Author:
Srivastava Satwik,Mishra Deepak
Abstract
AbstractClassification tasks today, especially for the medical domain, use datasets which are often hierarchical. These tasks are approached using methods that consider the class taxonomy for predicting a label. The classifiers are gradually becoming increasingly accurate over the complex datasets. While increasing accuracy is a good way to judge a model, in high-risk applications, it needs to be ensured that even if the model makes a mistake, it does not bear a severe consequence. This work explores the concept of severity of an error and extends it to the medical domain. Further, it aims to point out that accuracy or AUROC alone are not sufficient metrics to decide the performance of a model in a setting where a misclassification will incur a severe cost. Various approaches to reduce severity for classification models are compared and evaluated in this work, which indicate that while many of them might be suited for a traditional image classification setting, there is a need for techniques tailored toward tasks and settings of medical domain to push artificial intelligence in healthcare to a deployable state.
Publisher
Springer Science and Business Media LLC
Reference37 articles.
1. Rajpurkar, P., Chen, E., Banerjee, O. & Topol, E. J. Ai in health and medicine. Nat. Med. 28(1), 31–38 (2022).
2. Secinaro, S., Calandra, D., Secinaro, A., Muthurangu, V. & Biancone, P. The role of artificial intelligence in healthcare: A structured literature review. BMC Med. Inform. Decis. Mak. 21(1), 125 (2021).
3. Davenport, T. & Kalakota, R. The potential for artificial intelligence in healthcare. Future Healthc. J. 6(2), 94–98 (2019).
4. Kim, D. et al. Accurate auto-labeling of chest x-ray images based on quantitative similarity to an explainable AI model. Nat. Commun. 13(1), 1867 (2022).
5. Tiu, E. et al. Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning. Nat. Biomed. Eng. 20, 20 (2022).