Sleep patterns and risk of chronic disease as measured by long-term monitoring with commercial wearable devices in the All of Us Research Program.

Poor sleep health is associated with increased all-cause mortality and incidence of many chronic conditions. Previous studies have relied on cross-sectional and self-reported survey data or polysomnograms, which have limitations with respect to data granularity, sample size and longitudinal information. Here, using objectively measured, longitudinal sleep data from commercial wearable devices linked to electronic health record data from the All of Us Research Program, we show that sleep patterns, including sleep stages, duration and regularity, are associated with chronic disease incidence. Of the 6,785 participants included in this study, 71% were female, 84% self-identified as white and 71% had a college degree; the median age was 50.2 years (interquartile range = 35.7, 61.5) and the median sleep monitoring period was 4.5 years (2.5, 6.5). We found that rapid eye movement sleep and deep sleep were inversely associated with the odds of incident atrial fibrillation and that increased sleep irregularity was associated with increased odds of incident obesity, hyperlipidemia, hypertension, major depressive disorder and generalized anxiety disorder. Moreover, J-shaped associations were observed between average daily sleep duration and hypertension, major depressive disorder and generalized anxiety disorder. These findings show that sleep stages, duration and regularity are all important factors associated with chronic disease development and may inform evidence-based recommendations on healthy sleeping habits.

Harnessing Consumer Wearable Digital Biomarkers for Individualized Recognition of Postpartum Depression Using the All of Us Research Program Data Set: Cross-Sectional Study.

BACKGROUND: Postpartum depression (PPD) poses a significant maternal health challenge. The current approach to detecting PPD relies on in-person postpartum visits, which contributes to underdiagnosis. Furthermore, recognizing PPD symptoms can be challenging. Therefore, we explored the potential of using digital biomarkers from consumer wearables for PPD recognition. OBJECTIVE: The main goal of this study was to showcase the viability of using machine learning (ML) and digital biomarkers related to heart rate, physical activity, and energy expenditure derived from consumer-grade wearables for the recognition of PPD. METHODS: Using the All of Us Research Program Registered Tier v6 data set, we performed computational phenotyping of women with and without PPD following childbirth. Intraindividual ML models were developed using digital biomarkers from Fitbit to discern between prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods. Models were built using generalized linear models, random forest, support vector machine, and k-nearest neighbor algorithms and evaluated using the κ statistic and multiclass area under the receiver operating characteristic curve (mAUC) to determine the algorithm with the best performance. The specificity of our individualized ML approach was confirmed in a cohort of women who gave birth and did not experience PPD. Moreover, we assessed the impact of a previous history of depression on model performance. We determined the variable importance for predicting the PPD period using Shapley additive explanations and confirmed the results using a permutation approach. Finally, we compared our individualized ML methodology against a traditional cohort-based ML model for PPD recognition and compared model performance using sensitivity, specificity, precision, recall, and F1-score. RESULTS: Patient cohorts of women with valid Fitbit data who gave birth included <20 with PPD and 39 without PPD. Our results demonstrated that intraindividual models using digital biomarkers discerned among prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods, with random forest (mAUC=0.85; κ=0.80) models outperforming generalized linear models (mAUC=0.82; κ=0.74), support vector machine (mAUC=0.75; κ=0.72), and k-nearest neighbor (mAUC=0.74; κ=0.62). Model performance decreased in women without PPD, illustrating the method's specificity. Previous depression history did not impact the efficacy of the model for PPD recognition. Moreover, we found that the most predictive biomarker of PPD was calories burned during the basal metabolic rate. Finally, individualized models surpassed the performance of a conventional cohort-based model for PPD detection. CONCLUSIONS: This research establishes consumer wearables as a promising tool for PPD identification and highlights personalized ML approaches, which could transform early disease detection strategies.

The Combined Influence of Sleep Disturbance and Depression on 12-month Outcomes after Lumbar Spine Surgery.

STUDY DESIGN: Retrospective analysis of prospectively collected data. OBJECTIVE: To examine the combined influence of preoperative sleep disturbance and depression on 12-month patient-reported outcomes after lumbar spine surgery (LSS). SUMMARY OF BACKGROUND DATA: Psychological and behavioral factors are considered major risk factors of poor outcome after LSS. However, there is a need to explore the combined effects of preoperative factors such as sleep disturbance and depression. Understanding the influence of sleep disturbance and depression can inform evidence-based preoperative assessment and shared-decision making of preoperative and postoperative treatment. METHODS: Data from 700 patients undergoing LSS were analyzed. Preoperative sleep disturbance and depression were assessed with PROMIS subscales. Established thresholds defined patients with moderate/severe symptoms. Outcomes for disability (Oswestry Disability Index) and back and leg pain (Numeric Rating Scales) were assessed preoperatively and at 12 months. Separate multivariable linear regressions examined the influence of each factor on 12-month outcomes with and without accounting for the other, and in combination as a 4-level variable: 1) moderate/severe sleep disturbance alone, 2) moderate/severe depression alone, 3) both moderate/severe sleep disturbance and depression, 4) no moderate/severe sleep disturbance or depression. RESULTS: Preoperative sleep disturbance and depression were associated with 12-month disability and pain (P<0.05). After accounting for depression, preoperative sleep disturbance remained associated with disability, while preoperative depression adjusting for sleep disturbance remained associated with all outcomes (P<0.05). Patients reporting both moderate/severe sleep disturbance and moderate/severe depression had 12.6 points higher disability and 1.5 points higher back and leg pain compared to patients without moderate/severe sleep disturbance or depression. CONCLUSION: The combination of sleep disturbance and depression impacts postoperative outcomes considerably. The high-risk group of patients with moderate/severe sleep disturbance and depression could benefit from targeted treatment strategies.

Physical Activity and Incident Obesity Across the Spectrum of Genetic Risk for Obesity.

Importance: Despite consistent public health recommendations, obesity rates in the US continue to increase. Physical activity recommendations do not account for individual genetic variability, increasing risk of obesity. Objective: To use activity, clinical, and genetic data from the All of Us Research Program (AoURP) to explore the association of genetic risk of higher body mass index (BMI) with the level of physical activity needed to reduce incident obesity. Design, Setting, and Participants: In this US population-based retrospective cohort study, participants were enrolled in the AoURP between May 1, 2018, and July 1, 2022. Enrollees in the AoURP who were of European ancestry, owned a personal activity tracking device, and did not have obesity up to 6 months into activity tracking were included in the analysis. Exposure: Physical activity expressed as daily step counts and a polygenic risk score (PRS) for BMI, calculated as weight in kilograms divided by height in meters squared. Main Outcome and Measures: Incident obesity (BMI ≥30). Results: A total of 3124 participants met inclusion criteria. Among 3051 participants with available data, 2216 (73%) were women, and the median age was 52.7 (IQR, 36.4-62.8) years. The total cohort of 3124 participants walked a median of 8326 (IQR, 6499-10 389) steps/d over a median of 5.4 (IQR, 3.4-7.0) years of personal activity tracking. The incidence of obesity over the study period increased from 13% (101 of 781) to 43% (335 of 781) in the lowest and highest PRS quartiles, respectively (P = 1.0 × 10-20). The BMI PRS demonstrated an 81% increase in obesity risk (P = 3.57 × 10-20) while mean step count demonstrated a 43% reduction (P = 5.30 × 10-12) when comparing the 75th and 25th percentiles, respectively. Individuals with a PRS in the 75th percentile would need to walk a mean of 2280 (95% CI, 1680-3310) more steps per day (11 020 total) than those at the 50th percentile to have a comparable risk of obesity. To have a comparable risk of obesity to individuals at the 25th percentile of PRS, those at the 75th percentile with a baseline BMI of 22 would need to walk an additional 3460 steps/d; with a baseline BMI of 24, an additional 4430 steps/d; with a baseline BMI of 26, an additional 5380 steps/d; and with a baseline BMI of 28, an additional 6350 steps/d. Conclusions and Relevance: In this cohort study, the association between daily step count and obesity risk across genetic background and baseline BMI were quantified. Population-based recommendations may underestimate physical activity needed to prevent obesity among those at high genetic risk.

Racial and Ethnic Differences in the Prevalence of Patients With Arthritis and Severe Joint Pain and Who Received Provider Counseling About Physical Activity for Arthritis Among Adults Aged 18 Years or Older-United States, 2019.

OBJECTIVE: This study examined the racial and ethnic differences in individuals with self-reported and doctor-diagnosed arthritis, severe joint pain, and provider counseling for physical activity among US adults with arthritis. METHODS: We estimated prevalence by race and ethnicity among 31,997 adults aged ≥18 years in the 2019 National Health Interview Survey. We used multiple logistic regression models to investigate associations between outcomes and race and ethnicity. RESULTS: Compared with non-Hispanic White adults (22.9%), we found a significantly higher age-adjusted prevalence of arthritis among American Indian/Alaska Native adults (30.3%). Among adults with arthritis, higher age-adjusted prevalence of severe joint pain among American Indian/Alaska Native (39.1%), non-Hispanic Black (36.4%), and Hispanic adults (35.7% vs 22.5% [White]) and higher provider counseling for physical activity among non-Hispanic Black adults (58.9% vs 52.1% [White]) were observed and could not be fully explained by differences in socioeconomic factors, body mass index, depression history, and comorbid conditions. Additional models also containing inability to pay medical bills and food insecurity did not explain racial and ethnic differences. CONCLUSION: Our findings highlight a need for multilevel interventions to mitigate social and environmental barriers to physical activity and eliminate disparities in individuals with arthritis and severe joint pain.

Impact of Racial/Ethnic Disparities on Patient-Reported Outcomes Following Cervical Spine Surgery: QOD Analysis.

STUDY DESIGN: Retrospective analysis of data from the cervical module of a National Spine Registry, the Quality Outcomes Database. OBJECTIVE: To examine the association of race and ethnicity with patient-reported outcome measures (PROMs) at one year after cervical spine surgery. SUMMARY OF BACKGROUND DATA: Evidence suggests that Black individuals are 39% to 44% more likely to have postoperative complications and a prolonged length of stay after cervical spine surgery compared with Whites. The long-term recovery assessed with PROMs after cervical spine surgery among Black, Hispanic, and other non-Hispanic groups ( i.e . Asian) remains unclear. MATERIALS AND METHODS: PROMs were used to assess disability (neck disability index) and neck/arm pain preoperatively and one-year postoperative. Primary outcomes were disability and pain, and not being satisfied from preoperative to 12 months after surgery. Multivariable logistic and proportional odds regression analyses were used to determine the association of racial/ethnic groups [Hispanic, non-Hispanic White (NHW), non-Hispanic Black (NHB), and non-Hispanic Asian (NHA)] with outcomes after covariate adjustment and to compute the odds of each racial/ethnic group achieving a minimal clinically important difference one-year postoperatively. RESULTS: On average, the sample of 14,429 participants had significant reductions in pain and disability, and 87% were satisfied at one-year follow-up. Hispanic and NHB patients had higher odds of not being satisfied (40% and 80%) and having worse pain outcomes (30%-70%) compared with NHW. NHB had 50% higher odds of worse disability scores compared with NHW. NHA reported similar disability and neck pain outcomes compared with NHW. CONCLUSIONS: Hispanic and NHB patients had worse patient-reported outcomes one year after cervical spine surgery compared with NHW individuals, even after adjusting for potential confounders, yet there was no difference in disability and neck pain outcomes reported for NHA patients. This study highlights the need to address inherent racial/ethnic disparities in recovery trajectories following cervical spine surgery.

Combining Wearable Technology and Telehealth Counseling for Rehabilitation After Lumbar Spine Surgery: Feasibility and Acceptability of a Physical Activity Intervention.

OBJECTIVE: The purpose of this study was to examine the feasibility and acceptability of a wearable device and telehealth counseling physical activity intervention early after lumbar spine surgery. METHODS: Sixteen patients were randomized to an 8-session physical activity intervention or to usual postoperative care after surgery. The intervention included a wearable device (ie, Fitbit) and telehealth counseling by a licensed physical therapist. The feasibility of study procedures was assessed through recruitment, randomization, retention, and participation rates. Acceptability was assessed through a satisfaction survey and median within-participant change in objective physical activity (steps per day and time spent in moderate-to-vigorous physical activity [MVPA]) and patient-reported outcomes. RESULTS: Of 64 participants who were eligible, recruitment and randomization rates were 41 and 62%, respectively. Retention for objective physical activity and patient-reported outcomes was 94 and 100%, respectively, at 6-month follow-up. Seven (88%) participants in the intervention group completed all telehealth sessions, and 6 (75%) met step goals over the 8 sessions. All participants in the intervention group found the wearable device and telehealth counseling to be helpful and reported it much or somewhat more important than other postoperative services. Median within-participant change for steps per day improved from baseline (preoperative) to 6 months after surgery for both the intervention (1070) and usual care (679) groups, while MVPA only improved for the intervention group (2.2. minutes per day). Improvements in back and leg pain and disability were noted for both groups. No adverse events were reported in the study. CONCLUSION: Combining wearable technology and telehealth counseling is a feasible approach to promote the physical activity during the early postoperative period after spine surgery. Future randomized controlled trials are needed to investigate the efficacy of leveraging wearables and telehealth during postoperative rehabilitation. IMPACT: This study has implications for the clinical dissemination of physical activity strategies in the rehabilitation setting.

Harnessing consumer wearable digital biomarkers for individualized recognition of postpartum depression using the All of Us Research Program dataset.

Postpartum depression (PPD), afflicting one in seven women, poses a major challenge in maternal health. Existing approaches to detect PPD heavily depend on in-person postpartum visits, leading to cases of the condition being overlooked and untreated. We explored the potential of consumer wearable-derived digital biomarkers for PPD recognition to address this gap. Our study demonstrated that intra-individual machine learning (ML) models developed using these digital biomarkers can discern between pre-pregnancy, pregnancy, postpartum without depression, and postpartum with depression time periods (i.e., PPD diagnosis). When evaluating variable importance, calories burned from the basal metabolic rate (calories BMR) emerged as the digital biomarker most predictive of PPD. To confirm the specificity of our method, we demonstrated that models developed in women without PPD could not accurately classify the PPD-equivalent phase. Prior depression history did not alter model efficacy for PPD recognition. Furthermore, the individualized models demonstrated superior performance compared to a conventional cohort-based model for the detection of PPD, underscoring the effectiveness of our individualized ML approach. This work establishes consumer wearables as a promising avenue for PPD identification. More importantly, it also emphasizes the utility of individualized ML model methodology, potentially transforming early disease detection strategies.

The All of Us Data and Research Center: Creating a Secure, Scalable, and Sustainable Ecosystem for Biomedical Research.

The All of Us Research Program's Data and Research Center (DRC) was established to help acquire, curate, and provide access to one of the world's largest and most diverse datasets for precision medicine research. Already, over 500,000 participants are enrolled in All of Us, 80% of whom are underrepresented in biomedical research, and data are being analyzed by a community of over 2,300 researchers. The DRC created this thriving data ecosystem by collaborating with engaged participants, innovative program partners, and empowered researchers. In this review, we first describe how the DRC is organized to meet the needs of this broad group of stakeholders. We then outline guiding principles, common challenges, and innovative approaches used to build the All of Us data ecosystem. Finally, we share lessons learned to help others navigate important decisions and trade-offs in building a modern biomedical data platform.

Quantifying physical activity needed to mitigate genetic risk for obesity.

Despite consistent public health recommendations, obesity rates continue to increase. Physical activity (e.g. daily steps) is a well-established modifier of body weight. Genetic background is an important, but typically uncaptured, contributor to obesity risk. Leveraging physical activity, clinical, and genetic data from the All of Us Research Program, we measured the impact of genetic risk of obesity on the level of physical activity needed to reduce incident obesity. For example, we show that an additional 3,310 steps per day (11,910 steps total) would be needed to mitigate a 25% higher than average genetic risk of obesity. We quantify the number of daily steps needed to mitigate obesity risk across the spectrum of genetic risk. This work quantifies the relationship between physical activity and genetic risk showing significant independent effects and provides a first step towards personalized activity recommendations that incorporate genetic information to reduce incident obesity risk.

Physical Activity Over the Lifecourse and Cardiovascular Disease.

Despite improvements in cardiovascular care in recent decades, cardiovascular disease (CVD) remains a leading cause of death worldwide. At its core, CVD is a largely preventable disease with diligent risk factor management and early detection. As highlighted in the American Heart Association's Life's Essential 8, physical activity plays a central role in CVD prevention at an individual and population level. Despite pervasive knowledge of the numerous cardiovascular and noncardiovascular health benefits of physical activity, physical activity has steadily decreased over time and unfavorable changes in physical activity occur throughout people's lives. Here, we use a lifecourse framework to examine the evidence reporting on the association of physical activity with CVD. From in utero to older adults, we review and discuss the evidence detailing how physical activity may prevent incident CVD and mitigate CVD-related morbidity and death across all life stages.

De-black-boxing health AI: demonstrating reproducible machine learning computable phenotypes using the N3C-RECOVER Long COVID model in the All of Us data repository.

Machine learning (ML)-driven computable phenotypes are among the most challenging to share and reproduce. Despite this difficulty, the urgent public health considerations around Long COVID make it especially important to ensure the rigor and reproducibility of Long COVID phenotyping algorithms such that they can be made available to a broad audience of researchers. As part of the NIH Researching COVID to Enhance Recovery (RECOVER) Initiative, researchers with the National COVID Cohort Collaborative (N3C) devised and trained an ML-based phenotype to identify patients highly probable to have Long COVID. Supported by RECOVER, N3C and NIH's All of Us study partnered to reproduce the output of N3C's trained model in the All of Us data enclave, demonstrating model extensibility in multiple environments. This case study in ML-based phenotype reuse illustrates how open-source software best practices and cross-site collaboration can de-black-box phenotyping algorithms, prevent unnecessary rework, and promote open science in informatics.

Sitting may increase risk for radiographic incidence and progression of knee osteoarthritis over 2 years: Data from a large cohort study.

OBJECTIVES: To examine the association of leisure-time sitting with radiographic incidence and progression of knee osteoarthritis (OA) over 2 years, and to determine whether worktime sitting modifies this association. METHODS: We included adults with or at high risk for knee OA who enroled in the Osteoarthritis Initiative (OAI). Participants reported leisure-time sitting (≤4 vs. >4 h/day) and worktime sitting (frequent vs. infrequent) at enrolment, and had bilateral knee radiographs at enrolment and 2 years later. Our outcome, radiographic knee OA incidence/progression (yes/no), was defined as any increase in Kellgren-Lawrence grade over 2 years. We examined the association of leisure-time sitting (≤4 vs. >4 h/day) with risk of radiographic knee OA incidence/progression using binary linear regression, adjusting for potential confounders. We stratified by worktime sitting (frequent vs. infrequent) and repeated our analysis. RESULTS: We included 4254 adults (mean age 61 years; 58% women; mean body mass index 29 kg/m2 ) who contributed a total of 8127 knees. Adults with >4 h/day of leisure-time sitting had 25% higher risk (adjusted risk ratio [RR] 1.25, 95% confidence interval [95% CI] 1.08-1.50) for radiographic knee OA incidence/progression compared with adults with ≤4 h/day of leisure-time sitting (referent group). Importantly, this association was intensified (RR 1.60, 95% CI 1.19-2.33) among adults with frequent worktime sitting, but was attenuated (RR 1.11, 95% CI 0.89-1.39) among adults with infrequent worktime sitting. CONCLUSIONS: Higher leisure-time sitting (>4 h/day) may be associated with greater risk for radiographic knee OA incidence/progression over 2 years. Furthermore, this association was intensified among adults who also reported frequent worktime sitting.

2022 American College of Rheumatology Guideline for Exercise, Rehabilitation, Diet, and Additional Integrative Interventions for Rheumatoid Arthritis.

OBJECTIVE: To develop initial American College of Rheumatology (ACR) guidelines on the use of exercise, rehabilitation, diet, and additional interventions in conjunction with disease-modifying antirheumatic drugs (DMARDs) as part of an integrative management approach for people with rheumatoid arthritis (RA). METHODS: An interprofessional guideline development group constructed clinically relevant Population, Intervention, Comparator, and Outcome (PICO) questions. A literature review team then completed a systematic literature review and applied the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach to rate the certainty of evidence. An interprofessional Voting Panel (n = 20 participants) that included 3 individuals with RA achieved consensus on the direction (for or against) and strength (strong or conditional) of recommendations. RESULTS: The Voting Panel achieved consensus on 28 recommendations for the use of integrative interventions in conjunction with DMARDs for the management of RA. Consistent engagement in exercise received a strong recommendation. Of 27 conditional recommendations, 4 pertained to exercise, 13 to rehabilitation, 3 to diet, and 7 to additional integrative interventions. These recommendations are specific to RA management, recognizing that other medical indications and general health benefits may exist for many of these interventions. CONCLUSION: This guideline provides initial ACR recommendations on integrative interventions for the management of RA to accompany DMARD treatments. The broad range of interventions included in these recommendations illustrates the importance of an interprofessional, team-based approach to RA management. The conditional nature of most recommendations requires clinicians to engage persons with RA in shared decision-making when applying these recommendations.

2022 American College of Rheumatology Guideline for Exercise, Rehabilitation, Diet, and Additional Integrative Interventions for Rheumatoid Arthritis.

OBJECTIVE: To develop initial American College of Rheumatology (ACR) guidelines on the use of exercise, rehabilitation, diet, and additional interventions in conjunction with disease-modifying antirheumatic drugs (DMARDs) as part of an integrative management approach for people with rheumatoid arthritis (RA). METHODS: An interprofessional guideline development group constructed clinically relevant Population, Intervention, Comparator, and Outcome (PICO) questions. A literature review team then completed a systematic literature review and applied the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach to rate the certainty of evidence. An interprofessional Voting Panel (n = 20 participants) that included 3 individuals with RA achieved consensus on the direction (for or against) and strength (strong or conditional) of recommendations. RESULTS: The Voting Panel achieved consensus on 28 recommendations for the use of integrative interventions in conjunction with DMARDs for the management of RA. Consistent engagement in exercise received a strong recommendation. Of 27 conditional recommendations, 4 pertained to exercise, 13 to rehabilitation, 3 to diet, and 7 to additional integrative interventions. These recommendations are specific to RA management, recognizing that other medical indications and general health benefits may exist for many of these interventions. CONCLUSION: This guideline provides initial ACR recommendations on integrative interventions for the management of RA to accompany DMARD treatments. The broad range of interventions included in these recommendations illustrates the importance of an interprofessional, team-based approach to RA management. The conditional nature of most recommendations requires clinicians to engage persons with RA in shared decision-making when applying these recommendations.

Wearable Devices in Cardiovascular Medicine.

Wearable devices, such as smartwatches and activity trackers, are commonly used by patients in their everyday lives to manage their health and well-being. These devices collect and analyze long-term continuous data on measures of behavioral or physiologic function, which may provide clinicians with a more comprehensive view of a patients' health compared with the traditional sporadic measures captured by office visits and hospitalizations. Wearable devices have a wide range of potential clinical applications ranging from arrhythmia screening of high-risk individuals to remote management of chronic conditions such as heart failure or peripheral artery disease. As the use of wearable devices continues to grow, we must adopt a multifaceted approach with collaboration among all key stakeholders to effectively and safely integrate these technologies into routine clinical practice. In this Review, we summarize the features of wearable devices and associated machine learning techniques. We describe key research studies that illustrate the role of wearable devices in the screening and management of cardiovascular conditions and identify directions for future research. Last, we highlight the challenges that are currently hindering the widespread use of wearable devices in cardiovascular medicine and provide short- and long-term solutions to promote increased use of wearable devices in clinical care.

Daily Step Counts Before and After the COVID-19 Pandemic Among All of Us Research Participants.

This cohort study of US adults examines changes in physical activity following the onset of the COVID-19 pandemic.