This study presents an algorithmic framework for real-time multi-parameter fusion of biometric data and anomaly detection in cardiac monitor systems. Modern cardiac monitors continuously acquire and analyze multiple physiological parameters, including electrocardiographic signals, heart rate, oxygen saturation, non-invasive or invasive blood pressure, respiratory rate, body temperature, and other vital indicators. The simultaneous analysis of these parameters is essential for early detection of patient deterioration, arrhythmias, hypoxemia, hemodynamic instability, respiratory failure, and other critical conditions.

However, real-time cardiac monitoring systems face several technical challenges. These include sensor noise, motion artifacts, missing values, asynchronous data streams, false alarms, parameter drift, and inter-patient variability. Traditional threshold-based alarm systems are often insufficient because they evaluate each parameter separately and do not fully consider temporal dynamics or physiological relationships between signals. Therefore, multi-parameter data fusion and intelligent anomaly detection algorithms are required to improve monitoring accuracy and reduce clinically irrelevant alarms.

The proposed methodology includes real-time biometric data acquisition, preprocessing, synchronization of heterogeneous signals, feature extraction, multi-parameter fusion, temporal modeling, anomaly scoring, and alert generation. Machine learning and deep learning models such as recurrent neural networks, temporal convolutional networks, autoencoders, transformer-based models, and hybrid statistical-learning approaches are considered within the proposed framework. The study demonstrates that multi-parameter fusion can improve the reliability of anomaly detection by integrating complementary physiological information and identifying clinically meaningful deviations from normal patient-specific patterns.

cardiac monitor, biometric data fusion, anomaly detection, vital signs, real-time monitoring, ECG, SpO₂, blood pressure, respiratory rate, machine learning, temporal modeling, patient deterioration.

Abdullayev I. N. et al. Early Detection and Prognostic Assessment of Ischemic Heart Diseases Based on Multimodal Artificial Intelligence Algorithms //Technical Science Integrated Research. – 2026. – Т. 2. – №. 1. – С. 33-42.

Magrupov T., Nazirov R., Abdullaev I. Formation of a database of lung disease sound signals //Science and innovation. – 2024. – Т. 3. – №. A9. – С. 90-96.

Abdullayev I. N. et al. Generative Adversarial Network-Driven Segmentation of Myocardial Fibrosis in Transthoracic Echocardiography //Technical Science Integrated Research. – 2026. – Т. 2. – №. 1. – С. 43-51.

Nematov S. Q., Kamolova Y. M., Abdullayev I. N. Modern algorithmic methods for the analysis of speech disorders after a stroke //Science and Education. – 2023. – Т. 4. – №. 6. – С. 452-456.

Nematov S. Q., Kamolova Y. M., Abdullayev I. N. Speech therapy for adults //Science and Education. – 2022. – Т. 3. – №. 10. – С. 48-53.

Juraev V. et al. Fe3O4-ZnO Incorporated in Chitosan-Carbon Nanotubes (Fe3O4-ZnO-CHIT-CNT) as a Hybrid Organic Inorganic Biodegradable Nano-composites for Application in Bone Tissue Engineering //Journal of Nanostructures. – 2025. – Т. 15. – №. 3. – С. 1380-1393.

Nasimov R. et al. Asosda MRT tasvirlarni avtomat tahlili olish usuli. sun'iy intellekt //Universal xalqaro ilmiy jurnal. – 2025. – Т. 2. – №. 4.5. – С. 1004-1012.

Jiyanbayev O. E., Abdullayev I. N. Advantages of manufacturing according to international standards //Conference on the Role and Importance of Science in the Modern World. – 2025. – Т. 2. – №. 2. – С. 231-232.

Jiyanbayev O. E., Abdullayev I. N. Strategies for manufacturing medical equipment that meets international standards //sciencE. – 2025. – Т. 4. – №. 2-1. – С. 78-82.

Jiyanbayev O. E., Abdullayev I. N. methods for improving the system of servicing medical equipment //science. – 2025. – Т. 4. – №. 2-1. – С. 83-87.

Karabayeva L. X., Abdullayev I. N. O. G. L., Shakarov F. Q. Methods and technologies for increasing the energy efficiency of portable medical devices //Science and Education. – 2025. – Т. 6. – №. 2. – С. 170-175.

Abdullayev I. N. O., Yusupova N. S. Q., Tashev B. J. O. Modern echocardiographic methods for detection of cardiac dysynhrony //Science and Education. – 2025. – Т. 6. – №. 2. – С. 75-81.

Mirametov A. et al. Application of Artificial Intelligence in ECG Analysis: Problems and Their Solutions in Healthcare //Science and innovation. – 2024. – Т. 3. – №. A3. – С. 110-115.

Eshdavlatovich J. O., Nigmatilla o’g’li A. I. Effective resource management in medical facilities through artificial intelligence //International Journal of Medical Sciences And Clinical Research. – 2024. – Т. 4. – №. 08. – С. 39-43.

Абдуллаев И. Н., Жиянбаев О. Э., Насимов Р. Ҳ. Методика сокращения разрыва качества между реальными и синтетическими эхокардиографическими изображениями с применением глубокого обучения и механизмов мультивнимания //Science and Education. – 2025. – Т. 6. – №. 11. – С. 189-206