Surrogate-guided sampling designs for classification of rare outcomes from electronic medical records data
| Autor: | W. Katherine Tan, Patrick J. Heagerty |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Statistics and Probability Computer science Machine learning computer.software_genre 01 natural sciences Outcome (game theory) Methodology (stat.ME) Set (abstract data type) 010104 statistics & probability 03 medical and health sciences 0302 clinical medicine 030212 general & internal medicine 0101 mathematics Statistics - Methodology Selection (genetic algorithm) Abstraction (linguistics) business.industry Sampling (statistics) General Medicine Simple random sample Stratified sampling Identification (information) Artificial intelligence Statistics Probability and Uncertainty business computer |
| Zdroj: | Biostatistics. 23:345-361 |
| ISSN: | 1468-4357 1465-4644 |
| Popis: | Summary Scalable and accurate identification of specific clinical outcomes has been enabled by machine-learning applied to electronic medical record systems. The development of classification models requires the collection of a complete labeled data set, where true clinical outcomes are obtained by human expert manual review. For example, the development of natural language processing algorithms requires the abstraction of clinical text data to obtain outcome information necessary for training models. However, if the outcome is rare then simple random sampling results in very few cases and insufficient information to develop accurate classifiers. Since large scale detailed abstraction is often expensive, time-consuming, and not feasible, more efficient strategies are needed. Under such resource constrained settings, we propose a class of enrichment sampling designs, where selection for abstraction is stratified by auxiliary variables related to the true outcome of interest. Stratified sampling on highly specific variables results in targeted samples that are more enriched with cases, which we show translates to increased model discrimination and better statistical learning performance. We provide mathematical details and simulation evidence that links sampling designs to their resulting prediction model performance. We discuss the impact of our proposed sampling on both model training and validation. Finally, we illustrate the proposed designs for outcome label collection and subsequent machine-learning, using radiology report text data from the Lumbar Imaging with Reporting of Epidemiology study. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|