Publications by authors named "Inggeol Lee"
Article Synopsis
- Machine learning applications in healthcare have potential benefits, but their real-world accuracy, especially for different patient groups, is still uncertain, prompting a community challenge focused on predicting all-cause mortality.
- The challenge involved 345 participants forming 25 teams from across 10 countries, who created 25 models trained on a dataset of over 1.1 million patients, with the best model achieving a high performance score.
- Analysis showed significant variability in model accuracy based on patient subpopulations, indicating both the possibilities and limitations of using AI in clinical settings.
Motivation: Recent advances in deep learning have offered solutions to many biomedical tasks. However, there remains a challenge in applying deep learning to survival analysis using human cancer transcriptome data. As the number of genes, the input variables of survival model, is larger than the amount of available cancer patient samples, deep-learning models are prone to overfitting.
View Article and Find Full Text PDF