VOVictor Opoku‐Yamoah

Victor Opoku‐Yamoah

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Victor Opoku‐Yamoah has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Machine Learning Prediction of Incident Hypertension in Australian Men: Integrating Survey, Pharmaceutical and Healthcare Utilisation Data From the Ten to Men Cohort

    by Ebenezer Afrifa-Yamoah, Emmanuel Peprah-Yamoah, Victor Opoku-Yamoah, Eric Adua

    Background: Hypertension is a leading modifiable contributor to cardiovascular disease. We developed and evaluated machine learning models to predict incident hypertension in Australian men using baseline survey data linked to pharmaceutical (PBS) and healthcare utilisation (MBS) administrative records from the Ten to Men cohort. Methods: Among 13,519 men free of hypertension at baseline (2014), incident hypertension over 10 years was ascertained from PBS antihypertensive dispensing. Twenty‐five baseline features spanning sociodemographic, anthropometric, lifestyle, clinical and administrative domains were used to train logistic regression, random forest, gradient boosting and XGBoost models, evaluated by five‐fold cross‐validation with out‐of‐fold prediction. Discrimination, calibration and threshold‐based operating characteristics were reported with 95% confidence intervals. Results: Incident hypertension occurred in 1310 men (9.7%). All algorithms achieved comparable discrimination (AUROC ≈ 0.77; XGBoost 0.771, 95% CI: 0.756–0.784), with no material advantage for flexible tree‐based methods over regularised logistic regression. Age, administrative markers of healthcare engagement and BMI were the leading predictors, and a parsimonious six‐variable model recovered almost all the discrimination of the full model. The model showed high negative predictive and low positive predictive values across decision thresholds, consistent with the 9.7% event rate. Incorporating measured blood pressure history from intervening waves increased apparent discrimination, but this gain was attributable to information contemporaneous with the outcome and is reported only as a concurrent surveillance benchmark. Conclusions: Routinely collected survey and administrative data can identify Australian men at low risk of incident hypertension with high negative predictive value, supporting population‐level risk stratification rather than individual diagnosis. Predictive performance was driven by feature availability and quality rather than algorithm choice.

  • Open Access

    Protocol for an Integrative Meta‐Analysis of the Application of Machine Learning Algorithms in the Prediction of Chronic Disease Risks and Outcomes

    by Ebenezer Afrifa‐Yamoah, Emmanuel Peprah‐Yamoah, Enoch Odame Anto, Victor Opoku‐Yamoah, Eric Adua

    Background: Precise risk prediction of chronic diseases is essential for effective preventive care and management. Machine learning (ML) is a promising avenue to enhance chronic disease risk prediction; however, a comprehensive assessment of ML performance across various chronic diseases, populations, and health settings is needed.Methods: This meta‐analysis aims to synthesize evidence on the performance of ML techniques for predicting the risks and outcomes of chronic diseases. A literature search was conducted through PubMed, Web of Science, Scopus, Science Direct, Medline, and Embase. Studies applying ML techniques to predict chronic disease risks or outcomes and reporting performance metrics were included. Two reviewers independently screened studies, extracted data, and assessed the risk of bias. Random‐effects meta‐analysis, subgroup analyses, and meta‐regression were performed to estimate pooled performance and explore heterogeneity.Discussion: This meta‐analysis provides a comprehensive evaluation of the performance of ML techniques in predicting the risks and consequences of chronic diseases. We reported the pooled estimates of performance metrics, such as the area under the receiver operating characteristic curve (AUC‐ROC), sensitivity, specificity, and F1 score, for each chronic disease. Subgroup analyses and meta‐regression identified factors that influence the performance of ML models, such as the ML algorithm, sample size, and data type. This meta‐analysis synthesized evidence on ML techniques for chronic disease risk prediction, guiding the development of robust and generalizable ML‐based tools. By identifying best practices and addressing challenges, this work advances predictive analytics in healthcare, facilitates translation into clinical practice, and ultimately improve patient outcomes.PROSPERO Protocol Registration: CRD42024566680.


  • Open Access

    Aging and Color Vision: A Model Using the Farnsworth‐MUNSELL 100‐Hue Test

    by Victor Opoku‐Yamoah, Stephen J. Dain, Jeffery K. Hovis

    Introduction: This study examined the theoretical changes in the FM100 Hue scores induced by age‐related changes in the ocular media transmittance. These changes were analyzed with and without a von Kries‐type chromatic adaptation to determine the role of this adaptation process on age‐related changes in hue discrimination.Methods: We calculated the CIECAM02 chromaticity coordinates of the FM100 Hue caps for 32‐ and 74‐year‐old ideal observers. The chromaticity coordinates were calculated using the CIE D65 illuminant, the individual caps' spectral reflectances, and the CIE 1931 2° color matching functions. We modified the spectral distribution of the D65 light source using the model of Pokorny et al. and the van de Kraats‐van Norren model of media transmittance to account for the age‐related changes by 74 years. We accounted for the decrease in retinal illuminance due to pupil miosis and ocular media spectral transmittance in the old observers. The predicted ordering of the FM100 Hue caps was based on the minimum color differences (ΔE) between nearby caps, calculated using the CIECAM02 model.Results: Reported outcomes were obtained for specific model parameters: adapting luminance (31.9 cd/m2); illuminance (500 lx); stimulus diameter (20°); surface reflectance 20%; CIE illuminant D65; CIE 1931 2° color‐matching functions/XYZ‐values; pupil size (4.35 mm for young observer and 3.46 mm for old observer models). The total error score (TES) increased from 8 for the 32‐year‐old observer to 12 for both 74‐year‐old observer models when complete and partial adaptation factors were applied. The increase in TES for the 74‐year‐old observer models was in the blue–blue‐purple band, which was along the red‐green axis. Without any adaptation for the old observer models, the error scores increased further. The increase was in the red–green score for the van de Kraats–van Norren model, whereas the increase for the Pokorny et al. model was in both the red–green and blue–yellow error scores. Overall, the mean color differences for the old observer models decreased uniformly under complete and partial adaptation.Conclusion: The predicted effect of age‐related changes in media transmittances on the FM100 Hue test showed an increase in the TES; however, the increase was primarily due to an increase in the red–green error score. This disagrees with the psychophysical data, which show a greater increase in the blue–yellow error score, thus suggesting the presence of age‐related neural changes. The two models for age‐related changes in media transmittance produced similar results under complete chromatic adaptation.


  • Open Access

    Predictive modelling of metabolic syndrome in Ghanaian diabetic patients: an ensemble machine learning approach

    by Emmanuel Acheampong, Eric Adua, Christian Obirikorang, Enoch Odame Anto, Emmanuel Peprah-Yamoah, Yaa Obirikorang, Evans Adu Asamoah, Victor Opoku-Yamoah, Michael Nyantakyi, John Taylor, et al.

    Objectives: The burgeoning prevalence of cardiometabolic disorders, including type 2 diabetes mellitus (T2DM) and metabolic syndrome (MetS) within Africa is concerning. Machine learning (ML) techniques offer a unique opportunity to leverage data-driven insights and construct predictive models for MetS risk, thereby enhancing the implementation of personalised prevention strategies. In this work, we employed ML techniques to develop predictive models for pre-MetS and MetS among diabetic patients. Methods: This multi-centre cross-sectional study comprised of 919 T2DM patients. Age, gender, novel anthropometric indices along with biochemical measures were analysed using BORUTA feature selection and an ensemble majority voting classification model, which included logistic regression, k-nearest neighbour, Gaussian Naive Bayes, Gradient boosting classification, and support vector machine. Results: Distinct metabolic profiles and phenotype clusters were associated with MetS progression. The BORUTA algorithm identified 10 and 16 significant features for pre-MetS and MetS prediction, respectively. For pre-MetS, the top-ranked features were lipid accumulation product (LAP), triglyceride-glucose index adjusted for waist-to-height ratio (TyG-WHtR), coronary risk (CR), visceral adiposity index (VAI) and abdominal volume index (AVI). For MetS prediction, the most influential features were VAI, LAP, waist triglyceride index (WTI), Very low-density cholesterol (VLDLC) and TyG-WHtR. Majority voting ensemble classifier demonstrated superior performance in predicting pre-MetS (AUC = 0.79) and MetS (AUC = 0.87). Conclusion: Identifying these risk factors reveals the complex interplay between visceral adiposity and metabolic dysregulation in African populations, enabling early detection and treatment. Ethical integration of ML algorithms in clinical decision-making can streamline identification of high-risk individuals, optimize resource allocation, and enable precise, tailored interventions.


  • Open Access

    Pathways to chronic disease detection and prediction: Mapping the potential of machine learning to the pathophysiological processes while navigating ethical challenges

    by Ebenezer Afrifa‐Yamoah, Eric Adua, Emmanuel Peprah‐Yamoah, Enoch O. Anto, Victor Opoku‐Yamoah, Emmanuel Acheampong, Michael J. Macartney, Rashid Hashmi

    Chronic diseases such as heart disease, cancer, and diabetes are leading drivers of mortality worldwide, underscoring the need for improved efforts around early detection and prediction. The pathophysiology and management of chronic diseases have benefitted from emerging fields in molecular biology like genomics, transcriptomics, proteomics, glycomics, and lipidomics. The complex biomarker and mechanistic data from these “omics” studies present analytical and interpretive challenges, especially for traditional statistical methods. Machine learning (ML) techniques offer considerable promise in unlocking new pathways for data‐driven chronic disease risk assessment and prognosis. This review provides a comprehensive overview of state‐of‐the‐art applications of ML algorithms for chronic disease detection and prediction across datasets, including medical imaging, genomics, wearables, and electronic health records. Specifically, we review and synthesize key studies leveraging major ML approaches ranging from traditional techniques such as logistic regression and random forests to modern deep learning neural network architectures. We consolidate existing literature to date around ML for chronic disease prediction to synthesize major trends and trajectories that may inform both future research and clinical translation efforts in this growing field. While highlighting the critical innovations and successes emerging in this space, we identify the key challenges and limitations that remain to be addressed. Finally, we discuss pathways forward toward scalable, equitable, and clinically implementable ML solutions for transforming chronic disease screening and prevention.


  • Open Access

    Comparing paediatric optometric vision care in Canada over a 14‐year period

    by Lisa W. Christian, Victor Opoku‐Yamoah, Kalpana Rose, Deborah A. Jones, Daphne McCulloch, Elizabeth L. Irving, Susan J. Leat

    Purpose: In Canada, teaching in paediatric eye care has increased in the past decade both within the optometry curriculum and as continuing education to optometrists. Paediatric vision care guidelines have also been established by North American optometric associations. This study examined whether this exposure was associated with changes in paediatric eye care in Canada over a 14‐year period. Methods: Canadian optometrists were invited to participate in an anonymous 35‐item survey in 2007 and 2021. The surveys sought to investigate optometrist's recommendations for first eye examinations, the number of paediatric patients seen in a typical week and preparedness to provide eye examinations to children. Response frequencies were determined for each survey item. Results: Across Canada, 133/1000 (13.3%) and 261/~6419 (~4.1%) optometrists responded to the survey in 2007 and 2021, respectively. No significant difference was found in the number of years practicing, days per week in practice and total number of patients seen per week. The modal age optometrists recommended children be seen for their first eye examination changed from 3–4 years in 2007 (53%) to 6–12 months in 2021 (61%). In 2007, 87% of respondents provided eye examinations to children p = 0.02). Despite a reduction in the recommended age between the two survey years, the most frequent age children were seen for their first eye examination was 3‐4 years (30% in both surveys) and the most common age seen in a typical week remained unchanged (4–6 years—56% 2007; 66% 2021). Conclusion: Although optometrists' willingness to provide paediatric eye care increased over the past 14 years, the number of children seen in a typical week did not change. Barriers to determine why more children are not being seen at an earlier age need to be investigated.

  • Open Access

    Conceptualised psycho-medical footprint for health status outcomes and the potential impacts for early detection and prevention of chronic diseases in the context of 3P medicine

    by Ebenezer Afrifa-Yamoah, Eric Adua, Enoch Odame Anto, Emmanuel Peprah-Yamoah, Victor Opoku-Yamoah, Emmanuel Aboagye, Rashid Hashmi

    Background: The Suboptimal Health Status Questionnaire-25 (SHSQ-25) is a distinctive medical psychometric diagnostic tool designed for the early detection of chronic diseases. However, the synaptic connections between the 25 symptomatic items and their relevance in supporting the monitoring of suboptimal health outcomes, which are precursors for chronic diseases, have not been thoroughly evaluated within the framework of predictive, preventive, and personalised medicine (PPPM/3PM). This baseline study explores the internal structure of the SHSQ-25 and demonstrates its discriminatory power to predict optimal and suboptimal health status (SHS) and develop photogenic representations of their distinct relationship patterns. Methods: The cross-sectional study involved healthy Ghanaian participants (n = 217; aged 30–80 years; ~ 61% female), who responded to the SHSQ-25. The median SHS score was used to categorise the population into optimal and SHS. Graphical LASSO model and multi-dimensional scaling configuration methods were employed to describe the network structures for the two populations. Results: We observed differences in the structural, node placement and node distance of the synaptic networks for the optimal and suboptimal populations. A statistically significant variance in connectivity levels was noted between the optimal (58 non-zero edges) and suboptimal (43 non-zero edges) networks (p = 0.024). Fatigue emerged as a prominently central subclinical condition within the suboptimal population, whilst the cardiovascular system domain had the greatest relevance for the optimal population. The contrast in connectivity levels and the divergent prominence of specific subclinical conditions across domain networks shed light on potential health distinctions. Conclusions: We have demonstrated the feasibility of creating dynamic visualizers of the evolutionary trends in the relationships between the domains of SHSQ-25 relative to health status outcomes. This will provide in-depth comprehension of the conceptual model to inform personalised strategies to circumvent SHS. Additionally, the findings have implications for both health care and disease prevention because at-risk individuals can be predicted and prioritised for monitoring, and targeted intervention can begin before their symptoms reach an irreversible stage.