Benchmark datasets driving artificial intelligence development fail to capture the needs of medical professionals.
Kathrin BlagecJakob KraigerWolfgang FrühwirtMatthias SamwaldPublished in: CoRR (2022)
Keyphrases
- benchmark datasets
- artificial intelligence
- software engineering
- knowledge based systems
- ensemble methods
- computer science
- uci repository
- expert systems
- uci machine learning repository
- intelligent systems
- medical experts
- decision support
- knowledge engineering
- terms of classification accuracy
- knowledge economy
- data sets
- highly specialized
- ambient intelligence
- information processing
- information technology
- information systems
- machine learning
- development process
- cognitive science
- medical imaging
- medical knowledge
- computational intelligence
- case study
- medical education