Statistical and machine-learning assessment of attitudinal, knowledge, and perceptual factors on diabetes awareness...

The primary objective was to identify and analyze the factors that impact diabetes awareness and perception among diabetic and non-diabetic participants. The study also sought to assess the effectiveness of current health awareness programs and identify gaps in public knowledge about diabetes.

Diabetes poses a significant global health challenge, with increasing prevalence worldwide. Comprehending the behavioral and demographic factors leading to diabetes is important for personalized interventions and prevention strategies in Kuwait.

This study was cross-sectional in nature and employed a quantitative approach. It involved distributing a structured questionnaire to a sample of N = 1268 participants in Kuwait, 391 of them were diabetic and 877 were non-diabetic. The sample was stratified based on age, gender, administrative division and nationality. The study employed machine learning and statistical analyses to examine the nature of the relationship between diabetes awareness and the demographic factors. The study executed a random forest approach before employing a logistic regression model to determine the most significant features influencing diabetes. This involved prioritizing variables based on their importance metrics like a mean dropout loss and mean decrease in accuracy, this ensures that the most important predictors are included in the logistic regression model, facilitating a more concentrated and comprehensible examination of the factors affecting diabetes.

The output shown above describes the results for the logistics regression model indicating the different variables that are significant predictors for diabetes among the participants. From the odds ratio it was observed that age was a significant predictor and people above 60 years of age were 11.47 times more likely to have diabetes compared to the 18-30 age group. For those aged 46-60 the likelihood of having diabetes compared to the 18-30 age group was 5.79 times. Similarly, gender was a significant predictor and males were 2.27 times likely to have diabetes than females. Those who frequently interacted with medical staff were also at higher risk (odds of 1.41), likewise, individuals who had kidney complications were also at higher risk of getting diabetes (odds of 1.60). On the contrast, being overweight decreased the odds of getting diabetic (odds ratio of 0.55), likewise, having pregnancy related diabetes decreased the likelihood of being diabetic (odds ratio of 0.65). From these results, it can be seen that age, gender and certain health complications while interacting with the dependent variable need to be considered while assessing the risk of getting diabetes.

The current study reveals that gender, age groups, kidney disorders and healthcare provider interactions among others, are significantly associated with the awareness and attitude towards diabetes among the Kuwaiti population. On one hand, males and older age groups found to be at higher risk whereas, obesity and pregnancy related diabetes seemed to have a protective effect. The current study findings emphasize the importance of designing specific public health policy and education programs that takes into account the demographic factors to enhance effective diabetes management and prevention strategies. These study findings offer policy knowledge that can assist policymakers to plan and implement more robust health policies that address specific population subgroup needs and challenges.