THE CAPABILITIES OF ARTIFICIAL INTELLIGENCE BASED NON INVASIVE DIAGNOSTIC METHODS IN DETECTING NEONATAL JAUNDICE
Keywords:
Neonatal jaundice, artificial intelligence, non invasive diagnostics, bilirubin, transcutaneous bilirubinometry, convolutional neural network, vision transformer, smartphone application, deep learning, medical image analysisAbstract
Neonatal jaundice or hyperbilirubinemia is a serious medical condition occurring in sixty to eighty percent of newborns worldwide, which can lead to kernicterus, cerebral palsy, hearing loss, and even death if not detected and treated in a timely manner. The traditional diagnostic method of measuring total serum bilirubin is invasive, painful for the infant, poses a risk of infection, and is a difficult procedure to widely apply in resource limited areas. In recent years, the development of artificial intelligence technologies has created new opportunities for the non invasive detection of neonatal jaundice. The capabilities of artificial intelligence based non invasive diagnostic methods in detecting neonatal jaundice are systematically analyzed. The results show that convolutional neural networks, vision transformer architectures, and other deep learning models achieve over ninety percent accuracy in detecting neonatal jaundice. Mobile applications analyzing skin and sclera images obtained through smartphone cameras serve as a practical solution in resource limited areas. At the same time, challenges such as skin pigmentation, lighting conditions, and limited datasets remain. The future prospects of these technologies and ways to introduce them into clinical practice are also discussed.References
1.Shabalov, N. P. Neonatology: Textbook: in 2 vols. Vol. 1 / N. P. Shabalov. — 7th ed., revised and enlarged. — Moscow: GEOTAR-Media, 2026. — 720 p. — ISBN 978-5-9704-7888-2.
2.Degtyareva, A. V. Nonhemolytic Jaundice in Newborn Infants: Teaching Manual / A. V. Degtyareva, D. N. Degtyarev, Yu. M. Golubtsova. — Moscow: GEOTAR-Media, 2019. — 192 p. — ISBN 978-5-9704-5155-7.
3.Zolkin, A. L. Machine Learning and Artificial Intelligence in Medicine. Algorithms, Applications and Prospects: Textbook for Universities / A. L. Zolkin, V. D. Munister, P. M. Podolko. — Moscow: Yurait, 2024. — 185 p.
4.Rysuly, M. R. Artificial Intelligence in Healthcare: Teaching Manual. Vol. 1 / M. R. Rysuly, D. M. Gorshkov, V. V. Yurasov [et al.]. — Almaty: [s. n.], 2021. — 240 p.
5.Davydenko, S. A. Artificial Intelligence in Medical Diagnostics: Teaching-Methodical Manual / S. A. Davydenko. — Tomsk: TUSUR, 2022. — 96 p.




United Kingdom
Germany
France
Uzbekistan
Türkiye
Kazakhstan
Kyrgyzstan
Turkmenistan
Azerbaijan
India
Republic of Korea
Japan
United States of America
Kosovo
Italy
Spain
Poland
Netherlands
Belgium
Sweden
Norway
Finland
Denmark
Switzerland
Austria
Czech Republic
Hungary
Romania
Bulgaria
Greece
Portugal