Objectives: Healthcare Professionals (HCPs) face multiple challenges in wound management, especially in community: choice of adapted wound dressing, follow-up of the wound throughout the healing pathway and communication within the care team. This leads into a non-optimal wound management, late referral to wound experts, negatively impacting healing time, costs and patient’s quality of life. To help HCPs face these challenges, an application was developed to monitor patient wound and coordinate care team around a secure patient wound file.

Materials / method: This new application presents different features:
• Pictures and wound data to monitor the wound
• Secured messaging to help coordination of the patient care team
• Treatment recommendations approved by wound experts based on the assessment of the wound
• When gathering sufficient historical wound data, predictive model within the application will allow to:
o Predict wound healing time for the patient
o Adapt the protocol recommendation in real time to the patient wound
o Automatically alert patient care team when the wound is not following the right trajectory

Results: Through this application enriched with artificial intelligence, following outcomes are expected:
• Improve wound healing process and reduce patient healing time by giving HCPs access to most efficient protocols for the patient wound
• Improve coordination among patient’s care team through a shared patient wound file

Solution has been launched in March 2019 in France, and first results from beta testers are very promising. It will be launched in UK, Spain and Germany early 2020.

Conclusion: Digital solutions enriched with artificial intelligence will play a pivotal role in the future of wound management by reducing healing time and costs and improving quality of life of the patients.

Disclosures

Did you receive any funding to support your research for this TOPIC?
Yes
Please specify entities (individual, company, society): URGO MEDICAL

Were you provided with any honoraria, payment or other compensation for your work on this study?
Yes
Please specify entities (individual, company, society): URGO MEDICAL

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): URGO MEDICAL

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: URGO MEDICAL

Objectives: description of the efficient and useful role of Artificial Intelligence in the today's dermatology practice

Introduction: Some people fear for their specialist field, others see AI as a helpful tool for diagnostic support, which in the future - in view of increasing patient demand and declining numbers of specialists - will be indispensable in practice. AI will be an effective tool for tele-dermatology and efficient categorization of patient risk groups.

Materials / method: "Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists”, by H.A. Haenssle et al. Annals of Oncology. doi:10.1093/annonc/mdy166
Artificial intelligence and melanoma diagnosis: ignoring human nature may lead to false predictions“ by Aimilios Lallas and Giuseppe Argenziano

Results: The "FotoFinder Moleanalyzer Pro" software detected 58 of the 60 cutaneous melanomas in the test database and thus reached a sensitivity of 96.7%. Out of 240 benign nevi, 205 were correctly diagnosed so that the specificity was 85.4%. The positive predictive value was 62.4%, while the negative predictive value was 99.0%.

Conclusion: Therefore we can say that the role of AI in the future dermatology practice is quite diverse but with focus on time saving and higher precision in detection of malignant lesions. FotoFinder’s technology considers a harmonized integration of Artificial Intelligence in the Software and Hardware configuration. Today’s problem and challenge in the health system is not only early diagnosis of skin cancer but also the high number of patients that block the time slots with benign angioma, dermatofibroma and other irrelevant lesions. AI can help to filter such cases and increase efficiency.

Disclosures

Did you receive any funding to support your research for this TOPIC?
No

Were you provided with any honoraria, payment or other compensation for your work on this study?
No

Do you have any financial relationship with any entity which may closely compete with the medications, materials or instruments covered by your study?
No

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 GmbH

Objectives: Discuss non invasive imaging of the skin and how it applies to both clinical dermatology, cosmetic dermatology and dermatologic surgery. Will discuss 3D photography, confocal microscopy, and dermoscopy.

Highlight the use of AI in dermatology for diagnosis of melanoma

Discuss the limitations and future advances

Introduction: The use of non invasive imaging is increasing in dermatology. This technology has been applied to diagnosis, management, monitoring, and more recently artificial intelligence. It is important to discuss the uses and limitations of the current technology including 3D total body photography, reflectance confocal microscopy, optical coherence tomography, and AI diagnosis. We will also discuss consumer facing technology such as mobile based applications.

Results: The use of technology such as total body photography, reflectance confocal microscopy, and dermoscopy have been shown to help dermatologists and physicians detect melanoma and other skin cancers earlier with a lower number needed to biopsy. The use deep neural networks have also improved artificial intelligence algorithms for the computer diagnosis of melanoma.

Conclusion: Technological advancements in non invasive imaging of the skin have improved and that coupled with artificial intelligence and machine learning will augment that practicing physician.

Disclosures

Did you receive any funding to support your research for this TOPIC?
No

Were you provided with any honoraria, payment or other compensation for your work on this study?
No

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): Canfield Scientific, Mavig, Lam Therapeutics

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 was not supported by any direct or non direct funding. It is under the author's own responsability

Objectives: We developed an artificial intelligence algorithm (AIA) for smartphones to determine the severity of facial acne using the GEA scale and to identify different types of acne lesion (comedonal, inflammatory) and postinflammatory hyperpigmentation (PIHP) or residual hyperpigmentation.

Materials / method: Overall, 5972 images (face, right and left profiles) obtained with smartphones (IOS and/or Android) from 1072 acne patients were collected. Three trained dermatologists assessed the acne severity for each patient. One acne severity grade per patient (grade given by the majority of the three dermatologists from the two sets of three images) was used to train the algorithm. Acne lesion identification was performed from a subgroup of 348 images using a tagging tool; tagged images served to train the algorithm.

Results: The algorithm evolved and was adjusted for sensibility, specificity and correlation using new images. The correlation between the GEA grade and the quantification and qualification of acne lesions both by the AIA and the experts for each image were evaluated for all AIA versions. At final version 6, the GEA grading provided by AIA reached 68% and was similar to that provided by the dermatologists.

Conclusion: Between version 4 and version 6, AIA improved precision results multiplied by 1.5 for inflammatory lesions, 2.5 for non-inflammatory lesions and by 2 for PIHP; recall was improved by 2.6, 1.6 and 2.7. The weighted average of precision and recall or F1 score was 84% for inflammatory lesions, 61% for non-inflammatory lesions and 72% for PIHP.

Disclosures

Did you receive any funding to support your research for this TOPIC?
Yes
Please specify entities (individual, company, society): La Roche-Posay Dermatological Laboratories

Were you provided with any honoraria, payment or other compensation for your work on this study?
Yes
Please specify entities (individual, company, society): La Roche-Posay Dermatological Laboratories

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): La Roche-Posay Dermatological Laboratories

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: La Roche-Posay Dermatological Laboratories

Disclosures

Did you receive any funding to support your research for this TOPIC?
Yes
Please specify entities (individual, company, society): Salary from LEO Pharma A/S

Were you provided with any honoraria, payment or other compensation for your work on this study?
Yes
Please specify entities (individual, company, society): Salary from LEO Pharma A/S

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): LEO Pharma A/S

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: Financial support from LEO Pharma A/S