Spotlight on Sarah Ogutu – SSACAB PhD Fellow
#SSACAB
|
#sceienceforafricafoundation
|
#welcometrsust
|
#PhDFellow
|
#DeepLearning
|
#SurvivalAnalysis
|
#DynamicDeepHit
|
#HIVResearch
|
#MachineLearning
|
#HealthDataScience
|
#Biostatistics
|
#MissingData
|
#ArtificialIntelligence
|
#ResearchSpotlight
|
#WomenInSTEM
|
#DataScience
|
#AcademicResearch
We are proud to spotlight Sarah Ogutu, an SSACAB PhD fellow from the University of KwaZulu-Natal, for her recent publication co-authored with Mohanad Mohammed and Prof. Henry Mwambi.
The paper, titled "Deep learning models for the analysis of high-dimensional survival data with time-varying covariates while handling missing data", explores the use of advanced deep learning techniques DeepSurv, DeepHit, and Dynamic DeepHit to model HIV incidence (a time-to-event outcome) using high-dimensional longitudinal data.
This study incorporates time-varying cytokine profiles alongside baseline covariates and addresses missing data using the missForest imputation method. The team evaluated model performance using the time-dependent concordance index (C-index) and Brier scores on both imputed and complete-case datasets.
Notably, the paper highlights the superior performance of Dynamic DeepHit, which retains the dynamic nature of cytokine data, over methods that use derived summary measures. This finding underscores the importance of preserving time-varying information in predictive modeling, particularly in clinical applications where variables evolve over time.
📖 Read the full article here:
🔗 https://lnkd.in/dDuahbP5
Congratulations to Sarah and her collaborators on this impactful contribution to survival analysis and deep learning in healthcare!