Alice Andongolile
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Alice Andongolile has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Blandina Theophil Mmbaga
KCMC University, Moshi, Tanzania
3 shared publications - Baraka Moshi
Kilimanjaro Clinical Research Institute
2 shared publications - Catherine Ann Staton
Duke Global Health Institute, Duke University, Durham, NC, USA
2 shared publications - Edwin Joseph Shewiyo
Department of Epidemiology and Biostatistics, School of Public Health KCMC University Moshi Tanzania
2 shared publications - William Nkenguye
Department of Epidemiology and Biostatistics KCMC University Moshi Tanzania
2 shared publications Anaelderrick Kimaro
Department of Psychiatry, KCMC University
1 shared publication
Latest Publications
- Open Access
- 4 August 2026
- Published by Wiley in Health Science Reports
- Vol. 9 (8) , e72956
Predicting Outcomes of Traumatic Brain Injury Using Machine Learning Models Among Patients at Kilimanjaro Christian Medical Centre, Tanzania: A Registry‐Based Cohort Study
Background: Traumatic brain injury (TBI) remains a major global health burden, disproportionately affecting low‐ and middle‐income countries (LMICs) where access to neurocritical care is limited. Accurate and context‐appropriate prognostic models are crucial to guide early clinical decision‐making and optimize resource allocation in such settings. This study aims to develop and evaluate machine learning (ML) models for predicting TBI outcomes among adult patients using trauma registry data from Kilimanjaro Christian Medical Centre (KCMC), Tanzania. Methods: This retrospective cohort study utilized data from 4596 adult TBI patients recorded in the KCMC trauma registry between 2013 and 2024. The outcome was dichotomized Glasgow Outcome Scale (GOS): poor (1–3) versus good (4–5). Ten supervised ML algorithms, including Random Forest (RF), Decision Tree (DT), Logistic Regression, Support Vector Machine (SVM), and Artificial Neural Networks (ANN), were trained on 70% of the data after applying multiple imputation and synthetic minority Over‐sampling Technique (SMOTE) to address missingness and class imbalance. Hyperparameter tuning was performed using 10‐fold cross‐validation. Model performance was assessed on a 30% test set using area under the ROC curve (AUC), accuracy, sensitivity, specificity, and predictive values. Results: Among the 4596 patients, 26.2% had poor outcomes. The RF and DT models achieved the highest AUCs of 0.83 and 0.82, respectively. RF also showed the highest accuracy (0.78) and strong positive predictive value (PPV = 0.87), while DT had the highest sensitivity for poor outcomes (84.5%). Predictors of poor outcomes included TBI severity, pupil non‐reactivity, low oxygen saturation, lack of CT scan, alcohol use, and abnormal vital signs. Conclusion: ML models, particularly RF and DT, demonstrated strong predictive performance for TBI outcomes using routinely collected variables in a resource‐limited LMIC setting. Their interpretability and reliance on admission‐level data make them potential tools for real‐time triage and risk stratification. Future research should focus on external validation and integration into clinical decision‐support systems to support scaleup across similar settings.
- 4 August 2026
- Published by Wiley in Health Science Reports
- Vol. 9 (8) , e72956
Open AccessPredicting Outcomes of Traumatic Brain Injury Using Machine Learning Models Among Patients at Kilimanjaro Christian Medical Centre, Tanzania: A Registry‐Based Cohort Study
Background: Traumatic brain injury (TBI) remains a major global health burden, disproportionately affecting low‐ and middle‐income countries (LMICs) where access to neurocritical care is limited. Accurate and context‐appropriate prognostic models are crucial to guide early clinical decision‐making and optimize resource allocation in such settings. This study aims to develop and evaluate machine learning (ML) models for predicting TBI outcomes among adult patients using trauma registry data from Kilimanjaro Christian Medical Centre (KCMC), Tanzania. Methods: This retrospective cohort study utilized data from 4596 adult TBI patients recorded in the KCMC trauma registry between 2013 and 2024. The outcome was dichotomized Glasgow Outcome Scale (GOS): poor (1–3) versus good (4–5). Ten supervised ML algorithms, including Random Forest (RF), Decision Tree (DT), Logistic Regression, Support Vector Machine (SVM), and Artificial Neural Networks (ANN), were trained on 70% of the data after applying multiple imputation and synthetic minority Over‐sampling Technique (SMOTE) to address missingness and class imbalance. Hyperparameter tuning was performed using 10‐fold cross‐validation. Model performance was assessed on a 30% test set using area under the ROC curve (AUC), accuracy, sensitivity, specificity, and predictive values. Results: Among the 4596 patients, 26.2% had poor outcomes. The RF and DT models achieved the highest AUCs of 0.83 and 0.82, respectively. RF also showed the highest accuracy (0.78) and strong positive predictive value (PPV = 0.87), while DT had the highest sensitivity for poor outcomes (84.5%). Predictors of poor outcomes included TBI severity, pupil non‐reactivity, low oxygen saturation, lack of CT scan, alcohol use, and abnormal vital signs. Conclusion: ML models, particularly RF and DT, demonstrated strong predictive performance for TBI outcomes using routinely collected variables in a resource‐limited LMIC setting. Their interpretability and reliance on admission‐level data make them potential tools for real‐time triage and risk stratification. Future research should focus on external validation and integration into clinical decision‐support systems to support scaleup across similar settings.
- Open Access
The impact and experience of a culturally adapted brief intervention for harmful alcohol use in an emergency care setting (PPKAY: Punguza Pombe Kwa Afya Yako): A case series
Background Harmful alcohol use is widespread in Tanzania, yet specialized resources to address this remain limited. This case series explores outcomes of three individuals who received a culturally-adapted brief intervention to reduce harmful alcohol use in an emergency department in Kilimanjaro, Tanzania. Methods The PPKAY intervention is a 15-minute nurse-delivered motivational interview for adults with acute (<□24□h) injuries, with an Alcohol Use Disorder Identification Test (AUDIT) of 8 or above or self-reported drinking alcohol within 6 hours of injury. The primary outcome was participants’ experience of the intervention. Secondary outcomes included number of binge drinking days in the prior month; depression, measured using the Patient Health Questionnaire-9 (PHQ-9); and alcohol-related consequences, measured by the Drinker Inventory of Consequences (DrInC). All outcomes were reported from baseline and at 3-month timepoints. Experience with the intervention was assessed with open-ended questions at a three-month post-intervention survey. Results Participants reported fewer binge drinking days, improved self-efficacy in managing triggers, reduced alcohol-related consequences, remission of depression, and strengthened interpersonal relationships. These were corroborated by significantly lower AUDIT, PHQ-9, and DrInC scores. One participant was not able to meet his drinking reduction target, accompanied by an avoidance of discussing interpersonal consequences of alcohol. Conclusions Our findings underscore the importance of integrated and targeted early screening and intervention in resource-limited emergency care settings. The narratives emphasize how a brief negotiational intervention can equip individuals with practical strategies to minimize harmful alcohol consumption. Further research is recommended to validate these outcomes in larger cohorts and diverse settings.
Open AccessThe impact and experience of a culturally adapted brief intervention for harmful alcohol use in an emergency care setting (PPKAY: Punguza Pombe Kwa Afya Yako): A case series
Background Harmful alcohol use is widespread in Tanzania, yet specialized resources to address this remain limited. This case series explores outcomes of three individuals who received a culturally-adapted brief intervention to reduce harmful alcohol use in an emergency department in Kilimanjaro, Tanzania. Methods The PPKAY intervention is a 15-minute nurse-delivered motivational interview for adults with acute (<□24□h) injuries, with an Alcohol Use Disorder Identification Test (AUDIT) of 8 or above or self-reported drinking alcohol within 6 hours of injury. The primary outcome was participants’ experience of the intervention. Secondary outcomes included number of binge drinking days in the prior month; depression, measured using the Patient Health Questionnaire-9 (PHQ-9); and alcohol-related consequences, measured by the Drinker Inventory of Consequences (DrInC). All outcomes were reported from baseline and at 3-month timepoints. Experience with the intervention was assessed with open-ended questions at a three-month post-intervention survey. Results Participants reported fewer binge drinking days, improved self-efficacy in managing triggers, reduced alcohol-related consequences, remission of depression, and strengthened interpersonal relationships. These were corroborated by significantly lower AUDIT, PHQ-9, and DrInC scores. One participant was not able to meet his drinking reduction target, accompanied by an avoidance of discussing interpersonal consequences of alcohol. Conclusions Our findings underscore the importance of integrated and targeted early screening and intervention in resource-limited emergency care settings. The narratives emphasize how a brief negotiational intervention can equip individuals with practical strategies to minimize harmful alcohol consumption. Further research is recommended to validate these outcomes in larger cohorts and diverse settings.
- Open Access
- 1 February 2025
- Published by SAGE Publications in Sage Open Pediatrics
- Vol. 12
Estimation of Disability Adjusted Life Years in Pediatric Injury Patients at a Zonal Referral Hospital in Northern Tanzania
Objective: This study aimed to estimates Disability-adjusted life years (DALYs) for pediatric injury patients at a zonal referral hospital. Methods: This is a retrospective cohort study using pediatric injury registry data, DALYs for pediatric injured patients was calculated by adding the Years of life lost (YLL) and Years lived with disability (YLD). Discounting rate of 3%, age weighting parameter of 0.04 and Constant 0.1658 were considered during analysis. Results: This study included 1000 pediatric injury patients with median age of 7 years, mostly male 639 (63.9%). Road traffic injuries were the leading cause 341 (34.1%), and 65 (6.5%) died, burns caused 27 (41.6%) of deaths. Pediatric injuries resulted in over 4500 DALYs, with road traffic injuries contributing the most (1650 DALYs). Conclusion: This study reveals the high burden of pediatric injuries, with males contributing most DALYs. Road traffic injuries significantly contribute to disabilities, highlighting the need for child-focused interventions.
- 1 February 2025
- Published by SAGE Publications in Sage Open Pediatrics
- Vol. 12
Open AccessEstimation of Disability Adjusted Life Years in Pediatric Injury Patients at a Zonal Referral Hospital in Northern Tanzania
Objective: This study aimed to estimates Disability-adjusted life years (DALYs) for pediatric injury patients at a zonal referral hospital. Methods: This is a retrospective cohort study using pediatric injury registry data, DALYs for pediatric injured patients was calculated by adding the Years of life lost (YLL) and Years lived with disability (YLD). Discounting rate of 3%, age weighting parameter of 0.04 and Constant 0.1658 were considered during analysis. Results: This study included 1000 pediatric injury patients with median age of 7 years, mostly male 639 (63.9%). Road traffic injuries were the leading cause 341 (34.1%), and 65 (6.5%) died, burns caused 27 (41.6%) of deaths. Pediatric injuries resulted in over 4500 DALYs, with road traffic injuries contributing the most (1650 DALYs). Conclusion: This study reveals the high burden of pediatric injuries, with males contributing most DALYs. Road traffic injuries significantly contribute to disabilities, highlighting the need for child-focused interventions.