Non-contact lung disease classification via orthogonal frequency division multiplexing-based passive 6G integrated sensing and communication

Abstract

Background: The screening tools for respiratory diseases typically involve spirometry (for asthma and COPD), CT scans (for interstitial lung disease), chest X-rays (for pneumonia and tuberculosis), and sputum analysis (for tuberculosis). Methods: This work examines a diagnostic approach whereby a subject’s chest is radio-exposed to non-ionizing 6G/WiFi multi-carrier radio signals at a frequency of 5.23 GHz. The fact that each respiratory disease modulates the amplitude, frequency, and phase of each radio frequency differently allows us to screen for five respiratory diseases: asthma, chronic obstructive pulmonary disease, interstitial lung disease, pneumonia, and tuberculosis. We collect a new dataset (OFDM-Breathe) from 220 individuals in a hospital setting, including 190 patients and 30 healthy controls. The dataset contains over 26,000 s of radio signal recordings across 64 frequencies. Several machine learning and deep learning models are evaluated to classify disease type based on the discriminatory signatures of radio signals. Results: We learn that a vanilla convolutional neural network achieves 98% accuracy in differentiating between the five respiratory diseases, along with strong performance in precision, recall, and F1-score. An ablation study demonstrates that reliable screening with up to 96% accuracy is possible using only eight frequencies, representing just 12.5% of the total bandwidth and leaving 87.5% available for 6G/WiFi data communication. Conclusions: The proposed method could enable real-time respiratory disease screening, could help realize the health equity in developing countries, and lays the groundwork for 6G/WiFi-enabled integrated sensing and communication platforms for healthcare systems of the future.