Publications by authors named "Christine Mueller-Christmann"
We consider the statistical analysis of clinical trial designs with multiple simultaneous treatments per subject and multiple raters. The work is motivated by a clinical research project in dermatology where different hair removal techniques were assessed based on a within-subject comparison. We assume that clinical outcomes are assessed by multiple raters as continuous or categorical scores, e.
View Article and Find Full Text PDFArticle Synopsis
- The diagnosis of face and scalp lesions (FSL) is difficult for dermatologists due to overlapping characteristics, making artificial intelligence, specifically convolutional neural networks (CNN), a potential aid.
- In a study with 64 dermatologists classifying 100 FSL images, a significant portion of diagnoses (8.8%) were labeled as 'unclear' and often incorrectly managed.
- When dermatologists followed CNN classifications in these unclear cases, the rate of wrong management decisions dropped significantly, suggesting that AI support could improve clinical outcomes for patients with FSL.