Objective Evaluation Metrics for Automatic Classification of EEG Events
| Autor: | Meysam Golmohammadi, Iyad Obeid, Saeedeh Ziyabari, Vinit Shah, Joseph Picone |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
010504 meteorology & atmospheric sciences
business.industry Event (computing) Computer science Machine learning computer.software_genre 01 natural sciences Constant false alarm rate 03 medical and health sciences Range (mathematics) 0302 clinical medicine Software Metric (unit) Sensitivity (control systems) Artificial intelligence business computer 030217 neurology & neurosurgery 0105 earth and related environmental sciences |
| Zdroj: | Biomedical Signal Processing ISBN: 9783030674939 |
| Popis: | The evaluation of machine learning algorithms in biomedical fields for applications involving sequential data lacks both rigor and standardization. Common quantitative scalar evaluation metrics such as sensitivity and specificity can often be misleading and not accurately integrate application requirements. Evaluation metrics must ultimately reflect the needs of users yet be sufficiently sensitive to guide algorithm development. For example, feedback from critical care clinicians who use automated event detection software in clinical applications has been overwhelmingly emphatic that a low false alarm rate, typically measured in units of the number of errors per 24 h, is the single most important criterion for user acceptance. Though using a single metric is not often as insightful as examining performance over a range of operating conditions, there is, nevertheless, a need for a single scalar figure of merit. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|