnancy and the postpartum period. This protocol leverages the pregnant population’s heightened interest in health and tracking. It aims to minimize the burden on the participants, increase retention, and assess the value of wearables compared to smartphones to determine the appropriate data collection methods.MethodsData will be collected from 30 nulliparous participants from the start of the third trimester through 6 weeks post partum. This protocol uses 3 distinct 1-time surveys, alongside daily and weekly EMAs, to capture real-time maternal experience data. Passive maternal data—such as activity, vitals, sleep, and location—are collected via smartphones and Garmin smartwatches. Participants are expected to log data about the newborn after delivery through the mobile app Huckleberry. This protocol was developed in collaboration with the Northeastern University Sath Laboratory, which focuses on digital phenotyping and longitudinal data collection, and the Tufts Medical Center’s obstetrics and gynecology department, which has expertise in working with the pregnant population.ResultsThis study was funded in August 2024. Data collection is projected to run from October 2025 to July 2026. As of September 2025, the study has been approved, and recruitment and data collection are to begin. The results are expected to be published by August 2026. We plan to assess the retention rates, survey and EMA completion rates, wear time of the smartwatch without intervention, and data volume logged in the Huckleberry app. In addition, we will perform digital phenotyping to determine whether the data collected during pregnancy can be used to predict breastfeeding outcomes, delivery outcomes, and maternal-infant well-being.ConclusionsThis protocol integrates the use of digital phenotyping in pregnancy and postpartum research, providing a novel method for capturing real-time indicators of maternal well-being. It will determine the expected rates of data completion and appropriate sample size using a power analysis for a more extensive future study. By integrating smartphone and wearable sensor data, this protocol has the potential to transform the way maternal health clinical interventions are designed and implemented in the future.International Registered Report Identifier (IRRID)PRR1-10.2196/77175

Background Multiple sclerosis (MS) is a chronic autoimmune disease caused by multiple factors. It can lead to many physical and mental symptoms. Fatigue is one of the most commonly mentioned complaints among MS patients that can affect their quality of life. Physical activityhas many benefits for the physical and mental health of patients with MS. Aim To assess the role of exercise on fatigue among patients with multiple sclerosis and identify the relationship between depression, sleep quality, sociodemographic variables, and fatigue. Methods This is an analytical cross-sectional study based on a sample size of 235patients recruited from the MS clinic at King Fahad Hospital (KFH) in Madinah. The outcome of the study was fatigue among MS patients. Data were collected through telephone calls from February to May 2022 using a structured questionnaire and scales, such as the Godin Leisure-Time Exercise Questionnaire (GLTEQ), Modified Fatigue Impact Scale (MFIS), Patient Health Questionnaire (PHQ2), and Pittsburgh Sleep Quality Index (PSQI). Data were analyzed through SPSS version 20 (IBM Corp., Armonk, NY, USA). The correlation coefficient (r), Chi-square tests, and simple and multiple logistic regression were used as found appropriate. Results Out of the total samples, 37.4% were male and 62.6% were female. The median age of patients was 36 years. The prevalence of fatigue was 37% among patients, with a reported median fatigue score of 26. It was found that 63% of the patients were physically inactive; 32.2% were overweight, 14.2% were obese; 63.8% of patients had poor sleep quality. The fatigue score was negatively correlated with the GLTEQ score, but the results were not significant (r=-0.066; P-value (level of significance)=0.335). Nonetheless, a moderately significant correlation was observed between the MFIS and PSQI and MFIS and PHQ2 (r=0.505, P=<0.001 and r=0.520, P=<0.001, respectively). The Chi-square test showed a significant association between fatigue and progressive types of MS, the primary progressive MS (PPMS), secondary progressive MS (SPMS), and relapsing-remitting MS (RRMS) (odds ratio (OR)=4.4; 95%confidence interval (CI): 2.1-8.9), P=<0.001). Depressed patients were 9.7 times more likely to develop fatigue compared to non-depressed patients (P=<0.001). Those with poor sleep quality were 4.6 times more likely to develop fatigue compared to those with good sleep quality (P=<0.001).Fifty-six percent of fatigue among MS patients were predicted by low income, progressive types, unemployment, obesity, depression, and poor sleep quality. Conclusion Fatigue is a major complaint among MS patients. Most of the patients were found to be physically inactive, depressed, and have poor sleep quality. This study found an association between physical inactivity and fatigue, but the results were not significant. There was a significant association between sociodemographic factors like low income and unemployment, poor sleep quality, obesity, progressive types of MS, depression, and fatigue. Encouraging exercise practice and implementing a regularexercise program are needed, along with weight management plans. Further studies and psychological support meetings are required, with the importance of a holistic approach to patient care.

BackgroundEpilepsy and multiple sclerosis (MS) are both chronic neurological diseases with a high symptom burden, including depression and resulting in lower health-related quality of life (HRQoL). Peer-support groups seem to be beneficial to improve HRQoL and depression. Since the course of the two diseases varies, the question arises if they differ in terms of HRQoL, depression and coping strategies and which predictors are related to HRQoL in peer-supported people. MethodsA total of 90 participants with epilepsy (n = 46) or MS (n = 44), recruited from local or online peer-support groups, were surveyed by questionnaire. HRQoL (SF-36), coping with illness (FKV-LIS), depression (BDI-II), socio-demographic and clinical data were examined. ResultsThe two peer-supported groups did not differ, neither in coping strategies nor in HRQoL, with the exception of the physical related scales. However, the HRQoL values in both groups were worse than in general population. An important predictor of HRQoL in epilepsy as well as in MS was depression, which was present in 40 % of cases. ConclusionsEven people with MS or epilepsy who attended a peer-support group, i.e. who have been actively coping with their disease, had a reduced HRQoL. Neither coping strategies nor other disease related variables but comorbid depression was the most significant predictor of poorer HRQoL. Our results support the necessity to treat comorbid depression and thereby improve HRQoL, even in peer-supported people.

BackgroundSensors embedded in smartphones allow for the passive momentary quantification of people’s states in the context of their daily lives in real time. Such data could be useful for alleviating the burden of ecological momentary assessments and increasing utility in clinical assessments. Despite existing research on using passive sensor data to assess participants’ moment-to-moment states and activity levels, only limited research has investigated temporally linking sensor assessment and self-reported assessment to further integrate the 2 methodologies.ObjectiveWe investigated whether sparse movement-related sensor data can be used to train machine learning models that are able to infer states of individuals’ work-related rumination, fatigue, mood, arousal, life engagement, and sleep quality. Sensor data were only collected while the participants filled out the questionnaires on their smartphones.MethodsWe trained personalized machine learning models on data from employees (N=158) who participated in a 3-week ecological momentary assessment study.ResultsThe results suggested that passive smartphone sensor data paired with personalized machine learning models can be used to infer individuals’ self-reported states at later measurement occasions. The mean R2 was approximately 0.31 (SD 0.29), and more than half of the participants (119/158, 75.3%) had an R2 of ≥0.18. Accuracy was only slightly attenuated compared with earlier studies and ranged from 38.41% to 51.38%.ConclusionsPersonalized machine learning models and temporally linked passive sensing data have the capability to infer a sizable proportion of variance in individuals’ daily self-reported states. Further research is needed to investigate factors that affect the accuracy and reliability of the inference.

Feasibility and treatment effect of cognitive behavioral therapy for insomnia in individuals with multiple sclerosis: A pilot randomized controlled trial