Transparent deep learning to identify autism spectrum disorders (ASD) in EHR using clinical notes.
Gondy LeroyJennifer G AndrewsMadison KeAlohi-PreeceAjay JaswaniHyunju SongMaureen Kelly GalindoSydney A RicePublished in: Journal of the American Medical Informatics Association : JAMIA (2024)
Transparent ML is achievable even with small datasets. By focusing on intermediate steps, deep ML can provide transparent decisions. By leveraging data redundancies, ML errors at the intermediate level have a low impact on final outcomes.
Keyphrases
- autism spectrum disorder
- deep learning
- electronic health record
- attention deficit hyperactivity disorder
- intellectual disability
- light emitting
- big data
- artificial intelligence
- adverse drug
- patient safety
- convolutional neural network
- type diabetes
- metabolic syndrome
- rna seq
- single cell
- quality improvement
- drug induced