Browsing by Subject "Prognostic model"
Results Per Page
Sort Options
Item Open Access A Feasibility Assessment of a Traumatic Brain Injury Predictive Modelling Tool at Kilimanjaro Christian Medical Center and Duke University Hospital(2020) O'Leary, PaigeTraumatic brain injury (TBI) is the most common cause of death and disability globally. TBI is a leading cause of resource consumption and disproportionately affects LMICs. Innovative solutions are required to address this high burden of TBI. Prognostic models could provide a solution since the models enhance diagnostic ability of physicians, thereby helping to tailor treatments more effectively. This study aims to evaluate the feasibility of a prognostic model developed in Tanzania for TBI patients amongst Kilimanjaro Christian Medical Center (KCMC) healthcare providers and Duke affiliated healthcare providers. Duke health system participants were included primarily to gain insight from a different context with more established practices to inform the TBI tool implementation strategy at KCMC. To evaluate the feasibility of integrating the TBI tool into potential workflows co-design interviews were conducted with emergency physicians and nursing staff. Qualitatively, the tool was assessed using human centered design (HCD) techniques. Our research design methods were created using the Consolidated Framework for Implementation Research which considers overarching characteristics of successful implementation to contribute to theory development and verification of implementation strategies across multiple contexts. Findings of this study will aid in determining under what conditions a TBI prognostic model intervention will work at KCMC and the potential use of HCD in implementation research.
Item Embargo Developing a Machine Learning Based Clinical Decision-Making Tool for Traumatic Brain Injury Patients in Moshi, Tanzania(2023) Huo, LilyBackground: Traumatic brain injury (TBI) has a disproportionate burden on low- and middle-income countries (LMICs) and cost-effective and culturally relevant measures are necessary to improve TBI care. This study aims to characterize emergency healthcare providers’ decision making when treating TBI patients, develop a machine learning-based model to predict TBI patient outcome, and conduct a decision curve analysis (DCA) to evaluate model clinical applicability. Methods: This study is twofold: 1) a secondary analysis of a TBI data registry with 4142 patients and 2) a survey examining physicians decision-making in treating 50 TBI patients in real time. Results: Five machine learning models were developed with AUCs ranging from 70.86% (Single C5.0 Ruleset) to 85.67% (Ensemble Model). DCA showed that all models exhibited a greater net benefit over ranges of clinical thresholds. The survey collected information on 50 patients providing insight on tools used by physicians in real-time when treating TBI patients as well as the unmet need patients at KCMC faced. Conclusions: This study is the first to use machine learning modeling and DCA in the context of TBI prognosis in Sub-Saharan Africa. Prognostic models have great potential within the decision-making process for treating TBI patients in LMIC health systems and such utility can be expanded through determining different threshold probabilities for various interventions.
Item Open Access Transferring and Adapting a Prognostic Model to Improve Care of Brazilian Traumatic Brain Injury Patients(2020) Wu, JiawenAbstract
Background: Traumatic brain injury (TBI) is a major cause of death and disability. About 10 million people annually are affected by TBI, with a prominent burden in low- and middle-income countries (LMICs). In Brazil, TBI is responsible for 125,500 admissions and 9700 hospital deaths annually. The poor prognosis could be caused by insufficient medical professionals and diagnostic machines. This study aims to find an optimum TBI prognostic model to serve as a diagnostic tool that can be adapted from prior work in Tanzania to Brazil. We aim to develop an effective TBI prognostic model that could be generalized in LMICs.
Methods: The study was a secondary data analysis on clinical and sociodemographic variables of 3209 TBI patients at Kilimanjaro Christian Medical Center (KCMC) and 725 TBI patients at six Brazilian traumatic care hospitals. We trained and tested eight machine learning models using three strategies: 1) using Tanzanian dataset trained models to test Brazilian dataset, 2) using Tanzanian-Brazilian combined dataset for training and testing and 3) using Brazilian dataset for training and testing. We compared the performance of models using confusion matrix statistics: area under the ROC curve(AUC), sensitivity, specificity, positive predictive value, negative predictive value and accuracy.
Findings: Models using Tanzanian-Brazilian combined dataset for training and testing outperformed models of other two strategies. The AUC of the models varied from 80.9% (K nearest neighbor) to 91.9% (Random Forest). The optimum model, Random Forest, had a strong predictive power of classification with sensitivity of 0.927, specificity of 0.756, positive predictive value of 0.960, negative predictive value of 0.620 and accuracy of 0.903.
Interpretations: Our study shows the successful adaptation of TBI prognostic model from Tanzania to Brazil. Additionally, it indicates the possibility of generalizing a TBI prognostic model to LMICs. With larger multi-national data, we hope to develop an effective model that could accurately predict the potential outcome of TBI patients. The model could serve as a powerful auxiliary tool for diagnosis and help reduce mortality of TBI patients in LMICs.
Source of Funding: The project is conducted with the funding from Duke Global Health Institute.