Digital phenotyping by wearable-driven artificial intelligence in older adults and people with Parkinson's disease: Protocol of the mixed method, cyclic ActiveAgeing study

The comprehensive clinical benefits of digital phenotyping: from broad adoption to full impact

Digital phenotyping collects health data digitally, supporting early disease diagnosis and health management. This paper systematically reviews the diversity of research methods in digital phenotyping and its clinical benefits, while also focusing on its importance within the P4 medicine paradigm and its core role in advancing its application in biobanks. Furthermore, the paper envisions the continued clinical benefits of digital phenotyping, driven by technological innovation, global collaboration, and policy support.

Digital phenotyping from heart rate dynamics: Identification of zero-poles models with data-driven evolutionary learning

Heart rate response to physical activity is widely investigated in clinical and training practice, as it provides information on a person's physical state. For emerging digital phenotyping approaches, there is a need for individualized model estimation. In this study, we propose a zero-poles model and a data-driven evolutionary learning method for identification. We also perform a comparison with existing first and second order models and gradient descent identification methods. The proposed model is based on a five-phase description of heart rate dynamics. Data was collected from 30 healthy participants using a treadmill and a thoracic sensor in two protocols (static and dynamic), for increasing and decreasing activity. Results show that the zero-poles model is a good fit for heart rate response to exercise (Pearson's coefficient ρ>.95), while first and second order models are also suitable (ρ>.92). The evolutionary learning method shows excellent results for fast model identification, in comparison with least-squares methods (p<.03). We surmise that the parameters of investigated linear dynamic models make good candidates for digital biomarkers and continuous monitoring.

The Interplay Between Epilepsy and Parkinson's Disease: Gene Expression Profiling and Functional Analysis

The results of many epidemiological studies suggest a bidirectional causality may exist between epilepsy and Parkinson's disease (PD). However, the underlying molecular landscape linking these two diseases remains largely unknown. This study aimed to explore this possible bidirectional causality by identifying differentially expressed genes (DEGs) in each disease as well as their intersection based on two respective disease-related datasets. We performed enrichment analyses and explored immune cell infiltration based on an intersection of the DEGs. Identifying a protein-protein interaction (PPI) network between epilepsy and PD, and this network was visualised using Cytoscape software to screen key modules and hub genes. Finally, exploring the diagnostic values of the identified hub genes. NetworkAnalyst 3.0 and Cytoscape software were also used to construct and visualise the transcription factor-micro-RNA regulatory and co-regulatory networks, the gene-microRNA interaction network, as well as gene-disease association. Based on the enrichment results, the intersection of the DEGs mainly revealed enrichment in immunity-, phosphorylation-, metabolism-, and inflammation-related pathways. The boxplots revealed similar trends in infiltration of many immune cells in epilepsy and Parkinson's disease, with greater infiltration in patients than in controls. A complex PPI network comprising 186 nodes and 512 edges were constructed. According to node connection degree, top 15 hub genes were considered the kernel targets of epilepsy and PD. The area under curve values of hub gene expression profiles confirmed their excellent diagnostic values. This study is the first to analyse the molecular landscape underlying the epidemiological link between epilepsy and Parkinson's disease. The two diseases are closely linked through immunity-, inflammation-, and metabolism-related pathways. This information was of great help in understanding the pathogenesis, diagnosis, and treatment of the diseases. The present results may provide guidance for further in-depth analysis about molecular mechanisms of epilepsy and PD and novel potential targets.

Cross-evaluation of wearable data for use in Parkinson's disease research: a free-living observational study on Empatica E4, Fitbit Sense, and Oura

BACKGROUND

Established assessment scales used for Parkinson's disease (PD) have several limitations in tracking symptom progression and fluctuation. Both research and commercial-grade wearables show potential in improving these assessments. However, it is not known whether pervasive and affordable devices can deliver reliable data, suitable for designing open-source unobtrusive around-the-clock assessments. Our aim is to investigate the usefulness of the research-grade wristband Empatica E4, commercial-grade smartwatch Fitbit Sense, and the Oura ring, for PD research.

METHOD

The study included participants with PD (N = 15) and neurologically healthy controls (N = 16). Data were collected using established assessment scales (Movement Disorders Society Unified Parkinson's Disease Rating Scale, Montreal Cognitive Assessment, REM Sleep Behavior Disorder Screening Questionnaire, Hoehn and Yahr Stage), self-reported diary (activities, symptoms, sleep, medication times), and 2-week digital data from the three devices collected simultaneously. The analyses comprised three steps: preparation (device characteristics assessment, data extraction and preprocessing), processing (data structuring and visualization, cross-correlation analysis, diary comparison, uptime calculation), and evaluation (usability, availability, statistical analyses).

RESULTS

We found large variation in data characteristics and unsatisfactory cross-correlation. Due to output incongruences, only heart rate and movement could be assessed across devices. Empatica E4 and Fitbit Sense outperformed Oura in reflecting self-reported activities. Results show a weak output correlation and significant differences. The uptime was good, but Oura did not record heart rate and movement concomitantly. We also found variation in terms of access to raw data, sampling rate and level of device-native processing, ease of use, retrieval of data, and design. We graded the system usability of Fitbit Sense as good, Empatica E4 as poor, with Oura in the middle.

CONCLUSIONS

In this study we identified a set of characteristics necessary for PD research: ease of handling, cleaning, data retrieval, access to raw data, score calculation transparency, long battery life, sufficient storage, higher sampling frequencies, software and hardware reliability, transparency. The three analyzed devices are not interchangeable and, based on data features, none were deemed optimal for PD research, but they all have the potential to provide suitable specifications in future iterations.

Selecting a smartwatch for trials involving older adults with neurodegenerative diseases: A researcher's framework to avoid hidden pitfalls

BACKGROUND

Increased prevalence of neurodegenerative diseases complicates care needs for older adults. Sensing technologies, such as smartwatches, are one available solution which can help address the challenges of aging. Knowledge of the possibilities and pitfalls of these sensing technologies is of key importance to researchers when choosing a device for a trial and considering the sustainability of these technologies in real-world settings.

OBJECTIVE

This study aims to uncover hidden truths related to the suitability of smartwatches for use in clinical trials which include older adults with neurodegenerative diseases, including end-of-life and palliative care studies.

METHOD

We perform an analysis of smartwatch features vs. user and researcher needs and provide an overview of hidden expenses which should be considered by the research team. Investigative research on 11 smartwatches is presented, selected based on previous use in clinical studies and recommendations from fellow researchers.

RESULTS

We found that expenses, battery life, choice of research vs. commercial grade devices, data management, study methodology, and participant demographics are principal factors in selecting a smartwatch for a clinical trial involving older adults with neurodegenerative diseases. A revised framework based on our findings, and concepts from Connely (2021), Mattison (2023), and Espay (2019) et al.'s previous work, is presented as a tool for researchers in evaluation of smartwatches and future sensing technologies.

CONCLUSION

Careful consideration must be given to the fitness of technologies for future research, especially considering that this is a rapidly changing field. The process of selection of a smartwatch for a clinical trial should be thoughtful, scrutinous, and include interdisciplinary collaboration.

From Steps to Context: Optimizing Digital Phenotyping for Physical Activity Monitoring in Older Adults by Integrating Wearable Data and Ecological Momentary Assessment

Physical activity (PA) is essential for healthy aging, but its accurate assessment in older adults remains challenging due to the limitations and biases of traditional clinical assessment. Mobile technologies and wearable sensors offer a more ecological, less biased alternative for evaluating PA in this population. This study aimed to optimize digital phenotyping strategies for assessing PA patterns in older adults, by integrating ecological momentary assessment (EMA) and continuous wearable sensor data collection. Over two weeks, 108 community-dwelling older adults provided real-time EMA responses while their PA was continuously monitored using Garmin Vivo 5 sensors. The combined approach proved feasible, with 67.2% adherence to EMA prompts, consistent across time points (morning: 68.1%; evening: 65.4%). PA predominantly occurred at low (51.4%) and moderate (46.2%) intensities, with midday activity peaks. Motivation and self-efficacy were significantly associated with low-intensity PA (R = 0.20 and 0.14 respectively), particularly in the morning. However, discrepancies between objective step counts and self-reported PA measures, which showed no correlation (R = -0.026, p = 0.65), highlight the complementary value of subjective and objective data sources. These findings support integrating EMA, wearable sensors, and temporal frameworks to enhance PA assessment, offering precise insights for personalized, time-sensitive interventions to promote PA.

Movement Disorders and Smart Wrist Devices: A Comprehensive Study

In the medical field, there are several very different movement disorders, such as tremors, Parkinson's disease, or Huntington's disease. A wide range of motor and non-motor symptoms characterizes them. It is evident that in the modern era, the use of smart wrist devices, such as smartwatches, wristbands, and smart bracelets is spreading among all categories of people. This diffusion is justified by the limited costs, ease of use, and less invasiveness (and consequently greater acceptability) than other types of sensors used for health status monitoring. This systematic review aims to synthesize research studies using smart wrist devices for a specific class of movement disorders. Following PRISMA-S guidelines, 130 studies were selected and analyzed. For each selected study, information is provided relating to the smartwatch/wristband/bracelet model used (whether it is commercial or not), the number of end-users involved in the experimentation stage, and finally the characteristics of the benchmark dataset possibly used for testing. Moreover, some articles also reported the type of raw data extracted from the smart wrist device, the implemented designed algorithmic pipeline, and the data classification methodology. It turned out that most of the studies have been published in the last ten years, showing a growing interest in the scientific community. The selected articles mainly investigate the relationship between smart wrist devices and Parkinson's disease. Epilepsy and seizure detection are also research topics of interest, while there are few papers analyzing gait disorders, Huntington's Disease, ataxia, or Tourette Syndrome. However, the results of this review highlight the difficulties still present in the use of the smartwatch/wristband/bracelet for the identified categories of movement disorders, despite the advantages these technologies could bring in the dissemination of low-cost solutions usable directly within living environments and without the need for caregivers or medical personnel.

Digital biomarkers for non-motor symptoms in Parkinson's disease: the state of the art

Digital biomarkers that remotely monitor symptoms have the potential to revolutionize outcome assessments in future disease-modifying trials in Parkinson's disease (PD), by allowing objective and recurrent measurement of symptoms and signs collected in the participant's own living environment. This biomarker field is developing rapidly for assessing the motor features of PD, but the non-motor domain lags behind. Here, we systematically review and assess digital biomarkers under development for measuring non-motor symptoms of PD. We also consider relevant developments outside the PD field. We focus on technological readiness level and evaluate whether the identified digital non-motor biomarkers have potential for measuring disease progression, covering the spectrum from prodromal to advanced disease stages. Furthermore, we provide perspectives for future deployment of these biomarkers in trials. We found that various wearables show high promise for measuring autonomic function, constipation and sleep characteristics, including REM sleep behavior disorder. Biomarkers for neuropsychiatric symptoms are less well-developed, but show increasing accuracy in non-PD populations. Most biomarkers have not been validated for specific use in PD, and their sensitivity to capture disease progression remains untested for prodromal PD where the need for digital progression biomarkers is greatest. External validation in real-world environments and large longitudinal cohorts remains necessary for integrating non-motor biomarkers into research, and ultimately also into daily clinical practice.

Exploring active ageing in a community-based living environment: an ethnographic study in the Western Norway context

Background

Age-friendly environments intend to promote active ageing by facilitating social, mental, and physical participation. This could potentially delay the onset of chronic complex conditions, enabling people to live longer independently at home, and prevent loneliness. This study investigates a community-based living environment in Norway called Helgetun and aims to explore how it can facilitate active ageing.

Method

We chose an ethnographic approach consisting of observation, informal conversations, and in-depth semi-structured interviews with 15 residents (11 female, 4 male, ages 62-84). We analysed the data using reflexive thematic analysis.

Result

We developed three themes on facilitating active ageing in this living environment: maintaining self-identity, experiencing growth and development, and feeling a sense of belonging. These themes were related to physical activity levels, social engagement, and overall satisfaction with the living environment. Maintaining self-identity concerned getting a new role in life as well as access to meaningful activities. Experiencing growth and development involved being exposed to new activities, learning new skills, and experiencing mastery. Lastly, feeling a sense of belonging meant feeling safe and part of a group, as well as receiving social support and help. This feeling of social connectedness and safety was reflected in their experience with the COVID-19 pandemic, in which most felt relatively unaffected, suggesting that this way of living could increase reliance among this age group.

Conclusion

Having a flexible structure, adapting to the core needs and individual resources of the residents, can facilitate active ageing in community-based living environments. Our findings contribute to the growing evidence that these environments increase social and physical engagement, whilst reducing social isolation and loneliness. These findings may be particularly relevant in a Norwegian context-where older adults are less dependent on family for care-and are meant as grounding points for policymakers to reflect upon designing future senior living.

The Difficulties of Managing Pain in People Living with Frailty: The Potential for Digital Phenotyping

Pain and frailty are closely linked. Chronic pain is a risk factor for frailty, and frailty is a risk factor for pain. People living with frailty also commonly have cognitive impairment, which can make assessment of pain and monitoring of pain management even more difficult. Pain may be sub-optimally treated in people living with frailty, people living with cognitive impairment and those with both these factors. Reasons for sub-optimal treatment in these groups are pharmacological (increased drug side effects, drug-drug interactions, polypharmacy), non-pharmacological (erroneous beliefs about pain, ageism, bidirectional communication challenges), logistical (difficulty in accessing primary care practitioners and unaffordable cost of drugs), and, particularly in cognitive impairment, related to communication difficulties. Thorough assessment and characterisation of pain, related sensations, and their functional, emotional, and behavioural consequences ("phenotyping") may help to enhance the assessment of pain, particularly in people with frailty and cognitive impairment, as this may help to identify who is most likely to respond to certain types of treatment. This paper discusses the potential role of "digital phenotyping" in the assessment and management of pain in people with frailty. Digital phenotyping is concerned with observable characteristics in digital form, such as those obtained from sensing-capable devices, and may provide novel and more informative data than existing clinical approaches regarding how pain manifests and how treatment strategies affect it. The processing of extensive digital and usual data may require powerful algorithms, but processing these data could lead to a better understanding of who is most likely to benefit from specific and targeted treatments.

Returning Individual Research Results from Digital Phenotyping in Psychiatry

Psychiatry is rapidly adopting digital phenotyping and artificial intelligence/machine learning tools to study mental illness based on tracking participants' locations, online activity, phone and text message usage, heart rate, sleep, physical activity, and more. Existing ethical frameworks for return of individual research results (IRRs) are inadequate to guide researchers for when, if, and how to return this unprecedented number of potentially sensitive results about each participant's real-world behavior. To address this gap, we convened an interdisciplinary expert working group, supported by a National Institute of Mental Health grant. Building on established guidelines and the emerging norm of returning results in participant-centered research, we present a novel framework specific to the ethical, legal, and social implications of returning IRRs in digital phenotyping research. Our framework offers researchers, clinicians, and Institutional Review Boards (IRBs) urgently needed guidance, and the principles developed here in the context of psychiatry will be readily adaptable to other therapeutic areas.

Proteostasis failure exacerbates neuronal circuit dysfunction and sleep impairments in Alzheimer's disease

Failed proteostasis is a well-documented feature of Alzheimer's disease, particularly, reduced protein degradation and clearance. However, the contribution of failed proteostasis to neuronal circuit dysfunction is an emerging concept in neurodegenerative research and will prove critical in understanding cognitive decline. Our objective is to convey Alzheimer's disease progression with the growing evidence for a bidirectional relationship of sleep disruption and proteostasis failure. Proteostasis dysfunction and tauopathy in Alzheimer's disease disrupts neurons that regulate the sleep-wake cycle, which presents behavior as impaired slow wave and rapid eye movement sleep patterns. Subsequent sleep loss further impairs protein clearance. Sleep loss is a defined feature seen early in many neurodegenerative disorders and contributes to memory impairments in Alzheimer's disease. Canonical pathological hallmarks, β-amyloid, and tau, directly disrupt sleep, and neurodegeneration of locus coeruleus, hippocampal and hypothalamic neurons from tau proteinopathy causes disruption of the neuronal circuitry of sleep. Acting in a positive-feedback-loop, sleep loss and circadian rhythm disruption then increase spread of β-amyloid and tau, through impairments of proteasome, autophagy, unfolded protein response and glymphatic clearance. This phenomenon extends beyond β-amyloid and tau, with interactions of sleep impairment with the homeostasis of TDP-43, α-synuclein, FUS, and huntingtin proteins, implicating sleep loss as an important consideration in an array of neurodegenerative diseases and in cases of mixed neuropathology. Critically, the dynamics of this interaction in the neurodegenerative environment are not fully elucidated and are deserving of further discussion and research. Finally, we propose sleep-enhancing therapeutics as potential interventions for promoting healthy proteostasis, including β-amyloid and tau clearance, mechanistically linking these processes. With further clinical and preclinical research, we propose this dynamic interaction as a diagnostic and therapeutic framework, informing precise single- and combinatorial-treatments for Alzheimer's disease and other brain disorders.

Promotors and barriers to the implementation and adoption of assistive technology and telecare for people with dementia and their caregivers: a systematic review of the literature

BACKGROUND

One of the most pressing issues in our society is the provision of proper care and treatment for the growing global health challenge of ageing. Assistive Technology and Telecare (ATT) is a key component in facilitation of safer, longer, and independent living for people with dementia (PwD) and has the potential to extend valuable care and support for caregivers globally. The objective of this study was to identify promotors and barriers to implementation and adoption of ATT for PwD and their informal (family and friends) and formal (healthcare professionals) caregivers.

METHODS

Five databases Medline (Ovid), CINAHL, Web of Science, APA PsycINFO and EMBASE were searched. PRISMA guidelines have been used to guide all processes and results. Retrieved studies were qualitative, mixed-method and quantitative, screened using Rayyan and overall quality assessed using Critical Appraisal Skills Programme (CASP) and Mixed Methods Assessment Tool (MMAT). Certainty of evidence was assessed using Grading of Recommendations Assessment, Development and Evaluation (GRADE) criteria and assigned within categories of high, moderate, or low. NVivo was used for synthesis and analysis of article content. A narrative synthesis combines the study findings.

RESULTS

Thirty studies (7 quantitative, 19 qualitative and 4 mixed methods) met the inclusion criteria. Identified primary promotors for the implementation and adoption of ATT were: personalized training and co-designed solutions, safety for the PwD, involvement of all relevant stakeholders, ease of use and support, and cultural relevance. Main barriers for the implementation and adoption of ATT included: unintended adverse consequences, timing and disease progress, technology anxiety, system failures, digital divide, and lack of access to or knowledge of available ATT.

CONCLUSION

The most crucial elements for the adoption of ATT in the future will be a focus on co-design, improved involvement of relevant stakeholders, and the adaptability (tailoring related to context) of ATT solutions over time (disease process).