As technology advances rapidly and vast amounts of data are collected, artificial intelligence (AI) is increasing its presence in our lives. Medicine is a major focus point of AI developers. There are examples of algorithms on par with medical professionals, the most prominent case being skin cancer recognition. However, advancement involves the necessity to adapt to technology and to patients utilizing it on a daily basis. What is more, patients present growing trust towards machine-aided health care. Dermatology is a potent field for AI use as visual data are easy to collect, hold a lot of information and are paramount for diagnosis.

No abstract

Psoriasis is a common skin disorder that should be differentiated from other dermatoses if an effective treatment has to be applied. Regions of Interests, or scans for short, of diseased skin are processed by the VGG16 (or VGG19) deep convolutional neural network operating as a feature extractor. 1280 features related to a given scan are passed to the Support Vector Machine (SVM) classifier using Radial Basis Functions (RBF) kernels. The main quality of the described setup is a very small number of 75 psoriasis patients and 75 non-psoriasis patients used in the teaching and testing sets taken together. For each patient, a variable number of clinical images are taken. Then, the scans of size $$256 \times 256$$ 256 × 256 pixels are cropped from these images. There are 1988 scans of psoriasis patients and 1582 of non-psoriasis patients. The other quality of the described setup is the use of transfer learning for carrying over the neural network’s weights from non-medical domain (ImageNet) to clinical images of dermatoses. The next quality is that the input images are obtained with smart phone cameras without any special arrangements or equipment, so there is a great variability in working conditions, which hampers discriminative power of the classifier. The primary classification is carried out on individual scans, and then, majority voting is executed among the scans pertaining to an individual patient. The obtained recall (sensitivity) is 85.33%, and the precision is 82.58%. The 95% confidence interval for the accuracy of 80.08% is [77.14, 83.04]%. These numbers indicate that the described system can be useful for remote diagnosing of psoriasis, particularly in areas where access to dermatological personnel is limited.

Introduction: Dermatology offers great potential for the use of modern technologies such as remote online consultations, initial diagnostics via smartphone and computer applications, and artificial intelligence (AI)-based support for doctors. Aim: To investigate the attitude of dermatologists to such technologies. Material and methods: The participants completed a paper questionnaire comprising 16 questions regarding data such as age, gender and advancement in specialization, as well as views on the safety, benefits and future role of technologies such as AI and telemedicine in the future of medicine. The participants were chosen by snowball sampling. In total, 140 questionnaires were obtained; this was reduced to 90 by removing 50 respondents who were not familiar with term "telemedicine". The obtained data were subjected to statistical analysis. Results: The prevailing opinion was that while AI will not be able to replace doctors in the future, it could be used to improve the skills of medical personnel. Among the possible applications of these technologies in medicine, most of the responses indicated disease prevention (32%) and education (26%). None of the participants indicated that telemedicine could completely replace the traditional visit to the doctor's office. Conclusions: While the connection between medicine and modern technology is becoming stronger, most respondents believe that it is not possible for technologies such as AI or telemedicine to replace the work of human doctors.