Digital phenotyping and the (data) shadow of Alzheimer's disease

Detecting value(s): Digital biomarkers for Alzheimer's disease and the valuation of new diagnostic technologies

This article explores how the meanings and values of diagnosis are being reconfigured at the interface between technological innovation and imaginaries of precision medicine. From genome sequencing to biological and digital 'markers' of disease, technological innovation occupies an increasingly central space in the way we imagine future health and illness. These imaginaries are usually centred on the promise of faster, more precise and personalised diagnosis, and the associated hope that if detected early enough disease can be effectively treated and prevented. Underpinning and reproduced through these narratives of the future is a re-conceptualisation of diagnostic processes and categories around the anticipation of future risk, as noted by recent theoretical developments in the sociology of diagnosis and related disciplines. Adding to this literature, in this article we explore what makes these emerging diagnostic arrangements valuable, to whom and how. Drawing on interviews with experts involved in the development of digital biomarkers for Alzheimer's disease, we trace how multiple and at times conflicting applications of the tools, and the value(s) attached to them, are coproduced. We thus ask what possibilities are pursued, or foreclosed, through the work of imagining the future of diagnosis.

Machine Learning and Digital Biomarkers Can Detect Early Stages of Neurodegenerative Diseases

Neurodegenerative diseases (NDs) such as Alzheimer's Disease (AD) and Parkinson's Disease (PD) are devastating conditions that can develop without noticeable symptoms, causing irreversible damage to neurons before any signs become clinically evident. NDs are a major cause of disability and mortality worldwide. Currently, there are no cures or treatments to halt their progression. Therefore, the development of early detection methods is urgently needed to delay neuronal loss as soon as possible. Despite advancements in Medtech, the early diagnosis of NDs remains a challenge at the intersection of medical, IT, and regulatory fields. Thus, this review explores "digital biomarkers" (tools designed for remote neurocognitive data collection and AI analysis) as a potential solution. The review summarizes that recent studies combining AI with digital biomarkers suggest the possibility of identifying pre-symptomatic indicators of NDs. For instance, research utilizing convolutional neural networks for eye tracking has achieved significant diagnostic accuracies. ROC-AUC scores reached up to 0.88, indicating high model performance in differentiating between PD patients and healthy controls. Similarly, advancements in facial expression analysis through tools have demonstrated significant potential in detecting emotional changes in ND patients, with some models reaching an accuracy of 0.89 and a precision of 0.85. This review follows a structured approach to article selection, starting with a comprehensive database search and culminating in a rigorous quality assessment and meaning for NDs of the different methods. The process is visualized in 10 tables with 54 parameters describing different approaches and their consequences for understanding various mechanisms in ND changes. However, these methods also face challenges related to data accuracy and privacy concerns. To address these issues, this review proposes strategies that emphasize the need for rigorous validation and rapid integration into clinical practice. Such integration could transform ND diagnostics, making early detection tools more cost-effective and globally accessible. In conclusion, this review underscores the urgent need to incorporate validated digital health tools into mainstream medical practice. This integration could indicate a new era in the early diagnosis of neurodegenerative diseases, potentially altering the trajectory of these conditions for millions worldwide. Thus, by highlighting specific and statistically significant findings, this review demonstrates the current progress in this field and the potential impact of these advancements on the global management of NDs.

Living with my diabetes - introducing eHealth into daily practices of patients with type 2 diabetes mellitus

Objective

Diabetes patients can draw on an increasing number of eHealth apps to support them in the self-management of their disease. While studies so far have focused on patients with type 1 diabetes, we explored how patients with type 2 diabetes mellitus (T2DM) integrate eHealth apps into their practices aimed at managing and coping with the disease, which aspects were considered particularly valuable and which challenges users encountered.

Methods

Semi-structured interviews and focus group sessions were conducted to explore how patients cope with T2DM in their daily lives and their attitude towards eHealth. In a further step, four eHealth apps were tested by patients and their expectations and experiences studied by way of qualitative interviews and focus groups.

Results

The analysis showed that the study participants valued in particular the possibility to use eHealth apps to sense and gain a better understanding of their own body, to learn about specific responses of their body to nutrition and physical activity, and to support changes in daily routines and lifestyle. Key challenges encountered related to difficulties in interpreting the data, matching the data to other bodily sensations, getting overly occupied with the disease and difficulties in integrating the apps into personal, family, and care practices.

Conclusion

Under certain conditions, eHealth can play an important role for patients in developing a nuanced, personal understanding of their body and coping with T2DM. A prerequisite is that eHealth needs to be fitted into the specific practices of users, and patients desire a strong role by their care professionals in providing support in interpretation of data.

Associations between perceived usefulness and willingness to use smart healthcare devices among Chinese older adults: The multiple mediating effect of technology interactivity and technology anxiety

Objective

This study aims to explore the mediating roles of technological interactivity and technological anxiety in the relationship between perceived usefulness and the willingness to use a smart health device to provide insight into the decision-making process of older adults in relation to the adoption of smart devices.

Methods

A cross-sectional survey was conducted in Jiangsu, China involving 552 older adults. The study utilized structural equation modeling (SEM) to analyze the relationship between the independent variable 'perceived usefulness' and the dependent variable 'willingness to use.' It also examined the multiple mediating effects of technological interactivity and technological anxiety between the independent and dependent variables.

Results

The results indicate that the direct effect of perceived usefulness on willingness to use was insignificant. However, technological interactivity completely mediated the relationship between perceived usefulness and willingness to use. Additionally, technological interactivity and technological anxiety were found to have a serial mediating effect on the impact of perceived usefulness on willingness to use smart healthcare devices.

Conclusions

These findings suggest that increasing older adults' intention to use smart healthcare devices requires not only raising awareness of their usefulness, but also addressing technological anxiety and enhancing the interactivity of these devices to improve the overall user experience.

A scoping review of neurodegenerative manifestations in explainable digital phenotyping

Neurologists nowadays no longer view neurodegenerative diseases, like Parkinson's and Alzheimer's disease, as single entities, but rather as a spectrum of multifaceted symptoms with heterogeneous progression courses and treatment responses. The definition of the naturalistic behavioral repertoire of early neurodegenerative manifestations is still elusive, impeding early diagnosis and intervention. Central to this view is the role of artificial intelligence (AI) in reinforcing the depth of phenotypic information, thereby supporting the paradigm shift to precision medicine and personalized healthcare. This suggestion advocates the definition of disease subtypes in a new biomarker-supported nosology framework, yet without empirical consensus on standardization, reliability and interpretability. Although the well-defined neurodegenerative processes, linked to a triad of motor and non-motor preclinical symptoms, are detected by clinical intuition, we undertake an unbiased data-driven approach to identify different patterns of neuropathology distribution based on the naturalistic behavior data inherent to populations in-the-wild. We appraise the role of remote technologies in the definition of digital phenotyping specific to brain-, body- and social-level neurodegenerative subtle symptoms, emphasizing inter- and intra-patient variability powered by deep learning. As such, the present review endeavors to exploit digital technologies and AI to create disease-specific phenotypic explanations, facilitating the understanding of neurodegenerative diseases as "bio-psycho-social" conditions. Not only does this translational effort within explainable digital phenotyping foster the understanding of disease-induced traits, but it also enhances diagnostic and, eventually, treatment personalization.

Visualizing the datasphere: Representations of old bodies and their data in promotional images of smart sensor technologies for aging at home

Technologies for people aging at home are increasingly prevalent and include ambient monitoring devices that work together with wearables to remotely track and monitor older adults' biometric data and activities of daily living. There is, however, little research into the promotional and speculative images of technology-in-use. Our paper examines the ways in which the datafication of aging is offered up visually by technology companies to promote their products. Specifically, we ask: how are data visualized in promotional images of smart sensor technologies for aging at home? And in these visualizations, what happens to the aging body and relations of care? We include in our definition of smart sensor technologies both wearable and ambient monitoring devices, so long as they are used for the in-home passive monitoring of the inhabitant by a caregiver, excluding those devices targeted for institutional settings or those used for self-monitoring purposes. Our sample consists of 221 images collected between January and July of 2021 from the websites of 14 English-language companies that offer smart sensor technology for aging at home. Following a visual semiotic analysis, we present 3 themes on the visual representation of old bodies and their data: (1) Captured Data, (2) Spatialized Data, and (3) Networked Data. Each, we argue, contribute to a broader visualization of the "datasphere". We conclude by highlighting the underlying assumptions of old bodies in the co-constitution of aging and technologies in which the fleshy and lived corporeality of bodies is more often lost, reduced to data points and automated care scenarios, and further disentangled from other bodies, contexts and things.

Digital Phenotyping for Mental Health: Reviewing the Challenges of Using Data to Monitor and Predict Mental Health Problems

PURPOSE OF REVIEW

We review recent developments within digital phenotyping for mental health, a field dedicated to using digital data for diagnosing, predicting, and monitoring mental health problems. We especially focus on recent critiques and challenges to digital phenotyping from within the social sciences.

RECENT FINDINGS

Three significant strands of criticism against digital phenotyping for mental health have been developed within the social sciences. This literature problematizes the idea that digital data can be objective, that it can be unbiased, and argues that it has multiple ethical and practical challenges. Digital phenotyping for mental health is a rapidly growing and developing field, but with considerable challenges that are not easily solvable. This includes when, and if, data from digital phenotyping is actionable in practice; the involvement of user and patient perspectives in digital phenotyping research; the possibility of biased data; and challenges to the idea that digital phenotyping can be more objective than other forms of psychiatric assessment.