Small datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases sample size and is seen as a form of regularization that increases the diversity of small datasets, leading them to perform better on unseen data. We found that augmentation improves prognostic performance for datasets that: have fewer observations, with smaller baseline AUC, have higher cardinality categorical variables, and have more balanced outcome variables. No specific generative model consistently outperformed the others. We developed a decision support model that can be used to inform analysts if augmentation would be useful. For seven small application datasets, augmenting the existing data results in an increase in AUC between 4.31

BackgroundElectronic health records are a valuable source of patient information that must be properly deidentified before being shared with researchers. This process requires expertise and time. In addition, synthetic data have considerably reduced the restrictions on the use and sharing of real data, allowing researchers to access it more rapidly with far fewer privacy constraints. Therefore, there has been a growing interest in establishing a method to generate synthetic data that protects patients’ privacy while properly reflecting the data. ObjectiveThis study aims to develop and validate a model that generates valuable synthetic longitudinal health data while protecting the privacy of the patients whose data are collected. MethodsWe investigated the best model for generating synthetic health data, with a focus on longitudinal observations. We developed a generative model that relies on the generalized canonical polyadic (GCP) tensor decomposition. This model also involves sampling from a latent factor matrix of GCP decomposition, which contains patient factors, using sequential decision trees, copula, and Hamiltonian Monte Carlo methods. We applied the proposed model to samples from the MIMIC-III (version 1.4) data set. Numerous analyses and experiments were conducted with different data structures and scenarios. We assessed the similarity between our synthetic data and the real data by conducting utility assessments. These assessments evaluate the structure and general patterns present in the data, such as dependency structure, descriptive statistics, and marginal distributions. Regarding privacy disclosure, our model preserves privacy by preventing the direct sharing of patient information and eliminating the one-to-one link between the observed and model tensor records. This was achieved by simulating and modeling a latent factor matrix of GCP decomposition associated with patients. ResultsThe findings show that our model is a promising method for generating synthetic longitudinal health data that is similar enough to real data. It can preserve the utility and privacy of the original data while also handling various data structures and scenarios. In certain experiments, all simulation methods used in the model produced the same high level of performance. Our model is also capable of addressing the challenge of sampling patients from electronic health records. This means that we can simulate a variety of patients in the synthetic data set, which may differ in number from the patients in the original data. ConclusionsWe have presented a generative model for producing synthetic longitudinal health data. The model is formulated by applying the GCP tensor decomposition. We have provided 3 approaches for the synthesis and simulation of a latent factor matrix following the process of factorization. In brief, we have reduced the challenge of synthesizing massive longitudinal health data to synthesizing a nonlongitudinal and significantly smaller data set.

Background: Electronic health records are a valuable source of patient information that must be properly deidentified beforebeing shared with researchers. This process requires expertise and time. In addition, synthetic data have considerably reducedthe restrictions on the use and sharing of real data, allowing researchers to access it more rapidly with far fewer privacy constraints.Therefore, there has been a growing interest in establishing a method to generate synthetic data that protects patients'privacywhile properly reflecting the data.Objective: This study aims to develop and validate a model that generates valuable synthetic longitudinal health data whileprotecting the privacy of the patients whose data are collected.Methods: We investigated the best model for generating synthetic health data, with a focus on longitudinal observations. Wedeveloped a generative model that relies on the generalized canonical polyadic (GCP) tensor decomposition. This model alsoinvolves sampling from a latent factor matrix of GCP decomposition, which contains patient factors, using sequential decisiontrees, copula, and Hamiltonian Monte Carlo methods. We applied the proposed model to samples from the MIMIC-III (version1.4) data set. Numerous analyses and experiments were conducted with different data structures and scenarios. We assessed thesimilarity between our synthetic data and the real data by conducting utility assessments. These assessments evaluate the structureand general patterns present in the data, such as dependency structure, descriptive statistics, and marginal distributions. Regardingprivacy disclosure, our model preserves privacy by preventing the direct sharing of patient information and eliminating theone-to-one link between the observed and model tensor records. This was achieved by simulating and modeling a latent factormatrix of GCP decomposition associated with patients.Results: The findings show that our model is a promising method for generating synthetic longitudinal health data that is similarenough to real data. It can preserve the utility and privacy of the original data while also handling various data structures andscenarios. In certain experiments, all simulation methods used in the model produced the same high level of performance. Ourmodel is also capable of addressing the challenge of sampling patients from electronic health records. This means that we cansimulate a variety of patients in the synthetic data set, which may differ in number from the patients in the original data.Conclusions: We have presented a generative model for producing synthetic longitudinal health data. The model is formulatedby applying the GCP tensor decomposition. We have provided 3 approaches for the synthesis and simulation of a latent factormatrix following the process of factorization. In brief, we have reduced the challenge of synthesizing massive longitudinal healthdata to synthesizing a nonlongitudinal and significantly smaller data set

A status update on applying generative AI to synthetic data generation.

Sharing health data for research purposes across international jurisdictions has been a challenge due to privacy concerns. Two privacy enhancing technologies that can enable such sharing are synthetic data generation (SDG) and federated analysis, but their relative strengths and weaknesses have not been evaluated thus far. In this study we compared SDG with federated analysis to enable such international comparative studies. The objective of the analysis was to assess country-level differences in the role of sex on cardiovascular health (CVH) using a pooled dataset of Canadian and Austrian individuals. The Canadian data was synthesized and sent to the Austrian team for analysis. The utility of the pooled (synthetic Canadian + real Austrian) dataset was evaluated by comparing the regression results from the two approaches. The privacy of the Canadian synthetic data was assessed using a membership disclosure test which showed an F1 score of 0.001, indicating low privacy risk. The outcome variable of interest was CVH, calculated through a modified CANHEART index. The main and interaction effect parameter estimates of the federated and pooled analyses were consistent and directionally the same. It took approximately one month to set up the synthetic data generation platform and generate the synthetic data, whereas it took over 1.5 years to set up the federated analysis system. Synthetic data generation can be an efficient and effective tool for enabling multi-jurisdictional studies while addressing privacy concerns.

INTRODUCTION:The burden of metabolic syndrome (MetS) and its components has been increasing mainly amongst male individuals. Nevertheless, clinical outcomes related to MetS (i.e., cardiovascular diseases), are worse among female individuals. Whether these sex differences in the components and sequalae of MetS are influenced by gender (i.e., psycho-socio-cultural factors)) is a matter of debate.  Therefore, the purpose of this study was to determine the association between gender-related factors and the development of MetS, and to assess if the magnitude of the associations vary by sex. METHOD:Data from the Colaus/PsyColaus study, a prospective population-based cohort of 6,734 middle-aged participants in Lausanne (Switzerland) (2003-2006) were used. The primary endpoint was the development of MetS as defined by the Adult Treatment Panel III of the National Cholesterol Education Program. Multivariable models were estimated using logistic regression to assess the association between gender-related factors and the development of MetS. Two-way interactions between sex,  age and gender-related factors were also tested. RESULTS:Among 5,195 participants without MetS (mean age=51.3 ± 10.6, 56.1 % females), 27.9 % developed MetS during a mean follow-up of 10.9 years. Female sex (OR:0.48, 95 %CI:0.41-0.55) was associated with decreased risk of developing MetS. Conversely, older age, educational attainment less than university, and low income were associated with an increased risk of developing MetS. Statistically significant interaction between sex and strata of age, education, income, smoking, and employment were identified showing that the reduced risk of MetS in female individuals was attenuated in the lowest education, income, and advanced age strata. However, females who smoke and reported being employed demonstrated a decreased risk of MetS compared to males. Conversely smoking and unemployment were significant risk factors for MetS development among male adults. CONCLUSIONS:Gender-related factors such as income level and educational attainment play a greater role in the development of MetS in female than individuals. These factors represent novel modifiable targets for implementation of sex- and gender-specific strategies to achieve health equity for all people.

Aims The aim of this study was to elucidate whether sex and gender factors influence access to health care and/or are associated with cardiovascular (CV) outcomes of individuals with diabetes mellitus (DM) across different countries. Methods Using data from the Canadian Community Health Survey (8.4% of respondent reporting DM) and the European Health Interview Survey (7.3% of respondents reporting DM), were analyzed. Self-reported sex and a composite measure of socio-cultural gender was constructed (range: 0–1; higher score represent participants who reported more characteristics traditionally ascribed to women). For the purposes of analyses the Gender Inequality Index (GII) was used as a country level measure of institutionalized gender. Results Canadian females with DM were more likely to undergo HbA1c monitoring compared to males (OR = 1.26, 95% CI: 1.01–1.58), while conversely in the European cohort females with DM were less likely to have their blood sugar measured compared to males (OR = 0.88, 95% CI: 0.79–0.99). A higher gender score in both cohorts was associated with less frequent diabetes monitoring. Additionally, independent of sex, higher gender scores were associated with higher prevalence of self-reported heart disease, stroke, and hospitalization in all countries albeit European countries with medium-high GII, conferred a higher risk of all outcomes and hospitalization rates than low GII countries. Conclusion Regardless of sex, individuals with DM who reported characteristics typically ascribed to women and those living in countries with greater gender inequity for women exhibited poorer diabetes care and greater risk of CV outcomes and hospitalizations.

e24126 Background: Vasomotor symptoms (VMS), such as hot flashes, are a common reason for early discontinuation of endocrine therapy for patients (pts) with breast cancer (BC). The optimal intervention for VMS remains unknown. Using a novel symptom change analysis and regression trees, we examined whether clinically important change in VMS severity depends on baseline symptomatology. Methods: In this prospective study, pts with BC experiencing VMS chose either a lifestyle (LS), or non-LS (i.e. complementary and alternative therapies [CAM], prescription medications [PM], or endocrine therapy modification [ETM]) intervention. The primary outcome was change in symptom severity using the 10-point Hot Flush Rating Scale (HFRS). Patients declining interventions were included as controls. At the end of the 6-week intervention, participants rated the effectiveness of their chosen intervention on a five-point Likert scale. A logistic sigmoid function and Bayesian optimization were used to weight the change in VMS score based on baseline VMS severity. A regression tree was trained to predict which intervention resulted in the greatest improvement in VMS at 6 weeks. Results: 100 baseline and follow-up questionnaires from 85 pts were included in an intention to treat analysis. The median baseline HFRS was 5.0 (IQR 3.33 ,7.00). Selected interventions included LS (27%), CAM (25%), PM (11%) and ETM (8%), with 29% declining interventions. After removal of missing data, 59 individuals provided responses for both the HFRS score and the effectiveness score. Higher baseline HFRS scores had greater impact on symptom change scores. The largest difference in VMS improvement was noted between the non-LS (median symptom change –0.82, IQR –2.00, –0.01) and LS/control groups (median symptom change – 0.38, IQR –1.46, 0.00) (Table 1). Of non-LS interventions, CAM had the greatest improvement in VMS severity. Pre-menopausal individuals who pursued LS interventions had the least improvement in VMS severity. Conclusions: Interventions for VMS were most impactful among pts with greater baseline symptoms. While LS interventions were the most commonly selected intervention, the resulting improvement in symptoms at 6 weeks was negligible, and alternative strategies should be encouraged. Future studies integrating pt preferences and accounting for baseline symptom severity are needed. [Table: see text]

Introduction: With many anonymization algorithms developed for structured medical health data (SMHD) in the last decade, our systematic review provides a comprehensive bird’s eye view of algorithms for SMHD anonymization.Methods: This systematic review was conducted according to the recommendations in the Cochrane Handbook for Reviews of Interventions and reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Eligible articles from the PubMed, ACM digital library, Medline, IEEE, Embase, Web of Science Collection, Scopus, ProQuest Dissertation, and Theses Global databases were identified through systematic searches. The following parameters were extracted from the eligible studies: author, year of publication, sample size, and relevant algorithms and/or software applied to anonymize SMHD, along with the summary of outcomes.Results: Among 1,804 initial hits, the present study considered 63 records including research articles, reviews, and books. Seventy five evaluated the anonymization of demographic data, 18 assessed diagnosis codes, and 3 assessed genomic data. One of the most common approaches was k-anonymity, which was utilized mainly for demographic data, often in combination with another algorithm; e.g., l-diversity. No approaches have yet been developed for protection against membership disclosure attacks on diagnosis codes.Conclusion: This study reviewed and categorized different anonymization approaches for MHD according to the anonymized data types (demographics, diagnosis codes, and genomic data). Further research is needed to develop more efficient algorithms for the anonymization of diagnosis codes and genomic data. The risk of reidentification can be minimized with adequate application of the addressed anonymization approaches.Systematic Review Registration: [http://www.crd.york.ac.uk/prospero], identifier [CRD42021228200].

Cardiovascular diseases (CVD) are the leading cause of mortality and morbidity worldwide. Whether sex is associated with outcomes in patients with CVD differently across countries remains unknown. Assessing the interaction between sex and psycho-socio-cultural factors (gender) and country requires merging of country specific databases. Privacy concerns are barriers to data access and sharing. Therefore, we assessed the feasibility of pooling data from Canadian and Austrian populations to assess country-level differences in the role of sex, gender in cardiovascular health (CVH) using federated analysis and data synthesis. The datasets used were from the Canadian Community Health Survey (CCHS), and the Austrian Health Interview Survey (ATHIS) in 2014. Only CCHS dataset was synthesized using sequential classification and regression trees. The privacy of the CCHS synthetic data was assessed using a membership disclosure test and F1 score. The low value means that the dataset can be deemed as having low privacy risks. Once it was deemed to be non-personal information, the synthetic dataset was sent to the Austrian team for pooling and analysis. The analysis was performed on the pooled source ATHIS data and the synthetic CCHS data. The outcome variable was CVH, calculated through a modified CANHEART index in both countries. The utility of the pooled dataset was evaluated by comparing the regression model with the model constructed from federated analysis using DataSHIELD. A significant time elapsed to set-up the necessary servers in multiple locations with the requisite security protocols for the federated analysis. For assessing Privacy Risks of Synthetic Data, the largest membership disclosure F1 score across different attack datasets was 0.001, indicating low privacy risk. A comparison of the marginal distributions between males and females showed consistent results in the federated and pooled analyses of synthetic data. In the multivariate analysis of the main effects, the parameter estimates of the federated and pooled analysis were directionally the same as for the univariate analysis. In the multivariate analyses considering the country interactions to determine whether country moderates the relationship between the other variables and CVH, the impact of several factors differed between countries (Table 1). The result of this secondary analysis of population-based datasets revealed that synthetic data generation methods can be safely and reproducibly used to pool datasets across countries for international studies. There were significant country-level differences in the role of sex, and gender in CVH which demonstrates the importance of pooling datasets from different jurisdictions.View Large Image Figure ViewerDownload Hi-res image Download (PPT)

Despite the frequency of vasomotor symptoms (VMS) in patients with early breast cancer (EBC), their optimal management remains unknown. A patient survey was performed to determine perspectives on this important clinical challenge. Patients with EBC experiencing VMS participated in an anonymous survey. Patients reported on the frequency and severity of VMS using the validated Hot Flush Rating Scale (HFRS) and ranked their most bothersome symptoms. Respondents were also asked to determine endpoints that defined effective treatment of VMS and report on the effectiveness of previously tried interventions. Responses were received from 373 patients, median age 56 years (range 23–83), who experienced an average of 5.0 hot flashes per day (SD 6.57). Patients reported the most bothersome symptoms to be feeling hot/sweating (155/316, 49%) and sleeping difficulties (86/316, 27%). Fifty-five percent (201/365) of patients would consider a treatment to be effective if it reduced night-time awakenings. While 68% of respondents were interested in trying interventions from their healthcare team to manage VMS, only 18% actually did so. Of the 137 patients who had tried an intervention for VMS, pharmacological treatments, exercise, and relaxation strategies were more likely to be effective, while therapies such as melatonin and black cohosh were deemed less effective. VMS are a common and bothersome problem for EBC patients, with a minority receiving interventions to manage these symptoms. Further research is needed to identify patient-centered strategies for managing these distressing symptoms.

This article provides a state-of-the-art summary of location privacy issues and geoprivacy-preserving methods in public health interventions and health research involving disaggregate geographic data about individuals. Synthetic data generation (from real data using machine learning) is discussed in detail as a promising privacy-preserving approach. To fully achieve their goals, privacy-preserving methods should form part of a wider comprehensive socio-technical framework for the appropriate disclosure, use and dissemination of data containing personal identifiable information. Select highlights are also presented from a related December 2021 AAG (American Association of Geographers) webinar that explored ethical and other issues surrounding the use of geospatial data to address public health issues during challenging crises, such as the COVID-19 pandemic.

Objective To examine sex and gender roles in COVID-19 test positivity and hospitalisation in sex-stratified predictive models using machine learning. Design Cross-sectional study. Setting UK Biobank prospective cohort. Participants Participants tested between 16 March 2020 and 18 May 2020 were analysed. Main outcome measures The endpoints of the study were COVID-19 test positivity and hospitalisation. Forty-two individuals’ demographics, psychosocial factors and comorbidities were used as likely determinants of outcomes. Gradient boosting machine was used for building prediction models. Results Of 4510 individuals tested (51.2% female, mean age=68.5±8.9 years), 29.4% tested positive. Males were more likely to be positive than females (31.6% vs 27.3%, p=0.001). In females, living in more deprived areas, lower income, increased low-density lipoprotein (LDL) to high-density lipoprotein (HDL) ratio, working night shifts and living with a greater number of family members were associated with a higher likelihood of COVID-19 positive test. While in males, greater body mass index and LDL to HDL ratio were the factors associated with a positive test. Older age and adverse cardiometabolic characteristics were the most prominent variables associated with hospitalisation of test-positive patients in both overall and sex-stratified models. Conclusion High-risk jobs, crowded living arrangements and living in deprived areas were associated with increased COVID-19 infection in females, while high-risk cardiometabolic characteristics were more influential in males. Gender-related factors have a greater impact on females; hence, they should be considered in identifying priority groups for COVID-19 infection vaccination campaigns.

Background: A regular task by developers and users of synthetic data generation (SDG) methods is to evaluate and compare the utility of these methods. Multiple utility metrics have been proposed and used to evaluate synthetic data. However, they have not been validated in general or for comparing SDG methods. Objective: This study evaluates the ability of common utility metrics to rank SDG methods according to performance on a specific analytic workload. The workload of interest is the use of synthetic data for logistic regression prediction models, which is a very frequent workload in health research. Methods: We evaluated 6 utility metrics on 30 different health data sets and 3 different SDG methods (a Bayesian network, a Generative Adversarial Network, and sequential tree synthesis). These metrics were computed by averaging across 20 synthetic data sets from the same generative model. The metrics were then tested on their ability to rank the SDG methods based on prediction performance. Prediction performance was defined as the difference between each of the area under the receiver operating characteristic curve and area under the precision-recall curve values on synthetic data logistic regression prediction models versus real data models. Results: The utility metric best able to rank SDG methods was the multivariate Hellinger distance based on a Gaussian copula representation of real and synthetic joint distributions. Conclusions: This study has validated a generative model utility metric, the multivariate Hellinger distance, which can be used to reliably rank competing SDG methods on the same data set. The Hellinger distance metric can be used to evaluate and compare alternate SDG methods.

Background Novartis and the University of Oxford’s Big Data Institute (BDI) have established a research alliance with the aim to improve health care and drug development by making it more efficient and targeted. Using a combination of the latest statistical machine learning technology with an innovative IT platform developed to manage large volumes of anonymised data from numerous data sources and types we plan to identify novel patterns with clinical relevance which cannot be detected by humans alone to identify phenotypes and early predictors of patient disease activity and progression. Method The collaboration focuses on highly complex autoimmune diseases and develops a computational framework to assemble a research-ready dataset across numerous modalities. For the Multiple Sclerosis (MS) project, the collaboration has anonymised and integrated phase II to phase IV clinical and imaging trial data from ≈35,000 patients across all clinical phenotypes and collected in more than 2200 centres worldwide. For the “IL-17” project, the collaboration has anonymised and integrated clinical and imaging data from over 30 phase II and III Cosentyx clinical trials including more than 15,000 patients, suffering from four autoimmune disorders (Psoriasis, Axial Spondyloarthritis, Psoriatic arthritis (PsA) and Rheumatoid arthritis (RA)). Results A fundamental component of successful data analysis and the collaborative development of novel machine learning methods on these rich data sets has been the construction of a research informatics framework that can capture the data at regular intervals where images could be anonymised and integrated with the de-identified clinical data, quality controlled and compiled into a research-ready relational database which would then be available to multi-disciplinary analysts. The collaborative development from a group of software developers, data wranglers, statisticians, clinicians, and domain scientists across both organisations has been key. This framework is innovative, as it facilitates collaborative data management and makes a complicated clinical trial data set from a pharmaceutical company available to academic researchers who become associated with the project. Conclusions An informatics framework has been developed to capture clinical trial data into a pipeline of anonymisation, quality control, data exploration, and subsequent integration into a database. Establishing this framework has been integral to the development of analytical tools.

Background: Stroke is one of the most common cerebrovascular diseases causing permanent disability, and decreased quality of life (QoL). Both sex and gender have been reported to be associated with health outcomes. Gender, unlike biological sex, encompasses the psycho-socio-cultural roles, behaviors and identities of men, women, and gender-diverse people. Hypothesis: To examine the association between sociocultural gender, biological sex and health status among stroke survivors in the Canadian population. Methods: Data from cycles 2013-2014 and 2015-16 (n=237,121) of the Canadian Community Health Survey (CCHS) were analyzed. The primary endpoint of the study was Health Utility Index (HUI), a measure of health status and QoL. This index measures a range of health domains (i.e. vision, hearing, speech, ambulation, dexterity, emotion, cognition, and pain) and ranges between -0.36 (severe health state) to 1 (perfect health state). A gender score was computed based on the Genesis-Praxy method, using a principal component analysis-derived propensity score method. The final gender scores ranging from 0 to 1 (higher score identifying characteristics traditionally ascribed to women) included household size, perceived life stress, education, sense of belonging to community, marital status, and income. All statistical analyses were performed using R (V.4.0.2) with survey design. Results: Amongst 3,773 (1.1%) stroke survivors in two cycles, 47.8% were female and a majority were older than 50 years (85.3%). Overall, 76.4% of the stroke survivors had moderate to severe HUI (<=0.88), however, this rate was higher in females (82.5% vs 70.2%, P<0.001). Median gender score was 0.49 [0.46-0.55]. Higher gender scores (OR=12.5, 95%CI=1.4-116.2, P=0.02) and female sex (OR=1.8, 95%CI=1.2-2.8, P=0.002) were independently associated with moderately to severely diminished health status (HUI) in a model adjusted for age, and comorbidities (i.e. hypertension, diabetes, heart disease, and history of cancer). Conclusion: Characteristics traditionally ascribed to women’s gender and female sex were associated with poorer health status in stroke survivors. Gender-related factors must be targeted for improving the health status of patients suffering from stroke.

Gender refers to the socially constructed roles, behaviours, expressions and identities of girls, women, boys, men and gender diverse people. Gender-related factors are seldom assessed as determinants of health outcomes, despite their powerful contribution. The Gender Outcomes INternational Group: to Further Well-being Development (GOING-FWD) project developed a standard five-step methodology applicable to retrospectively identify gender-related factors and assess their relationship to outcomes across selected cohorts of non-communicable chronic diseases from Austria, Canada, Spain, Sweden. Step 1 (identification of gender-related variables): Based on the gender framework of the Women Health Research Network (ie, identity, role, relations and institutionalised gender), and available literature for a certain disease, an optimal ‘wish-list’ of gender-related variables was created and discussed by experts. Step 2 (definition of outcomes): Data dictionaries were screened for clinical and patient-relevant outcomes, using the International Consortium for Health Outcome Measurement framework. Step 3 (building of feasible final list): a cross-validation between variables per database and the ‘wish-list’ was performed. Step 4 (retrospective data harmonisation): The harmonisation potential of variables was evaluated. Step 5 (definition of data structure and analysis): The following analytic strategies were identified: (1) local analysis of data not transferable followed by a meta-analysis combining study-level estimates; (2) centrally performed federated analysis of data, with the individual-level participant data remaining on local servers; (3) synthesising the data locally and performing a pooled analysis on the synthetic data and (4) central analysis of pooled transferable data. The application of the GOING-FWD multistep approach can help guide investigators to analyse gender and its impact on outcomes in previously collected data.

BACKGROUND The impact of biological sex and social determinants of health (gender) on the prevalence of cardiovascular (CV) risk factors such as diabetes mellitus (DM) may vary by culture and health systems. In this study, we aimed to elucidate how sex and gender influence access to care and CV outcomes of individuals with DM across different countries. METHODS AND RESULTS Data from the Canadian Community Health Survey (2015-16) (N=109,659, 53.7% Females, 8.4% DM) and the European Health Interview Survey (N=316,333, 51.3% Females, 7.3% DM), were analyzed. A composite measure of socio-cultural gender was constructed (score range: 0-1; higher score identifying characteristics traditionally ascribed to women). The relationship between the gender score, antihyperglycemic care, complications and hospitalization of individuals with DM was assessed with a logistic regression model. European countries were stratified based on their Gender Inequality Index (GII); which quantifies gender disparity and inequity amongst various countries in the world, from low-GII (GII < 0.077), to medium (GII: 0.077-0.1635) and high (>=0.1635). Characteristics traditionally ascribe to women (i.e., higher gender score) included greater stress level, being widowed or divorced, larger household size, higher education, good sense of belonging to community, and lower income in Canadians; while being divorced or widowed, having greater household size, lower education and lower income were found in Europeans. Sex and gender significantly influenced the standard care of patients with diabetes including periodic glucose and HbA1C monitoring. Canadian diabetic females were more likely to check their HbA1c (OR: 1.29, 95%CI:1.03-1.6), while European counterparts were less likely to check their blood sugar (OR: 0.89, 95%CI:0.79-0.99). A higher gender score in both populations was associated with less frequent monitoring of HbA1C and blood glucose levels (Table 1). When stratifying by GII, DM patients in countries with medium and high GII were less likely to check their blood glucose levels compared to low GII countries (Table1). Additionally, higher gender scores independent of sex were associated with higher risk of heart disease, stroke and hospitalization in all countries albeit European countries with medium to high GII, conferred a higher risk of all complications and hospitalization rates (Table1). CONCLUSION Regardless of biological sex, diabetic individuals with characteristics typically ascribed to women and those living in countries with greater gender inequality, exhibited poorer antihyperglycemic care, greater risk of cardiovascular complications, and higher hospitalization rates. Country-specific gender related factors and gender disparity must be targeted for improving health status and access to care of patients with DM. The impact of biological sex and social determinants of health (gender) on the prevalence of cardiovascular (CV) risk factors such as diabetes mellitus (DM) may vary by culture and health systems. In this study, we aimed to elucidate how sex and gender influence access to care and CV outcomes of individuals with DM across different countries. Data from the Canadian Community Health Survey (2015-16) (N=109,659, 53.7% Females, 8.4% DM) and the European Health Interview Survey (N=316,333, 51.3% Females, 7.3% DM), were analyzed. A composite measure of socio-cultural gender was constructed (score range: 0-1; higher score identifying characteristics traditionally ascribed to women). The relationship between the gender score, antihyperglycemic care, complications and hospitalization of individuals with DM was assessed with a logistic regression model. European countries were stratified based on their Gender Inequality Index (GII); which quantifies gender disparity and inequity amongst various countries in the world, from low-GII (GII < 0.077), to medium (GII: 0.077-0.1635) and high (>=0.1635). Characteristics traditionally ascribe to women (i.e., higher gender score) included greater stress level, being widowed or divorced, larger household size, higher education, good sense of belonging to community, and lower income in Canadians; while being divorced or widowed, having greater household size, lower education and lower income were found in Europeans. Sex and gender significantly influenced the standard care of patients with diabetes including periodic glucose and HbA1C monitoring. Canadian diabetic females were more likely to check their HbA1c (OR: 1.29, 95%CI:1.03-1.6), while European counterparts were less likely to check their blood sugar (OR: 0.89, 95%CI:0.79-0.99). A higher gender score in both populations was associated with less frequent monitoring of HbA1C and blood glucose levels (Table 1). When stratifying by GII, DM patients in countries with medium and high GII were less likely to check their blood glucose levels compared to low GII countries (Table1). Additionally, higher gender scores independent of sex were associated with higher risk of heart disease, stroke and hospitalization in all countries albeit European countries with medium to high GII, conferred a higher risk of all complications and hospitalization rates (Table1). Regardless of biological sex, diabetic individuals with characteristics typically ascribed to women and those living in countries with greater gender inequality, exhibited poorer antihyperglycemic care, greater risk of cardiovascular complications, and higher hospitalization rates. Country-specific gender related factors and gender disparity must be targeted for improving health status and access to care of patients with DM.