Research Article
Electronic Health Record Adoption Among Health Information Management and ICT Staff in Tertiary Hospitals in North-East Nigeria: Level and Associated Factors
Issue:
Volume 11, Issue 4, December 2026
Pages:
86-98
Received:
2 October 2026
Accepted:
12 October 2026
Published:
21 October 2026
Abstract: Background: Electronic health records (EHRs) underpin clinical documentation, disease classification and health reporting, but little is known about their adoption in tertiary hospitals in North-East Nigeria or about the views of the staff who manage them. This study assessed the level of EHR adoption among health information management (HIM) officers and information and communication technology (ICT) personnel and identified factors associated with high adoption. Methods: A cross-sectional survey was conducted in three tertiary teaching hospitals in Yola, Bauchi and Maiduguri. Staff were selected by proportionate stratified sampling (target 486, Cochran’s formula). A structured questionnaire measured adoption with 15 five-point items in five domains (availability, functional maturity, compatibility with the International Classification of Diseases, 11th Revision (ICD-11), interoperability, user proficiency); a score above 70% of the maximum was classed as high adoption. Data were analysed with chi-square tests and binary logistic regression in SPSS version 27. Results: Of 486 questionnaires, 475 were analysed (response rate 97.7%): 373 from HIM officers and 102 from ICT personnel. The mean adoption score was 3.77 (standard deviation [SD] 0.84) out of 5, and 74.9% (95% confidence interval [CI] 70.9-78.6) were high adopters (HIM 74.0%, ICT 78.4%, p = 0.359). ICD-11 compatibility was the lowest-scoring domain in both groups. High adoption was reported by 90.6% of respondents in Yola, 67.1% in Bauchi and 73.4% in Maiduguri (p < 0.001). After adjustment, high adoption was less likely in Bauchi (adjusted odds ratio [AOR] 0.18; 95% CI 0.08-0.38) and Maiduguri (AOR 0.23; 0.11-0.48) than in Yola, and more likely among middle-status respondents (AOR 3.19; 1.49-6.81) and those with 11 or more years of experience (AOR 2.94 and 3.01); odds fell with age (AOR 0.96 per year; 0.93-0.99). Professional group was not associated with adoption. Conclusion: Reported EHR adoption is high among HIM and ICT staff but differs markedly between hospitals, and readiness for ICD-11 is the weakest dimension. Hospital-specific support and ICD-11-oriented system configuration should be prioritised; the findings reflect staff perceptions and need confirmation by system audits.
Abstract: Background: Electronic health records (EHRs) underpin clinical documentation, disease classification and health reporting, but little is known about their adoption in tertiary hospitals in North-East Nigeria or about the views of the staff who manage them. This study assessed the level of EHR adoption among health information management (HIM) offic...
Show More
Research Article
A Bagging-Initialised Residual Gradient-Boosting Framework for Predicting Malaria Infection Among Children Under Five Years in Kenya
Issue:
Volume 11, Issue 4, December 2026
Pages:
99-112
Received:
10 October 2026
Accepted:
21 October 2026
Published:
3 November 2026
DOI:
10.11648/j.bsi.20261104.12
Downloads:
Views:
Abstract: Background: Malaria remains an important cause of morbidity and mortality among children younger than five years in Kenya. Although machine-learning models can capture complex relationships in population-based data, bias–variance trade-offs and limited geographical transportability may constrain their performance. This study developed and evaluated a bagging-initialised residual gradient-boosting (BIRGB) framework to predict microscopy-confirmed malaria infection in children under five years in Kenya. Methods: Data were obtained from 3,749 children with microscopy results in the 2020 Kenya Malaria Indicator Survey. The proposed BIRGB framework used leakage-safe, out-of-fold random-forest probabilities, transformed into log-odds, to initialise XGBoost, which fitted regularised additive trees to correct residual prediction errors. Performance was compared with standalone random forest and XGBoost models using held-out test data and leave-one-county-out geographical validation. Sequential forward floating selection identified the optimal predictor subset, and SHapley Additive exPlanations quantified the magnitude and direction of predictor contributions to malaria predictions. Results: BIRGB achieved the best mean internal-test F1 score (88.4%), followed by random forest (68.5%) and XGBoost (56.8%). This advantage was also observed in the leave-one-county-out validation, where BIRGB had a mean F1 score of 90.5% compared to 68.3% for random forest and 55.5% for XGBoost. SHAP analysis identified altitude, household-member age, haemoglobin level, household wealth, mobile-phone ownership, household size, number of children ever born, and number of daughters living elsewhere as influential predictors. Higher altitude, haemoglobin, and wealth generally shifted predictions toward malaria negativity, whereas higher age and household size generally shifted predictions toward malaria positivity. Conclusions: Sequentially initialising XGBoost with random-forest probability estimates improved malaria classification in both internal testing and geographical validation.
Abstract: Background: Malaria remains an important cause of morbidity and mortality among children younger than five years in Kenya. Although machine-learning models can capture complex relationships in population-based data, bias–variance trade-offs and limited geographical transportability may constrain their performance. This study developed and evaluated...
Show More
,
Peter Uduak Augustine,
Queen Desmond Atuzie
