Ibrahim Khalil Ja'Afar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ibrahim Khalil Ja'Afar has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Olalekan Abdulrahman Uthman
Warwick Medical School, University of Warwick, Coventry CV4 7AL, UK
3 shared publications - Abdulaziz Alrubayyi
Warwick Medical School, University of Warwick, Coventry CV4 7AL, UK
2 shared publications - Habibullah Muhammad Kamal
Warwick Medical School, University of Warwick, Gibbet Hill Road, Coventry CV4 7AL, UK
2 shared publications - Mohanad Alhothify
Warwick Medical School, University of Warwick, Gibbet Hill Road, Coventry CV4 7AL, UK
2 shared publications - Reza Fahimi
Warwick Medical School, University of Warwick, Coventry CV4 7AL, UK
2 shared publications - Jason Madan
Warwick Medical School, University of Warwick, Warwick, UK
1 shared publication
Latest Publications
- Open Access
- 11 November 2026
- Published by MDPI AG in Journal of Cardiovascular Development and Disease
- Vol. 13 (11) , 587
A Fast-And-Frugal Tree for Case Finding of Diagnosed Angina Among Adults Not Receiving Cardiovascular Treatment: A UK Biobank Analysis
Background: Adults with angina outside cardiovascular care may miss preventive treatment. We developed a transparent fast-and-frugal tree (FFT) for case finding in adults not receiving cardiovascular treatment. Methods: Cross-sectional analysis of UK Biobank data. The outcome was self-reported doctor-diagnosed angina. FFTs were developed from 39 candidate predictors in 294,238 participants with complete data, in all participants (primary FFT) and in those receiving neither cholesterol-lowering nor blood pressure medication (refined FFT), and compared with machine-learning models and the Pooled Cohort Equations. Results: Overall, 8970 participants (3.0%) had diagnosed angina. The primary FFT selected only these two medications. Among 63,975 untreated test participants, the refined FFT used chest pain, age, family history of heart disease and triglycerides (sensitivity 0.682; specificity 0.789; positive predictive value 0.011). Its first three cues were stable across sensitivity analyses. Logistic regression and classification and regression trees performed similarly to the refined FFT, whereas the Pooled Cohort Equations performed less well (area under the curve 0.655). Conclusions: A four-cue FFT identified two-thirds of untreated adults with diagnosed angina while flagging about one in five, and may serve as a first-stage filter for clinical assessment in primary and community care. The tool requires external and prospective validation before clinical application.
- 11 November 2026
- Published by MDPI AG in Journal of Cardiovascular Development and Disease
- Vol. 13 (11) , 587
Open AccessA Fast-And-Frugal Tree for Case Finding of Diagnosed Angina Among Adults Not Receiving Cardiovascular Treatment: A UK Biobank Analysis
Background: Adults with angina outside cardiovascular care may miss preventive treatment. We developed a transparent fast-and-frugal tree (FFT) for case finding in adults not receiving cardiovascular treatment. Methods: Cross-sectional analysis of UK Biobank data. The outcome was self-reported doctor-diagnosed angina. FFTs were developed from 39 candidate predictors in 294,238 participants with complete data, in all participants (primary FFT) and in those receiving neither cholesterol-lowering nor blood pressure medication (refined FFT), and compared with machine-learning models and the Pooled Cohort Equations. Results: Overall, 8970 participants (3.0%) had diagnosed angina. The primary FFT selected only these two medications. Among 63,975 untreated test participants, the refined FFT used chest pain, age, family history of heart disease and triglycerides (sensitivity 0.682; specificity 0.789; positive predictive value 0.011). Its first three cues were stable across sensitivity analyses. Logistic regression and classification and regression trees performed similarly to the refined FFT, whereas the Pooled Cohort Equations performed less well (area under the curve 0.655). Conclusions: A four-cue FFT identified two-thirds of untreated adults with diagnosed angina while flagging about one in five, and may serve as a first-stage filter for clinical assessment in primary and community care. The tool requires external and prospective validation before clinical application.
- Open Access
- 7 August 2026
- Published by MDPI AG in Diabetology
- Vol. 7 (8) , 151
Non-Invasive Sociodemographic Cues for Type 2 Diabetes Risk Stratification in South Africa
Background/Objectives: Type 2 diabetes mellitus (T2DM) is a growing burden in low- and middle-income countries, and non-invasive risk tools have been proposed where laboratory screening is not feasible. Fast-and-frugal decision trees (FFDTs) are transparent, non-compensatory rules that make sensitivity–specificity trade-offs explicit. We asked how far five routinely collected sociodemographic cues can go for classifying self-reported diabetes status and benchmarked FFDTs against the simplest possible alternatives. Methods: A cross-sectional secondary analysis of the 2016 South Africa Demographic and Health Survey Adult Health recode (N = 10,292; 459 self-reported cases, 4.46%) was carried out. Five binary cues were derived: age category, household wealth, employment, education and sex. Data were split 70/30 into development and a locked hold-out set. Three purpose-specific FFDTs were selected by 5 × 10-fold cross-validation within the development data only, frozen, and then evaluated once on the hold-out set. Comparators were a pre-specified age-only rule and logistic regression using the same five predictors at a development-derived Youden threshold. We report survey-weighted estimates, internal–external cross-validation across nine provinces, external validation in 12 further DHS, subgroup performance, and a log–log analysis of error against training sample size. Results: On the hold-out set the balanced screening FFDT achieved sensitivity 0.920 (95% CI 0.862–0.959), specificity 0.585 (0.567–0.602) and balanced accuracy 0.752 (0.727–0.776). The pre-specified age-only rule achieved balanced accuracy 0.751 (0.724–0.775), while logistic regression at the development-derived Youden threshold achieved 0.766 (0.735–0.797). Across 50 independent splits, the case-finding FFDT was arithmetically identical to the age-only rule in every split; the balanced FFDT exceeded it by a median of 0.001 (95% range −0.004 to +0.025); the referral-minimisation FFDT was worse by a median of 0.124. Performance was stable across provinces (balanced accuracy 0.731–0.801) but degraded across countries (0.508–0.724), with referral rate ranging from 0.225 to 0.806. Error scaled with training size as beta = −0.044 (95% CI −0.063 to −0.025). Conclusions: Transparent decision trees built from non-invasive sociodemographic cues classify self-reported diabetes status no better than a single question about age, do not transport reliably across countries, and are unlikely to be materially improved by simply increasing the training sample size. Their value lies in auditability rather than accuracy. Progress in low-burden risk stratification for T2DM in these settings will require cues that carry a biological rather than health system signal.
- 7 August 2026
- Published by MDPI AG in Diabetology
- Vol. 7 (8) , 151
Open AccessNon-Invasive Sociodemographic Cues for Type 2 Diabetes Risk Stratification in South Africa
Background/Objectives: Type 2 diabetes mellitus (T2DM) is a growing burden in low- and middle-income countries, and non-invasive risk tools have been proposed where laboratory screening is not feasible. Fast-and-frugal decision trees (FFDTs) are transparent, non-compensatory rules that make sensitivity–specificity trade-offs explicit. We asked how far five routinely collected sociodemographic cues can go for classifying self-reported diabetes status and benchmarked FFDTs against the simplest possible alternatives. Methods: A cross-sectional secondary analysis of the 2016 South Africa Demographic and Health Survey Adult Health recode (N = 10,292; 459 self-reported cases, 4.46%) was carried out. Five binary cues were derived: age category, household wealth, employment, education and sex. Data were split 70/30 into development and a locked hold-out set. Three purpose-specific FFDTs were selected by 5 × 10-fold cross-validation within the development data only, frozen, and then evaluated once on the hold-out set. Comparators were a pre-specified age-only rule and logistic regression using the same five predictors at a development-derived Youden threshold. We report survey-weighted estimates, internal–external cross-validation across nine provinces, external validation in 12 further DHS, subgroup performance, and a log–log analysis of error against training sample size. Results: On the hold-out set the balanced screening FFDT achieved sensitivity 0.920 (95% CI 0.862–0.959), specificity 0.585 (0.567–0.602) and balanced accuracy 0.752 (0.727–0.776). The pre-specified age-only rule achieved balanced accuracy 0.751 (0.724–0.775), while logistic regression at the development-derived Youden threshold achieved 0.766 (0.735–0.797). Across 50 independent splits, the case-finding FFDT was arithmetically identical to the age-only rule in every split; the balanced FFDT exceeded it by a median of 0.001 (95% range −0.004 to +0.025); the referral-minimisation FFDT was worse by a median of 0.124. Performance was stable across provinces (balanced accuracy 0.731–0.801) but degraded across countries (0.508–0.724), with referral rate ranging from 0.225 to 0.806. Error scaled with training size as beta = −0.044 (95% CI −0.063 to −0.025). Conclusions: Transparent decision trees built from non-invasive sociodemographic cues classify self-reported diabetes status no better than a single question about age, do not transport reliably across countries, and are unlikely to be materially improved by simply increasing the training sample size. Their value lies in auditability rather than accuracy. Progress in low-burden risk stratification for T2DM in these settings will require cues that carry a biological rather than health system signal.
- Open Access
- 29 September 2025
- Published by Wiley in Public Health Challenges
- Vol. 4 (4)
Predicting Childhood Anaemia in Nigeria: A Machine Learning Approach to Uncover Key Risk Factors
Background: Childhood anaemia is a major public health challenge in Nigeria, with high prevalence among children under five. This study identifies key determinants and develops a predictive model using advanced machine learning technique. Methods: A total of 13,136 children aged 6–59 months from the 2018 National Demographic and Health Survey (NDHS) were analysed. Sixteen machine learning algorithms were evaluated on the basis of their ability to predict childhood anaemia using a wide range of individual, community and environmental factors. The Extra Trees (ET) classifier, demonstrating the highest predictive performance, was used to identify the top 10 predictors of childhood anaemia. A fairness and demographic bias assessment framework was incorporated to evaluate the model's performance across different regions, wealth index categories, ethnic groups and gender. Results: The ET classifier achieved an area under the curve (AUC) of 0.8319, an accuracy of 0.7565 and a recall of 0.7565. The top 10 predictors identified by the model included the number of under‐five children in the household, birth order, child age, media access, maternal health‐seeking behaviour, child gender, proximity to water, money problems, day land surface temperature and all population count. The demographic bias assessment revealed variations in model performance across different subgroups, with the lowest AUCs observed in the north‐east region (0.79), the poorest wealth index category (0.80) and the Hausa/Fulani ethnic group (0.81). Conclusion: This study shows that machine learning can accurately predict childhood anaemia in Nigeria and identify key risk factors, supporting targeted interventions. Future work should focus on refining models and integrating AI‐based interventions to reduce anaemia.
- 29 September 2025
- Published by Wiley in Public Health Challenges
- Vol. 4 (4)
Open AccessPredicting Childhood Anaemia in Nigeria: A Machine Learning Approach to Uncover Key Risk Factors
Background: Childhood anaemia is a major public health challenge in Nigeria, with high prevalence among children under five. This study identifies key determinants and develops a predictive model using advanced machine learning technique. Methods: A total of 13,136 children aged 6–59 months from the 2018 National Demographic and Health Survey (NDHS) were analysed. Sixteen machine learning algorithms were evaluated on the basis of their ability to predict childhood anaemia using a wide range of individual, community and environmental factors. The Extra Trees (ET) classifier, demonstrating the highest predictive performance, was used to identify the top 10 predictors of childhood anaemia. A fairness and demographic bias assessment framework was incorporated to evaluate the model's performance across different regions, wealth index categories, ethnic groups and gender. Results: The ET classifier achieved an area under the curve (AUC) of 0.8319, an accuracy of 0.7565 and a recall of 0.7565. The top 10 predictors identified by the model included the number of under‐five children in the household, birth order, child age, media access, maternal health‐seeking behaviour, child gender, proximity to water, money problems, day land surface temperature and all population count. The demographic bias assessment revealed variations in model performance across different subgroups, with the lowest AUCs observed in the north‐east region (0.79), the poorest wealth index category (0.80) and the Hausa/Fulani ethnic group (0.81). Conclusion: This study shows that machine learning can accurately predict childhood anaemia in Nigeria and identify key risk factors, supporting targeted interventions. Future work should focus on refining models and integrating AI‐based interventions to reduce anaemia.
- Open Access
- 23 May 2025
- Published by Cambridge University Press (CUP) in Cambridge Prisms: Global Mental Health
- Vol. 12, e50
Addressing the psychological impact of climate-induced disasters on young people in Africa: Challenges and pathways forward
Climate change is exacerbating the frequency and severity of disasters across Africa, with profound psychological consequences for young people. This paper examines the mental health impacts of climate-related events like droughts, floods and extreme weather on African youth. It explores how climate stresses compound existing societal issues, affecting young people’s well-being. Studies highlighted indicate events strongly associated with negative emotions, anxiety, post-traumatic stress disorder (PTSD) and depression among youth. Vulnerabilities are due to disrupted community contexts and limited support systems. Challenges in providing adequate care are also reviewed, with African health systems grappling with a shortage of professionals and inadequate youth-focused care. This article proposes solutions centred on integrated disaster response, community resilience programmes and specialised youth services. Recommendations involve prioritising mental health education, establishing accessible services and collaborating with local partners. The overall aim is to comprehensively address African youth mental health needs in climate-changing contexts through holistic multi-stakeholder approaches, building coping skills and promoting wellness.
- 23 May 2025
- Published by Cambridge University Press (CUP) in Cambridge Prisms: Global Mental Health
- Vol. 12, e50
Open AccessAddressing the psychological impact of climate-induced disasters on young people in Africa: Challenges and pathways forward
Climate change is exacerbating the frequency and severity of disasters across Africa, with profound psychological consequences for young people. This paper examines the mental health impacts of climate-related events like droughts, floods and extreme weather on African youth. It explores how climate stresses compound existing societal issues, affecting young people’s well-being. Studies highlighted indicate events strongly associated with negative emotions, anxiety, post-traumatic stress disorder (PTSD) and depression among youth. Vulnerabilities are due to disrupted community contexts and limited support systems. Challenges in providing adequate care are also reviewed, with African health systems grappling with a shortage of professionals and inadequate youth-focused care. This article proposes solutions centred on integrated disaster response, community resilience programmes and specialised youth services. Recommendations involve prioritising mental health education, establishing accessible services and collaborating with local partners. The overall aim is to comprehensively address African youth mental health needs in climate-changing contexts through holistic multi-stakeholder approaches, building coping skills and promoting wellness.
- Open Access
- 18 January 2025
- Published by Wiley
Predicting Childhood Anaemia in Nigeria: A Machine Learning Approach to Uncover Key Risk Factors
Background : Childhood anaemia remains a significant public health challenge, particularly in low- and middle-income countries like Nigeria, where the prevalence among children under five is alarmingly high. This study aims to identify the key determinants of childhood anaemia, develop an accurate predictive model using advanced machine learning techniques, and assess the model’s performance across different demographic groups to ensure equitable risk prediction. Methods : Data from 13,136 children aged 6-59 months from the 2018 National Demographic Health Survey (NDHS) were analysed. Sixteen machine learning algorithms were evaluated based on their ability to predict childhood anaemia using a wide range of individual, community, and environmental factors. The Extra Trees (ET) classifier, demonstrating the highest predictive performance, was used to identify the top ten predictors of childhood anaemia. A fairness and demographic bias assessment framework was incorporated to evaluate the model’s performance across different regions, wealth index categories, ethnic groups, and gender. Results : The ET classifier outperformed all other algorithms, achieving an area under the curve (AUC) of 0.8319, accuracy of 0.7565, and a recall of 0.7565. The top ten predictors identified by the ET model included the number of under-five children in the household, birth order, child age, media access, maternal health-seeking behaviour, child gender, proximity to water, money problems, day land surface temperature, and all population count. The demographic bias assessment revealed variations in model performance across different subgroups, with the lowest AUCs observed in the North-East region (0.79), the poorest wealth index category (0.80), and the Hausa/Fulani ethnic group (0.81). Conclusion : This study demonstrates the potential of machine learning techniques to accurately predict childhood anaemia in Nigeria and identify key risk factors that inform targeted interventions. Future research should focus on refining the predictive model, exploring integrated interventions, and deploying AI-based tools to combat childhood anaemia in Nigeria and beyond.
- 18 January 2025
- Published by Wiley
Open AccessPredicting Childhood Anaemia in Nigeria: A Machine Learning Approach to Uncover Key Risk Factors
Background : Childhood anaemia remains a significant public health challenge, particularly in low- and middle-income countries like Nigeria, where the prevalence among children under five is alarmingly high. This study aims to identify the key determinants of childhood anaemia, develop an accurate predictive model using advanced machine learning techniques, and assess the model’s performance across different demographic groups to ensure equitable risk prediction. Methods : Data from 13,136 children aged 6-59 months from the 2018 National Demographic Health Survey (NDHS) were analysed. Sixteen machine learning algorithms were evaluated based on their ability to predict childhood anaemia using a wide range of individual, community, and environmental factors. The Extra Trees (ET) classifier, demonstrating the highest predictive performance, was used to identify the top ten predictors of childhood anaemia. A fairness and demographic bias assessment framework was incorporated to evaluate the model’s performance across different regions, wealth index categories, ethnic groups, and gender. Results : The ET classifier outperformed all other algorithms, achieving an area under the curve (AUC) of 0.8319, accuracy of 0.7565, and a recall of 0.7565. The top ten predictors identified by the ET model included the number of under-five children in the household, birth order, child age, media access, maternal health-seeking behaviour, child gender, proximity to water, money problems, day land surface temperature, and all population count. The demographic bias assessment revealed variations in model performance across different subgroups, with the lowest AUCs observed in the North-East region (0.79), the poorest wealth index category (0.80), and the Hausa/Fulani ethnic group (0.81). Conclusion : This study demonstrates the potential of machine learning techniques to accurately predict childhood anaemia in Nigeria and identify key risk factors that inform targeted interventions. Future research should focus on refining the predictive model, exploring integrated interventions, and deploying AI-based tools to combat childhood anaemia in Nigeria and beyond.
- Open Access
- 29 August 2024
- Published by Wiley
FACTORS THAT LED TO THE STATE BEING UNSUCCESSFUL IN ADDRESSING THE RISK OF COVID-19
The COVID-19 pandemic, originating in Wuhan, China, in late 2019, swiftly escalated into a global health crisis by March 2020, severely impacting nations worldwide. The World Health Organization (WHO) faced criticism for delayed responses and underreporting, particularly from China, compounded by geopolitical tensions and funding shortages. This constrained the WHO’s ability to effectively manage the pandemic. Additionally, national responses varied significantly, influencing outcomes. Key factors contributing to the state’s failure to address COVID-19 effectively include delayed government actions, governance and leadership failures, poor communication, and inadequate economic support. Early and stringent measures, as demonstrated by New Zealand, resulted in better outcomes compared to countries like Italy and the United States, which experienced severe outbreaks due to delayed responses and inconsistent communication. Governance issues, such as the lack of cohesive strategies and leadership coordination, were evident in countries like Indonesia and Japan, leading to inconsistent policy implementation and poor outcomes. Economic support measures played a critical role in public compliance and economic stability. Countries like the UK provided substantial financial aid, yet disparities in support led to ongoing struggles for low-income families. In contrast, countries in the Global South faced significant challenges in providing adequate economic support, exacerbating existing inequalities and complicating pandemic management. Recommendations for future responses include improving targeted health interventions, enhancing community engagement in policy-making, increasing international financial and technical support, and revising global health treaties to ensure equitable resource access. These steps are essential to build more resilient health systems capable of effectively managing future global health crises.
- 29 August 2024
- Published by Wiley
Open AccessFACTORS THAT LED TO THE STATE BEING UNSUCCESSFUL IN ADDRESSING THE RISK OF COVID-19
The COVID-19 pandemic, originating in Wuhan, China, in late 2019, swiftly escalated into a global health crisis by March 2020, severely impacting nations worldwide. The World Health Organization (WHO) faced criticism for delayed responses and underreporting, particularly from China, compounded by geopolitical tensions and funding shortages. This constrained the WHO’s ability to effectively manage the pandemic. Additionally, national responses varied significantly, influencing outcomes. Key factors contributing to the state’s failure to address COVID-19 effectively include delayed government actions, governance and leadership failures, poor communication, and inadequate economic support. Early and stringent measures, as demonstrated by New Zealand, resulted in better outcomes compared to countries like Italy and the United States, which experienced severe outbreaks due to delayed responses and inconsistent communication. Governance issues, such as the lack of cohesive strategies and leadership coordination, were evident in countries like Indonesia and Japan, leading to inconsistent policy implementation and poor outcomes. Economic support measures played a critical role in public compliance and economic stability. Countries like the UK provided substantial financial aid, yet disparities in support led to ongoing struggles for low-income families. In contrast, countries in the Global South faced significant challenges in providing adequate economic support, exacerbating existing inequalities and complicating pandemic management. Recommendations for future responses include improving targeted health interventions, enhancing community engagement in policy-making, increasing international financial and technical support, and revising global health treaties to ensure equitable resource access. These steps are essential to build more resilient health systems capable of effectively managing future global health crises.