Non-invasive heart failure monitoring: leveraging smart scales and digital biomarkers to improve heart failure outcomes.

Heart failure (HF) is a significant global concern, impacting patient morbidity, mortality, and healthcare costs. Guideline-directed medical therapy and various preventive measures have proven effective in improving clinical outcomes and reducing HF hospitalizations. Recent data indicates that remote HF monitoring facilitates early detection of HF decompensation by observing upstream events and parameters before clinical signs and symptoms manifest. Moreover, these innovative devices have been shown to decrease unnecessary HF hospitalizations and, in some cases, provide predictive insights before an actual HF incident. In this review, we aim to explore the data regarding smart scales and digital biomarkers and summarize both FDA-approved devices and emerging technologies by assessing their clinical utility, mechanism of HF decompensation detection, and ongoing trials. Furthermore, we also discuss the future trend of integrating these devices into routine clinical practice to improve patient clinical outcomes.

Collecting health-related research data using consumer-based wireless smart scales.

BACKGROUND: Serious public-health concerns such as overweight and obesity are in many cases caused by excess intake of food combined with decreases in physical activity. Smart scales with wireless data transfer can, together with smart watches and trackers, observe changes in the population's health. They can present us with a picture of our metabolism, body health, and disease risks. Combining body composition data with physical activity measurements from devices such as smart watches could contribute to building a human digital twin. OBJECTIVE: The objectives of this study were to (1) investigate the evolution of smart scales in the last decade, (2) map status and supported sensors of smart scales, (3) get an overview of how smart scales have been used in research, and (4) identify smart scales for current and future research. METHOD: We searched for devices through web shops and smart scale tests/reviews, extracting data from the manufacturer's official website, user manuals when available, and data from web shops. We also searched scientific literature databases for smart scale usage in scientific papers. RESULT: We identified 165 smart scales with a wireless connection from 72 different manufacturers, released between 2009 and end of 2021. Of these devices, 49 (28%) had been discontinued by end of 2021. We found that the use of major variables such as fat and muscle mass have been as good as constant over the years, and that minor variables such as visceral fat and protein mass have increased since 2015. The main contribution is a representative overview of consumer grade smart scales between 2009 and 2021. CONCLUSION: The last six years have seen a distinct increase of these devices in the marketplace, measuring body composition with bone mass, muscle mass, fat mass, and water mass, in addition to weight. Still, the number of research projects featuring connected smart scales are few. One reason could be the lack of professionally accurate measurements, though trend analysis might be a more feasible usage scenario.

Safety evaluation of smart scales, smart watches, and smart rings with bioimpedance technology shows evidence of potential interference in cardiac implantable electronic devices.

BACKGROUND: Smart scales, smart watches, and smart rings with bioimpedance technology may create interference in patients with cardiac implantable electronic devices (CIEDs). OBJECTIVES: The purpose of this study was to determine interference at CIEDs with simulations and benchtop testing, and to compare the results with maximum values defined in the ISO 14117 electromagnetic interference standard for these devices. METHODS: The interference at pacing electrodes was determined by simulations on a male and a female computable model. A benchtop evaluation of representative CIEDs from 3 different manufacturers as specified in the ISO 14117 standard also was performed. RESULTS: Simulations showed evidence of interference with voltage values exceeding threshold values defined in the ISO 14117 standard. The level of interference varied with the frequency and amplitude of the bioimpedance signal, and between male and female models. The level of interference generated with smart scale and smart rings simulations was lower than with smart watches. Across device manufacturers, generators demonstrated susceptibility to oversensing and pacing inhibition at different signal amplitudes and frequencies. CONCLUSIONS: This study evaluated the safety of smart scales, smart watches, and smart rings with bioimpedance technology via simulation and testing. Our results indicate that these consumer electronic devices could interfere in patients with CIEDs. The present findings do not recommend the use of these devices in this population due to potential interference.

Pattern-based clustering of daily weigh-in trajectories using dynamic time warping.

"Smart"-scales are a new tool for frequent monitoring of weight change as well as weigh-in behavior. These scales give researchers the opportunity to discover patterns in the frequency that individuals weigh themselves over time, and how these patterns are associated with overall weight loss. Our motivating data come from an 18-month behavioral weight loss study of 55 adults classified as overweight or obese who were instructed to weigh themselves daily. Adherence to daily weigh-in routines produces a binary times series for each subject, indicating whether a participant weighed in on a given day. To characterize weigh-in by time-invariant patterns rather than overall adherence, we propose using hierarchical clustering with dynamic time warping (DTW). We perform an extensive simulation study to evaluate the performance of DTW compared to Euclidean and Jaccard distances to recover underlying patterns in adherence time series. In addition, we compare cluster performance using cluster validation indices (CVIs) under the single, average, complete, and Ward linkages and evaluate how internal and external CVIs compare for clustering binary time series. We apply conclusions from the simulation to cluster our real data and summarize observed weigh-in patterns. Our analysis finds that the adherence trajectory pattern is significantly associated with weight loss.

The Effect of Tailored, Daily, Smartphone Feedback to Lifestyle Self-Monitoring on Weight Loss at 12 Months: the SMARTER Randomized Clinical Trial.

BACKGROUND: Self-monitoring (SM) is the centerpiece of behavioral weight loss treatment, but the efficacy of smartphone-delivered SM feedback (FB) has not been tested in large, long-term, randomized trials. OBJECTIVE: The aim of this study was to establish the efficacy of providing remote FB to diet, physical activity (PA), and weight SM on improving weight loss outcomes when comparing the SM plus FB (SM+FB) condition to the SM-only condition in a 12-month randomized controlled trial. The study was a single-site, population-based trial that took place in southwestern Pennsylvania, USA, conducted between 2018 and 2021. Participants were smartphone users age ≥18 years, able to engage in moderate PA, with a mean BMI between 27 and 43 kg/m2. METHODS: All participants received a 90-minute, one-to-one, in-person behavioral weight loss counseling session addressing behavioral strategies, establishing participants' dietary and PA goals, and instructing on use of the PA tracker (Fitbit Charge 2), smart scale, and diet SM app. Only SM+FB participants had access to an investigator-developed smartphone app that read SM data, in which an algorithm selected tailored messages sent to the smartphone up to 3 times daily. The SM-only participants did not receive any tailored FB based on SM data. The primary outcome was percent weight change from baseline to 12 months. Secondary outcomes included engagement with digital tools (eg, monthly percentage of FB messages opened and monthly percentage of days adherent to the calorie goal). RESULTS: Participants (N=502) were on average 45.0 (SD 14.4) years old with a mean BMI of 33.7 (SD 4.0) kg/m2. The sample was 79.5% female (n=399/502) and 82.5% White (n=414/502). At 12 months, retention was 78.5% (n=394/502) and similar by group (SM+FB: 202/251, 80.5%; SM: 192/251, 76.5%; P=.28). There was significant percent weight loss from baseline in both groups (SM+FB: -2.12%, 95% CI -3.04% to -1.21%, P<.001; SM: -2.39%, 95% CI -3.32% to -1.47%; P<.001), but no difference between the groups (-0.27%; 95% CI -1.57% to 1.03%; t =-0.41; P=.68). Similarly, 26.3% (66/251) of the SM+FB group and 29.1% (73/251) of the SM group achieved ≥5% weight loss (chi-square value=0.49; P=.49). A 1% increase in FB messages opened was associated with a 0.10 greater percent weight loss at 12 months (b=-0.10; 95% CI -0.13 to -0.07; t =-5.90; P<.001). A 1% increase in FB messages opened was associated with 0.12 greater percentage of days adherent to the calorie goal per month (b=0.12; 95% CI 0.07-0.17; F=22.19; P<.001). CONCLUSIONS: There were no significant between-group differences in weight loss; however, the findings suggested that the use of commercially available digital SM tools with or without FB resulted in a clinically significant weight loss in over 25% of participants. Future studies need to test additional strategies that will promote greater engagement with digital tools. TRIAL REGISTRATION: Clinicaltrials.gov NCT03367936; https://clinicaltrials.gov/ct2/show/NCT03367936.

Accuracy of Smart Scales on Weight and Body Composition: Observational Study.

BACKGROUND: Smart scales are increasingly used at home by patients to monitor their body weight and body composition, but scale accuracy has not often been documented. OBJECTIVE: The goal of the research was to determine the accuracy of 3 commercially available smart scales for weight and body composition compared with dual x-ray absorptiometry (DEXA) as the gold standard. METHODS: We designed a cross-sectional study in consecutive patients evaluated for DEXA in a physiology unit in a tertiary hospital in France. There were no exclusion criteria except patient declining to participate. Patients were weighed with one smart scale immediately after DEXA. Three scales were compared (scale 1: Body Partner [Téfal], scale 2: DietPack [Terraillon], and scale 3: Body Cardio [Nokia Withings]). We determined absolute error between the gold standard values obtained from DEXA and the smart scales for body mass, fat mass, and lean mass. RESULTS: The sample for analysis included 53, 52, and 48 patients for each of the 3 tested smart scales, respectively. The median absolute error for body weight was 0.3 kg (interquartile range [IQR] -0.1, 0.7), 0 kg (IQR -0.4, 0.3), and 0.25 kg (IQR -0.10, 0.52), respectively. For fat mass, absolute errors were -2.2 kg (IQR -5.8, 1.3), -4.4 kg (IQR -6.6, 0), and -3.7 kg (IQR -8.0, 0.28), respectively. For muscular mass, absolute errors were -2.2 kg (IQR -5.8, 1.3), -4.4 kg (IQR -6.6, 0), and -3.65 kg (IQR -8.03, 0.28), respectively. Factors associated with fat mass measurement error were weight for scales 1 and 2 (P=.03 and P<.001, respectively), BMI for scales 1 and 2 (P=.034 and P<.001, respectively), body fat for scale 1 (P<.001), and muscular and bone mass for scale 2 (P<.001 for both). Factors associated with muscular mass error were weight and BMI for scale 1 (P<.001 and P=.004, respectively), body fat for scales 1 and 2 (P<.001 for both), and muscular and bone mass for scale 2 (P<.001 and P=.002, respectively). CONCLUSIONS: Smart scales are not accurate for body composition and should not replace DEXA in patient care. TRIAL REGISTRATION: ClinicalTrials.gov NCT03803098; https://clinicaltrials.gov/ct2/show/NCT03803098.

Data Imputation and Body Weight Variability Calculation Using Linear and Nonlinear Methods in Data Collected From Digital Smart Scales: Simulation and Validation Study.

BACKGROUND: Body weight variability (BWV) is common in the general population and may act as a risk factor for obesity or diseases. The correct identification of these patterns may have prognostic or predictive value in clinical and research settings. With advancements in technology allowing for the frequent collection of body weight data from electronic smart scales, new opportunities to analyze and identify patterns in body weight data are available. OBJECTIVE: This study aims to compare multiple methods of data imputation and BWV calculation using linear and nonlinear approaches. METHODS: In total, 50 participants from an ongoing weight loss maintenance study (the NoHoW study) were selected to develop the procedure. We addressed the following aspects of data analysis: cleaning, imputation, detrending, and calculation of total and local BWV. To test imputation, missing data were simulated at random and using real patterns of missingness. A total of 10 imputation strategies were tested. Next, BWV was calculated using linear and nonlinear approaches, and the effects of missing data and data imputation on these estimates were investigated. RESULTS: Body weight imputation using structural modeling with Kalman smoothing or an exponentially weighted moving average provided the best agreement with observed values (root mean square error range 0.62%-0.64%). Imputation performance decreased with missingness and was similar between random and nonrandom simulations. Errors in BWV estimations from missing simulated data sets were low (2%-7% with 80% missing data or a mean of 67, SD 40.1 available body weights) compared with that of imputation strategies where errors were significantly greater, varying by imputation method. CONCLUSIONS: The decision to impute body weight data depends on the purpose of the analysis. Directions for the best performing imputation methods are provided. For the purpose of estimating BWV, data imputation should not be conducted. Linear and nonlinear methods of estimating BWV provide reasonably accurate estimates under high proportions (80%) of missing data.

Concordance of In-Home "Smart" Scale Measurement with Body Weight Measured In-Person.

OBJECTIVE: Newer "smart" scales that transmit participants' body weights directly to data collection centers offer the opportunity to simplify weight assessment in weight management research; however, little data exist on the concordance of these data compared to weights measured at in-person assessments. METHODS: We compared the weights of 58 participants (mean±SD BMI = 31.6±4.8, age = 52.1±9.7 years, 86.2% White, 65.5% Female) measured by study staff at an in-person assessment visit to weights measured on the same day at home using BodyTrace "smart" scales. These measures occurred after 3 months of an internet-based weight management intervention. RESULTS: Weight (mean±SD) measured at the 3-month in-person assessment visit was 81.5±14.7kg compared to 80.4±14.5kg measured on the same day using in-home body weight scales; mean bias =1.1±0.8kg, 95% limits of agreement = -0.5 to 2.6. Two outliers in the data suggest that there may be greater variability between measurements for participants weighing above 110 kg. CONCLUSION: Results suggest good concordance between the measurements and support the use of the BodyTrace smart scale in weight management research. Future trials using BodyTrace scales for outcome assessment should clearly define protocols for measurement and associated instructions to participants (e.g., instruct individuals to weigh at the same time of day, similarly clothed). Finally, measure concordance should be investigated in a group of individuals weighing more than 110kg.