Using Neural Networks for Diagnosing in Dermatology

Margarita Bobrova, Maksim Taranik, Georgy Kopanitsa

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


The paper deals with neural networks for decision support in diagnosing in dermatology. There were several iterations during development. We classified six diseases using ANN: (1) Psoriasis, (2) Seborrheic dermatitis, (3) Lichen planus, (4) Pityriasis rosea, (5) Cronic dermatitis, (6) Pityriasis rubra pilaris. At first, we used all 35 attributes to conclude skin disease diagnosis with the accuracy of 96.9%. Then, we reduced the set of analyzed attributes by Pearson correlation approach to eight attributes and increased the accuracy to 98.64%. Data collection time was reduced. Thereby, the speed of the diagnosing process was increased and, as a result, it was possible to form a treatment plan more effectively. The tools used for neural network development were the Python language, Keras library and PyCharm platform.

Original languageEnglish
Pages (from-to)211-216
Number of pages6
JournalStudies in Health Technology and Informatics
Publication statusPublished - 1 Jan 2019
Externally publishedYes


  • dermatology
  • Keras
  • Neural networks

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Fingerprint Dive into the research topics of 'Using Neural Networks for Diagnosing in Dermatology'. Together they form a unique fingerprint.

Cite this