Background: Despite efforts to decrease the burden, vaccine reluctance is increasing worldwide and hindering efforts to control the spread of COVID-19. Therefore, understanding the willingness of a community to receive a COVID-19 vaccine will help to develop and implement effective means of promoting COVID-19 vaccine uptake. Objectives: This study was aimed to assess the willingness of the Ethiopian population to receive the COVID-19 vaccine and its determinant factors. Methods: E-survey was conducted from February 2021 to March 2021. After developing the questionnaire, the template was created on Google Forms and disseminated in public on different social media channels (e.g., Telegram, WhatsApp, Facebook, email, etc.) by using a shareable link. Descriptive statistics were performed. Finally, multivariable logistic regression analysis was done to assess their relationship with socio-demographic factors. Results: In total, 31.4% (n = 372) of respondents were willing to get a vaccine. One-third of respondents, 32.2% (n = 381), reported that COVID-19 vaccines are safe. Almost all 94.9% (n = 1124) responded that health workers should be vaccinated first. Only 21.7% (n = 257) willing to buy the vaccine if it is not provided free. Being female [OR (95% CI):1.85 (1.05– 3.25)], aged less than 25 years old [OR (95% CI): 5.09 (3.41– 7.59)], aged between 26– 30 years [OR (95% CI): 3.57 (2.55– 5.00)], being unmarried[OR (95% CI):1.12 (0.81– 1.55)], urban in residence [OR (95% CI): 1.06 (0.69– 1.62)], private sector worker in occupation [OR (95% CI):0.45 (0.26 – 0.77)], university/college student [OR (95% CI): 0.88 (0.59– 1.32)], not having a health-related job [OR (95% CI): 4.08 (2.57– 6.48)], orthodox [OR (95% CI): 1.16 (0.61– 2.19)], Muslim [OR (95% CI): 0.285 (0.13 – 0.61)], educational status of university/above [OR (95% CI): 4.87 (3.15– 7.53)] have a statistically significant association and were more likely willing to take COVID-19 than their counterparts. Conclusion: This study found that only 31.4% were willing to take the COVID-19 vaccine. Being female, older age, marital status, residence, occupations, not having a health-related job, religion, educational status were statistically significantly associated with willingness to receive the COVID-19 vaccine.

Background: Type 2 diabetes mellitus (T2DM) is associated with a high risk of early mortality and morbidity from hypertension. Even though Ethiopia is Africa’s first country among the top five in the prevalence of DM, there is a paucity of data on hypertension and its associated factors among patients with type 2 diabetes mellitus. Therefore, this study aimed to determine the prevalence and associated factors of hypertension among type 2 diabetes mellitus patients at Debre Tabor General Hospital, 2019. Methods and Materials: An institution-based cross-sectional study was employed on 378 T2DM patients. Data were collected using an interviewer-administered questionnaire and analyzed by Stata 14. A multivariable logistic regression model was used to identify associated factors of hypertension among T2DM patients. Associated factors were declared at p < 0.05. Results: The prevalence of hypertension among T2DM patients was 59.5% (95% CI: 54.5– 64.5). Stage 1 hypertension was the most common (30.95%). The odds of hypertension was higher among age group of 50– 60 years (adjusted odds ratio (AOR)=2.5, 95% confidence interval (CI) (1.27– 4.90)), patients from urban area (AOR = 2.8, 95% CI (1.08– 7.18)), with longer duration of T2DM (AOR =1.16, 95% CI (1.08– 1.25)), with BMI ≥ 25 kg/m² (AOR = 3.2, 95% CI (1.71– 5.96)), with poor glycemic control (AOR = 3.0, 95% CI (1.75– 5.19)), and patients who were current cigarette smokers (AOR = 3.8, 95% CI (1.98– 14.96)). Conclusion: The prevalence of hypertension is high and the majority have poor blood pressure control. Hence, DM care providers and other health sector stakeholders have to work in collaboration to prevent it through designing appropriate strategies especially for those at higher risk of developing hypertension.

Early identification of pregnant women at high risk of developing gestational diabetes (GDM) is desirable as effective lifestyle interventions are available to prevent GDM and to reduce associated adverse outcomes. Personalised probability of developing GDM during pregnancy can be determined using a risk prediction model. These models extend from traditional statistics to machine learning methods; however, accuracy remains sub-optimal. We aimed to compare multiple machine learning algorithms to develop GDM risk prediction models, then to determine the optimal model for predicting GDM. A supervised machine learning predictive analysis was performed on data from routine antenatal care at a large health service network from January 2016 to June 2021. Predictor set 1 were sourced from the existing, internationally validated Monash GDM model: GDM history, body mass index, ethnicity, age, family history of diabetes, and past poor obstetric history. New models with different predictors were developed, considering statistical principles with inclusion of more robust continuous and derivative variables. A randomly selected 80% dataset was used for model development, with 20% for validation. Performance measures, including calibration and discrimination metrics, were assessed. Decision curve analysis was performed. Upon internal validation, the machine learning and logistic regression model's area under the curve (AUC) ranged from 71% to 93% across the different algorithms, with the best being the CatBoost Classifier (CBC). Based on the default cut-off point of 0.32, the performance of CBC on predictor set 4 was: Accuracy (85%), Precision (90%), Recall (78%), F1-score (84%), Sensitivity (81%), Specificity (90%), positive predictive value (92%), negative predictive value (78%), and Brier Score (0.39). In this study, machine learning approaches achieved the best predictive performance over traditional statistical methods, increasing from 75 to 93%. The CatBoost classifier method achieved the best with the model including continuous variables.

The rapid uptake of supervised machine learning (ML) in clinical prediction modelling, particularly for binary outcomes based on tabular data, has sparked debate about its comparative advantage over traditional statistical logistic regression. Although ML has demonstrated superiority in unstructured data domains, its performance gains in structured, tabular clinical datasets remain inconsistent and context dependent. This viewpoint synthesizes recent comparative studies and simulation findings to argue that there is no universal best modelling approach. Model performance depends heavily on dataset characteristics (eg, linearity, sample size, number of candidate predictors, minority class proportion) and data quality (eg, completeness, accuracy). Consequently, we argue that efforts to improve data quality, not model complexity, are more likely to enhance the reliability and real-world utility of clinical prediction models.

Background: This study aimed to assess the level of attitude, practices, and its associated factors towards complications of diabetes mellitus among type 2 diabetes patients.Methods: An institution-based cross-sectional study was done on type 2 diabetes patients coming to the diabetes outpatient department at Addis Zemen District Hospital in Northwest Ethiopia. Interviewer-administered structured questionnaires were used to collect data from 402 patients. Multivariable logistic regression was employed to decide on factors related to practices and attitudes towards diabetes complications. AOR with 95% CI andp-value under 0.05 was considered to select significantly associated variables.Results: Two-thirds of the study participants (65.2% (95% CI: 60.2, 69.4)) had a good attitude level while less than half of study participants (48.8% (95% CI: 44.0, 53.5)) had a good practice on diabetes complications. Educational status of read and write (AOR = 2.32, 95% CI(1.26, 4.27)), primary school (AOR = 4.31, 95% CI(2.06, 9.02)), high school and above (AOR = 2.79, 95% CI (1.41, 5.50)), and urban residence (AOR = 1.80, 95% CI (1.12 2.91)) were significant factors for good attitude while educational status of read and write (AOR = 1.96, 95% CI (1.06, 3.61)), and high school and above (AOR = 2.57, 95% CI (1.32, 5.02)) were associated with diabetes complication practices.Conclusions: A greater proportion of diabetes patients had a relatively good attitude but poor practice towards diabetes complication preventions. Residence was a contributing variable for a good attitude while the level of education was significantly associated with both practice and attitude. The current study suggests the need for structured educational programs about diabetes complications regularly to improve patient’s attitudes and practice.

Objectives: Awareness about complications is important to reduce diabetes related morbidity and mortality. This study aimed to assess awareness of diabetes complications and associated factors among type 2 diabetic patients. Institution based cross sectional study was conducted from April to June, 2019, using simple random sampling technique, and interviewer administered questionnaires.Results: The mean age was 41 ± 1.46 years and 56% were females. Awareness regarding diabetic complications was 48.5% with 95% CI (43.3, 52.7%). Male sex (AOR: 4.67, 95% CI (2.53, 8.61)), age of 31–45 years (AOR: 7.30, 95% CI (3.10, 17.17)), 46–70 years old (AOR: 15.02, 95% CI (6.11, 36.92)), read and write (AOR: 3.79, 95% CI (1.78, 8.06)), primary school (AOR: 9.58, 95% CI (3.26, 28.18)), high school and above (AOR: 7.46, 95% CI (3.02, 18.44)), NGO employee (AOR: 7.24, 95% CI (2.68, 19.53)), having a family history of DM (AOR: 5.55, 95% CI (2.53, 12.20)); income of 1001–1500 (AOR: 3.22, 95% CI (1.28, 8.10)), 1501–2500 (AOR: 11.73, 95% CI (4.32, 31.81)) and > 2500 Ethiopian birr (AOR: 7.18, 95% CI (1.70, 30.28)) ≥ 2500 ETB (AOR: 7.18, 95% CI (1.70, 30.28)) were significantly associated with good awareness. To improve patient’s awareness on DM complications providing health education for type 2 diabetic patients is crucial.