{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T10:54:17Z","timestamp":1764759257101,"version":"3.46.0"},"reference-count":33,"publisher":"IOP Publishing","issue":"1","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:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Research and Publication Division at the University of Kelaniya","award":["RP\/03\/02\/08\/03\/2022"],"award-info":[{"award-number":["RP\/03\/02\/08\/03\/2022"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Hyperlipidemia detection involves invasive, time-consuming procedures requiring clinical laboratories and blood samples. Often asymptomatic in its early stages, hyperlipidemia significantly increases the risk of cardiovascular diseases. The objective of this study was to investigate whether hyperlipidemia produces detectable changes in pulse wave patterns and to develop a non-invasive, cost-effective diagnostic approach using deep learning techniques applied to finger pulse images. Pulse waves were recorded from 81 hyperlipidemia patients and 65 participants in the control group, with 700 single pulse wave cycles selected from each group. These waveforms were preprocessed and divided into training (70%), validation (15%), and testing (15%) subsets. Custom Convolutional Neural Network (CNN) architectures trained from scratch were developed and evaluated to identify the most effective classification model. After model selection, hyperparameter tuning was applied to enhance predictive performance. In parallel, pre-trained models such as Visual Geometry Group 16 (VGG16) were fine-tuned and optimized. The models were assessed using accuracy, precision, recall, and F1-score. The custom CNN models achieved the highest performance, with the top model reaching approximately 95%\u201396% for accuracy, precision, recall, and F1-score. The VGG16 models also performed well, with all metrics around 91%. Training and validation curves for both model types indicated strong learning capabilities with minimal overfitting or underfitting, showcasing their potential for generalization to unseen data. Deep learning models effectively differentiated pulse waves between individuals with hyperlipidemia and those in the control group, indicating that hyperlipidemia causes detectable changes in pulse wave patterns. This study could lead to the development of a reliable, efficient, and non-invasive device for hyperlipidemia screening.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae212a","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T22:47:54Z","timestamp":1763592474000},"page":"015004","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards real-time non-invasive detection of hyperlipidemia through finger pulse image analysis using deep learning"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7160-2904","authenticated-orcid":false,"given":"Hiruni","family":"Gunathilaka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rumesh","family":"Rajapaksha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0964-7826","authenticated-orcid":true,"given":"Thosini","family":"Kumarika","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinusha","family":"Perera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Uditha","family":"Herath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6958-1435","authenticated-orcid":false,"given":"Charith","family":"Jayathilaka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janitha A","family":"Liyanage","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S R D","family":"Kalingamudali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"bpexae212abib1","doi-asserted-by":"publisher","first-page":"2305","DOI":"10.1093\/eurheartj\/ehad371","type":"journal-article","article-title":"Lipid distributions in the global diagnostics network across five continents","volume":"44","author":"Martin","year":"2023","journal-title":"Eur. Heart J."},{"key":"bpexae212abib2","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1161\/CIRCULATIONAHA.122.062132","type":"journal-article","article-title":"Efficacy and safety of an investigational single-course CRISPR base-editing therapy targeting PCSK9 in nonhuman primate and mouse models","volume":"147","author":"Lee","year":"2023","journal-title":"Circulation"},{"key":"bpexae212abib3","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1186\/s12944-022-01721-y","type":"journal-article","article-title":"Distribution of lipid levels and prevalence of hyperlipidemia: data from the NHANES 2007\u20132018","volume":"21","author":"Li","year":"2022","journal-title":"Lipids Health Dis."},{"key":"bpexae212abib4","doi-asserted-by":"publisher","first-page":"809","DOI":"10.3390\/biomedicines11030809","type":"journal-article","article-title":"Hyperlipidemia and cardiovascular risk in children and adolescents","volume":"11","author":"Mainieri","year":"2023","journal-title":"Biomedicines"},{"key":"bpexae212abib5","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/s11886-018-1036-1","type":"journal-article","article-title":"Which lipids should be analyzed for diagnostic workup and follow-up of patients with hyperlipidemias?","volume":"20","author":"Langlois","year":"2018","journal-title":"Curr. Cardiol. Rep."},{"key":"bpexae212abib6","doi-asserted-by":"publisher","first-page":"3","DOI":"10.55578\/joaims.230308.001","type":"journal-article","article-title":"Development of a modern pulse diagnosis using harmonics analysis of arterial signals","volume":"4","author":"Wang","year":"2023","journal-title":"J. Artif. Intell Med. Sci."},{"key":"bpexae212abib7","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.amjhyper.2006.09.015","type":"journal-article","article-title":"Pulse wave velocity in familial combined hyperlipidemia","volume":"20","author":"Ter Avest","year":"2007","journal-title":"Am J. Hypertens."},{"key":"bpexae212abib8","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s10877-007-9097-5","type":"journal-article","article-title":"The relationship between the photoplethysmographic waveform and systemic vascular resistance","volume":"21","author":"Awad","year":"2007","journal-title":"J. Clin. Monit. Comput."},{"key":"bpexae212abib9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1504\/IJBET.2015.066962","type":"journal-article","article-title":"A multiple signal classification approach for photoplethysmography signals in healthy and athletic subjects","volume":"17","author":"Al-Fahoum","year":"2015","journal-title":"Int. J. Biomed. Eng. Technol."},{"key":"bpexae212abib10","doi-asserted-by":"publisher","first-page":"808451","DOI":"10.3389\/fphys.2021.808451","type":"journal-article","article-title":"Photoplethysmogram analysis and applications: an integrative review","volume":"12","author":"Park","year":"2022","journal-title":"Front Physiol."},{"key":"bpexae212abib11","doi-asserted-by":"publisher","first-page":"51","DOI":"10.3390\/informatics11030051","type":"journal-article","article-title":"Non-invasive diagnostic approach for diabetes using pulse wave analysis and deep learning","volume":"11","author":"Gunathilaka","year":"2024","journal-title":"Informatics."},{"key":"bpexae212abib12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-94913-y","type":"journal-article","article-title":"Imputation of the continuous arterial line blood pressure waveform from non-invasive measurements using deep learning","volume":"11","author":"Hill","year":"2021","journal-title":"Sci. Rep."},{"key":"bpexae212abib13","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/ab030e","type":"journal-article","article-title":"Estimating blood pressure trends and the nocturnal dip from photoplethysmography","volume":"40","author":"Radha","year":"2019","journal-title":"Physiol. Meas."},{"key":"bpexae212abib14","doi-asserted-by":"publisher","first-page":"3697","DOI":"10.1109\/JBHI.2022.3172514","type":"journal-article","article-title":"Deepcnap: a deep learning approach for continuous noninvasive arterial blood pressure monitoring using photoplethysmography","volume":"26","author":"Kim","year":"2022","journal-title":"IEEE J. Biomed Heal Informatics."},{"key":"bpexae212abib15","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102301","type":"journal-article","article-title":"Deep learning models for cuffless blood pressure monitoring from PPG signals using attention mechanism","volume":"65","author":"El-Hajj","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae212abib16","doi-asserted-by":"publisher","first-page":"4292","DOI":"10.1109\/TIM.2019.2947103","type":"journal-article","article-title":"Cuffless deep learning-based blood pressure estimation for smart wristwatches","volume":"69","author":"Song","year":"2020","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"bpexae212abib17","doi-asserted-by":"publisher","first-page":"7233","DOI":"10.3390\/s21217233","type":"journal-article","article-title":"Atrial fibrillation classification with smart wearables using short-term heart rate variability and deep convolutional neural networks","volume":"21","author":"Ramesh","year":"2021","journal-title":"Sensors"},{"key":"bpexae212abib18","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.hroo.2020.02.002","type":"journal-article","article-title":"Atrial fibrillation detection from raw photoplethysmography waveforms: a deep learning application","volume":"1","author":"Aschbacher","year":"2020","journal-title":"Hear Rhythm O2"},{"key":"bpexae212abib19","doi-asserted-by":"publisher","first-page":"1921","DOI":"10.1136\/heartjnl-2018-313147","type":"journal-article","article-title":"Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms","volume":"104","author":"Poh","year":"2018","journal-title":"Heart"},{"key":"bpexae212abib20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76816-6","type":"journal-article","article-title":"Prediction of vascular aging based on smartphone acquired PPG signals","volume":"10","author":"Dall\u2019Olio","year":"2020","journal-title":"Sci. Rep."},{"key":"bpexae212abib21","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3390\/info13020059","type":"journal-article","article-title":"Non-invasive classification of blood glucose level for early detection diabetes based on photoplethysmography signal","volume":"13","author":"Susana","year":"2022","journal-title":"Information."},{"key":"bpexae212abib22","first-page":"43","type":"conference-proceedings","article-title":"Design and development of non-invasive glucose measurement system","author":"Paul","year":"2012"},{"key":"bpexae212abib23","doi-asserted-by":"publisher","first-page":"7815","DOI":"10.3390\/s21237815","type":"journal-article","article-title":"90% accuracy for photoplethysmography-based non-invasive blood glucose prediction by deep learning with cohort arrangement and quarterly measured HbA1c","volume":"21","author":"Chu","year":"2021","journal-title":"Sensors"},{"key":"bpexae212abib24","doi-asserted-by":"publisher","first-page":"6506","DOI":"10.1038\/s41598-022-10360-3","type":"journal-article","article-title":"Deduction learning for precise noninvasive measurements of blood glucose with a dozen rounds of data for model training","volume":"12","author":"Lu","year":"2022","journal-title":"Sci. Rep."},{"key":"bpexae212abib25","doi-asserted-by":"publisher","first-page":"zsab142","DOI":"10.1093\/sleep\/zsab142","type":"journal-article","article-title":"Assessment of obstructive sleep apnea-related sleep fragmentation utilizing deep learning-based sleep staging from photoplethysmography","volume":"44","author":"Huttunen","year":"2021","journal-title":"Sleep"},{"key":"bpexae212abib26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-69935-7","type":"journal-article","article-title":"Wearable monitoring of sleep-disordered breathing: estimation of the apnea\u2013hypopnea index using wrist-worn reflective photoplethysmography","volume":"10","author":"Papini","year":"2020","journal-title":"Sci. Rep."},{"key":"bpexae212abib27","doi-asserted-by":"publisher","first-page":"3355","DOI":"10.3390\/app9163355","type":"journal-article","article-title":"Fast emotion recognition based on single pulse PPG signal with convolutional neural network","volume":"9","author":"Lee","year":"2019","journal-title":"Appl. Sci."},{"key":"bpexae212abib28","first-page":"2374","type":"conference-proceedings","article-title":"Feature augmented hybrid CNN for stress recognition using wrist-based photoplethysmography sensor","author":"Rashid","year":"2021"},{"key":"bpexae212abib29","first-page":"5556","type":"conference-proceedings","article-title":"RespNet: a deep learning model for extraction of respiration from photoplethysmogram","author":"Ravichandran","year":"2019"},{"key":"bpexae212abib30","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-51334-2","type":"journal-article","article-title":"Pulse-wave-pattern classification with a convolutional neural network","volume":"9","author":"Li","year":"2019","journal-title":"Sci. Rep."},{"key":"bpexae212abib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104662","type":"journal-article","article-title":"Non-invasive triglyceride detection: Using a combination of complementary multivariate photoplethysmogram features","volume":"83","author":"Chen","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae212abib32","doi-asserted-by":"publisher","first-page":"547","DOI":"10.3390\/healthcare10030547","type":"journal-article","article-title":"Diagnostic features and potential applications of PPG signal in healthcare: a systematic review","volume":"10","author":"Almarshad","year":"2022","journal-title":"Healthcare."},{"key":"bpexae212abib33","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","type":"journal-article","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T10:49:39Z","timestamp":1764758979000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae212a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12,3]]},"published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae212a","relation":{},"ISSN":["2057-1976"],"issn-type":[{"type":"electronic","value":"2057-1976"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"Towards real-time non-invasive detection of hyperlipidemia through finger pulse image analysis using deep learning","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-07-03","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-11-19","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-03","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}