Case Report: Ambient Sensor Signals as Digital Biomarkers for Early Signs of Heart Failure Decompensation

Sleep characteristics and self-reported sleep quality in the oldest-old: Results from a prospective longitudinal cohort study

Little is known about the correlation between subjective perception and objective measures of sleep quality in particular in the oldest-old. The aim of this study was to perform longitudinal home sleep monitoring in this age group, and to correlate results with self-reported sleep quality. This is a prospective longitudinal home sleep-monitoring study in 12 oldest-old persons (age 83-100 years, mean 93 years, 10 females) without serious sleep disorders over 1 month using a contactless piezoelectric bed sensor (EMFIT QS). Participants provided daily information about perceived sleep. Duration in bed: 264-639 min (M = 476 min, SD = 94 min); sleep duration: 239-561 min (M = 418 min, SD = 91 min); sleep efficiency: 83.9%-90.7% (M = 87.4%, SD = 5.0%); rapid eye movement sleep: 21.1%-29.0% (M = 24.9%, SD = 5.5%); deep sleep: 13.3%-19.6% (M = 16.8%, SD = 4.5%). All but one participant showed a weak (r = 0.2-0.39) or very weak (r = 0-0.19) positive or negative correlation between self-rated sleep quality and the sleep score. In conclusion, longitudinal sleep monitoring in the home of elderly people by a contactless piezoelectric sensor system is feasible and well accepted. Subjective perception of sleep quality does not correlate well with objective measures in our study. Our findings may help to develop new approaches to sleep problems in the oldest-old including home monitoring. Further studies are needed to explore the full potential of this approach.

Health Care Professionals and Data Scientists' Perspectives on a Machine Learning System to Anticipate and Manage the Risk of Decompensation From Patients With Heart Failure: Qualitative Interview Study

BACKGROUND

Heart failure (HF) is a significant global health problem, affecting approximately 64.34 million people worldwide. The worsening of HF, also known as HF decompensation, is a major factor behind hospitalizations, contributing to substantial health care costs related to this condition.

OBJECTIVE

This study aimed to explore the perspectives of health care professionals and data scientists regarding the relevance, challenges, and potential benefits of using machine learning (ML) models to predict decompensation from patients with HF.

METHODS

A total of 13 individual, semistructured, qualitative interviews were conducted in Portugal between October 31, 2022, and June 23, 2023. Participants represented different health care specialties and were selected from different contexts and regions of the country to ensure a comprehensive understanding of the topic. Data saturation was determined as the point at which no new themes emerged from participants' perspectives, ensuring a sufficient sample size for analysis. The interviews were audio recorded, transcribed, and analyzed using MAXQDA (VERBI Software GmbH) through a reflexive thematic analysis. Two researchers (JS and AH) coded the interviews to ensure the consistency of the codes. Ethical approval was granted by the NOVA National School of Public Health ethics committee (CEENSP 14/2022), and informed consent was obtained from all participants.

RESULTS

The participants recognized the potential benefits of ML models for early detection, risk stratification, and personalized care of patients with HF. The importance of selecting appropriate variables for model development, such as rapid weight gain and symptoms, was emphasized. The use of wearables for recording vital signs was considered necessary, although challenges related to adoption among older patients were identified. Risk stratification emerged as a crucial aspect, with the model needing to identify patients at high-, medium-, and low-risk levels. Participants emphasized the need for a response model involving health care professionals to validate ML-generated alerts and determine appropriate interventions.

CONCLUSIONS

The study's findings highlight ML models' potential benefits and challenges for predicting HF decompensation. The relevance of ML models for improving patient outcomes, reducing health care costs, and promoting patient engagement in disease management is highlighted. Adequate variable selection, risk stratification, and response models were identified as essential components for the effective implementation of ML models in health care. In addition, the study identified technical, regulatory and ethical, and adoption and acceptance challenges that need to be overcome for the successful integration of ML models into clinical workflows. Interpretation of the findings suggests that future research should focus on more extensive and diverse samples, incorporate the patient perspective, and explore the impact of ML models on patient outcomes and personalized care in HF management. Incorporation of this study's findings into practice is expected to contribute to developing and implementing ML-based predictive models that positively impact HF management.

Exploring Older Adults' Perspectives on Digital Home Care Interventions and Home Modifications: Focus Group Study

BACKGROUND

Emerging gerontechnology seeks to enable older adults (OAs) to remain independently and safely in their homes by connecting to health and social support and services. There are increasing attempts to develop gerontechnology, but successful implementations are more likely limited because of the uncertainty of developers about the needs and priorities of OAs. As the global population ages, the challenges faced by older OAs in maintaining independence and well-being within their homes have become increasingly important. With the proportion of OAs expected to triple by 2068, addressing the needs of this demographic has become a pressing social and public health priority. OAs often encounter various challenges related to physical, cognitive, and social well-being, including reduced mobility, memory impairments, and social isolation, which can compromise their ability to age in place and maintain a high quality of life.

OBJECTIVE

The goals of this qualitative research study are to (1) determine the best strategies for promoting aging well in the community with the support of gerontechnology, (2) establish the top priorities for implementing gerontechnology with OAs and their families, and (3) create a road map for the creation and application of gerontechnology for aging well in Manitoba.

METHODS

A total of 14 OAs participated in a qualitative research study conducted through a coconstruction workshop format, including a presentation of novel research facilities and a demonstration of research and development products. This activity was followed by an interactive discussion focused on revisiting the ongoing research and innovation programs and planning for a new research and innovation agenda. The workshop contents, notes, and recorded conversation underwent a data-driven inductive analysis.

RESULTS

Emerging themes included home design, accessibility, and safety for OAs, particularly those with memory impairments. The participants also underlined the need for digital reminders and ambient technologies in current homes as a priority. Participants stressed the importance of including OAs in gerontechnology development programs and the need to consider dignity and independence as the guiding values for future research.

CONCLUSIONS

This study presents a tentative road map for the development of gerontechnology in Manitoba. The main principles of our road map are the inclusion of OAs as early as possible in gerontechnology development and the prioritization of independence and dignity. Applying these principles would contribute to combatting digital ageism and the marginalization of OAs in technology development because of the perceived lack of technological skills and the stereotypes associated with this presumption.

Evaluation of Ambient Sensor Systems for the Early Detection of Heart Failure Decompensation in Older Patients Living at Home Alone: Protocol for a Prospective Cohort Study

BACKGROUND

The results of telemedicine intervention studies in patients with heart failure (HF) to reduce rehospitalization rate and mortality by early detection of HF decompensation are encouraging. However, the benefits are lower than expected. A possible reason for this could be the fact that vital signs, including blood pressure, heart rate, heart rhythm, and weight changes, may not be ideal indicators of the early stages of HF decompensation but are more sensitive for acute events triggered by ischemic episodes or rhythm disturbances. Preliminary results indicate a potential role of ambient sensor-derived digital biomarkers in this setting.

OBJECTIVE

The aim of this study is to identify changes in ambient sensor system-derived digital biomarkers with a high potential for early detection of HF decompensation.

METHODS

This is a prospective interventional cohort study. A total of 24 consecutive patients with HF aged 70 years and older, living alone, and hospitalized for HF decompensation will be included. Physical activity in the apartment and toilet visits are quantified using a commercially available, passive, infrared motion sensing system (DomoHealth SA). Heart rate, respiration rate, and toss-and-turns in bed are recorded by using a commercially available Emfit QS device (Emfit Ltd), which is a contact-free piezoelectric sensor placed under the participant's mattress. Sensor data are visualized on a dedicated dashboard for easy monitoring by health professionals. Digital biomarkers are evaluated for predefined signs of HF decompensation, including particularly decreased physical activity; time spent in bed; increasing numbers of toilet visits at night; and increasing heart rate, respiration rate, and motion in bed at night. When predefined changes in digital biomarkers occur, patients will be called in for clinical evaluation, and N-terminal pro b-type natriuretic peptide measurement (an increase of >30% considered as significant) will be performed. The sensitivity and specificity of the different biomarkers and their combinations for the detection of HF decompensation will be calculated.

RESULTS

The study is in the data collection phase. Study recruitment started in February 2024. Data analysis is scheduled to start after all data are collected. As of manuscript submission, 5 patients have been recruited. Results are expected to be published by the end of 2025.

CONCLUSIONS

The results of this study will add to the current knowledge about opportunities for telemedicine to monitor older patients with HF living at home alone by evaluating the potential of ambient sensor systems for this purpose. Timely recognition of HF decompensation could enable proactive management, potentially reducing health care costs associated with preventable emergency presentations or hospitalizations.

TRIAL REGISTRATION

ClinicalTrials.gov NCT06126848; https://clinicaltrials.gov/study/NCT06126848.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/55953.

Clinical validation of a contactless respiration rate monitor

Respiratory rate (RR) is an often underestimated and underreported vital sign with tremendous clinical value. As a predictor of cardiopulmonary arrest, chronic obstructive pulmonary disease (COPD) exacerbation or indicator of health state for example in COVID-19 patients, respiratory rate could be especially valuable in remote long-term patient monitoring, which is challenging to implement. Contactless devices for home use aim to overcome these challenges. In this study, the contactless Sleepiz One+ respiration monitor for home use during sleep was validated against the thoracic effort belt. The agreement of instantaneous breathing rate and breathing rate statistics between the Sleepiz One+ device and the thoracic effort belt was initially evaluated during a 20-min sleep window under controlled conditions (no body movement) on a cohort of 19 participants and secondly in a more natural setting (uncontrolled for body movement) during a whole night on a cohort of 139 participants. Excellent agreement was shown for instantaneous breathing rate to be within 3 breaths per minute (Brpm) compared to thoracic effort band with an accuracy of 100% and mean absolute error (MAE) of 0.39 Brpm for the setting controlled for movement, and an accuracy of 99.5% with a MAE of 0.48 Brpm for the whole night measurement, respectively. Excellent agreement was also achieved for the respiratory rate statistics over the whole night with absolute errors of 0.43, 0.39 and 0.67 Brpm for the 10th, 50th and 90th percentiles, respectively. Based on these results we conclude that the Sleepiz One+ can estimate instantaneous respiratory rate and its summary statistics at high accuracy in a clinical setting. Further studies are required to evaluate the performance in the home environment, however, it is expected that the performance is at similar level, as the measurement conditions for the Sleepiz One+ device are better at home than in a clinical setting.

Applications of deep learning methods in digital biomarker research using noninvasive sensing data

Introduction: Noninvasive digital biomarkers are critical elements in digital healthcare in terms of not only the ease of measurement but also their use of raw data. In recent years, deep learning methods have been put to use to analyze these diverse heterogeneous data; these methods include representation learning for feature extraction and supervised learning for the prediction of these biomarkers. Methods: We introduce clinical cases of digital biomarkers and various deep-learning methods applied according to each data type. In addition, deep learning methods for the integrated analysis of multidimensional heterogeneous data are introduced, and the utility of these data as an integrated digital biomarker is presented. The current status of digital biomarker research is examined by surveying research cases applied to various types of data as well as modeling methods. Results: We present a future research direction for using data from heterogeneous sources together by introducing deep learning methods for dimensionality reduction and mode integration from multimodal digital biomarker studies covering related domains. The integration of multimodality has led to advances in research through the improvement of performance and complementarity between modes. Discussion: The integrative digital biomarker will be more useful for research on diseases that require data from multiple sources to be treated together. Since delicate signals from patients are not missed and the interaction effects between signals are also considered, it will be helpful for immediate detection and more accurate prediction of symptoms.

Digital Biomarkers in Living Labs for Vulnerable and Susceptible Individuals: An Integrative Literature Review

PURPOSE

The study aimed to identify which digital biomarkers are collected and which specific devices are used according to vulnerable and susceptible individual characteristics in a living-lab setting.

MATERIALS AND METHODS

A literature search, screening, and appraisal process was implemented using the Web of Science, Pubmed, and Embase databases. The search query included a combination of terms related to "digital biomarkers," "devices that collect digital biomarkers," and "vulnerable and susceptible groups." After the screening and appraisal process, a total of 37 relevant articles were obtained.

RESULTS

In elderly people, the main digital biomarkers measured were values related to physical activity. Most of the studies used sensors. The articles targeting children aimed to predict diseases, and most of them used devices that are simple and can induce some interest, such as wearable device-based smart toys. In those who were disabled, digital biomarkers that measured location-based movement for the purpose of diagnosing disabilities were widely used, and most were measured by easy-to-use devices that did not require detailed explanations. In the disadvantaged, digital biomarkers related to health promotion were measured, and various wearable devices, such as smart bands and headbands were used depending on the purpose and target.

CONCLUSION

As the digital biomarkers and devices that collect them vary depending on the characteristics of study subjects, researchers should pay attention not only to the purpose of the study but also the characteristics of study subjects when collecting and analyzing digital biomarkers from living labs.