Objectives: Highlighting the impact of AI as an assistant in daily practice of a modern dermatology clinic. Understanding the strengths and weaknesses of AI as a medical tool.
Introduction: The concept and integration of AI, the validation process and today`s accuracy of the tool. Based on clinical cases the positive aspects and the challenge on boarderline lesions is explained.
Materials / method: Human With Machine Study - Assessment of Diagnostic Performance of Dermatologists Cooperating With a Convolutional Neural Network in a Prospective Clinical Study - Winkler et al. (2023)
Skin lesions of face and scalp - Classification by a market-approved convolutional neural network in comparison with 64 dermatologists
Haenssle et al. (2021)
Results: The CNN revealed a sensitivity, specificity, and ROC AUC with corresponding 95% confidence intervals (CI) of 95.0% (95% CI 83.5% to 98.6%), 76.7% (95% CI 64.6% to 85.6%), and 0.918 (95% CI 0.866–0.970), respectively.
Conclusion: FotoFinder Study findings suggest that dermatologists may improve their performance when they cooperate with the market-approved CNN and that a broader application of this human with machine approach could be beneficial for dermatologists and patients.
Disclosures
Did you receive any funding to support your research for this TOPIC?
Yes
Please specify entities (individual, company, society): FOTOFINDER SYSTEMS
Were you provided with any honoraria, payment or other compensation for your work on this study?
Yes
Please specify entities (individual, company, society): FOTOFINDER SYSTEMS
Do you have any financial relationship with any entity which may closely compete with the medications, materials or instruments covered by your study?
Yes
Please specify entities (individual, company, society): FOTOFINDER SYSTEMS
Do you own or have you applied for any patents in conjunction with the instruments, medications or materials discussed in your study?
No
This work is presented thanks to the support of: FOTOFINDER SYSTEMS