{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T21:33:24Z","timestamp":1793309604539,"version":"4.5.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Parkinson's disease (PD) is a common neurodegenerative disorder. Traditional diagnostic methods, relying on clinical assessment and imaging, are often invasive, costly, and require specialized personnel, posing barriers to early detection. As approximately 90% of PD patients develop vocal impairments, vocal analysis emerges as a promising non-invasive diagnostic tool. However, individual deep learning models are often limited by overfitting and poor generalizability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposes a PD classification method using spectrogram feature fusion with pre-trained convolutional neural networks (CNNs). Voice recordings were obtained from 61 PD patients and 70 healthy controls (HC) at the First Affiliated Hospital of Henan University of Science and Technology. Preprocessing the raw speech signals yielded 2,476 spectrograms. Three pre-trained models, DenseNet121, MobileNetV3-Large, and ShuffleNetV2, were used for feature extraction. The output of MobileNetV3-Large was adjusted using a 1 \u00d7 1 convolutional layer to ensure dimensional alignment before features were fused via summation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Evaluation using 5-fold cross-validation demonstrated that models employing feature fusion consistently outperformed individual models across all metrics. Specifically, the fusion of MobileNetV3-Large and ShuffleNetV2 achieved the highest accuracy of 95.56% and an AUC of 0.99. Comparative experiments with existing state-of-the-art methods confirmed the competitive performance of the proposed approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>\n                      The fusion of multi-model features more effectively captures subtle pathological signatures in PD speech, overcoming the limitations of single models. This method provides a reliable, low-cost, and non-invasive tool for auxiliary PD diagnosis, with significant potential for clinical application. The code is available at\n                      <jats:ext-link>https:\/\/github.com\/lvrongfu\/pjs<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2025.1706317","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:25:12Z","timestamp":1762352712000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Parkinson's disease detection using spectrogram-based multi-model feature fusion networks"],"prefix":"10.3389","volume":"16","author":[{"given":"Wenna","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongfu","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jincan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ganqin","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"11687","DOI":"10.1038\/s41598-025-96575-6","article-title":"Explainable artificial intelligence to diagnose early Parkinson's disease via voice analysis","volume":"15","author":"Shen","year":"2025","journal-title":"Sci Rep."},{"key":"B2","first-page":"1","article-title":"Ensemble learning approaches for detecting Parkinson's disease","volume-title":"2022 IEEE 9th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON)","author":"Bhoomika","year":"2022"},{"key":"B3","first-page":"1","article-title":"Parkinson disease detection using various machine learning algorithms","volume-title":"2022 International Conference on Advanced Computing Technologies and Applications (ICACTA)","author":"Kanakaprabha","year":"2022"},{"key":"B4","doi-asserted-by":"publisher","first-page":"109767","DOI":"10.1016\/j.compbiomed.2025.109767","article-title":"Review on computational methods for the detection and classification of Parkinson's Disease","volume":"187","author":"Singh","year":"2025","journal-title":"Comput Biol Med."},{"key":"B5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/GCAT55367.2022.9971828","article-title":"Classification using radial basis function for prediction of Parkinson's disease","volume-title":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","author":"Umar","year":"2022"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/GCAT55367.2022.9971993","article-title":"Detecting Parkinsons disease with image classification","volume-title":"2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT)","author":"Kanagaraj","year":"2022"},{"key":"B7","doi-asserted-by":"publisher","first-page":"20615","DOI":"10.1038\/s41598-023-47568-w","article-title":"machine learning method to process voice samples for identification of Parkinson's disease","volume":"13","author":"Iyer","year":"2023","journal-title":"Sci Rep."},{"key":"B8","first-page":"734","article-title":"A machine learning model for early prediction of Parkinson's disease from wearable sensors","volume-title":"2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC)","author":"Gene","year":"2023"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1084001","DOI":"10.3389\/frai.2023.1084001","article-title":"Machine learning approaches to identify Parkinson's disease using voice signal features","volume":"6","author":"Alshammri","year":"2023","journal-title":"Front Artif Intell."},{"key":"B10","doi-asserted-by":"publisher","first-page":"9562","DOI":"10.1109\/TNNLS.2022.3158966","article-title":"RegNet: self-regulated network for image classification","volume":"34","author":"Xu","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst."},{"key":"B11","doi-asserted-by":"publisher","first-page":"107660","DOI":"10.1016\/j.cmpb.2023.107660","article-title":"ResNet and its application to medical image processing: research progress and challenges","volume":"240","author":"Xu","year":"2023","journal-title":"Comput Methods Programs Biomed."},{"key":"B12","doi-asserted-by":"crossref","first-page":"11966","DOI":"10.1109\/CVPR52688.2022.01167","article-title":"A ConvNet for the 2020s","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2022"},{"key":"B13","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Liu","year":"2021"},{"key":"B15","doi-asserted-by":"publisher","first-page":"105021","DOI":"10.1016\/j.compbiomed.2021.105021","article-title":"Convolutional neural network ensemble for Parkinson's disease detection from voice recordings","volume":"141","author":"Hire\u0161","year":"2022","journal-title":"Comput Biol Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.patrec.2019.04.005","article-title":"Detecting Parkinson's disease with sustained phonation and speech signals using machine learning techniques","volume":"125","author":"Almeida","year":"2019","journal-title":"Pattern Recognit Lett."},{"key":"B17","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.bspc.2018.12.024","article-title":"On the design of automatic voice condition analysis systems. Part I: Review of concepts and an insight to the state of the art","volume":"51","author":"G\u00f3mez-Garc\u00eda","year":"2019","journal-title":"Biomed Signal Process Control."},{"key":"B18","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.neucom.2015.02.085","article-title":"Robust and complex approach of pathological speech signal analysis","volume":"167","author":"Mekyska","year":"2015","journal-title":"Neurocomputing."},{"key":"B19","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s12938-021-00951-y","article-title":"mobile-assisted voice condition analysis system for Parkinson's disease: assessment of usability conditions","volume":"20","author":"Carr\u00f3n","year":"2021","journal-title":"BioMed Eng Online."},{"key":"B20","doi-asserted-by":"publisher","first-page":"100184","DOI":"10.1016\/j.ibmed.2024.100184","article-title":"AIoT-based embedded systems optimization using feature selection for Parkinson's disease diagnosis through speech disorders","volume":"10","author":"Saleh","year":"2024","journal-title":"Intell-Based Med."},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1109\/IRASET57153.2023.10153040","article-title":"Healthcare embedded system for predicting Parkinson's disease based on ai of things","volume-title":"2023 3rd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)","author":"Saleh","year":"2023"},{"key":"B22","doi-asserted-by":"publisher","first-page":"16","DOI":"10.3390\/s19010016","article-title":"Classifying Parkinson's disease based on acoustic measures using artificial neural networks","volume":"19","author":"Berus","year":"2018","journal-title":"Sensors."},{"key":"B23","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/978-3-030-58323-1_36","article-title":"Transfer learning to detect Parkinson's disease from speech in different languages using convolutional neural networks with layer freezing","volume-title":"Text, Speech, and Dialogue","author":"Rios-Urrego","year":"2020"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1002\/mds.26424","article-title":"MDS clinical diagnostic criteria for Parkinson's disease: MDS-PD clinical diagnostic criteria","volume":"30","author":"Postuma","year":"2015","journal-title":"Mov Disord."},{"key":"B25","doi-asserted-by":"publisher","first-page":"102418","DOI":"10.1016\/j.bspc.2021.102418","article-title":"Advances in Parkinson's disease detection and assessment using voice and speech: a review of the articulatory and phonatory aspects","volume":"66","author":"Moro-Velazquez","year":"2021","journal-title":"Biomed Signal Process Control."},{"key":"B26","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s12880-022-00793-7","article-title":"Transfer learning for medical image classification: a literature review","volume":"22","author":"Kim","year":"2022","journal-title":"BMC Med Imaging."},{"key":"B27","doi-asserted-by":"publisher","first-page":"40","DOI":"10.3390\/technologies11020040","article-title":"A review of deep transfer learning and recent advancements","volume":"11","author":"Iman","year":"2023","journal-title":"Technologies."},{"key":"B28","doi-asserted-by":"publisher","first-page":"2827","DOI":"10.3390\/diagnostics13172827","article-title":"Classification of Parkinson's disease in patch-based MRI of Substantia Nigra","volume":"13","author":"Hussain","year":"2023","journal-title":"Diagnostics."},{"key":"B29","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1186\/s40537-022-00652-w","article-title":"Transfer learning: a friendly introduction","volume":"9","author":"Hosna","year":"2022","journal-title":"J Big Data."},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Huang","year":"2017"},{"key":"B31","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.1109\/ICCV.2019.00140","article-title":"Searching for MobileNetV3","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Howard","year":"2019"},{"key":"B32","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1007\/978-3-030-01264-9_8","article-title":"In: Lecture Notes in Computer Science","author":"ShuffleNet","year":"2018"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.6084\/m9.figshare.23849127.v1","article-title":"Voice samples for patients with Parkinson's disease and healthy controls","author":"Prior","year":"2023"},{"key":"B34","doi-asserted-by":"publisher","first-page":"36401","DOI":"10.1007\/s11042-024-19314-5","article-title":"novel hybrid CNN-KNN ensemble voting classifier for Parkinson's disease prediction from hand sketching images","volume":"84","author":"Saleh","year":"2024","journal-title":"Multimed Tools Appl."},{"key":"B35","doi-asserted-by":"publisher","first-page":"33207","DOI":"10.1007\/s11042-023-16881-x","article-title":"Predicting patients with Parkinson's disease using machine learning and ensemble voting technique","volume":"83","author":"Saleh","year":"2023","journal-title":"Multimed Tools Appl."},{"key":"B36","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1109\/CVPR42600.2020.00165","article-title":"GhostNet: more features from cheap operations","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Han","year":"2020"},{"key":"B37","doi-asserted-by":"crossref","first-page":"10425","DOI":"10.1109\/CVPR42600.2020.01044","article-title":"Designing network design spaces","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Radosavovic","year":"2020"},{"key":"B38","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/978-3-031-26409-2_27","article-title":"No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"Sunkara","year":"2023"},{"key":"B39","doi-asserted-by":"publisher","first-page":"107079","DOI":"10.1016\/j.engappai.2023.107079","article-title":"Multidimensional collaborative attention in deep convolutional neural networks for image recognition","volume":"126","author":"Yu","year":"2023","journal-title":"Eng Appl Artif Intell."},{"key":"B40","doi-asserted-by":"crossref","first-page":"16133","DOI":"10.1109\/CVPR52729.2023.01548","article-title":"ConvNeXt V2: co-designing and scaling ConvNets with masked autoencoders","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Woo","year":"2023"},{"key":"B41","doi-asserted-by":"crossref","first-page":"5694","DOI":"10.1109\/CVPR52733.2024.00544","article-title":"Rewrite the stars","volume-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Ma","year":"2024"},{"key":"B42","doi-asserted-by":"publisher","first-page":"105534","DOI":"10.1016\/j.bspc.2023.105534","article-title":"HiFuse: hierarchical multi-scale feature fusion network for medical image classification","volume":"87","author":"Huo","year":"2024","journal-title":"Biomed Signal Process Control."},{"key":"B43","doi-asserted-by":"publisher","first-page":"8274","DOI":"10.1109\/TPAMI.2024.3401450","article-title":"Conv2Former: a simple transformer-style ConvNet for visual recognition","volume":"46","author":"Hou","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"key":"B44","doi-asserted-by":"publisher","first-page":"108261","DOI":"10.1016\/j.engappai.2024.108261","article-title":"Multi-scale spatial pyramid attention mechanism for image recognition: an effective approach","volume":"133","author":"Yu","year":"2024","journal-title":"Eng Appl Artif Intell."},{"key":"B45","doi-asserted-by":"publisher","first-page":"5513","DOI":"10.1109\/CVPR52733.2024.00527","article-title":"UniRepLKNet: a universal perception large-kernel ConvNet for audio, video, point cloud, time-series and image recognition","author":"Ding","year":"2024","journal-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B46","unstructured":"MogaNet: multi-order gated aggregation network\n          \n          \n            \n              Li\n              S\n            \n            \n              Wang\n              Z\n            \n            \n              Liu\n              Z\n            \n            \n              Tan\n              C\n            \n            \n              Lin\n              H\n            \n            \n              Wu\n              D\n            \n          \n          The Twelfth International Conference on Learning Representations\n          \n          2024"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1706317\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T11:28:44Z","timestamp":1762428524000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1706317\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":46,"alternative-id":["10.3389\/fneur.2025.1706317"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1706317","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,5]]},"article-number":"1706317"}}