A Digitally Enabled Combined Lifestyle Intervention for Weight Loss: Pilot Study in a Dutch General Population Cohort

BACKGROUND

Overweight and obesity rates among the general population of the Netherlands keep increasing. Combined lifestyle interventions (CLIs) focused on physical activity, nutrition, sleep, and stress management can be effective in reducing weight and improving health behaviors. Currently available CLIs for weight loss (CLI-WLs) in the Netherlands consist of face-to-face and community-based sessions, which face scalability challenges. A digitally enabled CLI-WL with digital and human components may provide a solution for this challenge; however, the feasibility of such an intervention has not yet been assessed in the Netherlands.

OBJECTIVE

The aim of this study was two-fold: (1) to determine how weight and other secondary cardiometabolic outcomes (lipids and blood pressure) change over time in a Dutch population with overweight or obesity and cardiometabolic risk participating in a pilot digitally enabled CLI-WL and (2) to collect feedback from participants to guide the further development of future iterations of the intervention.

METHODS

Participants followed a 16-week digitally enabled lifestyle coaching program rooted in the Fogg Behavior Model, focused on nutrition, physical activity, and other health behaviors, from January 2020 to December 2021. Participants could access the digital app to register and track health behaviors, weight, and anthropometrics data at any time. We retrospectively analyzed changes in weight, blood pressure, and lipids for remeasured users. Surveys and semistructured interviews were conducted to assess critical positive and improvement points reported by participants and health care professionals.

RESULTS

Of the 420 participants evaluated at baseline, 53 participated in the pilot. Of these, 37 (70%) were classified as overweight and 16 (30%) had obesity. Mean weight loss of 4.2% occurred at a median of 10 months postintervention. The subpopulation with obesity (n=16) showed a 5.6% weight loss on average. Total cholesterol decreased by 10.2% and low-density lipoprotein cholesterol decreased by 12.9% on average. Systolic and diastolic blood pressure decreased by 3.5% and 7.5%, respectively. Participants identified the possibility of setting clear action plans to work toward and the multiple weekly touch points with coaches as two of the most positive and distinctive components of the digitally enabled intervention. Surveys and interviews demonstrated that the digital implementation of a CLI-WL is feasible and well-received by both participants and health care professionals.

CONCLUSIONS

Albeit preliminary, these findings suggest that a behavioral lifestyle program with a digital component can achieve greater weight loss than reported for currently available offline CLI-WLs. Thus, a digitally enabled CLI-WL is feasible and may be a scalable alternative to offline CLI-WL programs. Evidence from future studies in a Dutch population may help elucidate the mechanisms behind the effectiveness of a digitally enabled CLI-WL.

Deep embedded clustering generalisability and adaptation for integrating mixed datatypes: two critical care cohorts

We validated a Deep Embedded Clustering (DEC) model and its adaptation for integrating mixed datatypes (in this study, numerical and categorical variables). Deep Embedded Clustering (DEC) is a promising technique capable of managing extensive sets of variables and non-linear relationships. Nevertheless, DEC cannot adequately handle mixed datatypes. Therefore, we adapted DEC by replacing the autoencoder with an X-shaped variational autoencoder (XVAE) and optimising hyperparameters for cluster stability. We call this model "X-DEC". We compared DEC and X-DEC by reproducing a previous study that used DEC to identify clusters in a population of intensive care patients. We assessed internal validity based on cluster stability on the development dataset. Since generalisability of clustering models has insufficiently been validated on external populations, we assessed external validity by investigating cluster generalisability onto an external validation dataset. We concluded that both DEC and X-DEC resulted in clinically recognisable and generalisable clusters, but X-DEC produced much more stable clusters.

Effective questionnaire-based prediction models for type 2 diabetes across several ethnicities: a model development and validation study

Background

Type 2 diabetes disproportionately affects individuals of non-White ethnicity through a complex interaction of multiple factors. Therefore, early disease detection and prediction are essential and require tools that can be deployed on a large scale. We aimed to tackle this problem by developing questionnaire-based prediction models for type 2 diabetes prevalence and incidence for multiple ethnicities.

Methods

In this proof of principle analysis, logistic regression models to predict type 2 diabetes prevalence and incidence, using questionnaire-only variables reflecting health state and lifestyle, were trained on the White population of the UK Biobank (n = 472,696 total, aged 37-73 years, data collected 2006-2010) and validated in five other ethnicities (n = 29,811 total) and externally in Lifelines (n = 168,205 total, aged 0-93 years, collected between 2006 and 2013). In total, 631,748 individuals were included for prevalence prediction and 67,083 individuals for the eight-year incidence prediction. Type 2 diabetes prevalence in the UK Biobank ranged between 6% in the White population to 23.3% in the South Asian population, while in Lifelines, the prevalence was 1.9%. Predictive accuracy was evaluated using the area under the receiver operating characteristic curve (AUC), and a detailed sensitivity analysis was conducted to assess potential clinical utility. We compared the questionnaire-only models to models containing physical measurements and biomarkers as well as to clinical non-laboratory type 2 diabetes risk tools and conducted a reclassification analysis.

Findings

Our algorithms accurately predicted type 2 diabetes prevalence (AUC = 0.901) and eight-year incidence (AUC = 0.873) in the White UK Biobank population. Both models replicated well in the Lifelines external validation, with AUCs of 0.917 and 0.817 for prevalence and incidence, respectively. Both models performed consistently well across different ethnicities, with AUCs of 0.855-0.894 for prevalence and 0.819-0.883 for incidence. These models generally outperformed two clinically validated non-laboratory tools and correctly reclassified >3,000 additional cases. Model performance improved with the addition of blood biomarkers but not with the addition of physical measurements.

Interpretation

Our findings suggest that easy-to-implement, questionnaire-based models could be used to predict prevalent and incident type 2 diabetes with high accuracy across several ethnicities, providing a highly scalable solution for population-wide risk stratification. Future work should determine the effectiveness of these models in identifying undiagnosed type 2 diabetes, validated in cohorts of different populations and ethnic representation.

Funding

University Medical Center Groningen.

Comparison of Machine Learning Models Including Preoperative, Intraoperative, and Postoperative Data and Mortality After Cardiac Surgery

IMPORTANCE

A variety of perioperative risk factors are associated with postoperative mortality risk. However, the relative contribution of routinely collected intraoperative clinical parameters to short-term and long-term mortality remains understudied.

OBJECTIVE

To examine the performance of multiple machine learning models with data from different perioperative periods to predict 30-day, 1-year, and 5-year mortality and investigate factors that contribute to these predictions.

DESIGN, SETTING, AND PARTICIPANTS

In this prognostic study using prospectively collected data, risk prediction models were developed for short-term and long-term mortality after cardiac surgery. Included participants were adult patients undergoing a first-time valve operation, coronary artery bypass grafting, or a combination of both between 1997 and 2017 in a single center, the University Medical Centre Groningen in the Netherlands. Mortality data were obtained in November 2017. Data analysis took place between February 2020 and August 2021.

EXPOSURE

Cardiac surgery.

MAIN OUTCOMES AND MEASURES

Postoperative mortality rates at 30 days, 1 year, and 5 years were the primary outcomes. The area under the receiver operating characteristic curve (AUROC) was used to assess discrimination. The contribution of all preoperative, intraoperative hemodynamic and temperature, and postoperative factors to mortality was investigated using Shapley additive explanations (SHAP) values.

RESULTS

Data from 9415 patients who underwent cardiac surgery (median [IQR] age, 68 [60-74] years; 2554 [27.1%] women) were included. Overall mortality rates at 30 days, 1 year, and 5 years were 268 patients (2.8%), 420 patients (4.5%), and 612 patients (6.5%), respectively. Models including preoperative, intraoperative, and postoperative data achieved AUROC values of 0.82 (95% CI, 0.78-0.86), 0.81 (95% CI, 0.77-0.85), and 0.80 (95% CI, 0.75-0.84) for 30-day, 1-year, and 5-year mortality, respectively. Models including only postoperative data performed similarly (30 days: 0.78 [95% CI, 0.73-0.82]; 1 year: 0.79 [95% CI, 0.74-0.83]; 5 years: 0.77 [95% CI, 0.73-0.82]). However, models based on all perioperative data provided less clinically usable predictions, with lower detection rates; for example, postoperative models identified a high-risk group with a 2.8-fold increase in risk for 5-year mortality (4.1 [95% CI, 3.3-5.1]) vs an increase of 11.3 (95% CI, 6.8-18.7) for the high-risk group identified by the full perioperative model. Postoperative markers associated with metabolic dysfunction and decreased kidney function were the main factors contributing to mortality risk.

CONCLUSIONS AND RELEVANCE

This study found that the addition of continuous intraoperative hemodynamic and temperature data to postoperative data was not associated with improved machine learning-based identification of patients at increased risk of short-term and long-term mortality after cardiac operations.

Effect of a Digitally-Enabled, Preventive Health Program on Blood Pressure in an Adult, Dutch General Population Cohort: An Observational Pilot Study

Worldwide, it is estimated that at least one in four adults suffers from hypertension, and this number is expected to increase as populations grow and age. Blood pressure (BP) possesses substantial heritability, but is also heavily modulated by lifestyle factors. As such, digital, lifestyle-based interventions are a promising alternative to standard care for hypertension prevention and management. In this study, we assessed the prevalence of elevated and high BP in a Dutch general population cohort undergoing a health screening, and observed the effects of a subsequent self-initiated, digitally-enabled lifestyle program on BP regulation. Baseline data were available for 348 participants, of which 56 had partaken in a BP-focused lifestyle program and got remeasured 10 months after the intervention. Participants with elevated SBP and DBP at baseline showed a mean decrease of 7.2 mmHg and 5.4 mmHg, respectively. Additionally, 70% and 72.5% of participants showed an improvement in systolic and diastolic BP at remeasurement. These improvements in BP are superior to those seen in other recent studies. The long-term sustainability and the efficacy of this and similar digital lifestyle interventions will need to be established in additional, larger studies.

Changes in blood lipid levels after a digitally-enabled, cardiometabolic preventive health program: a pre-post study in an adult, Dutch general population cohort (Preprint)

Background

Despite widespread education, many individuals fail to follow basic health behaviors such as consuming a healthy diet and exercising. Positive changes in lifestyle habits are associated with improvements in multiple cardiometabolic health risk factors, including lipid levels. Digital lifestyle interventions have been suggested as a viable complement or potential alternative to conventional health behavior change strategies. However, the benefit of digital preventive interventions for lipid levels in a preventive health context remains unclear.

Objective

This observational study aimed to determine how the levels of lipids, namely total cholesterol, high-density lipoprotein (HDL) cholesterol, low-density lipoprotein (LDL) cholesterol, non-HDL cholesterol, and triglycerides, changed over time in a Dutch general population cohort undergoing a digital preventive health program. Moreover, we looked to establish associations between lifestyle factors at baseline and lipid levels.

Methods

We included 348 adults from the Dutch general population who underwent a digitally enabled preventive health program at Ancora Health between January 2020 and October 2021. Upon enrollment, participants underwent a baseline assessment involving a comprehensive lifestyle questionnaire, a blood biochemistry panel, physical measurements, and cardiopulmonary fitness measurements. Thereafter, users underwent a lifestyle coaching program and could access the digital application to register and track health behaviors, weight, and anthropometric data at any time. Lipid levels were categorized as normal, elevated, high, and clinical dyslipidemia according to accepted international standards. If at least one lipid marker was high or HDL was low, participants received specific coaching and advice for cardiometabolic health. We retrospectively analyzed the mean and percentage changes in lipid markers in users who were remeasured after a cardiometabolic health–focused intervention, and studied the association between baseline user lifestyle characteristics and having normal lipid levels.

Results

In our cohort, 199 (57.2%) participants had dyslipidemia at baseline, of which 104 participants were advised to follow a cardiometabolic health–focused intervention. Eating more amounts of favorable food groups and being more active were associated with normal lipid profiles. Among the participants who underwent remeasurement 9 months after intervention completion, 57% (17/30), 61% (19/31), 56% (15/27), 82% (9/11), and 100% (8/8) showed improvements at remeasurement for total, LDL, HDL, and non-HDL cholesterol, and triglycerides, respectively. Moreover, between 35.3% and 77.8% showed a return to normal levels. In those with high lipid levels at baseline, total cholesterol decreased by 0.5 mmol/L (7.5%), LDL cholesterol decreased by 0.39 mmol/L (10.0%), non-HDL cholesterol decreased by 0.44 mmol/L (8.3%), triglycerides decreased by 0.97 mmol/L (32.0%), and HDL increased by 0.17 mmol/L (15.6%), after the intervention.

Conclusions

A cardiometabolic screening program in a general population cohort identified a significant portion of individuals with subclinical and clinical lipid levels. Individuals who, after screening, actively engaged in a cardiometabolic health–focused lifestyle program improved their lipid levels.

Development and Validation of Decision Rules Models to Stratify Coronary Artery Disease, Diabetes, and Hypertension Risk in Preventive Care: Cohort Study of Returning UK Biobank Participants

Many predictive models exist that predict risk of common cardiometabolic conditions. However, a vast majority of these models do not include genetic risk scores and do not distinguish between clinical risk requiring medical or pharmacological interventions and pre-clinical risk, where lifestyle interventions could be first-choice therapy. In this study, we developed, validated, and compared the performance of three decision rule algorithms including biomarkers, physical measurements, and genetic risk scores for incident coronary artery disease (CAD), diabetes (T2D), and hypertension against commonly used clinical risk scores in 60,782 UK Biobank participants. The rules models were tested for an association with incident CAD, T2D, and hypertension, and hazard ratios (with 95% confidence interval) were calculated from survival models. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC), and Net Reclassification Index (NRI). The higher risk group in the decision rules model had a 40-, 40.9-, and 21.6-fold increased risk of CAD, T2D, and hypertension, respectively (p < 0.001 for all). Risk increased significantly between the three strata for all three conditions (p < 0.05). Based on genetic risk alone, we identified not only a high-risk group, but also a group at elevated risk for all health conditions. These decision rule models comprising blood biomarkers, physical measurements, and polygenic risk scores moderately improve commonly used clinical risk scores at identifying individuals likely to benefit from lifestyle intervention for three of the most common lifestyle-related chronic health conditions. Their utility as part of digital data or digital therapeutics platforms to support the implementation of lifestyle interventions in preventive and primary care should be further validated.

Identifying and characterizing high-risk clusters in a heterogeneous ICU population with deep embedded clustering

Critically ill patients constitute a highly heterogeneous population, with seemingly distinct patients having similar outcomes, and patients with the same admission diagnosis having opposite clinical trajectories. We aimed to develop a machine learning methodology that identifies and provides better characterization of patient clusters at high risk of mortality and kidney injury. We analysed prospectively collected data including co-morbidities, clinical examination, and laboratory parameters from a minimally-selected population of 743 patients admitted to the ICU of a Dutch hospital between 2015 and 2017. We compared four clustering methodologies and trained a classifier to predict and validate cluster membership. The contribution of different variables to the predicted cluster membership was assessed using SHapley Additive exPlanations values. We found that deep embedded clustering yielded better results compared to the traditional clustering algorithms. The best cluster configuration was achieved for 6 clusters. All clusters were clinically recognizable, and differed in in-ICU, 30-day, and 90-day mortality, as well as incidence of acute kidney injury. We identified two high mortality risk clusters with at least 60%, 40%, and 30% increased. ICU, 30-day and 90-day mortality, and a low risk cluster with 25–56% lower mortality risk. This machine learning methodology combining deep embedded clustering and variable importance analysis, which we made publicly available, is a possible solution to challenges previously encountered by clustering analyses in heterogeneous patient populations and may help improve the characterization of risk groups in critical care.

Mortality prediction models in the adult critically ill: A scoping review

BACKGROUND

Mortality prediction models are applied in the intensive care unit (ICU) to stratify patients into different risk categories and to facilitate benchmarking. To ensure that the correct prediction models are applied for these purposes, the best performing models must be identified. As a first step, we aimed to establish a systematic review of mortality prediction models in critically ill patients.

METHODS

Mortality prediction models were searched in four databases using the following criteria: developed for use in adult ICU patients in high-income countries, with mortality as primary or secondary outcome. Characteristics and performance measures of the models were summarized. Performance was presented in terms of discrimination, calibration and overall performance measures presented in the original publication.

RESULTS

In total, 43 mortality prediction models were included in the final analysis. In all, 15 models were only internally validated (35%), 13 externally (30%) and 10 (23%) were both internally and externally validated by the original researchers. Discrimination was assessed in 42 models (98%). Commonly used calibration measures were the Hosmer-Lemeshow test (60%) and the calibration plot (28%). Calibration was not assessed in 11 models (26%). Overall performance was assessed in the Brier score (19%) and the Nagelkerke's R² (4.7%).

CONCLUSIONS

Mortality prediction models have varying methodology, and validation and performance of individual models differ. External validation by the original researchers is often lacking and head-to-head comparisons are urgently needed to identify the best performing mortality prediction models for guiding clinical care and research in different settings and populations.

A Bayesian Network Analysis of the Diagnostic Process and Its Accuracy to Determine How Clinicians Estimate Cardiac Function in Critically Ill Patients: Prospective Observational Cohort Study

BACKGROUND

Hemodynamic assessment of critically ill patients is a challenging endeavor, and advanced monitoring techniques are often required to guide treatment choices. Given the technical complexity and occasional unavailability of these techniques, estimation of cardiac function based on clinical examination is valuable for critical care physicians to diagnose circulatory shock. Yet, the lack of knowledge on how to best conduct and teach the clinical examination to estimate cardiac function has reduced its accuracy to almost that of "flipping a coin."

OBJECTIVE

The aim of this study was to investigate the decision-making process underlying estimates of cardiac function of patients acutely admitted to the intensive care unit (ICU) based on current standardized clinical examination using Bayesian methods.

METHODS

Patient data were collected as part of the Simple Intensive Care Studies-I (SICS-I) prospective cohort study. All adult patients consecutively admitted to the ICU with an expected stay longer than 24 hours were included, for whom clinical examination was conducted and cardiac function was estimated. Using these data, first, the probabilistic dependencies between the examiners' estimates and the set of clinically measured variables upon which these rely were analyzed using a Bayesian network. Second, the accuracy of cardiac function estimates was assessed by comparison to the cardiac index values measured by critical care ultrasonography.

RESULTS

A total of 1075 patients were included, of which 783 patients had validated cardiac index measurements. A Bayesian network analysis identified two clinical variables upon which cardiac function estimate is conditionally dependent, namely, noradrenaline administration and presence of delayed capillary refill time or mottling. When the patient received noradrenaline, the probability of cardiac function being estimated as reasonable or good P(E_R,G) was lower, irrespective of whether the patient was mechanically ventilated (P[E_R,G|ventilation, noradrenaline]=0.63, P[E_R,G|ventilation, no noradrenaline]=0.91, P[E_R,G|no ventilation, noradrenaline]=0.67, P[E_R,G|no ventilation, no noradrenaline]=0.93). The same trend was found for capillary refill time or mottling. Sensitivity of estimating a low cardiac index was 26% and 39% and specificity was 83% and 74% for students and physicians, respectively. Positive and negative likelihood ratios were 1.53 (95% CI 1.19-1.97) and 0.87 (95% CI 0.80-0.95), respectively, overall.

CONCLUSIONS

The conditional dependencies between clinical variables and the cardiac function estimates resulted in a network consistent with known physiological relations. Conditional probability queries allow for multiple clinical scenarios to be recreated, which provide insight into the possible thought process underlying the examiners' cardiac function estimates. This information can help develop interactive digital training tools for students and physicians and contribute toward the goal of further improving the diagnostic accuracy of clinical examination in ICU patients.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02912624; https://clinicaltrials.gov/ct2/show/NCT02912624.

How the Uruguayan Judiciary Shapes Access to High-Priced Medicines: A Critique through the Right to Health Lens

Uruguay has witnessed an ever-increasing number of domestic court claims for high-priced medicines despite its comprehensive universal coverage of pharmaceuticals. In response to the current national debate and development of domestic legislation concerning high-priced medicines, we review whether Uruguayan courts adequately interpret the state's core obligations to provide essential medicines and ensure non-discriminatory access in line with the right to health in the International Covenant on Economic, Social and Cultural Rights. Using a sample of 42 amparo claims for the reimbursement of medicines in 2015, we found that the circuits of appeal fail to offer predictable legal argumentation, including for nearly identical cases. Moreover, the judiciary does not provide an interpretation of state obligations that is consistently aligned with the right to health in the International Covenant on Economic, Social and Cultural Rights. These findings illustrate that medicines litigation in Uruguay offers relief for some individual claims but may exacerbate systemic inequalities by failing to address the structural problems behind high medicines prices. We recommend that the judiciary adopt a consistent standard for assessing state action to realize the right to health within its available resources. Moreover, the legislature should address the need for medicines price control and offer a harmonized interpretation of the right to health. These transformations can increase the transparency and predictability of Uruguay's health and legal systems for patients and communities.