Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cardiovascular-Kidney-Metabolic Health: Insights from Wearables and Blood Biomarkers

Zeinab Esmaeilpour, A. Ali Heydari, Daniel McDuff, Anthony Z Faranesh, Conor Heneghan, Shwetak Patel, Mark Malhotra, Cathy Speed, Javier L. Prieto, Ahmed A. Metwally

Abstract

Cardiovascular-Kidney-Metabolic (CKM) syndrome represents a growing public health crisis, yet the subclinical heterogeneity of its component systems remains underexplored. Early detection of physiological deviation is critical for preventing irreversible organ damage and mortality. Here, we characterize the prevalence and interplay of CKM impairment in a US cohort (N=841) by integrating continuous wearable data with clinical biomarkers. We assessed cardiovascular, kidney via clinical biomarkers, namely Chol/HDL, eGFR, as well as metabolic health risk through Homeostatic Model Assessment of Insulin Resistance (HOMA-IR). We show that while metabolic and cardiovascular disruptions are significantly associated (r=0.26, p<0.001), early-stage kidney impairment manifests independently. Utilizing a normalized deviance score, we identified significant health impairments in 29.0% of the cohort. Cardiovascular deviation was the most prevalent singular phenotype (13.3%), followed by metabolic (9.1%) and renal (6.25%) deviations, with dual metabolic-cardiovascular impairment occurring in only 2.2% of participants. These findings suggest that high system-specific deviance may serve as an indicator for accelerated physiological aging within the respective organ system. Furthermore, feature ablation analysis revealed that step count, Active Zone Minutes, and resting heart rate are the most potent wearable-derived predictors of cardiovascular and metabolic decline. These findings underscore the necessity of a multi-system subtyping approach, demonstrating that wearable-derived phenotypes can facilitate the early, targeted interventions required to manage the complex landscape of CKM syndrome.

Cardiovascular-Kidney-Metabolic Health: Insights from Wearables and Blood Biomarkers

Abstract

Cardiovascular-Kidney-Metabolic (CKM) syndrome represents a growing public health crisis, yet the subclinical heterogeneity of its component systems remains underexplored. Early detection of physiological deviation is critical for preventing irreversible organ damage and mortality. Here, we characterize the prevalence and interplay of CKM impairment in a US cohort (N=841) by integrating continuous wearable data with clinical biomarkers. We assessed cardiovascular, kidney via clinical biomarkers, namely Chol/HDL, eGFR, as well as metabolic health risk through Homeostatic Model Assessment of Insulin Resistance (HOMA-IR). We show that while metabolic and cardiovascular disruptions are significantly associated (r=0.26, p<0.001), early-stage kidney impairment manifests independently. Utilizing a normalized deviance score, we identified significant health impairments in 29.0% of the cohort. Cardiovascular deviation was the most prevalent singular phenotype (13.3%), followed by metabolic (9.1%) and renal (6.25%) deviations, with dual metabolic-cardiovascular impairment occurring in only 2.2% of participants. These findings suggest that high system-specific deviance may serve as an indicator for accelerated physiological aging within the respective organ system. Furthermore, feature ablation analysis revealed that step count, Active Zone Minutes, and resting heart rate are the most potent wearable-derived predictors of cardiovascular and metabolic decline. These findings underscore the necessity of a multi-system subtyping approach, demonstrating that wearable-derived phenotypes can facilitate the early, targeted interventions required to manage the complex landscape of CKM syndrome.

Paper Structure

This paper contains 27 sections, 14 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Results
  3. Study Design and cohort characteristics
  4. Individual Heterogeneity in CKM Health as a Reflectance of System-Specific Accelerated Aging
  5. Association between CKM health metrics, wearables and blood biomarkers features
  6. Characterization of Modifiable CKM Health Determinants Independent of Age and Gender
  7. Prediction of Cardiovascular-Kidney-Metabolic Health markers using wearables and routine blood biomarkers
  8. Discussion
  9. Method
  10. Participant recruitment via Google Health studies (GHS)
  11. Study Design
  12. Metadata collection
  13. Blood biomarkers via Quest diagnostics
  14. Wearables data via Fitbit devices and Pixel Watches
  15. Selection of thresholds for Chol/HDL, eGFR and HOMA-IR
  16. ...and 12 more sections

Figures (14)

  • Figure 1: Study design and summary of Dataset. (A) The study combines wearables data, demographics information and blood lab results to understand how wearables can be used to assess Cardiovascular-kidney-Metabolic Health. (B) Distribution of Data Modalities Among Study Participants. The three donut plots display the percentage of individuals contributing wearable data, those providing only lab biomarker data, and percentage of participants with both wearable and lab biomarker data. (C) Number of study participants with Cardiovascular disease (CVD), Diabetes and Kidney disease per self reporting of participants and all comorbid combinations of these conditions, as recorded in each survey.
  • Figure 2: Subsystem-Specific Biomarkers and a Standardized Deviance Metric for Integrated Cardio-Kidney-Metabolic Health Monitoring. Identification of a key biomarker for CKM subsystems: the Chol/HDL ratio for cardiovascular health, eGFR for kidney health, and Homa-IR for metabolic health. Introduction of health status deviance determined by subtracting the normal threshold from the observed value and normalizing the difference by the population standard deviation (STD). A positive deviance value corresponds to a healthy condition in the respective subsystem, whereas a negative value indicates a decline in health.
  • Figure 3: Cardiovascular-Kidney-Metabolic health heterogeneity among individuals. Health statuses across cardiovascular, kidney, and metabolic subsystems within the study population. (A) Heatmap of the calculated health deviance for all participants across the CKM subsystems, allowing for the identification of individual health profiles and patterns of health across CKM subsystems. (B) Correlation matrix heatmap illustrating the inter-correlations among the health statuses of the three subsystems within the study population.
  • Figure 4: Correlated features in Cardiovascular, Kidney and Metabolic subsystems. The Pearson correlation (correlation coefficient > 0.05) between lifestyle, demographic and blood biomarkers and the health status of Cardiovascular, Kidney and Metabolic subsystems. (A) Illustrates the critical correlates for the cardiovascular health subsystem. (B) Presents the significant relationships for the kidney health subsystem. (C) Outlines the primary correlated factors for the metabolic health subsystem.
  • Figure S1: Deviance from Normal thresholds for cardiovascular health biomarkers in the study cohort.
  • ...and 9 more figures