Nebebe Demis Baykemagn

Nebebe Demis Baykemagn

Auto-generated profile, based on publicly available information

Nebebe Demis Baykemagn

Department of Health Informatics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 January 2025 in JMIR Public Health and Surveillance
Verified
Journal Article
Open access
NBNebebe Demis Baykemagn
Nebebe Demis Baykemagn
MAMekuriaw Aweke
Mekuriaw Aweke
AMAmare Mesfin
Amare Mesfin
LBLemlem Daniel Baffa
Lemlem Daniel Baffa
MAMuluken Chanie Agimas
Muluken Chanie Agimas
GAGebrie Getu Alemu
Gebrie Getu Alemu
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).

6 October 2025 in Malaria Journal
Verified
Journal Article
Open access
PDF file
NBNebebe Demis Baykemagn
Nebebe Demis Baykemagn
TTTesfahun Zemene Tafere
Tesfahun Zemene Tafere
GTGetachew Teshale
Getachew Teshale
AAAndualem Yalew Aschalew
Andualem Yalew Aschalew
MJMelak Jejaw
Melak Jejaw
JKJenberu Mekurianew Kelkay
Jenberu Mekurianew Kelkay
Malaria remains a major public health challenge, particularly in sub-Saharan Africa, where women of reproductive age are especially vulnerable during pregnancy and childbirth. To identify key predictors and improve predictive accuracy, machine learning algorithms such as Random Forest were applied, along with SHAP analysis, to a large multi-country DHS dataset, with class imbalance addressed using Tomek Links and Random Over-Sampling. This study employed a weighted dataset of 153,015 participants from the Demographic and Health Survey (DHS) conducted across ten sub-Saharan African countries. Data preprocessing and analysis were carried out using STATA version 17 and Python 3.10. Feature scaling was applied to standardize numerical variables, ensuring uniform weighting across predictors and improving model stability. An 80:20 data split ratio was applied, and class imbalance was addressed using Tomek Links combined with Random Over-Sampling. Eight models were selected and trained using both balanced and unbalanced datasets. The model performance was evaluated using metrics such as ROC-AUC, accuracy, recall, F1 score, and precision. The Random Forest algorithm performed best in this study, with an accuracy of 83%, an F1 score of 82%, recall of 80%, precision of 84%, and an AUC of 88%. Fifty-five percent of participants used mosquito nets. The SHAP analysis showed that Age above 34, being employed, frequent social media use, higher education, institutional deliveries, and female-headed households increased bed net use, while fewer ANC visits and being divorced decreased its use. Age above 34, being employed, frequent social media use, higher education, institutional deliveries, and female-headed households increased bed net use, while fewer ANC visits and being divorced decreased its use. Strengthening social media use for health information, promoting women's education, encouraging institutional delivery, motivate for antenatal care services, and providing support to socially and economically vulnerable women are essential strategies to enhance mosquito net utilization.

15 April 2026 in PLOS ONE
Verified
Journal Article
Open access
MAMekuriaw Aweke
Mekuriaw Aweke
HAHabtamu Wagnew Abuhay
Habtamu Wagnew Abuhay
MLMiteku Andualem Limenih
Miteku Andualem Limenih
AAAnas Ali Alhur
Anas Ali Alhur
NBNebebe Demis Baykemagn
Nebebe Demis Baykemagn
TYTirualem Zeleke Yehuala
Tirualem Zeleke Yehuala
Introduction: Overweight and obesity during early life increase the risk of premature morbidity and mortality. Adolescent obesity raises the likelihood of developing cardiovascular risk factors, including prediabetes, type 2 diabetes, dyslipidemia, hypertension, liver disease, and metabolic syndrome. Sedentary lifestyles and unhealthy diets are major contributors, with one of the fastest-growing unhealthy eating patterns being the consumption of ultra-processed foods (UPFs). No systematic review and meta-analysis has specifically examined the association between UPF consumption and overweight/obesity in adolescents. Objective: To systematically review and conduct a meta-analysis of available evidence on the association between UPF consumption and overweight or obesity among adolescents. Methods: We searched PubMed, ScienceDirect, HINARI, Google, and Google Scholar for primary studies reporting UPF consumption and overweight/obesity outcomes in adolescents, without restrictions on language or study period. Study quality was assessed using the Newcastle–Ottawa Scale. Heterogeneity was evaluated using Cochrane’s Q test and the I² statistic. Publication bias and small-study effects were assessed using Egger’s regression test (p < 0.05). A random-effects model estimated pooled associations. Results: Twenty-three studies involving 155,000 adolescents were included. Adolescents with higher UPF consumption had 63% greater odds of overweight or obesity compared with those with lower intake (OR = 1.63; 95% CI: 1.36–1.95). Conclusion: High UPF consumption is associated with an increased risk of overweight and obesity among adolescents. Public health strategies targeting reduced UPF intake and promotion of healthier diets should be prioritized to prevent adolescent overweight/obesity and associated health risks.

22 November 2024 in BMC Health Services Research
Verified
Journal Article
Open access
PDF file
EZEhite Melaku Zewdu
Ehite Melaku Zewdu
ADAdina Demessie
Adina Demessie
ANAraya Mesfin Nigatu
Araya Mesfin Nigatu
NBNebebe Demis Baykemagn
Nebebe Demis Baykemagn
Reminders via digital technology offer a novel and efficient means to address medication forgetfulness, as they are easily accessible and user-friendly for patients. In particular mobile text message reminders are more suitable for chronic patients, as they require few technical skills, can operate without internet connectivity, and are less expensive than other technologies. This study aimed to assess the intention to use mobile text message reminders for medication adherence among hypertensive patients at the Gondar City health facilities. A facility-based cross-sectional study was conducted. A simple random sampling method was used to select 423 hypertensive patients. Data was collected from April 1 to May 15, 2023. Data was collected using Kobo Toolbox, and the collected data was exported to MS Excel. Subsequently, the data was imported and analyzed using the SPSS version 20. Binary and multivariable logistic regression analysis was employed to assess factors associated with the outcome variable. The finding indicates that 64.5% of the patients have an Intention to use mobile text message reminders for medication adherence. Perceived usefulness (AOR = 2.53: 95%CI: 1.41, 4.52), perceived ease of use (AOR = 3.28: 95% CI: 1.81, 5.95), forgetting to take medication (AOR = 2.20: 95%CI: 1.38, 3.50) and patient holds their mobile phone always (AOR = 1.96: 95%CI: 1.04, 3.68) were associated factors with outcome variable. Forget taking medication, the patient holds their mobile phone always, Perceived ease of use and Perceived usefulness were significantly associated with the outcome variable. We recommend designing and implementing user-friendly text message reminder systems and educating hypertensive patients about the system’s benefits.

1 January 2024 in Digital Health
Verified
Journal Article
Open access
AMAbraraw Gebre Mesele
Abraraw Gebre Mesele
ABAbreham Yeneneh Birhanu
Abreham Yeneneh Birhanu
ASAtsede Mazengia Shiferaw
Atsede Mazengia Shiferaw
NBNebebe Demis Baykemagn
Nebebe Demis Baykemagn
Background: Globally, health information systems have been improved by District Health Information System Version 2 (DHIS2), which promotes consistency and integrity in collecting data, processing, and utilization. This success has been attributed to its user-friendly interface and incorporation of advanced data analysis and validation features. Objective: This study aimed to assess DHIS2 data utilization among health professionals working at private hospitals in the Amara region. Methods: An Institution-based cross-sectional study design was conducted from 9 May to 30 June 2022. A simple random sampling technique was used to select participants, with a total of 395 health professionals participating. Data was collected using a self-administered paper-based questionnaire. Data entry was performed using the Kobo Collect tool, and data analysis was conducted using STATA version 14.0. Bivariable and multivariable logistic regression analyses were used and p < .05 with a 95% CI was considered to measure statistically significant variables. Result: Out of 395 participants, about 37.72% of the participants had good DHIS2 data utilization. Had good data analysis skills (adjusted odds ratio (AOR) = 6.5, 95% CI [3.1–13.8]), regular supportive supervision and feedback (AOR = 5.2, 95% CI [2.8–9.5]), monthly salary > 5000 ETB (AOR = 2.0, 95% CI [1.1–3.7]), ease of use (AOR = 5.4, 95% CI [2.8–10.2]), and district health information system training (AOR = 4.2, 95% CI [2.2–7.3]) were enabling factors for utilization of DHIS2 data. Conclusion: Private healthcare providers had limited utilization of DHIS2 data. It is highly recommended to provide DHIS2 training, supervision, and feedback focused on private health facilities. Additionally, enhancing data analysis skills and prioritizing ease of use are crucial to improving DHIS2 data utilization.

1 January 2024 in Digital Health
Verified
Journal Article
Open access
NBNebebe Demis Baykemagn
Nebebe Demis Baykemagn
ANAraya Mesfin Nigatu
Araya Mesfin Nigatu
BFBerhanu Fikadie
Berhanu Fikadie
BTBinyam Tilahun
Binyam Tilahun
Background: Globally, healthcare providers have faced significant difficulties in adhering to clinical guidelines. Applying mobile health systems is a crucial strategy for enhancing the dissemination and accessibility of clinical guidelines. This study aimed to assess the acceptance of mobile app-based primary healthcare clinical guidelines and associated factors among health professionals in central Gondar health centers. Methods: A cross-sectional study supplemented with qualitative data was conducted on 403 health workers. Data were collected using a pre-test structured printed questionnaire and entered into EpiData version 4.6. Analysis was conducted using Stata version 14, which included bivariable and multivariable logistic regression analyses. For qualitative data, thematic analysis was conducted using Open Code v.4.2. Results: Approximately 28% (95% confidence interval (CI): 23%–32%) of health professionals had utilized mobile app-based clinical guidelines. The availability of IT support (adjusted odds ratio (AOR) = 3.51, 95% CI: 1.82–6.78), good knowledge (AOR = 3.46, 95% CI: 1.5–6.78), perceived usefulness (AOR = 2.21, 95% CI: 1.00–4.99), m-Health app exposure (AOR = 2.34, 95% CI: 1.2–4.50), and ease of use (AOR = 5.77, 95% CI: 2.50–13.32) were significantly associated with the acceptance of the mobile app-based clinical guideline. In qualitative data, lack of training and supervision and access to smartphones were barriers to acceptance of the mobile app-based clinical guideline. Conclusion: In summary, acceptance of the app is currently low. However, it can be increased by improving the availability of IT support in the workplace, offering training and supervision, and enhancing access to smartphones.