{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T11:23:13Z","timestamp":1764760993310,"version":"3.46.0"},"reference-count":51,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Sleep is increasingly acknowledged as a cornerstone of public health, with chronic sleep loss implicated in preventable injury and deaths. Obstructive sleep apnea (OSA) affects over one billion people worldwide but remains widely under-diagnosed due to dependence on polysomnography (PSG), an overnight, hospital-based intrusive procedure. As an adjunct to the clinical diagnosis of OSA, this paper presents a low-cost, smartphone-based Generative AI agent framework for sleep apnea detection and sleep coaching at the bedside. Powered by an on=device Generative AI model, the four agents of this framework include a classifier, an analyser, a visualiser, and a sleep coach. The key agent activities performed are sleep apnea detection, sleep data management, data analysis, and natural language sleep coaching. The framework was empirically evaluated on a subject-independent hold-out set drawn from a dataset of 500 clinician annotated clips collected from 10 clinically diagnosed OSA patients. Sleep apnea detection achieved an accuracy of 0.89, precision of 0.91, and recall of 0.88, with nightly Apnea\u2013Hypopnea Index (AHI) estimates strongly correlated with PSG-based clinical scores. The framework was further assessed on the performance metrics of computation, latency, memory, and energy usage. The results of these experiments confirm the feasibility of the proposed framework for large-scale, low-cost OSA screening, with pathways for future work in federated learning, noise robustness, and broad clinical validation.<\/jats:p>","DOI":"10.3390\/make7040159","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T10:34:01Z","timestamp":1764758041000},"page":"159","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generative AI Agents for Bedside Sleep Apnea Detection and Sleep Coaching"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3121-9212","authenticated-orcid":false,"given":"Ashan","family":"Dhananjaya","sequence":"first","affiliation":[{"name":"Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0837-0076","authenticated-orcid":false,"given":"Gihan","family":"Gamage","sequence":"additional","affiliation":[{"name":"Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, Australia"}]},{"given":"Sivaluxman","family":"Sivananthavel","sequence":"additional","affiliation":[{"name":"Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, Australia"},{"name":"East Grampians Health Service, Ararat, VIC 3377, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2157-3767","authenticated-orcid":false,"given":"Nishan","family":"Mills","sequence":"additional","affiliation":[{"name":"Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3878-5969","authenticated-orcid":false,"given":"Daswin","family":"De Silva","sequence":"additional","affiliation":[{"name":"Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1484-7678","authenticated-orcid":false,"given":"Milos","family":"Manic","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Virginia Commonwealth University, Richmond, VA 23284, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"211","DOI":"10.4324\/9781003161530-7","article-title":"Sleep Disorders","volume":"Volume I","author":"Hauri","year":"2021","journal-title":"Handbook of Psychology and Health"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"E133","DOI":"10.5888\/pcd10.130081","article-title":"Raising Awareness of Sleep as a Healthy Behavior","volume":"10","author":"Perry","year":"2013","journal-title":"Prev. Chronic Dis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1097\/JCMA.0000000000000741","article-title":"Comparison of a Home Sleep Test with In-Laboratory Polysomnography in the Diagnosis of Obstructive Sleep Apnea Syndrome","volume":"85","author":"Hung","year":"2022","journal-title":"J. Chin. Med. Assoc."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/B978-0-444-64032-1.00025-4","article-title":"Chapter 25\u2014Polysomnography","volume":"Volume 160","author":"Levin","year":"2019","journal-title":"Handbook of Clinical Neurology"},{"key":"ref_5","first-page":"1311","article-title":"Obstructive Sleep Apnea is a Common Disorder in the Population: A Review on the Epidemiology of Sleep Apnea","volume":"7","author":"Franklin","year":"2015","journal-title":"J. Thorac. Dis."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1001\/jamaoto.2022.0244","article-title":"Evaluating Prediction Models of Sleep Apnea From Smartphone-Recorded Sleep Breathing Sounds","volume":"148","author":"Cho","year":"2022","journal-title":"JAMA-Otolaryngol. Neck Surg."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ren, Y., Wang, C., Yang, J., and Chen, Y. (May, January 26). Fine-grained Sleep Monitoring: Hearing Your Breathing with Smartphones. Proceedings of the 2015 IEEE Conference on Computer Communications (INFOCOM \u201915), Kowloon, Hong Kong.","DOI":"10.1109\/INFOCOM.2015.7218494"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Nandakumar, R., Gollakota, S., and Watson, N. (2015, January 8\u201322). Contactless Sleep Apnea Detection on Smartphones. Proceedings of the 13th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys \u201915), Florence, Italy.","DOI":"10.1145\/2742647.2742674"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1109\/ETFA46521.2020.9212098","article-title":"A deep learning approach for work related stress detection from audio streams in cyber physical environments","volume":"Volume 1","author":"Madhavi","year":"2020","journal-title":"Proceedings of the 2020 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e42672","DOI":"10.2196\/42672","article-title":"Wearable artificial intelligence for anxiety and depression: Scoping review","volume":"25","author":"AlSaad","year":"2023","journal-title":"J. Med. Internet Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1737","DOI":"10.1245\/s10434-018-6372-2","article-title":"The Patient-Reported Information Multidimensional Exploration (PRIME) framework for investigating emotions and other factors of prostate cancer patients with low intermediate risk based on online cancer support group discussions","volume":"25","author":"Bandaragoda","year":"2018","journal-title":"Ann. Surg. Oncol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"De Silva, D., Burstein, F., Jelinek, H.F., and Stranieri, A. (2015). Addressing the complexities of big data analytics in healthcare: The diabetes screening case. Australas. J. Inf. Syst., 19.","DOI":"10.3127\/ajis.v19i0.1183"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5529","DOI":"10.1109\/JBHI.2022.3154719","article-title":"Acoustic Screening for Obstructive Sleep Apnea in Home Environments Based on Deep Neural Networks","volume":"26","author":"Romero","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_14","first-page":"1827","article-title":"Sleep Apnea Detection by Tracheal Motion and Sound, and Oximetry via Application of Deep Neural Networks","volume":"15","author":"Aguiar","year":"2023","journal-title":"Nat. Sci. Sleep"},{"key":"ref_15","first-page":"e81846","article-title":"Evaluation of a Breath-Indicating Device for Enhanced Respiratory Monitoring and Apnea Detection in Postoperative Care: A Comparative Study","volume":"17","author":"Rowe","year":"2025","journal-title":"Cureus"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tran, N.B.M.H., Tran, T.Q.T., Tsai, C.Y., and Kang, J.H. (2025). Radar-Based Detection of Obstructive Sleep Apnea: A Systematic Review and Network Meta-Analysis of Diagnostic Accuracy Across Frequency Bands. Diagnostics, 15.","DOI":"10.3390\/diagnostics15162111"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1080\/14737159.2021.2002686","article-title":"Current and Future Strategies for Diagnostic and Management of Obstructive Sleep Apnea","volume":"21","author":"Khurana","year":"2021","journal-title":"Expert Rev. Mol. Diagn."},{"key":"ref_18","first-page":"1057","article-title":"A comprehensive study based on MFCC and spectrogram for audio classification","volume":"44","author":"Rawat","year":"2023","journal-title":"J. Inf. Optim. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"47795","DOI":"10.1109\/ACCESS.2021.3068045","article-title":"A Comprehensive Review of Speech Emotion Recognition Systems","volume":"9","author":"Wani","year":"2021","journal-title":"IEEE Access"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Verhaegh, W., Aarts, E., and Korst, J. (2004). Features for Audio Classification. Algorithms in Ambient Intelligence, Springer.","DOI":"10.1007\/978-94-017-0703-9"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1038\/d41586-023-00288-7","article-title":"ChatGPT: Five priorities for research","volume":"614","author":"Bollen","year":"2023","journal-title":"Nature"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Han, X., Fan, F., Rong, J., Li, Z., El Fakhri, G., Chen, Q., and Liu, X. (2024). Fair Text to Medical Image Diffusion Model with Subgroup Distribution Aligned Tuning. arXiv.","DOI":"10.1117\/12.3046450"},{"key":"ref_23","unstructured":"Gu, Y., Yang, J., Usuyama, N., Li, C., Zhang, S., Lungren, M.P., Gao, J., and Poon, H. (2023). BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1001\/jama.2023.1344","article-title":"Nonhuman \u201cAuthors\u201d and Implications for the Integrity of Scientific Publication and Medical Knowledge","volume":"329","author":"Flanagin","year":"2023","journal-title":"JAMA"},{"key":"ref_25","unstructured":"Sun, R., Arik, S.\u00d6., Muzio, A., Miculicich, L., Gundabathula, S., Yin, P., Dai, H., Nakhost, H., Sinha, R., and Wang, Z. (2024). SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended). arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Vaithilingam, P., Zhang, T., and Glassman, E.L. (May, January 29). Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. Proceedings of the CHI EA \u201922: Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems, New York, NY, USA.","DOI":"10.1145\/3491101.3519665"},{"key":"ref_27","unstructured":"Lewis, P.S., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., K\u00fcttler, H., Lewis, M., Yih, W.t., and Rockt\u00e4schel, T. (2020, January 6\u201312). Retrieval-augmented generation for knowledge-intensive NLP tasks. Proceedings of the NIPS\u201920: Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"18912","DOI":"10.1109\/ACCESS.2025.3532853","article-title":"Agentic AI: Autonomous Intelligence for Complex Goals\u2014A Comprehensive Survey","volume":"13","author":"Acharya","year":"2025","journal-title":"IEEE Access"},{"key":"ref_29","unstructured":"Fedorov, I., Plawiak, K., Wu, L., Elgamal, T., Suda, N., Smith, E., Zhan, H., Chi, J., Hulovatyy, Y., and Patel, K. (2024). Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations. arXiv."},{"key":"ref_30","unstructured":"(2025, September 11). Meta AI. Llama-3.2-1B-Instruct. Available online: https:\/\/huggingface.co\/meta-llama\/Llama-3.2-1B-Instruct."},{"key":"ref_31","unstructured":"(2025, March 02). Normal Respiratory Rate, Volume, Breathing Chart. Available online: http:\/\/www.normalbreathing.com\/index-nb.php."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"597","DOI":"10.5664\/jcsm.2172","article-title":"Rules for scoring respiratory events in sleep: Update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events. Deliberations of the Sleep Apnea Definitions Task Force of the American Academy of Sleep Medicine","volume":"8","author":"Berry","year":"2012","journal-title":"J. Clin. Sleep Med."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Pahar, M., Klopper, M., Warren, R., and Niesler, T. (2021). COVID-19 Detection in Cough, Breath and Speech Using Deep Transfer Learning and Bottleneck Features. Comput. Biol. Med., 141.","DOI":"10.1016\/j.compbiomed.2021.105153"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Han, S., Williamson, B.D., and Fong, Y. (2021). Improving random forest predictions in small datasets from two-phase sampling designs. BMC Med. Inform. Decis. Mak., 21.","DOI":"10.1186\/s12911-021-01688-3"},{"key":"ref_35","unstructured":"Kohavi, R. (1995, January 20\u201325). A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the IJCAI\u201995: 14th International Joint Conference on Artificial Intelligence, San Francisco, CA, USA."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"375","DOI":"10.5664\/jcsm.5588","article-title":"Breathing and Snoring Sound Characteristics during Sleep in Adults","volume":"12","author":"Levartovsky","year":"2016","journal-title":"J. Clin. Sleep Med."},{"key":"ref_37","unstructured":"de S\u00e1, A.G.V.T., de Oliveira, G.M.B., and Ochi, L.S. (2014, January 10\u201312). An Android-Based Mobile System for Real-Time Human Activity Recognition. Proceedings of the 2014 IEEE 26th International Conference on Tools with Artificial Intelligence, Limassol, Cyprus."},{"key":"ref_38","first-page":"30","article-title":"Opportunities and challenges of generative artificial intelligence: Research, education, industry engagement, and social impact","volume":"19","author":"Kaynak","year":"2024","journal-title":"IEEE Ind. Electron. Mag."},{"key":"ref_39","unstructured":"American Academy of Sleep Medicine (2025, July 18). Clinical Practice Guideline for the Treatment of Obstructive Sleep Apnea in Adults. Available online: https:\/\/aasm.org\/clinical-resources\/practice-standards\/guidelines-in-development."},{"key":"ref_40","unstructured":"American Academy of Sleep Medicine (2023). International Classification of Sleep Disorders\u2014Third Edition, Text Revision (ICSD-3-TR), American Academy of Sleep Medicine."},{"key":"ref_41","unstructured":"Shen, W., Zhang, X., Yao, Y., Zheng, R., Guo, H., and Liu, Y. (2024). Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards. arXiv."},{"key":"ref_42","unstructured":"PyTorch (2025, September 11). ExecuTorch LLaMA Android Demo App. Available online: https:\/\/docs.pytorch.org\/executorch\/0.6\/llm\/llama-demo-android.html."},{"key":"ref_43","unstructured":"PyTorch (2025, September 11). ExecuTorch XNNPACK Delegate (CPU Backend). Available online: https:\/\/docs.pytorch.org\/executorch\/0.3\/native-delegates-executorch-xnnpack-delegate.html."},{"key":"ref_44","unstructured":"Han, J., Pei, J., and Tong, H. (2022). Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers Inc.. [4th ed.]."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Silhavy, R., and Silhavy, P. (2023). A Review of Evaluation Metrics in Machine Learning Algorithms. Artificial Intelligence Application in Networks and Systems, Springer.","DOI":"10.1007\/978-3-031-35314-7"},{"key":"ref_46","unstructured":"Thiemann, J., Ito, N., and Vincent, E. (2025, September 01). DEMAND: Diverse Environments Multi-Channel Acoustic Noise Database. Available online: https:\/\/zenodo.org\/record\/1227121."},{"key":"ref_47","unstructured":"MIT Laboratory for Computational Physiology (2025, September 01). PhysioNet Snore Database. Available online: https:\/\/physionet.org\/content\/?csrfmiddlewaretoken=lIU0mZC30K2DHE8r81LLfywZW2voWdN7nBv6M8aApladVAAGG8xpXbdePUcDWhWp&topic=&csrfmiddlewaretoken=lIU0mZC30K2DHE8r81LLfywZW2voWdN7nBv6M8aApladVAAGG8xpXbdePUcDWhWp&orderby=relevance-desc&csrfmiddlewaretoken=lIU0mZC30K2DHE8r81LLfywZW2voWdN7nBv6M8aApladVAAGG8xpXbdePUcDWhWp&types=0&types=1&types=2&types=3."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical methods for assessing agreement between two methods of clinical measurement","volume":"1","author":"Bland","year":"1986","journal-title":"Lancet"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"2191","DOI":"10.1001\/jama.2013.281053","article-title":"World Medical Association Declaration of Helsinki: Ethical principles for medical research involving human subjects","volume":"310","author":"Association","year":"2013","journal-title":"JAMA"},{"key":"ref_50","unstructured":"Colten, H.R., and Altevogt, B.M. (2006). Sleep Disorders and Sleep Deprivation: An Unmet Public Health Problem, Institute of Medicine, National Academies Press."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Kleyko, D., Osipov, E., De Silva, D., Wiklund, U., and Alahakoon, D. (2019, January 14\u201319). Integer self-organizing maps for digital hardware. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary.","DOI":"10.1109\/IJCNN.2019.8852471"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/159\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T11:15:19Z","timestamp":1764760519000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/159"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":51,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["make7040159"],"URL":"https:\/\/doi.org\/10.3390\/make7040159","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]}}}