@article{10.11648/j.ajtas.20261505.15,
  author = {Atem Bul Malang and Timothy Kevin Kuria Kamanu and David Musyimi Ndetei and Zakariya Mohammed Salih Mohammed and Stephen Wanyonyi Luketero},
  title = {Machine Learning Modelling of Mental Disorders in the People of South Sudan},
  journal = {American Journal of Theoretical and Applied Statistics},
  volume = {15},
  number = {5},
  pages = {243-256},
  doi = {10.11648/j.ajtas.20261505.15},
  url = {https://doi.org/10.11648/j.ajtas.20261505.15},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajtas.20261505.15},
  abstract = {The increase in mental health challenges among the population has raised serious concerns among educators, healthcare professionals, and lawmakers. Because of the substantial impact of mental diseases on emotions, cognition, and social relationships, creative preventative and intervention measures are required, particularly for those living in conflict-prone locations. Early detection is critical, and medical predictive analytics could change healthcare, especially given the severe impact of mental disorders on individuals. However, the conventional methods of mental illness prediction often suffer from the issue of either over-detection or under-detection and the time-consuming manual review process of patients' data during screening sessions. Therefore, the main objective of the study was to utilize machine learning approaches in the prediction of mental health problems that can complement the traditional clinical screening and diagnosis process. It developed five machine learning models namely logistic regression, Support Vector Machine, Random Forest, Decision Tree, and K-Nearest Neighbors that can be used to predict mental disorders outcomes among the people of South Sudan. They were trained and evaluated on the cross-sectional dataset collected from the South Sudan Demobilization, Disarmament and Re-integration Commission’s community surveys (DDRC, 2021). The study results show that the random forest model performs better than the other four models and the most important predictors of the target variable (mental health disorders) were, in order of influence, state, income and number of children. The study demonstrates that the use of machine learning models can help with mental health assessment, giving a patient-friendly and a solution that is scalable option for early detection. It is conceivable to integrate machine learning models into digital health platforms to help mental health providers make decisions that are informed and provide timely interventions. The research suggests that in order to enhance generalizability across diverse populations, it is necessary to incorporate multimodal information, enhance models, and utilize a variety of datasets in future investigations. AI-powered mental healthcare solutions have the potential to revolutionize the processes of diagnosing and arranging treatment for individuals with mental health issues in countries with limited resources.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Machine Learning Modelling of Mental Disorders in the People of South Sudan
AU  - Atem Bul Malang
AU  - Timothy Kevin Kuria Kamanu
AU  - David Musyimi Ndetei
AU  - Zakariya Mohammed Salih Mohammed
AU  - Stephen Wanyonyi Luketero
Y1  - 2026/09/20
PY  - 2026
N1  - https://doi.org/10.11648/j.ajtas.20261505.15
DO  - 10.11648/j.ajtas.20261505.15
T2  - American Journal of Theoretical and Applied Statistics
JF  - American Journal of Theoretical and Applied Statistics
JO  - American Journal of Theoretical and Applied Statistics
SP  - 243
EP  - 256
PB  - Science Publishing Group
SN  - 2326-9006
UR  - https://doi.org/10.11648/j.ajtas.20261505.15
AB  - The increase in mental health challenges among the population has raised serious concerns among educators, healthcare professionals, and lawmakers. Because of the substantial impact of mental diseases on emotions, cognition, and social relationships, creative preventative and intervention measures are required, particularly for those living in conflict-prone locations. Early detection is critical, and medical predictive analytics could change healthcare, especially given the severe impact of mental disorders on individuals. However, the conventional methods of mental illness prediction often suffer from the issue of either over-detection or under-detection and the time-consuming manual review process of patients' data during screening sessions. Therefore, the main objective of the study was to utilize machine learning approaches in the prediction of mental health problems that can complement the traditional clinical screening and diagnosis process. It developed five machine learning models namely logistic regression, Support Vector Machine, Random Forest, Decision Tree, and K-Nearest Neighbors that can be used to predict mental disorders outcomes among the people of South Sudan. They were trained and evaluated on the cross-sectional dataset collected from the South Sudan Demobilization, Disarmament and Re-integration Commission’s community surveys (DDRC, 2021). The study results show that the random forest model performs better than the other four models and the most important predictors of the target variable (mental health disorders) were, in order of influence, state, income and number of children. The study demonstrates that the use of machine learning models can help with mental health assessment, giving a patient-friendly and a solution that is scalable option for early detection. It is conceivable to integrate machine learning models into digital health platforms to help mental health providers make decisions that are informed and provide timely interventions. The research suggests that in order to enhance generalizability across diverse populations, it is necessary to incorporate multimodal information, enhance models, and utilize a variety of datasets in future investigations. AI-powered mental healthcare solutions have the potential to revolutionize the processes of diagnosing and arranging treatment for individuals with mental health issues in countries with limited resources.
VL  - 15
IS  - 5
ER  - 

Copy | Download