Article

6 tips for integrating a connected device into a digital health program

4 min read

When it comes to managing conditions like high blood pressure and diabetes, digital health programs need swift, regular updates about how patients are faring. Real-time insights into biomarkers such as weight and heart rate are essential for making fast, potentially life-saving care decisions, especially for seniors or others with chronic health issues.

Connected in-home health devices enable this vision to become a reality. This data allows care teams to adjust care plans, prescribe medications or identify early intervention strategies.

Why are health programs integrating connected devices?

Before sharing some tips about connected devices, it is interesting to understand why they are particularly useful in digital health programs. Without connected devices, the performance of digital health programs strongly and exclusively rely on the patient. Some behaviors that have been noticed in patients, and which could impact care, include: making an error in reporting the last blood-pressure reading, missing a measurement, or not wanting to report a measurement. In addition, having to think about measurements and manually report them on a specific interface can be painful for patients. Either patients are deeply annoyed by the process and feel less engaged in the whole program, or they abandon the full treatment. By automatically synchronizing data and providing trends and a history of objective data, connected devices provide an answer to many of these issues.

As Dr. Emil Baccash explained in a recent New York Times article, “[It is] taught in medical school that taking a medical history gives you 90 percent of the information you need, with the 10 percent coming from the physical exam.”

If connected devices are well chosen, they can help to reduce friction in the user experience. With less friction, patients are more engaged and become the main actors in their own care, which is key to achieving better health outcomes. Some studies have already proven that connected devices are changing the way chronic care is managed. More recent evidence from the American Medical Association confirms that providers are looking for digital health tools, including connected devices, to treat chronic illness.

But the goal of better healthcare outcomes using connected devices is only achievable if the devices are efficient. Here a few tips to help ensure that connected devices will add the maximum value to your program.

The importance of a well-chosen device

The right connected health devices can play a key role in this vision. Better health outcomes are only achieved if connected devices are efficient and engaging. This involves numerous factors:

Ease of use. Any friction point along the way – such as installation requirements, complex instructions, or even the need for frequent battery changes will drive down program adoption rates. Patients need devices that are truly plug and play. With intuitive devices, patients are more engaged and become the main actors in their care. 

Cellular enabled. For too long, the health device industry relied on Bluetooth and Wi-Fi to gather data from in-home devices, but these were cumbersome for patients to set up, and it limited who could participate (i.e., patients in rural areas or those without cell phones.) The answer to expanding access to patient data at home is using cellular devices that work right out of the box, regardless of whether the patient has cell service at home. This bridges the health equity gap by providing access to all patients, regardless of their tech-savviness or Wi-Fi/bluetooth connectivity limitations.

With the vision of making the lives of patients and care teams easier in combination with collaborating with hundreds of digital health partners and clinicians, Withings Health Solutions developed Body Pro 2. This advanced cellular smart scale transforms chronic condition management by offering personalized motivational messages, a vibrant LCD color screen, and engaging health trend data to show progress. 

Designed around positive health changes. Most in-home devices are a bit depressing to look at and do little to inspire patients. A sleek look and feel can make a profound difference on the patient experience and motivation. Designing in habit-forming features such as daily weather forecasts and motivational messages can help devices to effortlessly become part of patients’ everyday lives. 

Instant feedback. Patients are more engaged if they are able to see the results of their efforts. Being able to see decreased blood pressure or a lower weight after months of struggle is enough to keep patients motivated and confident in the program. A study published in the review Obesity shows that frequent weigh-ins with electronic graphic feedback are effective in preventing weight gain. Instant, understandable, color-coded feedback makes patients feel responsible for and more active in their care.

Accuracy. Devices should be highly accurate to provide precise data that will lead to the most efficient treatments. When considering a medical-grade device, look for agency approvals or markings indicating its accuracy.

Seamless integration. Devices should have the option to be easily integrated into a program’s existing workflow and to automate data collection, reducing the operational burden and associated costs. 

Integrate our suite of API solutions and retrieve data seamlessly, bridging the gap between our devices and your existing systems.

  • Easily integrate our drop shipment API in a matter of weeks – alternatively, if API development is not an option, use our portal and be up and running in just a few hours 
  • Eliminate the cost and headache of maintaining a third party fulfillment center or manually ordering devices with our drop shipment capabilities 
  • Avoid inventory risk and ensure patients get their devices shipped and delivered in a matter of days when dropshipping with Withings

How do health systems and patients benefit from this model?

Making better health part of daily life is possible with connected devices. These enable health systems to offer a higher level of care while fostering positive life changes in their patients. Through instant access to accurate patient data, care teams can better manage patients’ chronic conditions while alleviating extra work for their staff. With elegant, easy-to-use devices designed around patients’ daily lives, health systems can maximize program participation, improve health equity, and ultimately enhance outcomes for all. 

Don’t miss out,  subscribe to get the latest content updates.  

Related Content

WP_Query Object ( [query] => Array ( [post_type] => post [post_status] => publish [orderby] => date [order] => DESC [ignore_sticky_posts] => 1 [post__not_in] => Array ( [0] => 355 ) [cat] => 18 [posts_per_page] => 3 ) [query_vars] => Array ( [post_type] => post [post_status] => publish [orderby] => date [order] => DESC [ignore_sticky_posts] => 1 [post__not_in] => Array ( [0] => 355 ) [cat] => 18 [posts_per_page] => 3 [error] => [m] => [p] => 0 [post_parent] => [subpost] => [subpost_id] => [attachment] => [attachment_id] => 0 [name] => [pagename] => [page_id] => 0 [second] => [minute] => [hour] => [day] => 0 [monthnum] => 0 [year] => 0 [w] => 0 [category_name] => articles [tag] => [tag_id] => [author] => [author_name] => [feed] => [tb] => [paged] => 0 [meta_key] => [meta_value] => [preview] => [s] => [sentence] => [title] => [fields] => all [menu_order] => => [category__in] => Array ( ) [category__not_in] => Array ( ) [category__and] => Array ( ) [post__in] => Array ( ) [post_name__in] => Array ( ) [tag__in] => Array ( ) [tag__not_in] => Array ( ) [tag__and] => Array ( ) [tag_slug__in] => Array ( ) [tag_slug__and] => Array ( ) [post_parent__in] => Array ( ) [post_parent__not_in] => Array ( ) [author__in] => Array ( ) [author__not_in] => Array ( ) [search_columns] => Array ( ) [suppress_filters] => [cache_results] => 1 [update_post_term_cache] => 1 [update_menu_item_cache] => [lazy_load_term_meta] => 1 [update_post_meta_cache] => 1 [nopaging] => [comments_per_page] => 50 [no_found_rows] => ) [tax_query] => WP_Tax_Query Object ( [queries] => Array ( [0] => Array ( [taxonomy] => category [terms] => Array ( [0] => 18 ) [field] => term_id [operator] => IN [include_children] => 1 ) ) [relation] => AND [table_aliases:protected] => Array ( [0] => wp_term_relationships ) [queried_terms] => Array ( [category] => Array ( [terms] => Array ( [0] => 18 ) [field] => term_id ) ) [primary_table] => wp_posts [primary_id_column] => ID ) [meta_query] => WP_Meta_Query Object ( [queries] => Array ( ) [relation] => [meta_table] => [meta_id_column] => [primary_table] => [primary_id_column] => [table_aliases:protected] => Array ( ) [clauses:protected] => Array ( ) [has_or_relation:protected] => ) [date_query] => [request] => SELECT SQL_CALC_FOUND_ROWS wp_posts.ID FROM wp_posts LEFT JOIN wp_term_relationships ON (wp_posts.ID = wp_term_relationships.object_id) WHERE 1=1 AND wp_posts.ID NOT IN (355) AND ( wp_term_relationships.term_taxonomy_id IN (18) ) AND wp_posts.post_type = 'post' AND ((wp_posts.post_status = 'publish')) GROUP BY wp_posts.ID ORDER BY wp_posts.post_date DESC LIMIT 0, 3 [posts] => Array ( [0] => WP_Post Object ( [ID] => 2034 [post_author] => 11 [post_date] => 2025-09-02 16:47:55 [post_date_gmt] => 2025-09-02 16:47:55 [post_content] =>

Introduction

Sleep is an essential pillar of health and well-being. The clinical gold standard for sleep assessment, polysomnography or PSG, provides a detailed analysis of sleep architecture but is impractical for routine or long-term monitoring. Its reliance on complex equipment, high cost, and typically in-lab application make it an intrusive process. The proliferation of consumer wearable and nearable devices offers more accessible alternatives, yet their accuracy often lacks rigorous scientific validation, particularly in home environments.

 

A recent study sought to address this gap by evaluating the accuracy and reliability of the Withings Sleep Analyzer (WSA). This contactless sleep mat, placed under the mattress, was compared directly against simultaneous PSG recordings in a large and diverse group of individuals in their own homes. This research investigates the sensor's performance in real-world conditions, offering critical insights into the current state of consumer sleep-tracking technology.

 

Methods

The study involved 117 healthy participants, with 69 women, and a mean age of approximately 40 years. Each participant slept in their own bed for one night with both the PSG equipment and the under-mattress device active. This setup allowed for a direct, epoch-by-epoch comparison of the data recorded by the consumer device against the clinical reference standard. The analysis focused on two primary objectives: the accuracy of distinguishing sleep from wakefulness and the precision of classifying distinct sleep stages, including light, deep, and REM sleep. Performance was assessed using standard classification metrics to ensure a robust evaluation.

 

Results

The investigation found that the contactless device performs effectively in identifying sleep and wake states. It achieved an overall accuracy of 87% in this core task, demonstrating a high sensitivity of 93% for detecting sleep and a moderate sensitivity of 73% for detecting wakefulness. A key strength observed was the sleep mat's consistent performance across various subgroups. The accuracy of sleep-wake detection remained stable regardless of participant age, BMI, sex, mattress type, mattress thickness, sleep quality or the presence of a bed partner.

 

Challenges emerged in the classification of specific sleep stages. The sensor's mean accuracy for staging sleep was 63%, with a Cohen’s Kappa of 0.49. The primary difficulty was in distinguishing between light and deep sleep. This led to systematic biases in sleep duration estimates; the device tended to slightly overestimate total sleep time by an average of 20 minutes but substantially overestimated light sleep by 1 hour and 21 minutes. Conversely, it moderately underestimated REM sleep by 15 minutes and deep sleep by a more significant 46 minutes.

 

Notably, a notable proportion of misclassifications made by the sensor mirrored disagreements found between the expert human reviewers who scored the PSG data, especially concerning the boundary between light and deep sleep. Furthermore, participants reported that their perceived sleep quality was significantly altered for the worse on the night they used the PSG equipment, highlighting the intrusive nature of the gold standard itself.

In a comparative context, the Withings Sleep Analyzer exhibits highly competitive performance in sleep-wake discrimination relative to other devices on the market. For the more nuanced task of sleep stage classification, its accuracy is comparable to that of similar products. This level of performance is particularly noteworthy given the systemic challenges in sleep staging.

 

Conclusion

For individuals seeking to understand their sleep over weeks and months, the primary benefit of a device like the Withings Sleep Analyzer lies in its practicality. Its contactless, 'set-and-forget' nature eliminates the nightly burden of wearing a device and avoids the discomfort that can disrupt sleep, a notable issue even with the clinical gold standard. While the sensor's accuracy in distinguishing specific sleep stages requires further refinement, its strong performance in tracking overall sleep and wake times provides reliable insights into sleep duration and consistency. This capability for accessible, unobtrusive, and longitudinal monitoring is where at-home sensors currently provide the most value, empowering users with meaningful data on their long-term sleep trends.

 

Poster Session: Time and Location

“Evaluation of a Contactless Sleep Monitoring Device for Sleep Stage Detection against Home Polysomnography in a Healthy Population”

 

Session Title: Poster abstract group 2

 

Session Date: Monday, September 8, 2025

 

Presentation Time: 6:00pm to 7:00pm (Presenting authors will be present near their assigned poster board throughout the scheduled one-hour presentation window.)

 

Poster Board Number: 531

 

Location: Posters will be displayed in the exhibit hall on Level 4 and accessible during regular congress hours.

About Marie-Ange Stefanos

Marie-Ange Stefanos is a  Machine Learning Research Scientist and a PhD candidate pursuing a joint doctorate in Computer Science and Neuroscience from Université Paris Cité (France) and Reykjavik University (Iceland). Building on her background with an Engineering degree in Signal Processing from Grenoble INP - Phelma and an M.Sc. in Machine Learning from KTH Royal Institute of Technology, her path into health research was driven by a central question: how can my technical background be best applied to solve meaningful challenges in human health?

 

Her doctoral research focuses on insomnia, where she develops algorithms using data from wearables and self-reports to identify predictive biomarkers and differentiate subtypes of the disorder. This work depends entirely on data integrity, which is why she believes the rigorous validation of consumer devices, as discussed in this article, is the essential first step in translating complex signals into reliable, actionable insights for users.

Interested in partnering with us?

Contact Us [post_title] => The Promise and Pitfalls of At-Home Sleep Tracking: A Deep Dive into the Withings Sleep Analyzer [post_excerpt] => Chronic Kidney Disease stage 5 on dialysis (CKD5D) presents one of the most complex and high-risk scenarios in modern medicine.But what if technology could help bridge the gap between dialysis sessions, offering clinicians a window into the patient's health in real-time? [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => the-promise-and-pitfalls-of-at-home-sleep-tracking-a-deep-dive-into-the-withings-sleep-analyzer [to_ping] => [pinged] => [post_modified] => 2025-09-02 16:49:48 [post_modified_gmt] => 2025-09-02 16:49:48 [post_content_filtered] => [post_parent] => 0 [guid] => https://withingshealthsolutions.com/?p=2034 [menu_order] => 0 [post_type] => post [post_mime_type] => [comment_count] => 0 [filter] => raw ) [1] => WP_Post Object ( [ID] => 2015 [post_author] => 11 [post_date] => 2025-06-12 15:39:12 [post_date_gmt] => 2025-06-12 15:39:12 [post_content] =>

Chronic Kidney Disease stage 5 on dialysis (CKD5D) presents one of the most complex and high-risk scenarios in modern medicine. Among the many challenges faced by these patients, cardiovascular disease (CVD) stands out as the leading cause of mortality—a stark reminder of the systemic stress that accompanies kidney failure and dialysis.

 

But what if technology could help bridge the gap between dialysis sessions, offering clinicians a window into the patient's health in real-time? An article in Frontiers in Nephrology explores exactly that—highlighting the transformative potential of digital health technologies to monitor and manage CKD5D patients beyond the clinic.

 

The Hidden Risks Between Dialysis Sessions

For CKD5D patients, the risks of CVD are amplified by both traditional and disease-specific factors:

 

  • Traditional risks like hypertension, diabetes, and obesity.

  • CKD-specific risks such as inflammation, fluid overload, protein-energy wasting and vascular calcification.

  • The dialysis process itself, which induces rapid fluid shifts, blood pressure fluctuations, and metabolic imbalances.

Current clinical care models often focus on in-center dialysis data, leaving a crucial blind spot during the interdialytic period—a time when many adverse events begin to develop unnoticed.

 

A New Monitoring Paradigm: The Withings Toolkit

The article introduces a compelling case for home-based, connected health technologies—specifically, the Withings toolkit. This suite of medical-grade, consumer-friendly devices allows CKD patients to monitor key health indicators in the comfort of their homes:

 

  • Weight, body composition and ECG monitoring with the BodyScan smart scale.

  • Blood pressure, heart rate and survey responses for added context via BPM Pro 2.

  • Sleep quality and breathing event metrics using the Sleep Rx.

All data is seamlessly uploaded to the Withings Remote Patient Monitoring platform, providing healthcare providers and researchers with real-time, longitudinal insights into a patient’s well-being.

 

Why This Matters: Real-World Clinical Benefits

1. Early Detection of Complications

Weight gain could signal fluid retention, but muscle loss could indicate protein-energy wasting. A sudden spike in blood pressure or irregular heartbeat might indicate arrhythmias or volume overload. Poor sleep patterns could reflect apnea or restless leg syndrome—conditions with known ties to CKD.

2. Personalized, Data-Driven Care

These devices enable a dynamic view of health trends, allowing clinicians to tailor treatments proactively rather than reactively. Medication adjustments, fluid restrictions, or further diagnostics can be made with greater confidence.

3. Patient Empowerment

When patients can see and understand their own data, they become more engaged in their care. This promotes better self-management, increased treatment adherence, and a stronger sense of control over their condition.

4. Systemic Healthcare Advantages

Remote monitoring can reduce emergency visits and hospitalizations, easing the burden on overtaxed healthcare systems and offering a cost-effective alternative to frequent in-person evaluations.

 

The Future: Digital Tools as Standard of Care?

While still in its early stages, this integration of digital health into CKD care reflects a broader movement toward remote, preventative, and personalized medicine. The Withings case study serves as a promising example of how everyday technology can be adapted to serve complex clinical needs.

 

However, as the authors note, more clinical trials are needed to validate these tools in nephrology settings, establish protocols for data use, and ensure equitable access across diverse patient populations.

 

Final Thoughts

As we face growing rates of kidney disease and limited nephrology resources, connected health technologies offer a lifeline—not just to patients, but to an entire care infrastructure in need of modernization.

 

The Withings toolkit is more than a gadget suite; it's a glimpse into the future of chronic disease management, where data flows continuously, care is adaptive, and patients are active participants in their own health journey.

 

References
Article: Frontiers in Nephrology, 2023 - DOI: 10.3389/fneph.2023.1148565

Interested in partnering with us?

Contact Us [post_title] => Revolutionizing Chronic Kidney Disease Management with Digital Health Tools: The Withings Case Study [post_excerpt] => Chronic Kidney Disease stage 5 on dialysis (CKD5D) presents one of the most complex and high-risk scenarios in modern medicine.But what if technology could help bridge the gap between dialysis sessions, offering clinicians a window into the patient's health in real-time? [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => revolutionizing-chronic-kidney-disease-management-with-digital-health-tools-the-withings-case-study [to_ping] => [pinged] => [post_modified] => 2025-06-12 15:41:31 [post_modified_gmt] => 2025-06-12 15:41:31 [post_content_filtered] => [post_parent] => 0 [guid] => https://withingshealthsolutions.com/?p=2015 [menu_order] => 0 [post_type] => post [post_mime_type] => [comment_count] => 0 [filter] => raw ) [2] => WP_Post Object ( [ID] => 2012 [post_author] => 11 [post_date] => 2025-06-03 19:17:23 [post_date_gmt] => 2025-06-03 19:17:23 [post_content] =>

Introduction

 

Diabetic foot ulcers (DFUs) are a major and often debilitating complication of diabetes, contributing significantly to patient morbidity, mortality, and healthcare costs. Despite advancements in diabetes care, the incidence of DFUs remains high, with a substantial impact on quality of life and healthcare resources. A recent study published in the journal Frontiers in Endocrinology compared the use of electrochemical skin conductance (ESC) to the current standards in DFU detection. The current method for assessing DFU risk primarily involves clinical examination, including the monofilament test, which is subjective and dependent on the examiner’s skills. Therefore, there is a need for objective, reproducible, and reliable methods for early detection of at-risk patients.

 

One of the many complications of diabetes is peripheral neuropathy, which, if left untreated, can lead to DFUs. Electrochemical Skin Conductance (ESC) is a promising non-invasive diagnostic tool that can be used to assess autonomic nerve activity. ESC is measured in-clinic using Sudoscan, which assesses small fiber peripheral neuropathies, specifically the innervation around the sweat glands, by stimulating the glands and measuring the conductance (in µS) of chloride ions contained in the sweat. Lower ESC values indicate more severe neuropathy. This study investigates the association between ESC and DFU risk stratification, offering a potential new approach to managing and preventing diabetic foot complications.

Methods

 

This study was a retrospective analysis involving 2,149 diabetic patients from four clinics in Greater Paris University Hospitals, the largest hospital system in Europe and one of the largest in the world. The primary aim was to evaluate the relationship between ESC measurements and DFU risk, as classified using the 2016 International Working Group on Diabetic Foot (IWGDF) grading system. This grading system assigns DFU risk based on clinical evaluation, including the presence of neuropathy, ulceration, and other factors.

To assess the predictive performance of ESC in DFU risk stratification, the study incorporated a range of factors: age, sex, type of diabetes, and results from the monofilament test, which is a standard assessment of peripheral neuropathy. The study employed regression and Receiver Operating Characteristic (ROC) analyses to explore the predictive value of ESC measurements for different DFU risk categories.

 

Results

 

The study revealed a significant correlation between ESC values and DFU risk grades (p<0.001). Specifically, lower FESC values were associated with higher grades of DFU risk, suggesting that reduced sweat gland function, indicative of small fiber neuropathy, plays a role in the progression of foot ulcers in diabetic patients.

 

One of the most noteworthy findings of this study was that ESC measurements were able to identify patients at risk for DFUs who would not have been classified as high risk using the standard IWGDF grading system. Specifically, ESC detected autonomic dysfunction and small fiber nerve involvement in 43% patients classified as grade 0 (13% with severe cases of neuropathy), who otherwise showed no obvious signs of risk through traditional assessments, showing better granularity in the lower grades for better risk stratification.

 

The findings of this study suggest that Electrochemical Skin Conductance (ESC) provides a valuable, reproducible, and operator-independent tool for assessing DFU risk. ESC measurements offer an objective method for identifying early signs of small fiber neuropathy, a critical factor in the development of DFUs. Unlike traditional risk stratification, which relies heavily on clinical judgment and may overlook early-stage neuropathy, ESC can detect subtle changes in nerve function that precede visible foot ulcers.

 

The ability of ESC to detect at-risk patients in the grade 0 category, who would otherwise be overlooked by conventional classification methods, highlights its potential role in preventing DFUs. By identifying patients with early-stage nerve dysfunction, ESC could facilitate earlier intervention, potentially reducing the incidence of foot ulcers, amputations, and associated healthcare costs.

 

The ability to detect DFU risk early using ESC shows promise for the prevention of amputation.Therefore, we conclude that feet skin conductance is a relevant parameter for detecting diabetic foot syndrome, specifically at an early stage when there is still no presence of feet ulceration or wounds. A recent meta-analysis on ESC supports this conclusion, indicating that ESC, when combined with temperature measurements, serves as a valuable tool for the early detection of diabetic foot syndrome. ESC can be measured in-clinic, using Sudoscan, and at home using Withings Body Pro 2. Measuring ESC through home use of the Body Pro 2 scale allows for additional data collection and better assessment of trends and progression between appointments. Through this enhanced monitoring of DFU risk, care teams can better risk-stratify and provide targeted care that could prevent amputations and complications.

Interested in partnering with us?

Contact Us [post_title] => Electrochemical Skin Conductance as a Novel Tool for Diabetic Foot Ulcer Risk Stratification and Prevention [post_excerpt] => Diabetic foot ulcers (DFUs) are a major and often debilitating complication of diabetes, contributing significantly to patient morbidity, mortality, and healthcare costs.Electrochemical Skin Conductance (ESC) is a promising non-invasive diagnostic tool that can be used to assess autonomic nerve activity. [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => electrochemical-skin-conductance-as-a-novel-tool-for-diabetic-foot-ulcer-risk-stratification-and-prevention [to_ping] => [pinged] => [post_modified] => 2025-06-16 13:31:21 [post_modified_gmt] => 2025-06-16 13:31:21 [post_content_filtered] => [post_parent] => 0 [guid] => https://withingshealthsolutions.com/?p=2012 [menu_order] => 0 [post_type] => post [post_mime_type] => [comment_count] => 0 [filter] => raw ) ) [post_count] => 3 [current_post] => -1 [before_loop] => 1 [in_the_loop] => [post] => WP_Post Object ( [ID] => 2034 [post_author] => 11 [post_date] => 2025-09-02 16:47:55 [post_date_gmt] => 2025-09-02 16:47:55 [post_content] =>

Introduction

Sleep is an essential pillar of health and well-being. The clinical gold standard for sleep assessment, polysomnography or PSG, provides a detailed analysis of sleep architecture but is impractical for routine or long-term monitoring. Its reliance on complex equipment, high cost, and typically in-lab application make it an intrusive process. The proliferation of consumer wearable and nearable devices offers more accessible alternatives, yet their accuracy often lacks rigorous scientific validation, particularly in home environments.

 

A recent study sought to address this gap by evaluating the accuracy and reliability of the Withings Sleep Analyzer (WSA). This contactless sleep mat, placed under the mattress, was compared directly against simultaneous PSG recordings in a large and diverse group of individuals in their own homes. This research investigates the sensor's performance in real-world conditions, offering critical insights into the current state of consumer sleep-tracking technology.

 

Methods

The study involved 117 healthy participants, with 69 women, and a mean age of approximately 40 years. Each participant slept in their own bed for one night with both the PSG equipment and the under-mattress device active. This setup allowed for a direct, epoch-by-epoch comparison of the data recorded by the consumer device against the clinical reference standard. The analysis focused on two primary objectives: the accuracy of distinguishing sleep from wakefulness and the precision of classifying distinct sleep stages, including light, deep, and REM sleep. Performance was assessed using standard classification metrics to ensure a robust evaluation.

 

Results

The investigation found that the contactless device performs effectively in identifying sleep and wake states. It achieved an overall accuracy of 87% in this core task, demonstrating a high sensitivity of 93% for detecting sleep and a moderate sensitivity of 73% for detecting wakefulness. A key strength observed was the sleep mat's consistent performance across various subgroups. The accuracy of sleep-wake detection remained stable regardless of participant age, BMI, sex, mattress type, mattress thickness, sleep quality or the presence of a bed partner.

 

Challenges emerged in the classification of specific sleep stages. The sensor's mean accuracy for staging sleep was 63%, with a Cohen’s Kappa of 0.49. The primary difficulty was in distinguishing between light and deep sleep. This led to systematic biases in sleep duration estimates; the device tended to slightly overestimate total sleep time by an average of 20 minutes but substantially overestimated light sleep by 1 hour and 21 minutes. Conversely, it moderately underestimated REM sleep by 15 minutes and deep sleep by a more significant 46 minutes.

 

Notably, a notable proportion of misclassifications made by the sensor mirrored disagreements found between the expert human reviewers who scored the PSG data, especially concerning the boundary between light and deep sleep. Furthermore, participants reported that their perceived sleep quality was significantly altered for the worse on the night they used the PSG equipment, highlighting the intrusive nature of the gold standard itself.

In a comparative context, the Withings Sleep Analyzer exhibits highly competitive performance in sleep-wake discrimination relative to other devices on the market. For the more nuanced task of sleep stage classification, its accuracy is comparable to that of similar products. This level of performance is particularly noteworthy given the systemic challenges in sleep staging.

 

Conclusion

For individuals seeking to understand their sleep over weeks and months, the primary benefit of a device like the Withings Sleep Analyzer lies in its practicality. Its contactless, 'set-and-forget' nature eliminates the nightly burden of wearing a device and avoids the discomfort that can disrupt sleep, a notable issue even with the clinical gold standard. While the sensor's accuracy in distinguishing specific sleep stages requires further refinement, its strong performance in tracking overall sleep and wake times provides reliable insights into sleep duration and consistency. This capability for accessible, unobtrusive, and longitudinal monitoring is where at-home sensors currently provide the most value, empowering users with meaningful data on their long-term sleep trends.

 

Poster Session: Time and Location

“Evaluation of a Contactless Sleep Monitoring Device for Sleep Stage Detection against Home Polysomnography in a Healthy Population”

 

Session Title: Poster abstract group 2

 

Session Date: Monday, September 8, 2025

 

Presentation Time: 6:00pm to 7:00pm (Presenting authors will be present near their assigned poster board throughout the scheduled one-hour presentation window.)

 

Poster Board Number: 531

 

Location: Posters will be displayed in the exhibit hall on Level 4 and accessible during regular congress hours.

About Marie-Ange Stefanos

Marie-Ange Stefanos is a  Machine Learning Research Scientist and a PhD candidate pursuing a joint doctorate in Computer Science and Neuroscience from Université Paris Cité (France) and Reykjavik University (Iceland). Building on her background with an Engineering degree in Signal Processing from Grenoble INP - Phelma and an M.Sc. in Machine Learning from KTH Royal Institute of Technology, her path into health research was driven by a central question: how can my technical background be best applied to solve meaningful challenges in human health?

 

Her doctoral research focuses on insomnia, where she develops algorithms using data from wearables and self-reports to identify predictive biomarkers and differentiate subtypes of the disorder. This work depends entirely on data integrity, which is why she believes the rigorous validation of consumer devices, as discussed in this article, is the essential first step in translating complex signals into reliable, actionable insights for users.

Interested in partnering with us?

Contact Us [post_title] => The Promise and Pitfalls of At-Home Sleep Tracking: A Deep Dive into the Withings Sleep Analyzer [post_excerpt] => Chronic Kidney Disease stage 5 on dialysis (CKD5D) presents one of the most complex and high-risk scenarios in modern medicine.But what if technology could help bridge the gap between dialysis sessions, offering clinicians a window into the patient's health in real-time? [post_status] => publish [comment_status] => closed [ping_status] => closed [post_password] => [post_name] => the-promise-and-pitfalls-of-at-home-sleep-tracking-a-deep-dive-into-the-withings-sleep-analyzer [to_ping] => [pinged] => [post_modified] => 2025-09-02 16:49:48 [post_modified_gmt] => 2025-09-02 16:49:48 [post_content_filtered] => [post_parent] => 0 [guid] => https://withingshealthsolutions.com/?p=2034 [menu_order] => 0 [post_type] => post [post_mime_type] => [comment_count] => 0 [filter] => raw ) [comment_count] => 0 [current_comment] => -1 [found_posts] => 49 [max_num_pages] => 17 [max_num_comment_pages] => 0 [is_single] => [is_preview] => [is_page] => [is_archive] => 1 [is_date] => [is_year] => [is_month] => [is_day] => [is_time] => [is_author] => [is_category] => 1 [is_tag] => [is_tax] => [is_search] => [is_feed] => [is_comment_feed] => [is_trackback] => [is_home] => [is_privacy_policy] => [is_404] => [is_embed] => [is_paged] => [is_admin] => [is_attachment] => [is_singular] => [is_robots] => [is_favicon] => [is_posts_page] => [is_post_type_archive] => [query_vars_hash:WP_Query:private] => c2cc8fab039c2aec8a65b3e048ad7fae [query_vars_changed:WP_Query:private] => [thumbnails_cached] => [allow_query_attachment_by_filename:protected] => [stopwords:WP_Query:private] => [compat_fields:WP_Query:private] => Array ( [0] => query_vars_hash [1] => query_vars_changed ) [compat_methods:WP_Query:private] => Array ( [0] => init_query_flags [1] => parse_tax_query ) [query_cache_key:WP_Query:private] => wp_query:149160e97c2eed6af8edfa2b6d6c4430:0.88908500 17577550910.51677100 1757754946 )
Article

The Promise and Pitfalls of At-Home Sleep Tracking: A Deep Dive into the Withings Sleep Analyzer

Read More
Article

Revolutionizing Chronic Kidney Disease Management with Digital Health Tools: The Withings Case Study

Read More
Article

Electrochemical Skin Conductance as a Novel Tool for Diabetic Foot Ulcer Risk Stratification and Prevention

Read More

Withings On-The-Go

Our patient-centric care solution utilizes portable Withings cellular devices that are not tied to a single patient. Instead, care teams can use one device to collect and transmit data for an unlimited number of individuals. The integrated cellular connectivity automatically directs the data into the correct patient’s medical record, simplifying data collection and improving care delivery regardless of the setting.