Objectives: Presenting the advantages and added value of MDR approved AI driven digital dermoscope. explanation of work flow & precision of the AI tool.
Introduction: MDR and classification of AI tool in Dermoscopy and their added value in daily practice. results of latest publications and clinical trials. presenting the Hardware functions and practical examples in daily practice.
Materials / method: publications & clinical trial results
technical documentation of technology provided by FotoFinder Systems GmbH
Results: The CNN revealed an accuracy and ROC AUC with corresponding 95 % confidence intervals (CI) of 91.0 % (83.8 % to 95.2 %) and 0.981 (0.962 to 1). In level I, dermatologists showed a mean accuracy of 83.7 % (82.5 % to 84.8 %). With level II information, the accuracy improved to 87.8 % (86.7 % to 88.9 %; p < 0.001). When comparing accuracies of CNN and dermatologists in level II, the CNN’s accuracy was higher (91.0 % versus 87.8 %, p < 0.001). For experts with level II information results were on par with the CNN (91.0 % versus 90.4 %, p = 0.368).
Conclusion: The tested CNN accurately differentiated melanocytic from non-melanocytic skin lesions and outperformed dermatologists. The CNN may support clinicians and could be used in an ensemble approach combined with other CNN models. these 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.
Декларация COI
Получили ли вы финансовую поддержку для поисков этой ТЕМЫ?
Нет
Были ли вам предоставлены гонорары, выплаты или иная компенсация за вашу работу в этом исследовании?
Нет
Есть ли у Вас финансовые отношения с лицами, тесно конкурирующими с препаратами, изделиями или приборами, указанными в вашей презентации?
Да
Укажите лица (индивидуальное, предприятие, организация): FOTOFINDER SYSTEMS in Germany
Вы владеете или подали заявку на какие-либо патенты по инструментам, лекарствам или материалам для вашего исследования?
Нет
Эта работа представлена благодаря поддержке: FOTOFINDER SYSTEMS in Germany