Portia Buernarkie Nartey
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Portia Buernarkie Nartey has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Proscovia Nabunya
Brown School, Washington University in St. Louis, St. Louis, USA
5 shared publications - Fred M. Ssewamala
Washington University in St. Louis, USA
4 shared publications - Abdallah Ibrahim
School of Public Health, University of Ghana, Accra P.O. Box LG419, Ghana
2 shared publications - Alice Boateng
Department of Social Work, University of Ghana, Accra P.O. Box LG419, Ghana
2 shared publications - Kingsley Kumbelim
BasicNeeds Ghana, Tamale P.O. Box TL1140, Ghana
2 shared publications - Mary McKernon McKay
Washington University in St. Louis, St Louis, USA
2 shared publications
Latest Publications
- Open Access
- 21 March 2026
- Published by Springer Nature in Global Social Welfare
- p. 1-13
Using Machine Learning to Predict Depression among Adolescents Living with HIV in Uganda
Background: Adolescents living with HIV (ALWHIV) face a high prevalence of depression. In Uganda, limited access to mental health services exacerbates depression, necessitating innovative solutions for early detection and intervention. Machine learning (ML) provides a promising approach for identifying adolescents at risk of depression to facilitate early intervention. This study aims to use machine learning to predict depression among ALWHIV in Uganda. Methods: This study analyzed cross-sectional data from 833 ALWHIV aged 10–17 years in Southern Uganda. Depression was assessed using the Children’s Depression Inventory (CDI) –short version. Seven ML models, including Random Forest, Logistic Regression, Gradient Boosting, decision tree, XGBoost, Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine, were evaluated using stratified 10-fold cross-validation. Model performance metrics included Area under receiver operating characteristic curve (AUROC), Area under precision-recall curve (AUPRC), accuracy, sensitivity, specificity, and F1-score. SHapley Additive exPlanations (SHAP) analysis was used to interpret feature importance. Results: The median age was 13 years, and the majority of the participants were females (55.5%). The prevalence of depression was 30.97%. The Random Forest model achieved the highest performance (AUROC = 0.79, AUPRC = 0.66). Key predictors of depression included hopelessness, HIV stigma, shame, self-esteem, teacher support, and caregiver support. SHAP analysis highlighted psychosocial challenges as primary predictors of depression, emphasizing the need for psychosocial-based interventions. Conclusion: Our study results demonstrated good performance of ML in predicting depression among ALWHIV. However, we acknowledge that the absence of external validation limits the generalizability of these findings. Future research should seek to validate these models in independent cohorts of ALWHIV to confirm their robustness and applicability across different settings.
- 21 March 2026
- Published by Springer Nature in Global Social Welfare
- p. 1-13
Open AccessUsing Machine Learning to Predict Depression among Adolescents Living with HIV in Uganda
Background: Adolescents living with HIV (ALWHIV) face a high prevalence of depression. In Uganda, limited access to mental health services exacerbates depression, necessitating innovative solutions for early detection and intervention. Machine learning (ML) provides a promising approach for identifying adolescents at risk of depression to facilitate early intervention. This study aims to use machine learning to predict depression among ALWHIV in Uganda. Methods: This study analyzed cross-sectional data from 833 ALWHIV aged 10–17 years in Southern Uganda. Depression was assessed using the Children’s Depression Inventory (CDI) –short version. Seven ML models, including Random Forest, Logistic Regression, Gradient Boosting, decision tree, XGBoost, Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine, were evaluated using stratified 10-fold cross-validation. Model performance metrics included Area under receiver operating characteristic curve (AUROC), Area under precision-recall curve (AUPRC), accuracy, sensitivity, specificity, and F1-score. SHapley Additive exPlanations (SHAP) analysis was used to interpret feature importance. Results: The median age was 13 years, and the majority of the participants were females (55.5%). The prevalence of depression was 30.97%. The Random Forest model achieved the highest performance (AUROC = 0.79, AUPRC = 0.66). Key predictors of depression included hopelessness, HIV stigma, shame, self-esteem, teacher support, and caregiver support. SHAP analysis highlighted psychosocial challenges as primary predictors of depression, emphasizing the need for psychosocial-based interventions. Conclusion: Our study results demonstrated good performance of ML in predicting depression among ALWHIV. However, we acknowledge that the absence of external validation limits the generalizability of these findings. Future research should seek to validate these models in independent cohorts of ALWHIV to confirm their robustness and applicability across different settings.
- Open Access
- 28 November 2025
- Published by MDPI AG in Populations
- Vol. 1 (4) , 25
When Families Choose Sons: Parental Gender Norms and Girls’ Education in Ghana
Despite global progress toward gender parity in education, Ghanaian girls continue to face systemic barriers rooted in entrenched parental gender norms. This paper explores how parental gender norm beliefs and attitudes perpetuate disparities among school-aged, particularly disadvantaging girls in access to and retention in education. Using a desk review methodology, we analyzed peer-reviewed social science and development literature, legal documents, and international reports from organizations such as the United Nations and the World Bank to explore the structural and cultural dynamics affecting girls’ education in Ghana. Anchored in Social Impact Theory, Parental Ethnotheories, and Expectation States Theory, the study provides a multi-theoretical lens to understand how gender norms, cultural expectations, and parental beliefs converge to influence educational outcomes for girls. Analysis of sociocultural norms, economic trade-offs, and safety concerns reveals how parents—often guided by love and pragmatism—prioritize sons’ education while withdrawing daughters for caregiving, early marriages, or income-generating labor. The study highlights three critical dimensions: (1) the economic reasoning behind gendered investments in children’s schooling, (2) sociocultural gender norms limiting girls’ retention in school, and (3) the transformative potential of educated women as community leaders challenging these patterns. Evidence shows that educating girls yields broad benefits, from improved health outcomes to economic growth, yet systemic inequities remain. Findings underscore the need for interventions to move beyond school access to address the familial and cultural ecosystems shaping parental decisions. By disrupting entrenched gender norms, Ghana can advance SDGs 4 and 5 and promote long-term societal change.
- 28 November 2025
- Published by MDPI AG in Populations
- Vol. 1 (4) , 25
Open AccessWhen Families Choose Sons: Parental Gender Norms and Girls’ Education in Ghana
Despite global progress toward gender parity in education, Ghanaian girls continue to face systemic barriers rooted in entrenched parental gender norms. This paper explores how parental gender norm beliefs and attitudes perpetuate disparities among school-aged, particularly disadvantaging girls in access to and retention in education. Using a desk review methodology, we analyzed peer-reviewed social science and development literature, legal documents, and international reports from organizations such as the United Nations and the World Bank to explore the structural and cultural dynamics affecting girls’ education in Ghana. Anchored in Social Impact Theory, Parental Ethnotheories, and Expectation States Theory, the study provides a multi-theoretical lens to understand how gender norms, cultural expectations, and parental beliefs converge to influence educational outcomes for girls. Analysis of sociocultural norms, economic trade-offs, and safety concerns reveals how parents—often guided by love and pragmatism—prioritize sons’ education while withdrawing daughters for caregiving, early marriages, or income-generating labor. The study highlights three critical dimensions: (1) the economic reasoning behind gendered investments in children’s schooling, (2) sociocultural gender norms limiting girls’ retention in school, and (3) the transformative potential of educated women as community leaders challenging these patterns. Evidence shows that educating girls yields broad benefits, from improved health outcomes to economic growth, yet systemic inequities remain. Findings underscore the need for interventions to move beyond school access to address the familial and cultural ecosystems shaping parental decisions. By disrupting entrenched gender norms, Ghana can advance SDGs 4 and 5 and promote long-term societal change.
- Open Access
- 25 August 2025
- Published by MDPI AG in Preprints.org
When Families Choose Sons: Parental Gender Norms and Girls’ Education in Ghana
Despite global progress toward gender parity in education, Ghanaian girls continue to face systemic barriers rooted in entrenched parental gender norms. This paper explores how parental gender norm beliefs and attitudes perpetuate disparities among school-aged, particularly disadvantaging girls in access to and retention in education. Using a desk review methodology, we analyzed peer-reviewed social science and development literature, legal documents, and international reports from organizations such as the United Nations and the World Bank to explore the structural and cultural dynamics affecting girls’ education in Ghana. Anchored in Social Impact Theory, Parental Ethnotheories, and Expectation States Theory, the study provides a multi-theoretical lens to understand how social norms, cultural expectations, and parental beliefs converge to influence educational outcomes. Analysis of sociocultural norms, economic trade-offs, and safety concerns reveal how parents—often guided by love and pragmatism—prioritize sons’ education while withdrawing daughters for caregiving, early marriages, or income-generating labor. The study highlights three critical dimensions: (1) the economic reasoning behind gendered investments in children’s schooling, (2) sociocultural gender norms limiting girls’ retention in school, and (3) the transformative potential of educated women as community leaders challenging these patterns. Evidence shows that educating girls yields broad benefits, from improved health outcomes to economic growth, yet systemic inequities remain. Findings underscore the need for interventions to move beyond school access to address the familial and cultural ecosystems shaping parental decisions. By disrupting entrenched gender norms, Ghana can advance SDGs 4 and 5 and promote long-term societal change.
- 25 August 2025
- Published by MDPI AG in Preprints.org
Open AccessWhen Families Choose Sons: Parental Gender Norms and Girls’ Education in Ghana
Despite global progress toward gender parity in education, Ghanaian girls continue to face systemic barriers rooted in entrenched parental gender norms. This paper explores how parental gender norm beliefs and attitudes perpetuate disparities among school-aged, particularly disadvantaging girls in access to and retention in education. Using a desk review methodology, we analyzed peer-reviewed social science and development literature, legal documents, and international reports from organizations such as the United Nations and the World Bank to explore the structural and cultural dynamics affecting girls’ education in Ghana. Anchored in Social Impact Theory, Parental Ethnotheories, and Expectation States Theory, the study provides a multi-theoretical lens to understand how social norms, cultural expectations, and parental beliefs converge to influence educational outcomes. Analysis of sociocultural norms, economic trade-offs, and safety concerns reveal how parents—often guided by love and pragmatism—prioritize sons’ education while withdrawing daughters for caregiving, early marriages, or income-generating labor. The study highlights three critical dimensions: (1) the economic reasoning behind gendered investments in children’s schooling, (2) sociocultural gender norms limiting girls’ retention in school, and (3) the transformative potential of educated women as community leaders challenging these patterns. Evidence shows that educating girls yields broad benefits, from improved health outcomes to economic growth, yet systemic inequities remain. Findings underscore the need for interventions to move beyond school access to address the familial and cultural ecosystems shaping parental decisions. By disrupting entrenched gender norms, Ghana can advance SDGs 4 and 5 and promote long-term societal change.
- 26 June 2025
- Published by American Public Health Association in American Journal of Public Health
- p. e1-e9
Cost-Effectiveness of an Economic Empowerment and Family Intervention on Mental Health Among School-Going Adolescent Girls in Uganda, 2017‒2022
Objectives. To assess the cost-effectiveness of an economic empowerment and family intervention on mental health outcomes among school-going adolescent girls in Uganda from 2017 to 2022. Methods. We randomized adolescent girls aged 14 to 17 years into 3 arms: (1) health and sex education (usual care; n = 408), (2) youth development accounts (YDAs; n = 471), and (3) a combination intervention (YDA plus multiple family group [MFG]; n = 381). We fitted mixed-effects models and estimated intervention costs prospectively using the microcosting approach. Results. The combination intervention had a statistically significant impact on mental health outcomes (depressive symptoms, hopelessness, self-concept) at 12 and 24 months, except self-esteem at 24 months, relative to usual care, with incremental cost‒effectiveness ratios ranging from $51 to $100 per 0.2-SD change at 12 months, and $53 to $157 at 24 months per 0.2-SD change. Conclusions. The combination intervention positively and significantly impacted a higher number of mental health outcomes among school-going adolescent girls compared with YDA alone. The benefits were sustained in the short and long term, with the incremental cost-per-unit effect remaining comparable. Findings support the integration of combination interventions in school settings to promote adolescent girls’ positive mental health functioning. Trial Registration. ClinicalTrials.gov registration no. NCT03307226. ( Am J Public Health. Published online ahead of print June 26, 2025:e1–e9. https://doi.org/10.2105/AJPH.2025.308135 )
- 26 June 2025
- Published by American Public Health Association in American Journal of Public Health
- p. e1-e9
Cost-Effectiveness of an Economic Empowerment and Family Intervention on Mental Health Among School-Going Adolescent Girls in Uganda, 2017‒2022
Objectives. To assess the cost-effectiveness of an economic empowerment and family intervention on mental health outcomes among school-going adolescent girls in Uganda from 2017 to 2022. Methods. We randomized adolescent girls aged 14 to 17 years into 3 arms: (1) health and sex education (usual care; n = 408), (2) youth development accounts (YDAs; n = 471), and (3) a combination intervention (YDA plus multiple family group [MFG]; n = 381). We fitted mixed-effects models and estimated intervention costs prospectively using the microcosting approach. Results. The combination intervention had a statistically significant impact on mental health outcomes (depressive symptoms, hopelessness, self-concept) at 12 and 24 months, except self-esteem at 24 months, relative to usual care, with incremental cost‒effectiveness ratios ranging from $51 to $100 per 0.2-SD change at 12 months, and $53 to $157 at 24 months per 0.2-SD change. Conclusions. The combination intervention positively and significantly impacted a higher number of mental health outcomes among school-going adolescent girls compared with YDA alone. The benefits were sustained in the short and long term, with the incremental cost-per-unit effect remaining comparable. Findings support the integration of combination interventions in school settings to promote adolescent girls’ positive mental health functioning. Trial Registration. ClinicalTrials.gov registration no. NCT03307226. ( Am J Public Health. Published online ahead of print June 26, 2025:e1–e9. https://doi.org/10.2105/AJPH.2025.308135 )
- Open Access
- 1 January 2025
- Published by Wiley in Journal of Theoretical Social Psychology
- Vol. 2025 (1)
The Association Between Interpersonal Factors, Stress, Anxiety, and Depression Among Junior High School Students in the Greater Accra Region
This study investigates depression among junior high school students in Ghana’s Greater Accra Region, focusing on interpersonal and mental health factors, addressing a crucial research gap in low‐ and middle‐income countries (LMICs). Analyzing data from 800 students, we found anxiety to be a significant predictor of depression, with over threefold higher odds for students experiencing anxiety. Gender differences in depression prevalence were observed. These findings challenge the universality of the interpersonal theory of suicide constructs among Ghanaian youth, emphasizing the need for culturally sensitive mental health research and intervention. This study contributes to adolescent mental health understanding in Ghana, highlighting the cultural and developmental contexts’ importance. Further research is essential to better understand the factors affecting adolescent mental health in LMICs.
- 1 January 2025
- Published by Wiley in Journal of Theoretical Social Psychology
- Vol. 2025 (1)
Open AccessThe Association Between Interpersonal Factors, Stress, Anxiety, and Depression Among Junior High School Students in the Greater Accra Region
This study investigates depression among junior high school students in Ghana’s Greater Accra Region, focusing on interpersonal and mental health factors, addressing a crucial research gap in low‐ and middle‐income countries (LMICs). Analyzing data from 800 students, we found anxiety to be a significant predictor of depression, with over threefold higher odds for students experiencing anxiety. Gender differences in depression prevalence were observed. These findings challenge the universality of the interpersonal theory of suicide constructs among Ghanaian youth, emphasizing the need for culturally sensitive mental health research and intervention. This study contributes to adolescent mental health understanding in Ghana, highlighting the cultural and developmental contexts’ importance. Further research is essential to better understand the factors affecting adolescent mental health in LMICs.
- Open Access
- 17 August 2023
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 20 (16) , 6590
Correction: Sensoy Bahar et al. “ANZANSI Program Taught Me Many Things in Life”: Families’ Experiences with a Combination Intervention to Prevent Adolescent Girls’ Unaccompanied Migration for Labor. Int. J. Environ. Res. Public Health 2022, 19, 13168
There was an error in the original publication
- 17 August 2023
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 20 (16) , 6590
Open AccessCorrection: Sensoy Bahar et al. “ANZANSI Program Taught Me Many Things in Life”: Families’ Experiences with a Combination Intervention to Prevent Adolescent Girls’ Unaccompanied Migration for Labor. Int. J. Environ. Res. Public Health 2022, 19, 13168
There was an error in the original publication
- Open Access
- 13 October 2022
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 19 (20) , 13168
“ANZANSI Program Taught Me Many Things in Life”: Families’ Experiences with a Combination Intervention to Prevent Adolescent Girls’ Unaccompanied Migration for Labor
Approximately 160 million children work as child laborers globally, 39% of whom are female. Ghana is one of the countries with the highest rates of child labor. Child labor has serious health, mental health, and educational consequences, and those who migrate independently for child labor are even at higher risk. Yet, evidence-based efforts to prevent unaccompanied child migration are limited. In this study, we examined the acceptability of a family-level intervention, called ANZANSI (resilience in local language) combining two evidence-based interventions, a family economic empowerment intervention and a multiple family group family strengthening intervention, to reduce the risk factors associated with the independent migration of adolescent girls from the Northern region to big cities in Ghana. We conducted semi-structured interviews separately with 20 adolescent girls and their caregivers who participated in ANZANSI. Interviews were conducted in the local language and transcribed and translated verbatim. Informed by the theoretical framework of acceptability, the data were analyzed using thematic analysis. The results showed high intervention acceptability among both adolescent girls and their caregivers, including low burden, positive affective attitude, high perceived effectiveness, low opportunity costs, and high self-efficacy. The study findings underline the high need for such interventions in low-resource contexts in Ghana and provide the foundation for testing this intervention in a larger randomized trial.
- 13 October 2022
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 19 (20) , 13168
Open Access“ANZANSI Program Taught Me Many Things in Life”: Families’ Experiences with a Combination Intervention to Prevent Adolescent Girls’ Unaccompanied Migration for Labor
Approximately 160 million children work as child laborers globally, 39% of whom are female. Ghana is one of the countries with the highest rates of child labor. Child labor has serious health, mental health, and educational consequences, and those who migrate independently for child labor are even at higher risk. Yet, evidence-based efforts to prevent unaccompanied child migration are limited. In this study, we examined the acceptability of a family-level intervention, called ANZANSI (resilience in local language) combining two evidence-based interventions, a family economic empowerment intervention and a multiple family group family strengthening intervention, to reduce the risk factors associated with the independent migration of adolescent girls from the Northern region to big cities in Ghana. We conducted semi-structured interviews separately with 20 adolescent girls and their caregivers who participated in ANZANSI. Interviews were conducted in the local language and transcribed and translated verbatim. Informed by the theoretical framework of acceptability, the data were analyzed using thematic analysis. The results showed high intervention acceptability among both adolescent girls and their caregivers, including low burden, positive affective attitude, high perceived effectiveness, low opportunity costs, and high self-efficacy. The study findings underline the high need for such interventions in low-resource contexts in Ghana and provide the foundation for testing this intervention in a larger randomized trial.