RESUMO
BACKGROUND: According to previous reports, very high percentages of individuals in Saudi Arabia are undiagnosed for type 2 diabetes mellitus (T2DM). Despite conducting several screening and awareness campaigns, these efforts lacked full accessibility and consumed extensive human and material resources. Thus, developing machine learning (ML) models could enhance the population-based screening process. The study aims to compare a newly developed ML model's outcomes with the validated American Diabetes Association's (ADA) risk assessment regarding predicting people with high risk for T2DM. RESEARCH DESIGN AND METHODS: Patients' age, gender, and risk factors that were obtained from the National Health Information Center's dataset were used to build and train the ML model. To evaluate the developed ML model, an external validation study was conducted in three primary health care centers. A random sample (N = 3400) was selected from the non-diabetic individuals. RESULTS: The results showed the plotted data of sensitivity/100-specificity represented in the Receiver Operating Characteristic (ROC) curve with an AROC value of 0.803, 95% CI: 0.779-0.826. CONCLUSIONS: The current study reveals a new ML model proposed for population-level classification that can be an adequate tool for identifying those at high risk of T2DM or who already have T2DM but have not been diagnosed.
RESUMO
Introduction: The Saudi Ministry of Health launched a central appointment mobile application system (Mawid) that is linked to all primary healthcare (PHC) centres in the kingdom. The application allows patients to evaluate the healthcare services they receive. This study aimed to determine the frequency and nature of the complaints of patients visiting PHC centres through the Mawid application. Method: This cross-sectional study was conducted using 3-month secondary data from the Mawid application. The study included 3134 comments from 380,493 patients who visited 38 PHC centres in Riyadh and responded to the Mawid application evaluation questionnaire. Data were analysed using SPSS version 21. Results: Approximately 59.1% of the patients' comments were negative (patients' complaints); only 19%, positive; 8.40%, mixed; and 13.6%, unrelated. The patients' complaints (n=2969) were obtained from 380,493 patients within 3 months, yielding a complaint rate of 2.6 per 1000 attendances per month. The majority of the complaints (79.3%) were from patients visiting nonspecialised PHC centres. Approximately 59.1% of the complaints fell under the management domain; 23.6%, patient-staff relationship domain; and only 17.2%, clinical domain. Conclusion: Management and interpersonal problems constituted the main patients' complaints in the PHC centres in Saudi Arabia. Therefore, future studies must clarify the reasons contributing to these complaints. Increasing the number of physicians, providing staff training and continuous auditing are mandatory to improve patients' experiences in PHC centres.
RESUMO
Insulin resistance is a hallmark feature of type-2 diabetes mellitus (T2DM). We determined the homeostatic model assessment insulin resistance (HOMA-IR) and evaluated its association with C-peptide, insulin, fasting blood glucose (FBG) and glycated hemoglobin (HbA1c) in T2DM patients and non-diabetic subjects. This study comprised a total of 47 T2DM patients and 38 non-diabetic controls. Venous blood samples from all the subjects were collected and sera were analyzed for FBG, HbA1c, insulin and C-peptide using an autoanalyzer. HOMA-IR was calculated using the following equation: HOMA-IRâ¯=â¯fasting insulin (µU/ml)â¯×â¯fasting glucose (mmol/L)/22.5. There was a significant increase in the levels of FBG and HbA1c in diabetic patients. Although the levels of C-peptide and insulin did not differ significantly between the two groups, a significant increase in HOMA-IR was observed in T2DM patients. Both insulin and C-peptide were significantly correlated with HOMA-IR. In conclusion, C-peptide may serve as a simple and convenient predictor of HOMA-IR.