DEEP LEARNING BASED SYSTEM FOR EARLY DETECTION OF RESPIRATORY DISORDERS

This paper presented RespireCare AI, a web-based clinical decision support system designed to automate the detection and classification of respiratory disorders using a hybrid CNN-LSTM deep learning architecture. The system addressed a genuine gap in existing diagnostic tools by combining real-time audio processing, spectrogram-based feature extraction, and sequential pattern analysis into a single integrated platform. By converting raw respiratory sounds into Mel-spectrograms and processing them through convolutional and recurrent layers, the system achieved a classification accuracy of approximately 97.2% across four pulmonary conditions — Normal, Asthma, COPD, and Pneumonia. The results demonstrated that combining spatial and temporal analysis leads to more reliable disease prediction compared to conventional single-model approaches. The interactive web interface further enhanced the system's practical value by providing clinicians with real-time waveform visualization, probability scores, and actionable clinical recommendations alongside each diagnosis. While the current implementation shows promising results, factors such as input audio quality and training data diversity remain areas for further improvement. Future work will focus on expanding the dataset, integrating continuous microphone-based monitoring, and exploring transfer learning strategies to improve generalization across varied patient demographics. Overall, RespireCare AI demonstrates how combining modern deep learning techniques with accessible web technology can meaningfully support early respiratory diagnosis in clinical settings

[1]  M. H. Islam, M. Rashed, N. K. Podder, M. I. Hossain and A. K. Mondol, "Enhancing COPD Detection with WaveNet: Assessing the Efficacy of Deep Learning Model," 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), Rangpur, Bangladesh, 2025, pp. 1-6, doi: 10.1109/QPAIN66474.2025.11171716. [2]  P. Nirwani, V. Gouda, P. M K and B. S, "Respiratory Disease Detection from Lung Sounds," 2025 1st International Conference on Advancement in Futuristic Technologies (ICAFT), Belagavi, India, 2025, pp. 1-5, doi: 10.1109/ICAFT66710.2025.11453136. [3]  G. Gopi and A. Varghese, "Deep Learning for Respiratory Sound-Based Disease Classification," 2025 International Conference on Advancements in Power, Communication and Intelligent Systems (APCI), Kannur, India, 2025, pp. 1-6, doi: 10.1109/APCI65531.2025.11136918. [4]  M. S. Muqeet and Ambika, "Enhancing Early Detection of Chronic Obstructive Pulmonary Disease using High-Resolution MRI and Advanced Deep Learning Techniques," 2025 Global Conference in Emerging Technology (GINOTECH), PUNE, India,           2025,        pp.          1-8,        doi: 10.1109/GINOTECH63460.2025.11076697. [5]  K. Adsule, E. Gade, R. Bhurke, A. Ram and G. Nagare, "Classification of Respiratory Disorders Using Deep Learning," 2023 1st DMIHER International Conference on Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), Wardha, India,       2023,        pp.          1-6,        doi: 10.1109/IDICAIEI58380.2023.10406512. [6]  N. Bhuvaneswary, B. N. Babu, N. Pavithra and K. I. Reddy, "Design and Development of an IoT and Web-Integrated Respiratory Disease Prediction System using Machine Learning," 2025 5th International Conference on Evolutionary Computing and Mobile Sustainable Networks (ICECMSN), Coimbatore, India, 2025, pp. 1546-1552, doi: 10.1109/ICECMSN68058.2025.11383348. [7]  M. R. Koravanavar and C. B. Kolanur, "Lung Sound Based Pulmonary Disease Classification Using Deep Learning," 2023 2nd International Conference on Futuristic Technologies (INCOFT), Belagavi, Karnataka, India, 2023, pp. 1-4, doi: 10.1109/INCOFT60753.2023.10425681. [8]  M. A. Iqbal, Dr.K.Devarajan, S. M. Ahmed and M. Sadanandam, "AI Driven Speech-Based Asthma Detection using Feature Optimization for Early Diagnosis," 2025 2nd International Conference on Recent Trends in Electrical, Electronics and Computing Technologies (ICRTEECT), Warangal, India, 2025, pp. 1-6, doi: 10.1109/ICRTEECT67512.2025.11448874. [9]  R. Rampriya, R. S. Reddy, K. L. Prasad, H. B. K. Kumar and R. V. Raja, "Diagnosis and Risk Analysis of Pulmonary Disorder in CXR Images using Optimized Deep Learning Techniques," 2025 6th International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India,  2025, pp.  1221-1226, doi: 10.1109/ICIRCA65293.2025.11089624. [10]           A. Rama et al., "Attention-Based Deep Neural Networks for Identifying Atypical Pulmonary Disorders in Chest X-rays," 2025 7th International Symposium on Advanced Electrical and Communication Technologies (ISAECT), Mohali, Punjab, India, 2025, pp. 1-6, doi: 10.1109/ISAECT68904.2025.11318805.