Determinants of Diabetes Disease Management, 2011-2019

Healthcare insurance fraud detection using data mining

BACKGROUND

Healthcare programs and insurance initiatives play a crucial role in ensuring that people have access to medical care. There are many benefits of healthcare insurance programs but fraud in healthcare continues to be a significant challenge in the insurance industry. Healthcare insurance fraud detection faces challenges from evolving and sophisticated fraud schemes that adapt to detection methods. Analyzing extensive healthcare data is hindered by complexity, data quality issues, and the need for real-time detection, while privacy concerns and false positives pose additional hurdles. The lack of standardization in coding and limited resources further complicate efforts to address fraudulent activities effectively.

METHODOLGY

In this study, a fraud detection methodology is presented that utilizes association rule mining augmented with unsupervised learning techniques to detect healthcare insurance fraud. Dataset from the Centres for Medicare and Medicaid Services (CMS) 2008-2010 DE-SynPUF is used for analysis. The proposed methodology works in two stages. First, association rule mining is used to extract frequent rules from the transactions based on patient, service and service provider features. Second, the extracted rules are passed to unsupervised classifiers, such as IF, CBLOF, ECOD, and OCSVM, to identify fraudulent activity.

RESULTS

Descriptive analysis shows patterns and trends in the data revealing interesting relationship among diagnosis codes, procedure codes and the physicians. The baseline anomaly detection algorithms generated results in 902.24 seconds. Another experiment retrieved frequent rules using association rule mining with apriori algorithm combined with unsupervised techniques in 868.18 seconds. The silhouette scoring method calculated the efficacy of four different anomaly detection techniques showing CBLOF with highest score of 0.114 followed by isolation forest with the score of 0.103. The ECOD and OCSVM techniques have lower scores of 0.063 and 0.060, respectively.

CONCLUSION

The proposed methodology enhances healthcare insurance fraud detection by using association rule mining for pattern discovery and unsupervised classifiers for effective anomaly detection.

The Health Status of the US Veterans: A Longitudinal Analysis of Surveillance Data Prior to and during the COVID-19 Pandemic

Chronic diseases affect a disproportionate number of United States (US) veterans, causing significant long-term health issues and affecting entitlement spending. This longitudinal study examined the health status of US veterans as compared to non-veterans pre- and post-COVID-19, utilizing the annual Center for Disease Control and Prevention (CDC) behavioral risk factor surveillance system (BRFSS) survey data. Age-adjusted descriptive point estimates were generated independently for 2003 through 2021, while complex weighted panel data were generated from 2011 and onward. General linear modeling revealed that the average US veteran reports a higher prevalence of disease conditions except for mental health disorders when compared to a non-veteran. These findings were consistent with both pre- and post-COVID-19; however, both groups reported a higher prevalence of mental health issues during the pandemic years. The findings suggest that there have been no improvements in reducing veteran comorbidities to non-veteran levels and that COVID-19 adversely affected the mental health of both populations.

Diabetes management behaviors associated with depression in the U.S

BACKGROUND

There is a lack of nationally representative evidence from the U.S. investigating the relationships between depression and diabetes management behaviors. Our study aimed to assess the associations between diabetes management behaviors and depression status, and to compare U.S. population-level percentages of diabetes management behaviors among patients with and without depression.

METHODS

A cross-sectional study was conducted using population-based survey data to assess patient-reported variables retrospectively. We used the Behavioral Risk Factor Surveillance System (BRFSS) data and included states in the U.S. that continuously adopted the diabetes optional modules in 2013, 2015, 2017, and 2019. We included U.S. adults (≥ 18 years old) with self-reported diabetes in our analysis. Main outcomes were diabetes management behaviors (i.e., self-check for blood glucose and feet sores/irritation, regular diabetes clinical visit, HbA1c check, professional feet check, and dilated eye examination) and lifestyle behaviors (i.e., exercise, smoking, and alcohol consumption).

RESULTS

Among the 74,011 respondents with diabetes, patients with depression had a higher likelihood of performing routine HbA1c checks (adjusted odds ratio (AOR) = 1.12; 95% CI 1.01-1.23) but had a lower likelihood to perform regular self-check for blood glucose (AOR = 0.91; 95% CI 0.84-0.99), receive professional feet checks (AOR = 0.87; 95% CI 0.79-0.95), and receive a dilated eye examination (AOR = 0.89; 95% CI 0.82-0.98). For lifestyle behaviors, patients with depression were more likely to smoke (No smoking (AOR) = 0.65; 95% CI = 0.59-0.72) and less likely to engage in sufficient exercise time (AOR = 0.69; 95% CI 0.63-0.75). There were no significant associations between depression and other behaviors, including self-check for feet sores/irritation (AOR = 0.99; 95% CI 0.92-1.08), regular diabetes clinical visit (AOR = 1.03, 95% CI 0.94-1.13), and alcohol consumption (AOR = 1.01, 95% CI 0.92-1.10).

CONCLUSIONS

The association between depression status and diabetes management behaviors varied. People with depression were positively associated with HbA1c checks. However, less uptake of other behaviors may indicate the needs for improvement in diabetes management.

Examining Predictors of Myocardial Infarction

Cardiovascular diseases are the leading cause of death in the United States. This study analyzed predictors of myocardial infarction (MI) for those aged 35 and older based on demographic, socioeconomic, geographic, behavioral, and risk factors, as well as access to healthcare variables using the Center for Disease (CDC) Control Behavioral Risk Factor Surveillance System (BRFSS) survey for the year 2019. Multiple quasibinomial models were generated on an 80% training set hierarchically and then used to forecast the 20% test set. The final training model proved somewhat capable of prediction with a weighted F1-Score = 0.898. A complete model based on statistically significant variables using the entirety of the dataset was compared to the same model built on the training set. Models demonstrated coefficient stability. Similar to previous studies, age, gender, marital status, veteran status, income, home ownership, employment status, and education level were important demographic and socioeconomic predictors. The only geographic variable that remained in the model was associated with the West North Central Census Division (in-creased risk). Statistically important behavioral and risk factors as well as comorbidities included health status, smoking, alcohol consumption frequency, cholesterol, blood pressure, diabetes, stroke, chronic obstructive pulmonary disorder (COPD), kidney disease, and arthritis. Three access to healthcare variables proved statistically significant: lack of a primary care provider (Odds Ratio, OR = 0.853, p < 0.001), cost considerations prevented some care (OR = 1.232, p < 0.001), and lack of an annual checkup (OR = 0.807, p < 0.001). The directionality of these odds ratios is congruent with a marginal effects model and implies that those without MI are more likely not to have a primary provider or annual checkup, but those with MI are more likely to have missed care due to the cost of that care. Cost of healthcare for MI patients is associated with not receiving care after accounting for all other variables.