Tanmoy Paul

Dr. Tanmoy Paul


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 April 2025 in Bioengineering
Verified
Journal Article
Open access
PDF file
TPTanmoy Paul
Tanmoy Paul
OHOmiya Hassan
Omiya Hassan
CMChristina McCrae
Christina McCrae
Syed IslamSyed Islam
Syed Islam
AMAbu Mosa
Abu Mosa
Obstructive sleep apnea (OSA) is a common disorder characterized by disrupted breathing during sleep, leading to serious health consequences such as daytime fatigue, hypertension, metabolic issues, and cardiovascular disease. Polysomnography (PSG) is the standard diagnostic method but is costly and uncomfortable for patients, which has led to interest in artificial intelligence (AI) for automated OSA detection. To develop an explainable AI model that utilizes electrocardiogram (ECG) and blood oxygen saturation (SpO2) data for real-time apnea detection, providing visual explanations to enhance interpretability and support clinical decisions. It emphasizes giving visual explanations to show how specific segments of the signal contribute to the AI’s conclusions. Furthermore, it explores the combination of individual models to improve detection accuracy. The fusion of individual models demonstrates an enhanced performance in detection accuracy. Visual explanations for AI decisions highlight the importance of certain signal features, making the model’s operations transparent to healthcare providers. The proposed AI model addresses the crucial need for transparent and interpretable AI in healthcare. By providing real-time, explainable OSA detection, this approach represents a significant advancement in the field, potentially improving patient care and aiding in the early identification and management of OSA.

8 November 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
TPTanmoy Paul
Tanmoy Paul
OHOmiya Hassan
Omiya Hassan
CMChristina McCrae
Christina McCrae
Syed IslamSyed Islam
Syed Islam
AMAbu Mosa
Abu Mosa
Background: Obstructive sleep apnea is a sleep disorder that is linked to many health complications and can even be lethal in its severe form. Overnight polysomnography is the gold standard for diagnosing apnea, which is expensive, time-consuming, and requires manual analysis by a sleep expert. Artificial intelligence (AI)-embedded wearable device as a portable and less intrusive monitoring system is a highly desired alternative to polysomnography. However, AI models often require substantial storage capacity and computational power for edge inference which makes it a challenging task to implement the models in hardware with memory and power constraints. Methods: This study demonstrates the implementation of depth-wise separable convolution (DSC) as a resource-efficient alternative to spatial convolution (SC) for real-time detection of apneic activity. Single lead electrocardiogram (ECG) and oxygen saturation (SpO2) signals were acquired from the PhysioNet databank. Using each type of convolution, three different models were developed using ECG, SpO2, and model fusion. For both types of convolutions, the fusion models outperformed the models built on individual signals across all the performance metrics. Results: Although the SC-based fusion model performed the best, the DSC-based fusion model was 9.4, 1.85, and 11.3 times more energy efficient than SC-based ECG, SpO2, and fusion models, respectively. Furthermore, the accuracy, precision, and specificity yielded by the DSC-based fusion model were comparable to those of the SC-based individual models (~95%, ~94%, and ~94%, respectively). Conclusions: DSC is commonly used in mobile vision tasks, but its potential in clinical applications for 1-D signals remains unexplored. While SC-based models outperform DSC in accuracy, the DSC-based model offers a more energy-efficient solution with acceptable performance, making it suitable for AI-embedded apnea detection systems.