Open Access Open Access  Restricted Access Subscription Access

Analysis of Biomedical Signal for Health Diagnosis Using AI

Prof. Parvin Kinikar, Pallavi Kevale, Vaishnavi Kumbhar, Shweta Mane

Abstract


Biomedical signal analysis plays a crucial role in early disease detection and continuous health monitoring. This paper presents an AI-based system for the analysis of biomedical signals, particularly Electrocardiogram (ECG) signals, to assist in health diagnosis. The proposed system focuses on detecting abnormalities by applying machine learning techniques to physiological signal data. Initially, raw ECG signals are collected from publicly available datasets and preprocessed to remove noise and unwanted artifacts using filtering techniques. Important features such as heart rate variability, QRS complex characteristics, and statistical parameters are extracted from the cleaned signals. These features are then used to train and test machine learning models for classifying normal and abnormal cardiac conditions. The experimental results demonstrate that the proposed model achieves high accuracy in detecting abnormalities, making it suitable for early diagnosis and remote health monitoring applications. The system can support healthcare professionals by providing automated, reliable, and real-time analysis of biomedical signals. Future enhancements may include deep learning integration and multi-signal analysis for improved diagnostic performance.


Full Text:

PDF

References


Acharya U. R. et al., “Deep learning for automated heart disease detection using ECG signals,” Information Sciences, 2017.

Faust O. et al., “EEG signal processing for seizure detection and epilepsy diagnosis,” Seizure Journal, 2015.

Sharma R. and Pachori R. B., “Classifying epileptic seizures using K-nearest neighbor method,” Expert Systems with Applications, 2015.

Jha C. K. and Kolekar M. H., “Machine learning-based systems for biomedical signal analysis – A review,” Biomedical Signal Processing and Control, 2020.

Li H. and Liu C., “AI in biomedical signal processing for healthcare diagnosis,” IEEE Reviews in Biomedical Engineering, 2021.

Rajpurkar P. et al., “Heart arrhythmia detection using deep neural networks,” Nature Medicine, 2019.

IEEE Transactions on Biomedical Engineering — The classic Pan– Tompkin’s algorithm paper: J. Pan & W. J. Tompkins, “A Real-Time QRS Detection Algorithm,” IEEE Trans. Biomed. Eng., 1985.

Vasco Ponciano, Ivan M. Pires, Fernando R. Ribeiro, et al., “Machine Learning Techniques with ECG and EEG Data: An Exploratory Study,” Computers (though not IEEE, but relevant for ML on ECG/EEG).

Y. Ansari, O. Mourad, K. Qaraqe, E. Serpedin, “Deep learning for ECG Arrhythmia detection and classification: an overview …” (survey from 2017 2023).

M. Cao et al., “ECG Heartbeat classification using deep transfer learning …” (they reference several IEEE works, e.g., deep learning + ECG).


Refbacks

  • There are currently no refbacks.