122 -10 (84) 2025 - Kasimova O.O., Rakhimaeva G.S. - INTEGRATION OF ARTIFICIAL INTELLIGENCE TECHNOLOGIES INTO THE DIAGNOSIS OF SLEEP DISORDERS IN ADULTS: FROM AUTOMATION TO CLINICALLY ORIENTED SOLUTIONS

INTEGRATION OF ARTIFICIAL INTELLIGENCE TECHNOLOGIES INTO THE DIAGNOSIS OF SLEEP DISORDERS IN ADULTS: FROM AUTOMATION TO CLINICALLY ORIENTED SOLUTIONS

Kasimova O.O. - Tashkent State Medical University

Rakhimaeva G.S. - Tashkent State Medical University

Daminova Kh.M. - Tashkent State Medical University

Resume

Introduction: The implementation of artificial intelligence (AI) in sleep disorder diagnostics faces challenges related to low decision transparency and insufficient integration into clinical practice. Modern research, such as that by Liang et al. and Hu et al., is shifting the focus from pure automation to creating hybrid systems that effectively interact with physicians. Objective: To analyze modern AI systems for diagnosing sleep disorders in terms of their methodological features, diagnostic accuracy, and potential for integration into the practice of neurologists and sleep specialists. Material and Methods: An analysis of publications was conducted, identifying two key methodological platforms: the Human-Computer Collaborative Sleep Scoring (HCSS) system and the Apnea Interact Xplainer (AIX) platform. The evaluation included diagnostic efficacy, decision transparency, and impact on clinical workflows. Results: Validation of the systems demonstrated high accuracy: HCSS achieved 90.42% agreement with an expert (kappa=0.85), while AIX showed an accuracy of 73.8–81.0% for stratifying OSA severity (R²=0.92–0.96). The implementation of HCSS reduced PSG analysis time by 50%. AIX, supporting flexible monitoring protocols (including pulse oximetry), reduces screening costs. A key achievement is overcoming the "black box" model through the visualization of diagnostic patterns and the highlighting of uncertain cases for physician review. Conclusion: Modern AI systems, such as HCSS and AIX, are transforming sleep disorder diagnostics by ensuring effective collaboration between the algorithm and the physician. Their integration into neurological practice is a promising direction for improving the accuracy, accessibility, and cost-effectiveness of diagnostics.

Keywords: artificial intelligence, sleep disorders, obstructive sleep apnea syndrome, polysomnography, sleep stages, neurology.

First page

701

Last page

705

For citation:Kasimova O.O., Rakhimaeva G.S., Daminova Kh.M. - INTEGRATION OF ARTIFICIAL INTELLIGENCE TECHNOLOGIES INTO THE DIAGNOSIS OF SLEEP DISORDERS IN ADULTS: FROM AUTOMATION TO CLINICALLY ORIENTED SOLUTIONS//New Day in Medicine 10(84)2025 701-705 https://newdayworldmedicine.com/en/new_day_medicine/10-84-2025

List of References

1. Benjafield A.V. et al. Estimation of the global prevalence and burden of obstructive sleep apnoea: a literature-based analysis. // Lancet Respir. Med. 2019;7:687–698 https://doi.org/10.1016/s2213-2600(19)30198-5
2. Berry R.B. et al. The AASM manual for the scoring of sleep and associated events. Rules, Terminology and Technical Specifications, Darien, Illinois, // American Academy of Sleep Medicine. (2012).
3. Carberry, J. C., et al. "Personalized management approach for OSA." // Chest 2018;153(3):744-755.
4. Choo, B. P. et al. Benchmarking performance of an automatic polysomnography scoring system in a population with suspected sleep disorders. // Front. Neurol. 2023;14:1123935. https://doi.org/10.3389/fneur.2023.1123935
5. Supratak, A., Dong, H., Wu, C. & Guo, Y. DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Trans. Neural Syst. Rehabil. Eng. 2017;25:1998-2008. DOI:10.1109/TNSRE.2017.2721116
6. Yildirim O., Baloglu U. B. Acharya U. R. A deep learning model for automated sleep stages classification using PSG signals. // Int. J. Environ. Res. Public Health 2019;16:599.
7. Liang S.-F., Shih Y.-H., Chen P.-Y. Kuo C.-E. Development of a human-computer collaborative sleep scoring system for polysomnography recordings. PLoS ONE 14, e0218948 (2019). doi: 10.1371/journal.pone.0218948
8. Hu S.-C. et al. Transparent artificial intelligence-enabled interpretable and interactive sleep apnea assessment across flexible monitoring scenarios. // Nat. Commun. 2025;16:7548. https://doi.org/10.1038/s41467-025-62864-x
9. Liang S. F., Kuo C. E., Hu Y. H. Cheng Y.S. A rule-based automatic sleep staging method. J. Neurosci. Methods 2012;205:169-176. https://doi.org/10.1016/j.jneumeth.2011.12.022
10. Zinchuk A.V., et al. "Phenotypic subtypes of obstructive sleep apnea: implications for personalized therapy." // The Lancet Respiratory Medicine 2021;9.7:769-782. doi:10.1016/S2213-2600(21)00083-8

    file

    download