Continuous, non-invasive oxygen saturation $\left(\text{SpO}_{2}\right)$ monitoring is a cornerstone of remote patient monitoring (RPM) and Hospital-at-Home care, yet dedicated pulse oximeter hardware remains a barrier in low-resource and community settings. The most accurate method for assessing oxygen saturation, according to current medical practice, is arterial blood gas (ABG) analysis. The downside of ABG analysis lies in the inherent invasive nature of the procedure- painful, stressful, and requiring clinically specialized staff. Pulse oximetry is the framework for quantifying the amount of Oxygen flowing through the blood cells through a pulse oximeter, which was invented in the 80s. Since then, interdisciplinary research has focused on technological invention and broader application domains. This paper presents a smartphone-based $\text{SpO}_{2}$ estimation system targeting deployment in digital health and telehealth applications, requiring no external sensors. Fingertip photoplethysmography (PPG) signals are extracted from 10-second videos captured on a Google Pixel 2 smartphone (12.2 MP dual-pixel CMOS sensor, LED flashlight), and 45 time-domain, frequency-domain, and derivative-based features are computed per segment. Three regression models—Support Vector Regressor (SVR), Ridge Linear Regression, and Random Forest Regressor (RFR) are compared under 5-fold cross-validated grid search optimization. Reference SpO $_{2}$ measurements were obtained using a Masimo Pronto pulse oximeter across 213 participants at a clinical center in Bangladesh (IRB-approved). The fine-tuned Support Vector Regressor (SVR) model outperforms the other models for $\text{SPO} _{2}$ prediction. This model achieved MAE = 0.23% and MSE = 0.11% on a held-out test set. Limitations, including narrow $\text{S p O}_{2}$ range, single-device scope, and absence of demographic subgroup analysis, are discussed alongside a roadmap for clinically deployable, trustworthy digital health tools.
Nafi Us Sabbir Sabith, Md. Martuza Ahamad, Kazi Zawad Arefin et al.· International Conference on...· 0 citations
Peripheral Artery Disease (PAD) is a serious and potentially limb and life-threatening condition that demands a timely and accurate diagnosis to prevent severe complications. Traditional diagnostic methods are often slow and error prone. Although PAD localization remains relatively less explored using machine learning, the development of efficient and deployable models for real-time arterial blockage identification demands more investigation. In this paper, we propose PAD-Net, a novel end-to-end object detection framework specifically optimized for the identification and localization of arterial blockage. By integrating Light-Weight Feature Adapter (LFA) and Transformer block into You Only Look Once (YOLO) architecture, our model enhances the possibility of capturing multi-scale vascular structures often obscured in complex medical backgrounds/conditions. The proposed model was evaluated on a novel dataset of lower-extremity CT angiograms collected from the National Institute of Cardiovascular Disease, Bangladesh. Experimental results demonstrate that the model achieves a Mean Average Precision of 0.87 (mAP@0.5) and 0.423 (mAP@0.5:0.95), achieving competitive performance compared with state-of-theart YOLO and RT-DETR (Real Time Detection Transformer) models. At the same time, it maintains real-time speed to make predictions. The proposed PAD-Net gives a strong and scalable solution for AI-based PAD diagnosis. Furthermore, to validate real-world applicability, the model is deployed on a web-based Streamlit Community Cloud. The deployment of the proposed model highlights the effectiveness of reliable PAD detection and its integration into clinical workflows.
Md Raisul Islam, M. Zaman, S. Ahmmed et al.· International Conference on...· 0 citations
Large Language Models (LLMs) offer significant potential for clinical decision support, but their deployment is constrained by hallucination, privacy risks, and limited interpretability. Retrieval-Augmented Generation (RAG) improves reliability by grounding outputs in patient-specific electronic health records (EHRs); however, it introduces new challenges related to sensitive data exposure. This paper proposes a governanceaware, privacy-preserving RAG framework for clinical triage decision support using the MIMIC-IV-Ext dataset. The framework integrates retrieval-based grounding, differential privacy, explainability, and an agentic orchestration layer within a unified architecture. An $\epsilon$-ledger is introduced to track cumulative privacy expenditure, and a Privacy-Utility-Explainability (PUE) framework is used to systematically evaluate trade-offs. Experimental results demonstrate that the proposed approach improves classification performance (e.g., achieving up to 82% accuracy and 88% AUROC) and reduces under-triage risk, while privacy mechanisms introduce only modest performance degradation. Retrieval-based attribution further enhances interpretability by linking predictions to clinically relevant cases. These results highlight the effectiveness of combining retrieval, privacy, and explainability for developing trustworthy and deployable healthcare AI systems.
A. K. I. Riad, Md Abdul Barek, Hossain Shahriar et al.· International Conference on...· 0 citations