Answers are grounded in this paper and cite their sources.
Develops methods for sample size planning in clinical phenotyping, indicating a way to enhance classification accuracy.
Advances in automated document classification has led to identifying massive numbers of clinical concepts from handwritten clinical notes. These high dimensional clinical concepts can serve as highly informative predictors in building classification algorithms for identifying patients with different clinical conditions, commonly referred to as patient phenotyping. However, from a planning perspective, it is first critical to ensure that enough data is available to build a phenotyping algorithm that has good classification performance to ensure a required clinical impact. This challenge in sample size planning is further exacerbated by the high dimensionality of the covariates and the inherent imbalance of the response class as most phenotypes of interest are relatively rare. In this work, we develop methods for sample size planning, deriving plug-in formulas for determining sample size requirements based on optimizing classification performance metrics sensitive to class imbalance (e.g., Area Under the Curve (AUC), Matthews Correlation Coefficient (MCC)).
No takes yet. Share an insight, caveat, or question.
Dharmarajan et al. (2023) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: