Cardiovascular disease (CVD) outcomes and associated risk factors in a medicare population without prior CVD history: an analysis using statistical and machine learning algorithms.

There is limited information on predicting incident cardiovascular outcomes among high- to very high-risk populations such as the elderly (≥ 65 years) in the absence of prior cardiovascular disease and the presence of non-cardiovascular multi-morbidity. We hypothesized that statistical/machine learning modeling can improve risk prediction, thus helping inform care management strategies. We defined a population from the Medicare health plan, a US government-funded program mostly for the elderly and varied levels of non-cardiovascular multi-morbidity. Participants were screened for cardiovascular disease (CVD), coronary or peripheral artery disease (CAD or PAD), heart failure (HF), atrial fibrillation (AF), ischemic stroke (IS), transient ischemic attack (TIA), and myocardial infarction (MI) for a 3-yr period in the comorbid history. They were followed up for up to 45.2 months. Analyses included descriptive approaches in terms of incidence rates and density ratios, and inferential in terms of main effect statistical/complex machine learning modeling. The contemporary risk factors of interest spanned across the domains of comorbidity, lifestyle, and healthcare utilization history. The cohort consisted of 154,551 individuals (mean age 68.8 years; 62.2% female). The overall crude incidence rate of CVD events was 9.9 new cases per 100 person-years. The highest rates among its component outcomes were obtained for CAD or PAD (3.6 for each), followed by HF (2.2) and AF (1.8), then IS (1.3), and finally TIA (1.0) and MI (0.9).Model performance was modest in terms of discriminatory power (C index: 0.67, 95%CI 0.667-0.674 for training; and 0.668, 95%CI 0.663-0.673 for validation data), equal agreement between predicted and observed events for calibration purposes, and good clinical utility in terms of a net benefit of 15 true positives per 100 patients relative to the All-patient treatment strategy. Complex models based on machine learning algorithms yielded incrementally better discriminatory power and much improved goodness-of-fitness tests from those based on main effect statistical modeling. This Medicare population represents a highly vulnerable group for incident CVD events. This population would benefit from an integrated approach to their care and management, including attention to their comorbidities and lifestyle factors, as well as medication adherence.

Transient ischemic attack events and incident cardiovascular and non-cardiovascular complications: Observations from a large diversified multimorbid cohort.

Background: Transient ischemic attack (TIA) is a strong signal prompting the incidence of future cardiovascular and non-cardiovascular complications, in light of recent debate on the so-called "stroke-heart syndrome." We aimed to investigate the relation of TIAs to incident clinical events. Methods: Patients were drawn from three health plans with a wide spectrum of age groups and a wide mix of socio-economic/disability status. Two TIA cohorts in a retrospective design were used to achieve the study specific aims: (i) to investigate the incidence of TIA and associated cardiovascular and non-cardiovascular complications within 30 and 90 days from the onset of incident TIA events; and (ii) to examine the potential risk factors for developing incident TIA events in the general population with/without a history of prior stroke. Results: The incident TIA cohort consisted of 53,716 patients with an average age of 64.2 years (SD 15.2) and 46.1% male. Following TIA, the incidence proportions of ischemic stroke within 30 and 90 days were 2.7% and 3.8%, respectively, and for incident acute coronary syndrome being 0.94 and 1.84, respectively. Ventricular arrhythmia had proportions of 1.2 and 2.14, respectively within 30 and 90 days, with acute heart failure having values of 0.49 and 0.923. About 45% or more of the cardiovascular and non-cardiovascular complications occurred in the first 30 days following the incident TIA cases. About one-third of the recurrent TIA cases followed the incident TIA cases within a span of 30 days. Amongst comorbidities with stroke in the comorbid history, prior stroke provided the strongest risk factor in terms of odds ratio (OR = 8.34, 95% CI 7.21-9.66) for incident TIA events. Age was strongly associated with incident TIA events. Without a prior history of stroke (ischemic stroke/transient ischemic attack/thrombo-embolic events), valvular disease was the strongest risk factor from among the comorbidities (OR-1.87, 95% CI 1.51-2.32). Age also provided strong associations with incident TIA events. Conclusions: Following a TIA, there was a high risk of stroke, acute coronary syndrome, ventricular arrhythmia, acute heart failure, and non-cardiovascular complications.

Medication non-adherence patterns and profiles for patients with incident myocardial infarction: Observations from a large multi-morbid US population.

BACKGROUND: Consistent adherence levels to multiple long-term medications for patients with cardiovascular conditions are typically advocated in the range of 50% or higher, although very likely to be much lower in some populations. We investigated this issue in a large cohort covering a broad age and geographical spectrum, with a wide range of socio-economic disability status. METHODS: The patients were drawn from three different health plans with a varied mix of socio-economic/disability levels. Adherence patterns were examined on a monthly basis for up to 12 months past the index date for myocardial infarction (MI) using longitudinal analyses of group-based trajectory modelling. Each of the non-adherent patterns was profiled from comorbid history, demographic and health plan factors using main effect logistic regression modelling. Four medication classes were examined for MI: betablockers, statin, ACE inhibitors and anti-platelets. RESULTS: The participant population for the MI/non-MI cohorts was 1,987,605 (MI cohort: mean age 62 years, 45.9% female; non-MI cohort: mean age 45 years, 55.3% females). Cohorts characterized by medication non-adherence dominated the majority of MI population with values ranging from 74% to 82%. There were four types of consistent non-adherence patterns as a function of time for each medication class: fast decline, slow decline, occasional users and early gap followed by increased adherence. The characteristics of non-adherence profiles eligible for improvement included patients with a prior history of hypertension, diabetes mellitus and stroke as co-morbidities, and Medicare plan. CONCLUSIONS: We found consistent patterns of intermediate non-adherence for each of four drug classes for MI cohorts in the order of 56% who are eligible for interventions aimed at improving cardiovascular medication adherence levels. These insights may help improve cardiovascular medication adherence using large medication non-adherence improvement programs.

Adherence levels and patterns for multiple cardiac medications prescribed to patients with incident atrial fibrillation events.

AIMS: Using advanced longitudinal analyses, this real-world investigation examined medication adherence levels and patterns for incident atrial fibrillation (AF) patients with significant cardiovascular and noncardiovascular multimorbid conditions for each of 5 medication classes (ß-blockers, calcium channel blockers/digoxin, antiarrhythmics, anticoagulants, antiplatelets). The population was derived from a large cohort covering a wide age spectrum/diversified US geographical areas/wide range of socioeconomic-disability status. METHODS: The patients were drawn from 3 different health plans. Adherence was defined in terms of the proportion of day covered (PDC), and its patterns were modelled in terms of group-based trajectory, with each pattern profiled in terms of comorbid history, demographic variables and health plan factors using multinomial regression modelling. RESULTS: The total population consisted of 1 978 168 patients, with the AF cohort being older (average age of 64.6 years relative to 44.7 years for the non-AF cohort) and having fewer females (47.8% relative to 55.4 for the non-AF cohort). The AF cohort had significant cardiovascular/noncardiovascular multimorbidities and was much sicker than the non-AF cohort. A 6-group based trajectory solution appears to be the most logical outcome for each medication class according to assessed criteria. For each medication class, it consisted of one consistent adherent group (PDC ≥ 0.84), one fast declining group (PDC ≤ 0.11) and 4 intermediate nonadherence groups (slow decline [0.30-0.74 PDC range], occasional users [0.24-0.55 PDC range] and early gap/increased adherence [0.62-0.75]). The most consistent adherent groups were much lower than 50% of the total population and equal to 12.5-27.0% of the population, with the fast declining nonadherent pattern in the 5.6-35.0% of the population and the intermediate nonadherence equal to ~61% of the population. CONCLUSION: Our findings confirm that medication adherence is of major concern among multimorbid patients, with adherence levels lower much than those reported in the literature. There are 3 patterns of intermediate nonadherence (slow decline, occasional users, early gap/increased adherence), which were found to be eligible for interventions aimed at improving their adherence levels for each medication class. This may help improve cardiovascular medication adherence using large medication nonadherence improvement programmes.

Incidence and Complications of Atrial Fibrillation in a Low Socioeconomic and High Disability United States (US) Population: A Combined Statistical and Machine Learning Approach.

Background: Poor socioeconomic status coupled with individual disability is significantly associated with incident atrial fibrillation (AF) and AF-related adverse outcomes, with the information currently lacking for US cohorts. We examined AF incidence/complications and the dynamic nature of associated risk factors in a large socially disadvantaged US population. Methods: A large population representing a combined poor socioeconomic status/disability (Medicaid program) was examined from diverse geographical regions across the US continent. The target population was extracted from administrative databases with patients possessing medical/pharmacy benefits. This retrospective cohort study was conducted from Jan 1, 2016, to Sep 30, 2021, and was limited to 18- to 80-year age group drawn from the Medicaid program. Descriptive and inferential statistics (parametric: logistic regression and neural network) were applied to all computations using a combined statistical and machine learning (ML) approach. Results: A total of 617413 individuals participated in the study, with mean age of 41.7 years (standard deviation "SD" 15.2) and 65.6% female patients. Seven distinct groups were identified with different combinations of low socioeconomic status and disability constraints. The overall crude AF incidence rate was 0.49 cases/100 person-years (95% confidence limit "CI" 0.40-0.58), with the lowest rate for the younger group (temporary assistance for needy family "TANF") (0.20, 95%CI 0.18-0.21), the highest rates for the older groups (age, blindness, or disability "ABD" duals-1.51, 95% CI 1.31-1.58; long-term services and support "LTSS" duals-1.45, 95% CI 1.31-1.58), and the remaining four other groups in between the lower and upper rates. Based on independent effects after accounting for confounders in main effect modeling, the point estimates of odds ratios for AF status with various clinical outcomes were as follows: stroke (2.69, 95% CI 2.53-2.85); heart failure (6.18, 95% CI 5.86-6.52); myocardial infarction (3.71, 95% CI 3.49-3.94); major bleeding (2.26, 95% CI 2.14-2.38); and cognitive impairment (1.74, 95% CI 1.59-1.91). A logistic regression-based ML model produced excellent discriminant validity for high-risk AF outcomes (c "concordance" index based on training data 0.91, 95%CI 0.891-0.929), together with similar measures for external validity, calibration, and clinical utility. The performance measures for the ML models predicting associated complications with high-risk AF cases were good to excellent. Conclusions: A combination of low socioeconomic status and disability contributes to AF incidence and complications, elevating risks to higher levels relative to the general population. ML algorithms can be used to identify AF patients at high risk of clinical events. While further research is definitely in need on this socially important issue, the reported investigation is unique in which it integrates the general case about the subject due to the different ethnic groups around the world under a unified culture stemming from residing in the US.

Incident and recurrent myocardial infarction (MI) in relation to comorbidities: Prediction of outcomes using machine-learning algorithms.

BACKGROUND: To date, incident and recurrent MI remains a major health issue worldwide, and efforts to improve risk prediction in population health studies are needed. This may help the scalability of prevention strategies and management in terms of healthcare cost savings and improved quality of care. METHODS: We studied a large-scale population of 4.3 million US patients from different socio-economic and geographical areas from three health plans (Commercial, Medicare, Medicaid). Individuals had medical/pharmacy benefits for at least 30 months (2 years for comorbid history and followed up for 6 months or more for clinical outcomes). Machine-learning (ML) algorithms included supervised (logistic regression, neural network) and unsupervised (decision tree, gradient boosting) methodologies. Model discriminant validity, calibration and clinical utility were performed separately on allocated test sample (1/3 of original data). RESULTS: In the absence of MI in comorbid history, the overall incidence rates were 0.442 cases/100 person-years and in the presence of MI history, 0.652. ML algorithms showed that supervised formulations had incrementally higher discriminant validity than unsupervised techniques (e.g., for incident MI outcome in the absence of MI in comorbid history: logistic regression "LR" - c index 0.921, 95%CI 0.920-0.922; neural network "NN" - c index 0.914, 95%CI 0.913-0.915; gradient boosting "GB" - c index 0.902, 95%CI 0.900-0.904; decision tree "DT" - c index 0.500, 95%CI 0.495-0.505). Calibration and clinical utility showed good to excellent results. CONCLUSION: ML algorithms can substantially improve the prediction of incident and recurrent MI particularly in terms of the non-linear formulation. This approach may help with improved risk prediction, allowing implementation of cardiovascular prevention strategies across diversified sub-populations with different clusters of complexity.

Effects of multimorbidity on incident COVID-19 events and its interplay with COVID-19 event status on subsequent incident myocardial infarction (MI).

BACKGROUND: With the spread of COVID-19 pandemic, there have been reports on its impact on incident myocardial infarction (MI) emanating from studies with small to modest sample sizes. We therefore examined the incidence of MI in a very large population health cohort with COVID-19 using a methodology which integrates the dynamicity of prior comorbid history. We used two approaches, i.e. main effect modelling and a machine learning (ML) methodology, accounting for the complex dynamic relationships among comorbidity and other variables. METHODS: We studied a very large prospective 18-90-year US population, including 4,289,481 patients from medical databases in a 12-month investigation of those with/without newly incident COVID-19 cases together with a 2-year comorbid profile in the baseline period. Incident MI outcomes were examined in relationship to diverse multimorbid conditions, COVID-19 status and demographic variables-with ML accounting for the dynamic nature of changing multimorbidity risk factors. RESULTS: Multimorbidity, defined as a composite of cardiometabolic/noncardiometabolic comorbid profile, significantly contributed to the onset of confirmed COVID-19 cases. Furthermore, a main effect model (C-index value 0.932; 95%CI 0.930-0.934) had medium to large effect sizes with incident MI outcomes in a COVID-19 cohort for the classic multimorbid conditions in medical history profile which includes prior coronary artery disease (OR 4.61 95%CI 4.49-4.73); hypertension (OR 3.55 95%CI 3.55-3.83); congestive heart failure (2.31 95%CI 2.24-2.37); valvular disease (1.43 95%CI 1.39-1.47); stroke (1.30 95%CI 1.26-1.34); and diabetes (1.26 95%CI 1.23-1.34). COVID-19 status (1.86 95%CI 1.79-1.93) contributed an independent large size risk effect for incident MI. The ML algorithm demonstrated better discriminatory validity than the main effect model (training: C-index 0.949, 95%CI 0.948-0.95; validation: C-index 0.949, 95%CI 0.948-0.95). Calibration of the ML-based formulation was satisfactory and better than the main effect model. Decision curve analysis demonstrated that the ML clinical utility was better than the 'treat all' strategy and the main effect model. The ML logistic regression model was better than the neural network algorithm. CONCLUSION: The very large investigation conducted herein confirmed the importance of cardiometabolic and noncardiometabolic multimorbidity in increasing vulnerabilities to a higher risk of COVID-19 infections. Furthermore, the presence of COVID-19 infections increased incident MI complications both in terms of independent effects and interactions with the multimorbid profile and age.

Improving dynamic stroke risk prediction in non-anticoagulated patients with and without atrial fibrillation: comparing common clinical risk scores and machine learning algorithms.

AIMS: Diversified cardiovascular/non-cardiovascular multi-morbid risk and efficient machine learning algorithms may facilitate improvements in stroke risk prediction, especially in newly diagnosed non-anticoagulated atrial fibrillation (AF) patients where initial decision-making on stroke prevention is needed. Therefore the aims of this article are to study common clinical risk assessment for stroke risk prediction in AF/non-AF cohorts together with cardiovascular/ non-cardiovascular multi-morbid conditions; to improve stroke risk prediction using machine learning approaches; and to compare the improved clinical prediction rules for multi-morbid conditions using machine learning algorithms. METHODS AND RESULTS: We used cohort data from two health plans with 6 457 412 males/females contributing 14,188,679 person-years of data. The model inputs consisted of a diversified list of comorbidities/demographic/ temporal exposure variables, with the outcome capturing stroke event incidences. Machine learning algorithms used two parametric and two nonparametric techniques. The best prediction model was derived on the basis of non-linear formulations using machine learning criteria, with the highest c-index was obtained for logistic regression [0.892; 95% confidence interval (CI) 0.886-0.898] with consistency on external validation (0.891; 95% CI 0.882-0.9). These were significantly higher than those based on the conventional stroke risk scores (CHADS2: 0.7488, 95% CI 0.746-0.7516; CHA2DS2-VASc: 0.7801, 95% CI 0.7772-0.7831) and multi-morbid index (0.8508, 95% CI 0.8483-0.8532). The machine learning algorithm had good internal and external calibration and net benefit values. CONCLUSION: In this large cohort of newly diagnosed non-anticoagulated AF/non-AF patients, large improvements in stroke risk prediction can be shown with cardiovascular/non-cardiovascular multi-morbid index and a machine learning approach accounting for dynamic changes in risk factors.

Improving Stroke Risk Prediction in the General Population: A Comparative Assessment of Common Clinical Rules, a New Multimorbid Index, and Machine-Learning-Based Algorithms.

BACKGROUND: There are few large studies examining and predicting the diversified cardiovascular/noncardiovascular comorbidity relationships with stroke. We investigated stroke risks in a very large prospective cohort of patients with multimorbidity, using two common clinical rules, a clinical multimorbid index and a machine-learning (ML) approach, accounting for the complex relationships among variables, including the dynamic nature of changing risk factors. METHODS: We studied a prospective U.S. cohort of 3,435,224 patients from medical databases in a 2-year investigation. Stroke outcomes were examined in relationship to diverse multimorbid conditions, demographic variables, and other inputs, with ML accounting for the dynamic nature of changing multimorbidity risk factors, two clinical risk scores, and a clinical multimorbid index. RESULTS: Common clinical risk scores had moderate and comparable c indices with stroke outcomes in the training and external validation samples (validation-CHADS2: c index 0.812, 95% confidence interval [CI] 0.808-0.815; CHA2DS2-VASc: c index 0.809, 95% CI 0.805-0.812). A clinical multimorbid index had higher discriminant validity values for both the training/external validation samples (validation: c index 0.850, 95% CI 0.847-0.853). The ML-based algorithms yielded the highest discriminant validity values for the gradient boosting/neural network logistic regression formulations with no significant differences among the ML approaches (validation for logistic regression: c index 0.866, 95% CI 0.856-0.876). Calibration of the ML-based formulation was satisfactory across a wide range of predicted probabilities. Decision curve analysis demonstrated that clinical utility for the ML-based formulation was better than that for the two current clinical rules and the newly developed multimorbid tool. Also, ML models and clinical stroke risk scores were more clinically useful than the "treat all" strategy. CONCLUSION: Complex relationships of various comorbidities uncovered using a ML approach for diverse (and dynamic) multimorbidity changes have major consequences for stroke risk prediction. This approach may facilitate automated approaches for dynamic risk stratification in the significant presence of multimorbidity, helping in the decision-making process for risk assessment and integrated/holistic management.

Revisiting the dynamic risk profile of cardiovascular/non-cardiovascular multimorbidity in incident atrial fibrillation patients and five cardiovascular/non-cardiovascular outcomes: A machine-learning approach.

BACKGROUND: Patients with atrial fibrillation (AF) usually have a heterogeneous co-morbid history, with dynamic changes in risk factors impacting on multiple adverse outcomes. We investigated a large prospective cohort of patients with multimorbidity, using a machine-learning approach, accounting for the dynamic nature of comorbidity risks and incident AF. METHODS: Using machine-learning, we studied a prospective US cohort using medical/pharmacy databases of 1 091 911 patients, with an incident AF cohort of 14 078 and non-AF cohort of 1 077 833 enrolled in the 4-year study. Five incident clinical outcomes (heart failure, stroke, myocardial infarction, major bleeding, and cognitive impairment) were examined in relationship to AF status (AF vs non-AF), diverse multi-morbid (conditions and medications) history, and demographic parameters (age and gender), with supervised machine-learning techniques. RESULTS: Complex inter-relationships of various comorbidities were uncovered for AF cases, leading to 6-fold higher risk of heart failure relative to the non-AF cohort (OR 6.02, 95% CI 5.72-6.33), followed by myocardial infarction (OR=2.68), stroke (OR=2.19), and major bleeding (OR=1.36). Supervised machine learning algorithms on the original populations yielded comparable results for both neural network and logistic regression algorithms in terms of discriminant validity, with c-indexes for incident adverse outcomes: heart failure (0.924, 95%CI 0.923-0.925), stroke (0.871, 95%CI 0.869-0.873), myocardial infarction (0.901, 95% CI 0.899-0.903), major bleeding (0.700, 95%CI 0.697-0.703), and cognitive impairment (0.919, 95% CI 0.9170.921). External calibration of all models demonstrated a good fit between the predicted probabilities and observed events. Decision curve analysis demonstrated that the obtained models were much more clinically useful than the "treat all" strategy. CONCLUSIONS: Complex multimorbidity relationships uncovered using a machine learning approach for incident AF cases have major consequences for integrated care management, with implications for risk stratification and adverse clinical outcomes. This approach may facilitate automated approaches in the presence of multimorbidity, potentially helping decision making.

Incident atrial fibrillation and its risk prediction in patients developing COVID-19: A machine learning based algorithm approach.

BACKGROUND: The elderly multi-morbid patient is at high risk of adverse outcomes with COVID-19 complications, and in the general population, the development of incident AF is associated with worse outcomes in such patients. There is therefore the need to identify those patients with COVID-19 who are at highest risk of developing incident AF. We therefore investigated incident AF risks in a large prospective population of elderly patients with/without incident COVID-19 cases and baseline cardiovascular/non-cardiovascular multi-morbidities. We used two approaches: main effect modeling and secondly, a machine-learning (ML) approach, accounting for the complex dynamic relationships among comorbidity variables. METHODS: We studied a prospective elderly US cohort of 280,592 patients from medical databases in an 8-month investigation of with/without newly incident COVID19 cases. Incident AF outcomes were examined in relationship to diverse multi-morbid conditions, COVID-19 status and demographic variables, with ML accounting for the dynamic nature of changing multimorbidity risk factors. RESULTS: Multi-morbidity contributed to the onset of confirmed COVID-19 cases with cognitive impairment (OR 1.69; 95%CI 1.52-1.88), anemia (OR 1.41; 95%CI 1.32-1.50), diabetes mellitus (OR 1.35; 95%CI 1.27-1.44) and vascular disease (OR 1.30; 95%CI 1.21-1.39) having the highest associations. A main effect model (C-index value 0.718) showed that COVID-19 had the highest association with incident AF cases (OR 3.12; 95%CI 2.61-3.710, followed by congestive heart failure (1.72; 95%CI 1.50-1.96), then coronary artery disease (OR 1.43; 95%CI 1.27-1.60) and valvular disease (1.42; 95%CI 1.26-1.60). The ML algorithm demonstrated improved discriminatory validity incrementally over the statistical main effect model (training: C-index 0.729, 95%CI 0.718-0.740; validation: C-index 0.704, 95%CI 0.687-0.72). Calibration of the ML based formulation was satisfactory and better than the main-effect model. Decision curve analysis demonstrated that the clinical utility for the ML based formulation was better than the 'treat all' strategy and the main effect model. CONCLUSION: COVID-19 status has major implications for incident AF in a cohort with diverse cardiovascular/non-cardiovascular multi-morbidities. Our ML approach accounting for dynamic multimorbidity changes had good prediction for new onset AF amongst incident COVID19 cases.

Prevalence/incidence of atrial fibrillation based on integrated medical/pharmacy claims, and association with co-morbidity profiles/multi-morbidity in a large US adult cohort.

BACKGROUND: Identification of published data on prevalent/incidence of atrial fibrillation/flutter (AF) often relies on inpatient/outpatient claims, without consideration to other types of healthcare services and pharmacy claims. Accurate, population-level data that can enable the ongoing monitoring of AF epidemiology, quality of care at affordable cost, and complications are needed. We hypothesised that prevalent/incidence data would vary via the use of integrated medical/pharmacy claims, and associated comorbidities would vary accordingly. PURPOSE: To examine AF prevalence/incidence and associated individual comorbidity and multi-morbidity profiles for a large US adult cohort spanning across a wide age range for both males/females based on both integrated criteria from both medical/pharmacy claims. METHODS: We studied a population of 8 343 992 persons across many geographical areas in the US continent from 1 January/2016 to 31 October 2019. The prevalence and incidence of AF were comparatively analysed for different healthcare parameters (eg, emergency room visit, anticoagulant medication, heart rhythm control medication) and for integrated criteria based on medical/pharmacy claims. RESULTS: Based on integrated medical and pharmacy claims, AF prevalence was 12.7% in the elderly population (≥65 years) and 0.9% in the younger population (<65 years). These prevalence rates are different from estimates provided by the US CDC for those aged ≥65 years (9%) and age <65 years (2%); thus, the prevalence is under-estimated in the elderly population and over-estimated in the younger population. The incidence ratios for elderly females relative to younger females was 15.07 (95%CI 14.47-15.70), a value that is about 50% higher than for elderly males (10.57 (95%CI 10.24-10.92)). Comorbidity risk profile for AF identified on the basis of medical and pharmacy criteria varied by age and gender. The proportion with multi-morbidity (defined as ≥2 long term comorbidities) was 10%-12%. CONCLUSION: Continued reliance only on outpatient and inpatient claims greatly underestimates AF prevalence and incidence in the general population by over 100%. Multi-morbidity is common amongst AF patients, affecting approximately 1 in 10 patients. AF patients with four or more co-morbidities captured 20%-40% of the AF cohorts depending on age groups and prevalent or incident cases.