Speech signals-based Parkinson’s disease diagnosis using hybrid autoencoder-LSTM models
Parkinson’s disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no definitive treatment for PD, but some medications used to control symptoms in the early stages have a critical effect on the progression of the dis...
Uloženo v:
| Vydáno v: | Computers in biology and medicine Ročník 193; s. 110334 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
Elsevier Ltd
01.07.2025
|
| Témata: | |
| ISSN: | 0010-4825, 1879-0534, 1879-0534 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Parkinson’s disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no definitive treatment for PD, but some medications used to control symptoms in the early stages have a critical effect on the progression of the disease. Approximately 90% of patients with PD have vocal problems, and although voice disorders seen in the early stages are not apparent in the patient’s speech, they can be detected by acoustic analysis. In this study, a decision support system was proposed for the diagnosis of PD utilizing the feature extraction power of autoencoder (AE) & long short-term memory (LSTM) models by using speech signals as input data. Firstly, simple (SAE), convolutional (CAE), and recurrent (RAE) AE models were created for the ablation analysis. Then, the effect of hybridization and deepening of these models with LSTM layers on the classification performance was observed. Within the scope of the study, RAE achieved the highest accuracy among the base models while CAE & LSTM hybrid model provided the highest performance among all models with 95.79% accuracy for PD diagnosis based on audio signals. It was concluded that hybridization of the AE and LSTM models significantly improved the performance of simple and convolutional AE, and deepening the network to a certain extent improves the classification performance according to the type of AE.
•Diagnosability of PD based on sound signals with 1D autoencoders.•93.53% accuracy with RAE model.•95.79% accuracy with CAE and LSTM hybrid model.•Highest accuracy with CAE based hybrid models among all hybrid models.•Improved performance and more balanced results with deepened hybrid models. |
|---|---|
| AbstractList | Parkinson’s disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no definitive treatment for PD, but some medications used to control symptoms in the early stages have a critical effect on the progression of the disease. Approximately 90% of patients with PD have vocal problems, and although voice disorders seen in the early stages are not apparent in the patient’s speech, they can be detected by acoustic analysis. In this study, a decision support system was proposed for the diagnosis of PD utilizing the feature extraction power of autoencoder (AE) & long short-term memory (LSTM) models by using speech signals as input data. Firstly, simple (SAE), convolutional (CAE), and recurrent (RAE) AE models were created for the ablation analysis. Then, the effect of hybridization and deepening of these models with LSTM layers on the classification performance was observed. Within the scope of the study, RAE achieved the highest accuracy among the base models while CAE & LSTM hybrid model provided the highest performance among all models with 95.79% accuracy for PD diagnosis based on audio signals. It was concluded that hybridization of the AE and LSTM models significantly improved the performance of simple and convolutional AE, and deepening the network to a certain extent improves the classification performance according to the type of AE.
•Diagnosability of PD based on sound signals with 1D autoencoders.•93.53% accuracy with RAE model.•95.79% accuracy with CAE and LSTM hybrid model.•Highest accuracy with CAE based hybrid models among all hybrid models.•Improved performance and more balanced results with deepened hybrid models. Parkinson's disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no definitive treatment for PD, but some medications used to control symptoms in the early stages have a critical effect on the progression of the disease. Approximately 90% of patients with PD have vocal problems, and although voice disorders seen in the early stages are not apparent in the patient's speech, they can be detected by acoustic analysis. In this study, a decision support system was proposed for the diagnosis of PD utilizing the feature extraction power of autoencoder (AE) & long short-term memory (LSTM) models by using speech signals as input data. Firstly, simple (SAE), convolutional (CAE), and recurrent (RAE) AE models were created for the ablation analysis. Then, the effect of hybridization and deepening of these models with LSTM layers on the classification performance was observed. Within the scope of the study, RAE achieved the highest accuracy among the base models while CAE & LSTM hybrid model provided the highest performance among all models with 95.79% accuracy for PD diagnosis based on audio signals. It was concluded that hybridization of the AE and LSTM models significantly improved the performance of simple and convolutional AE, and deepening the network to a certain extent improves the classification performance according to the type of AE.Parkinson's disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no definitive treatment for PD, but some medications used to control symptoms in the early stages have a critical effect on the progression of the disease. Approximately 90% of patients with PD have vocal problems, and although voice disorders seen in the early stages are not apparent in the patient's speech, they can be detected by acoustic analysis. In this study, a decision support system was proposed for the diagnosis of PD utilizing the feature extraction power of autoencoder (AE) & long short-term memory (LSTM) models by using speech signals as input data. Firstly, simple (SAE), convolutional (CAE), and recurrent (RAE) AE models were created for the ablation analysis. Then, the effect of hybridization and deepening of these models with LSTM layers on the classification performance was observed. Within the scope of the study, RAE achieved the highest accuracy among the base models while CAE & LSTM hybrid model provided the highest performance among all models with 95.79% accuracy for PD diagnosis based on audio signals. It was concluded that hybridization of the AE and LSTM models significantly improved the performance of simple and convolutional AE, and deepening the network to a certain extent improves the classification performance according to the type of AE. AbstractParkinson’s disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no definitive treatment for PD, but some medications used to control symptoms in the early stages have a critical effect on the progression of the disease. Approximately 90% of patients with PD have vocal problems, and although voice disorders seen in the early stages are not apparent in the patient’s speech, they can be detected by acoustic analysis. In this study, a decision support system was proposed for the diagnosis of PD utilizing the feature extraction power of autoencoder (AE) & long short-term memory (LSTM) models by using speech signals as input data. Firstly, simple (SAE), convolutional (CAE), and recurrent (RAE) AE models were created for the ablation analysis. Then, the effect of hybridization and deepening of these models with LSTM layers on the classification performance was observed. Within the scope of the study, RAE achieved the highest accuracy among the base models while CAE & LSTM hybrid model provided the highest performance among all models with 95.79% accuracy for PD diagnosis based on audio signals. It was concluded that hybridization of the AE and LSTM models significantly improved the performance of simple and convolutional AE, and deepening the network to a certain extent improves the classification performance according to the type of AE. Parkinson's disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no definitive treatment for PD, but some medications used to control symptoms in the early stages have a critical effect on the progression of the disease. Approximately 90% of patients with PD have vocal problems, and although voice disorders seen in the early stages are not apparent in the patient's speech, they can be detected by acoustic analysis. In this study, a decision support system was proposed for the diagnosis of PD utilizing the feature extraction power of autoencoder (AE) & long short-term memory (LSTM) models by using speech signals as input data. Firstly, simple (SAE), convolutional (CAE), and recurrent (RAE) AE models were created for the ablation analysis. Then, the effect of hybridization and deepening of these models with LSTM layers on the classification performance was observed. Within the scope of the study, RAE achieved the highest accuracy among the base models while CAE & LSTM hybrid model provided the highest performance among all models with 95.79% accuracy for PD diagnosis based on audio signals. It was concluded that hybridization of the AE and LSTM models significantly improved the performance of simple and convolutional AE, and deepening the network to a certain extent improves the classification performance according to the type of AE. |
| ArticleNumber | 110334 |
| Author | Akman Aydın, Eda Tekindor, Ayşe Nur |
| Author_xml | – sequence: 1 givenname: Ayşe Nur orcidid: 0000-0002-6124-5621 surname: Tekindor fullname: Tekindor, Ayşe Nur email: anur.tekindor@gazi.edu.tr organization: Graduate School of Natural and Applied Sciences, Department of Electrical and Electronics Engineering, Gazi University, Ankara, Turkiye – sequence: 2 givenname: Eda orcidid: 0000-0002-9887-3808 surname: Akman Aydın fullname: Akman Aydın, Eda email: edaakman@gazi.edu.tr organization: Faculty of Technology, Department of Electrical and Electronics Engineering, Gazi University, Ankara, Turkiye |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/40418858$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNkc-KFDEQxoOsuLOjryB99NJjpZPuzlxEXdY_MKIw68FTyJ_q2cz2dMbUtDA3X8PX80lMM6uCICx1qCJ89VH5fRfsbIgDMlZwWHDgzfPtwsXd3oa4Q7-ooKoXnIMQ8gGbcdUuS6iFPGMzAA6lVFV9zi6ItgAgQcAjdi5BcqVqNWNf1ntEd1NQ2Aymp9IaQl98Muk2DBSHn99_UOEDYX7O3WyGSIGKkcKwKW6ONgVfmPEQcXDRYypX6-sPxS6PPT1mD7vsiE_u-px9fnN1ffmuXH18-_7y1ap0QqpDid2yUw2XynorLbZuqVAp1whsjZK2bgVvVVeB5YA1NsqbZe1EU3lrGzC-EXP27OS7T_HriHTQu0AO-94MGEfSouK5QDQqS5_eSUebyel9CjuTjvo3jixQJ4FLkShh90fCQU_k9Vb_Ja8n8vpEPq--Pq3mr-O3gEmTCxkL-pDQHbSP4T4mL_4xcX0YgjP9LR6RtnFMU0qaa6o06PUU8JRvVQM0KrOas5f_N7jfDb8AQmO84w |
| Cites_doi | 10.1007/s00330-023-10003-9 10.1007/s10772-021-09837-9 10.1016/j.bspc.2021.102584 10.1109/TFUZZ.2019.2903753 10.1109/TWC.2021.3095855 10.1016/S1474-4422(21)00030-2 10.1007/s10772-024-10128-2 10.1016/j.engappai.2023.107494 10.1016/j.specom.2020.07.005 10.1038/nrneurol.2013.10 10.1016/j.bspc.2021.102452 10.1016/j.neunet.2020.06.018 10.1109/ACCESS.2020.2967845 10.1109/TNSRE.2018.2828143 10.1109/TNSRE.2019.2939655 10.1016/j.mehy.2020.109678 10.1016/j.parkreldis.2013.11.001 10.1109/WTS51064.2021.9433683 10.1016/j.ymssp.2020.107322 10.1007/s11042-024-18584-3 10.35784/acs-2023-11 10.1109/AISP48273.2020.9073595 10.1016/j.compag.2018.02.016 10.1016/j.asoc.2018.10.022 10.1016/j.bspc.2020.102225 10.3390/app122211601 10.1016/j.engappai.2022.105099 10.1016/j.compbiomed.2023.107031 10.1109/ACCESS.2023.3318015 10.3390/s18082521 10.1016/j.ibmed.2024.100184 10.1109/ACCESS.2017.2762475 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Ltd Elsevier Ltd Copyright © 2025 Elsevier Ltd. All rights reserved. Copyright © 2025. Published by Elsevier Ltd. |
| Copyright_xml | – notice: 2025 Elsevier Ltd – notice: Elsevier Ltd – notice: Copyright © 2025 Elsevier Ltd. All rights reserved. – notice: Copyright © 2025. Published by Elsevier Ltd. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1016/j.compbiomed.2025.110334 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1879-0534 |
| EndPage | 110334 |
| ExternalDocumentID | 40418858 10_1016_j_compbiomed_2025_110334 S0010482525006857 1_s2_0_S0010482525006857 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M --Z -~X .1- .55 .DC .FO .GJ .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 29F 4.4 457 4G. 53G 5GY 5VS 7-5 71M 77I 7RV 7X7 88E 8AO 8FE 8FG 8FH 8FI 8FJ 8G5 8P~ 9DU 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABMZM ABOCM ABUWG ABWVN ABXDB ACDAQ ACGFS ACIEU ACIUM ACIWK ACLOT ACNNM ACPRK ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADJOM ADMUD ADNMO AEBSH AEIPS AEKER AENEX AEUPX AEVXI AFFHD AFJKZ AFKRA AFPUW AFRAH AFRHN AFTJW AFXIZ AGGLG AGHFR AGQPQ AGUBO AGYEJ AHHHB AHMBA AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AJRQY AJUYK AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ANZVX AOUOD APXCP ARAPS ASPBG AVWKF AXJTR AZFZN AZQEC BBNVY BENPR BGLVJ BHPHI BKEYQ BKOJK BLXMC BNPGV BPHCQ BVXVI CCPQU CS3 DU5 DWQXO EBS EFJIC EFKBS EFLBG EJD EMOBN EO8 EO9 EP2 EP3 EX3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN FYUFA G-2 G-Q GBLVA GBOLZ GNUQQ GUQSH HCIFZ HLZ HMCUK HMK HMO HVGLF HZ~ IHE J1W K6V K7- KOM LK8 LX9 M1P M29 M2O M41 M7P MO0 N9A NAPCQ O-L O9- OAUVE OZT P-8 P-9 P2P P62 PC. PHGZM PHGZT PJZUB PPXIY PQGLB PQQKQ PROAC PSQYO Q38 R2- ROL RPZ RXW SAE SBC SCC SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSV SSZ SV3 T5K TAE UAP UKHRP WOW WUQ X7M XPP Z5R ZGI ~G- ~HD PUEGO AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| ID | FETCH-LOGICAL-c348t-ef9f86148bdb4be7c98e88c63e7a84b573178f20b10e5e68da95c362dbb60ad63 |
| ISSN | 0010-4825 1879-0534 |
| IngestDate | Thu Oct 02 22:43:21 EDT 2025 Thu Nov 20 01:45:36 EST 2025 Thu Nov 27 00:43:50 EST 2025 Wed Dec 10 14:22:39 EST 2025 Sat Sep 20 19:12:29 EDT 2025 Wed Dec 10 14:09:52 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Long short-term memory Speech analysis Autoencoder Parkinson’s disease |
| Language | English |
| License | Copyright © 2025 Elsevier Ltd. All rights reserved. |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c348t-ef9f86148bdb4be7c98e88c63e7a84b573178f20b10e5e68da95c362dbb60ad63 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-9887-3808 0000-0002-6124-5621 |
| PMID | 40418858 |
| PQID | 3212120368 |
| PQPubID | 23479 |
| PageCount | 1 |
| ParticipantIDs | proquest_miscellaneous_3212120368 pubmed_primary_40418858 crossref_primary_10_1016_j_compbiomed_2025_110334 elsevier_sciencedirect_doi_10_1016_j_compbiomed_2025_110334 elsevier_clinicalkeyesjournals_1_s2_0_S0010482525006857 elsevier_clinicalkey_doi_10_1016_j_compbiomed_2025_110334 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-07-01 |
| PublicationDateYYYYMMDD | 2025-07-01 |
| PublicationDate_xml | – month: 07 year: 2025 text: 2025-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Computers in biology and medicine |
| PublicationTitleAlternate | Comput Biol Med |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Gunduz (b16) 2021; 66 Sun, Cong, Li, Zhou, Xia, Liu, Wang, Xu, Chen (b8) 2023; 34 J.R. Orozco-Arroyave, J.D. Arias-Londoño, J.F. Vargas-Bonilla, M.C. González-Rátiva, E. Nöth, New Spanish speech corpus database for the analysis of people suffering from Parkinson’s disease, in: Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC’14, 2014, pp. 342–347. Dimauro, Girardi (b30) 2019 Liu, Sun, Han, He, Zhang, Wu (b34) 2022; 71 Saleh, Alouani, Daanouni, Hamida, Cherradi, Bouattane (b47) 2024; 10 Dasan, Panneerselvam (b37) 2021; 63 Malekroodi, Madusanka, Lee, Yi (b24) 2024 Parnetti, Castrioto, Chiasserini, Persichetti, Tambasco, El-Agnaf, Calabresi (b10) 2013; 9 Nour, Senturk, Polat (b19) 2023; 161 Boualoulou, Drissi, Nsiri (b44) 2023; 19 Zaman, Sah, Direkoğlu, Unoki (b32) 2023; 11 Varalakshmi, Bhuvaneaswari (b14) 2021 Shibina, Thasleema (b26) 2024; 27 S.B. Appakaya, R. Sankar, E. Sheybani, Novel Unsupervised Feature Extraction Protocol using Autoencoders for Connected Speech: Application in Parkinson’s Disease Classification, in: 2021 Wireless Telecommunications Symposium (WTS), California, 2021, pp. 1–5. A. Tripathi, S.K. Kopparapu, CNN based Parkinson’s Disease Assessment using Empirical Mode Decomposition, in: 29th Association for Computing Machinery (ACM) International Conference on Information and Knowledge Management (CIKM 2020), Online, 2020, pp. 1–7. Veetil, Sowmya, Orozco-Arroyave, Gopalakrishnan (b27) 2024; 129 Kamilaris, Prenafeta-Boldú (b17) 2018; 147 Keles, Keles, Keles, Okatan (b2) 2023; 83 Jun, Lee, Lee, Lee, Kim (b36) 2020; 8 Polat (b15) 2019 Vasquez-Correa, Arias-Vergara, Schuster, Orozco-Arroyave, Nöth (b23) 2020; 122 Vidya, Sasikumar (b12) 2022; 114 Cowton, Kyriazakis, Plötz, J. (b41) 2018; 18 Yu, Kim, Mechefske (b42) 2021; 149 B. Karan, S.S. Sahu, K. Mahto, Stacked auto-encoder based Time-frequency features of Speech signal for Parkinson disease prediction, in: 2020 International Conference on Artificial Intelligence and Signal Processing (AISP), Amaravati, 2020, pp. 1–4. Pandey, Sahu, Karan, Mishra (b45) 2024; 5 Sakakibara, Tateno, Kishi, Tsuyusaki, Terada, Inaoka (b9) 2014; 20 Taheri (b40) 2018 Tolosa, Garrido, Scholz, Poewe (b4) 2021; 20 Yu, Lei, Song, Liu, Wang (b18) 2020; 28 Polat, Nour (b3) 2020; 140 Shah, Zhang, Bais (b7) 2020; 130 Pinaya, Vieira, Garcia-Dias, Mechelli (b33) 2020 Ke, Vikalo (b43) 2022; 21 Hadadi, Arabani (b11) 2024; 83 Yu, Li, Lei, Wang (b6) 2019; 27 Rozmán, Sztahó, Kiss, Jenei (b20) 2021 Sakar, Serbes, Gunduz, Tunc, Nizam, Sakar, Tutuncu, Aydin, Isenkul, Apaydin (b13) 2019; 74 Maskeliūnas, Damaševišius, Kulikajevas, Padervinskis, Pribuišis, Uloza (b29) 2022; 12 Y. Zhang, A Better Autoencoder for Image: Convolutional Autoencoder, in: International Conference on Neural Information Processing ICONIP17-DCEC (2018) Siem Reap, 2018, pp. 1–7. Yu, Wu, Cai, Deng, Wang (b5) 2018; 26 Pandey, Sahu, Karan, Mishra (b25) 2024; 5 Dimauro, Di Nicola, Bevilacqua, Caivano, Girardi (b31) 2017; 5 Farina, Nakai, Shih (b38) 2020; 101 Lamba, Gulati, Alharbi, Jain (b1) 2022; 25 Mirzaei, Ghasemi (b35) 2021; 68 Sakar (10.1016/j.compbiomed.2025.110334_b13) 2019; 74 Maskeliūnas (10.1016/j.compbiomed.2025.110334_b29) 2022; 12 Cowton (10.1016/j.compbiomed.2025.110334_b41) 2018; 18 Dimauro (10.1016/j.compbiomed.2025.110334_b30) 2019 Tolosa (10.1016/j.compbiomed.2025.110334_b4) 2021; 20 Polat (10.1016/j.compbiomed.2025.110334_b15) 2019 Yu (10.1016/j.compbiomed.2025.110334_b6) 2019; 27 Varalakshmi (10.1016/j.compbiomed.2025.110334_b14) 2021 Liu (10.1016/j.compbiomed.2025.110334_b34) 2022; 71 Yu (10.1016/j.compbiomed.2025.110334_b42) 2021; 149 Rozmán (10.1016/j.compbiomed.2025.110334_b20) 2021 Lamba (10.1016/j.compbiomed.2025.110334_b1) 2022; 25 Zaman (10.1016/j.compbiomed.2025.110334_b32) 2023; 11 Ke (10.1016/j.compbiomed.2025.110334_b43) 2022; 21 Shah (10.1016/j.compbiomed.2025.110334_b7) 2020; 130 Sakakibara (10.1016/j.compbiomed.2025.110334_b9) 2014; 20 Vidya (10.1016/j.compbiomed.2025.110334_b12) 2022; 114 Mirzaei (10.1016/j.compbiomed.2025.110334_b35) 2021; 68 Pandey (10.1016/j.compbiomed.2025.110334_b45) 2024; 5 10.1016/j.compbiomed.2025.110334_b22 Nour (10.1016/j.compbiomed.2025.110334_b19) 2023; 161 10.1016/j.compbiomed.2025.110334_b21 Taheri (10.1016/j.compbiomed.2025.110334_b40) 2018 10.1016/j.compbiomed.2025.110334_b46 Hadadi (10.1016/j.compbiomed.2025.110334_b11) 2024; 83 Pandey (10.1016/j.compbiomed.2025.110334_b25) 2024; 5 Vasquez-Correa (10.1016/j.compbiomed.2025.110334_b23) 2020; 122 10.1016/j.compbiomed.2025.110334_b28 Veetil (10.1016/j.compbiomed.2025.110334_b27) 2024; 129 Gunduz (10.1016/j.compbiomed.2025.110334_b16) 2021; 66 Parnetti (10.1016/j.compbiomed.2025.110334_b10) 2013; 9 Polat (10.1016/j.compbiomed.2025.110334_b3) 2020; 140 Yu (10.1016/j.compbiomed.2025.110334_b5) 2018; 26 Yu (10.1016/j.compbiomed.2025.110334_b18) 2020; 28 Kamilaris (10.1016/j.compbiomed.2025.110334_b17) 2018; 147 Sun (10.1016/j.compbiomed.2025.110334_b8) 2023; 34 Farina (10.1016/j.compbiomed.2025.110334_b38) 2020; 101 Dasan (10.1016/j.compbiomed.2025.110334_b37) 2021; 63 Malekroodi (10.1016/j.compbiomed.2025.110334_b24) 2024 Dimauro (10.1016/j.compbiomed.2025.110334_b31) 2017; 5 Keles (10.1016/j.compbiomed.2025.110334_b2) 2023; 83 Saleh (10.1016/j.compbiomed.2025.110334_b47) 2024; 10 Pinaya (10.1016/j.compbiomed.2025.110334_b33) 2020 Shibina (10.1016/j.compbiomed.2025.110334_b26) 2024; 27 10.1016/j.compbiomed.2025.110334_b39 Jun (10.1016/j.compbiomed.2025.110334_b36) 2020; 8 Boualoulou (10.1016/j.compbiomed.2025.110334_b44) 2023; 19 |
| References_xml | – start-page: 1 year: 2021 end-page: 6 ident: b20 article-title: Automatic recognition of depression and Parkinson’s disease by LSTM networks using sample chunking publication-title: 2021 IEEE 12th International Conference on Cognitive Infocommunications (CogInfoCom), Online – volume: 5 start-page: 22199 year: 2017 end-page: 22208 ident: b31 article-title: Assessment of speech intelligibility in parkinson’s disease using a speech-to-text system publication-title: IEEE Access – volume: 34 start-page: 662 year: 2023 end-page: 672 ident: b8 article-title: Identification of Parkinson’s disease and multiple system atrophy using multimodal PET/MRI radiomics publication-title: Eur. Radiol. – volume: 9 start-page: 131 year: 2013 end-page: 140 ident: b10 article-title: Cerebrospinal fluid biomarkers in Parkinson disease publication-title: Nat. Rev. Neurol. – start-page: 1 year: 2018 end-page: 8 ident: b40 article-title: Learning graph representations with recurrent neural network autoencoders publication-title: Deep. Learn. Day KDD – volume: 18 start-page: 2521 year: 2018 ident: b41 article-title: A combined deep learning GRU-autoencoder for the early detection of respiratory disease in pigs using multiple environmental sensors publication-title: Sensors – volume: 149 year: 2021 ident: b42 article-title: Analysis of different RNN autoencoder variants for time series classification and machine prognostics publication-title: Mech. Syst. Signal Process. – volume: 83 start-page: 1 year: 2023 end-page: 13 ident: b2 article-title: PARNet: Deep neural network for the diagnosis of Parkinson’s disease publication-title: Multimedia Tools Appl. – reference: A. Tripathi, S.K. Kopparapu, CNN based Parkinson’s Disease Assessment using Empirical Mode Decomposition, in: 29th Association for Computing Machinery (ACM) International Conference on Information and Knowledge Management (CIKM 2020), Online, 2020, pp. 1–7. – year: 2019 ident: b30 article-title: Italian Parkinson’s voice and speech. IEEE DataPort – volume: 27 start-page: 1973 year: 2019 end-page: 1984 ident: b6 article-title: Modulation effect of acupuncture on functional brain networks and classification of its manipulation with EEG signals publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – volume: 27 start-page: 657 year: 2024 end-page: 671 ident: b26 article-title: A hybrid approach to detecting Parkinson’s disease using spectrogram and deep learning CNN-LSTM network publication-title: Int. J. Speech Technol. – volume: 74 start-page: 255 year: 2019 end-page: 263 ident: b13 article-title: A comparative analysis of speech signal processing algorithms for Parkinson’s disease classification and the use of the tunable Q-factor wavelet transform publication-title: Appl. Soft Comput. – volume: 28 start-page: 60 year: 2020 end-page: 71 ident: b18 article-title: Supervised network-based fuzzy learning of EEG signals for Alzheimer’s disease identification publication-title: IEEE Trans. Fuzzy Syst. – volume: 66 year: 2021 ident: b16 article-title: An efficient dimensionality reduction method using filter-based feature selection and variational autoencoders on Parkinson’s disease classification publication-title: Biomed. Signal Process. Control. – volume: 161 year: 2023 ident: b19 article-title: Diagnosis and classification of Parkinson’s disease using ensemble learning and 1D-PDCovNN publication-title: Comput. Biol. Med. – volume: 63 year: 2021 ident: b37 article-title: A novel dimensionality reduction approach for ECG signal via convolutional denoising autoencoder with LSTM publication-title: Biomed. Signal Process. Control. – volume: 26 start-page: 977 year: 2018 end-page: 986 ident: b5 article-title: Modulation of spectral power and functional connectivity in human brain by acupuncture stimulation publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – volume: 114 year: 2022 ident: b12 article-title: Parkinson’s disease diagnosis and stage prediction based on gait signal analysis using EMD and CNN–LSTM network publication-title: Eng. Appl. Artif. Intell. – volume: 5 year: 2024 ident: b25 article-title: Parkinson disease prediction using CNN-LSTM model from voice signal publication-title: SN Comput. Sci. – reference: S.B. Appakaya, R. Sankar, E. Sheybani, Novel Unsupervised Feature Extraction Protocol using Autoencoders for Connected Speech: Application in Parkinson’s Disease Classification, in: 2021 Wireless Telecommunications Symposium (WTS), California, 2021, pp. 1–5. – volume: 101 year: 2020 ident: b38 article-title: Searching for new physics with deep autoencoders publication-title: Phys. Rev. – reference: Y. Zhang, A Better Autoencoder for Image: Convolutional Autoencoder, in: International Conference on Neural Information Processing ICONIP17-DCEC (2018) Siem Reap, 2018, pp. 1–7. – reference: B. Karan, S.S. Sahu, K. Mahto, Stacked auto-encoder based Time-frequency features of Speech signal for Parkinson disease prediction, in: 2020 International Conference on Artificial Intelligence and Signal Processing (AISP), Amaravati, 2020, pp. 1–4. – volume: 20 start-page: 267 year: 2014 end-page: 273 ident: b9 article-title: MIBG myocardial scintigraphy in pre-motor Parkinson’s disease: A review publication-title: Parkinsonism Rel. Disord. – start-page: 1 year: 2019 end-page: 3 ident: b15 article-title: A hybrid approach to Parkinson disease classification using speech signal: The combination of SMOTE and random forests publication-title: 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science – volume: 71 year: 2022 ident: b34 article-title: Arrhythmia classification of LSTM autoencoder based on time series anomaly detection publication-title: Biomed. Signal Process. Control. – volume: 8 start-page: 19196 year: 2020 end-page: 19207 ident: b36 article-title: Feature extraction using an RNN autoencoder for skeleton-based abnormal gait recognition publication-title: IEEE Access – volume: 19 start-page: 2 year: 2023 ident: b44 article-title: CNN and LSTM for the classification of Parkinson’s disease based on the GTCC and MFCC publication-title: Appl. Comput. Sci. – volume: 11 year: 2023 ident: b32 article-title: A survey of audio classification using deep learning publication-title: IEEE Access – volume: 68 year: 2021 ident: b35 article-title: EEG motor imagery classification using dynamic connectivity patterns and convolutional autoencoder publication-title: Biomed. Signal Process. Control. – volume: 83 start-page: 81491 year: 2024 end-page: 81510 ident: b11 article-title: A novel approach for Parkinson’s disease diagnosis using deep learning and Harris Hawks optimization algorithm with handwritten samples publication-title: Multimed Tools Appl. – volume: 25 start-page: 583 year: 2022 end-page: 593 ident: b1 article-title: A hybrid system for Parkinson’s disease diagnosis using machine learning techniques publication-title: Int. J. Speech Technol. – volume: 130 start-page: 75 year: 2020 end-page: 84 ident: b7 article-title: Dynamical system based compact deep hybrid network for classification of Parkinson disease related EEG signals publication-title: Neural Netw. – volume: 122 start-page: 56 year: 2020 end-page: 67 ident: b23 article-title: Parallel representation learning for the classification of pathological speech: Studies on Parkinson’s disease and cleft lip and palate publication-title: Speech Commun. – reference: J.R. Orozco-Arroyave, J.D. Arias-Londoño, J.F. Vargas-Bonilla, M.C. González-Rátiva, E. Nöth, New Spanish speech corpus database for the analysis of people suffering from Parkinson’s disease, in: Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC’14, 2014, pp. 342–347. – year: 2024 ident: b24 article-title: Leveraging deep learning for fine-grained categorization of Parkinson’s disease progression levels through analysis of vocal acoustic patterns publication-title: Bioeng. – start-page: 193 year: 2020 end-page: 208 ident: b33 article-title: Autoencoders. Machine Learning – volume: 140 year: 2020 ident: b3 article-title: Parkinson disease classification using one against all based data sampling with the acoustic features from the speech signals publication-title: Med. Hypotheses – volume: 5 start-page: 381 year: 2024 ident: b45 article-title: Parkinson disease prediction using CNN-LSTM model from voice signal publication-title: Springer Nat. (SN) Comput. Sci. – volume: 20 start-page: 385 year: 2021 end-page: 397 ident: b4 article-title: Challenges in the diagnosis of Parkinson’s disease publication-title: Lancet Neurol. – volume: 10 year: 2024 ident: b47 article-title: AIoT-based embedded systems optimization using feature selection for Parkinson’s disease diagnosis through speech disorders publication-title: Intelligence- Based Med. – volume: 12 start-page: 11601 year: 2022 ident: b29 article-title: A hybrid U-lossian deep learning network for screening and evaluating Parkinson’s disease publication-title: Appl. Sci. – volume: 129 year: 2024 ident: b27 article-title: Robust language independent voice data driven Parkinson’s disease detection publication-title: Eng. Appl. Artif. Intell. – volume: 147 start-page: 70 year: 2018 end-page: 90 ident: b17 article-title: Deep learning in agriculture: A survey publication-title: Comput. Electron. Agric. – volume: 21 start-page: 370 year: 2022 end-page: 382 ident: b43 article-title: Real-time radio technology and modulation classification via an LSTM auto-encoder publication-title: IEEE Trans. Wirel. Commun. – start-page: 1 year: 2021 end-page: 6 ident: b14 article-title: Parkinson disease detection based on speech using various machine learning models and deep learning models publication-title: 2021 International Conference on System, Computation, Automation and Networking, ICSCAN, Puducherry – volume: 34 start-page: 662 issue: 1 year: 2023 ident: 10.1016/j.compbiomed.2025.110334_b8 article-title: Identification of Parkinson’s disease and multiple system atrophy using multimodal PET/MRI radiomics publication-title: Eur. Radiol. doi: 10.1007/s00330-023-10003-9 – volume: 25 start-page: 583 issue: 3 year: 2022 ident: 10.1016/j.compbiomed.2025.110334_b1 article-title: A hybrid system for Parkinson’s disease diagnosis using machine learning techniques publication-title: Int. J. Speech Technol. doi: 10.1007/s10772-021-09837-9 – volume: 68 year: 2021 ident: 10.1016/j.compbiomed.2025.110334_b35 article-title: EEG motor imagery classification using dynamic connectivity patterns and convolutional autoencoder publication-title: Biomed. Signal Process. Control. doi: 10.1016/j.bspc.2021.102584 – volume: 28 start-page: 60 issue: 1 year: 2020 ident: 10.1016/j.compbiomed.2025.110334_b18 article-title: Supervised network-based fuzzy learning of EEG signals for Alzheimer’s disease identification publication-title: IEEE Trans. Fuzzy Syst. doi: 10.1109/TFUZZ.2019.2903753 – volume: 21 start-page: 370 issue: 1 year: 2022 ident: 10.1016/j.compbiomed.2025.110334_b43 article-title: Real-time radio technology and modulation classification via an LSTM auto-encoder publication-title: IEEE Trans. Wirel. Commun. doi: 10.1109/TWC.2021.3095855 – volume: 20 start-page: 385 issue: 5 year: 2021 ident: 10.1016/j.compbiomed.2025.110334_b4 article-title: Challenges in the diagnosis of Parkinson’s disease publication-title: Lancet Neurol. doi: 10.1016/S1474-4422(21)00030-2 – volume: 27 start-page: 657 year: 2024 ident: 10.1016/j.compbiomed.2025.110334_b26 article-title: A hybrid approach to detecting Parkinson’s disease using spectrogram and deep learning CNN-LSTM network publication-title: Int. J. Speech Technol. doi: 10.1007/s10772-024-10128-2 – start-page: 1 year: 2021 ident: 10.1016/j.compbiomed.2025.110334_b14 article-title: Parkinson disease detection based on speech using various machine learning models and deep learning models – start-page: 1 year: 2021 ident: 10.1016/j.compbiomed.2025.110334_b20 article-title: Automatic recognition of depression and Parkinson’s disease by LSTM networks using sample chunking – volume: 129 year: 2024 ident: 10.1016/j.compbiomed.2025.110334_b27 article-title: Robust language independent voice data driven Parkinson’s disease detection publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2023.107494 – volume: 122 start-page: 56 year: 2020 ident: 10.1016/j.compbiomed.2025.110334_b23 article-title: Parallel representation learning for the classification of pathological speech: Studies on Parkinson’s disease and cleft lip and palate publication-title: Speech Commun. doi: 10.1016/j.specom.2020.07.005 – year: 2019 ident: 10.1016/j.compbiomed.2025.110334_b30 – volume: 9 start-page: 131 issue: 3 year: 2013 ident: 10.1016/j.compbiomed.2025.110334_b10 article-title: Cerebrospinal fluid biomarkers in Parkinson disease publication-title: Nat. Rev. Neurol. doi: 10.1038/nrneurol.2013.10 – volume: 71 issue: B year: 2022 ident: 10.1016/j.compbiomed.2025.110334_b34 article-title: Arrhythmia classification of LSTM autoencoder based on time series anomaly detection publication-title: Biomed. Signal Process. Control. – volume: 66 year: 2021 ident: 10.1016/j.compbiomed.2025.110334_b16 article-title: An efficient dimensionality reduction method using filter-based feature selection and variational autoencoders on Parkinson’s disease classification publication-title: Biomed. Signal Process. Control. doi: 10.1016/j.bspc.2021.102452 – volume: 130 start-page: 75 year: 2020 ident: 10.1016/j.compbiomed.2025.110334_b7 article-title: Dynamical system based compact deep hybrid network for classification of Parkinson disease related EEG signals publication-title: Neural Netw. doi: 10.1016/j.neunet.2020.06.018 – volume: 8 start-page: 19196 year: 2020 ident: 10.1016/j.compbiomed.2025.110334_b36 article-title: Feature extraction using an RNN autoencoder for skeleton-based abnormal gait recognition publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2967845 – volume: 26 start-page: 977 issue: 5 year: 2018 ident: 10.1016/j.compbiomed.2025.110334_b5 article-title: Modulation of spectral power and functional connectivity in human brain by acupuncture stimulation publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2018.2828143 – volume: 101 year: 2020 ident: 10.1016/j.compbiomed.2025.110334_b38 article-title: Searching for new physics with deep autoencoders publication-title: Phys. Rev. – start-page: 193 year: 2020 ident: 10.1016/j.compbiomed.2025.110334_b33 – ident: 10.1016/j.compbiomed.2025.110334_b28 – volume: 27 start-page: 1973 issue: 10 year: 2019 ident: 10.1016/j.compbiomed.2025.110334_b6 article-title: Modulation effect of acupuncture on functional brain networks and classification of its manipulation with EEG signals publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2019.2939655 – volume: 140 year: 2020 ident: 10.1016/j.compbiomed.2025.110334_b3 article-title: Parkinson disease classification using one against all based data sampling with the acoustic features from the speech signals publication-title: Med. Hypotheses doi: 10.1016/j.mehy.2020.109678 – volume: 5 start-page: 381 issue: 4 year: 2024 ident: 10.1016/j.compbiomed.2025.110334_b45 article-title: Parkinson disease prediction using CNN-LSTM model from voice signal publication-title: Springer Nat. (SN) Comput. Sci. – volume: 20 start-page: 267 issue: 3 year: 2014 ident: 10.1016/j.compbiomed.2025.110334_b9 article-title: MIBG myocardial scintigraphy in pre-motor Parkinson’s disease: A review publication-title: Parkinsonism Rel. Disord. doi: 10.1016/j.parkreldis.2013.11.001 – ident: 10.1016/j.compbiomed.2025.110334_b21 doi: 10.1109/WTS51064.2021.9433683 – start-page: 1 year: 2019 ident: 10.1016/j.compbiomed.2025.110334_b15 article-title: A hybrid approach to Parkinson disease classification using speech signal: The combination of SMOTE and random forests – volume: 149 year: 2021 ident: 10.1016/j.compbiomed.2025.110334_b42 article-title: Analysis of different RNN autoencoder variants for time series classification and machine prognostics publication-title: Mech. Syst. Signal Process. doi: 10.1016/j.ymssp.2020.107322 – volume: 83 start-page: 81491 year: 2024 ident: 10.1016/j.compbiomed.2025.110334_b11 article-title: A novel approach for Parkinson’s disease diagnosis using deep learning and Harris Hawks optimization algorithm with handwritten samples publication-title: Multimed Tools Appl. doi: 10.1007/s11042-024-18584-3 – ident: 10.1016/j.compbiomed.2025.110334_b39 – volume: 19 start-page: 2 issue: 2 year: 2023 ident: 10.1016/j.compbiomed.2025.110334_b44 article-title: CNN and LSTM for the classification of Parkinson’s disease based on the GTCC and MFCC publication-title: Appl. Comput. Sci. doi: 10.35784/acs-2023-11 – ident: 10.1016/j.compbiomed.2025.110334_b22 doi: 10.1109/AISP48273.2020.9073595 – volume: 147 start-page: 70 year: 2018 ident: 10.1016/j.compbiomed.2025.110334_b17 article-title: Deep learning in agriculture: A survey publication-title: Comput. Electron. Agric. doi: 10.1016/j.compag.2018.02.016 – year: 2024 ident: 10.1016/j.compbiomed.2025.110334_b24 article-title: Leveraging deep learning for fine-grained categorization of Parkinson’s disease progression levels through analysis of vocal acoustic patterns publication-title: Bioeng. – volume: 74 start-page: 255 year: 2019 ident: 10.1016/j.compbiomed.2025.110334_b13 article-title: A comparative analysis of speech signal processing algorithms for Parkinson’s disease classification and the use of the tunable Q-factor wavelet transform publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2018.10.022 – volume: 63 year: 2021 ident: 10.1016/j.compbiomed.2025.110334_b37 article-title: A novel dimensionality reduction approach for ECG signal via convolutional denoising autoencoder with LSTM publication-title: Biomed. Signal Process. Control. doi: 10.1016/j.bspc.2020.102225 – volume: 12 start-page: 11601 issue: 22 year: 2022 ident: 10.1016/j.compbiomed.2025.110334_b29 article-title: A hybrid U-lossian deep learning network for screening and evaluating Parkinson’s disease publication-title: Appl. Sci. doi: 10.3390/app122211601 – volume: 83 start-page: 1 issue: 1 year: 2023 ident: 10.1016/j.compbiomed.2025.110334_b2 article-title: PARNet: Deep neural network for the diagnosis of Parkinson’s disease publication-title: Multimedia Tools Appl. – start-page: 1 year: 2018 ident: 10.1016/j.compbiomed.2025.110334_b40 article-title: Learning graph representations with recurrent neural network autoencoders publication-title: Deep. Learn. Day KDD – ident: 10.1016/j.compbiomed.2025.110334_b46 – volume: 114 year: 2022 ident: 10.1016/j.compbiomed.2025.110334_b12 article-title: Parkinson’s disease diagnosis and stage prediction based on gait signal analysis using EMD and CNN–LSTM network publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2022.105099 – volume: 161 year: 2023 ident: 10.1016/j.compbiomed.2025.110334_b19 article-title: Diagnosis and classification of Parkinson’s disease using ensemble learning and 1D-PDCovNN publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2023.107031 – volume: 5 issue: 381 year: 2024 ident: 10.1016/j.compbiomed.2025.110334_b25 article-title: Parkinson disease prediction using CNN-LSTM model from voice signal publication-title: SN Comput. Sci. – volume: 11 year: 2023 ident: 10.1016/j.compbiomed.2025.110334_b32 article-title: A survey of audio classification using deep learning publication-title: IEEE Access doi: 10.1109/ACCESS.2023.3318015 – volume: 18 start-page: 2521 issue: 8 year: 2018 ident: 10.1016/j.compbiomed.2025.110334_b41 article-title: A combined deep learning GRU-autoencoder for the early detection of respiratory disease in pigs using multiple environmental sensors publication-title: Sensors doi: 10.3390/s18082521 – volume: 10 year: 2024 ident: 10.1016/j.compbiomed.2025.110334_b47 article-title: AIoT-based embedded systems optimization using feature selection for Parkinson’s disease diagnosis through speech disorders publication-title: Intelligence- Based Med. doi: 10.1016/j.ibmed.2024.100184 – volume: 5 start-page: 22199 year: 2017 ident: 10.1016/j.compbiomed.2025.110334_b31 article-title: Assessment of speech intelligibility in parkinson’s disease using a speech-to-text system publication-title: IEEE Access doi: 10.1109/ACCESS.2017.2762475 |
| SSID | ssj0004030 |
| Score | 2.414461 |
| Snippet | Parkinson’s disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no... AbstractParkinson’s disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is... Parkinson's disease (PD) is a neurodegenerative disorder that occurs as a result of a decrease in the chemical called dopamine in the brain. There is no... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 110334 |
| SubjectTerms | Aged Autoencoder Deep learning Humans Internal Medicine Long short-term memory Neural Networks, Computer Other Parkinson Disease - diagnosis Parkinson Disease - physiopathology Parkinson’s disease Signal Processing, Computer-Assisted Speech - physiology Speech analysis |
| Title | Speech signals-based Parkinson’s disease diagnosis using hybrid autoencoder-LSTM models |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S0010482525006857 https://www.clinicalkey.es/playcontent/1-s2.0-S0010482525006857 https://dx.doi.org/10.1016/j.compbiomed.2025.110334 https://www.ncbi.nlm.nih.gov/pubmed/40418858 https://www.proquest.com/docview/3212120368 |
| Volume | 193 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1879-0534 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004030 issn: 0010-4825 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Li9swEBbdbCm9lL6bPhYXuqfg4rdG9JQuu7SluxSSQnoStjRmdwtOiJOyufVv9O_1l3Rkyc4-IaX0YoJBVjzzeTQazTfD2BuhdaTCHPwsjbWf0ALsCwhDH4tApUj7IIVB02yCHx3BZCK-uHapddNOgFcVnJ2J2X9VNd0jZRvq7F-ou3so3aDfpHS6ktrpupHiRzNEdTwwiRk0l2-WKT0w5GbL83LJDaJuz2ZM-NVk253Ug2UTODheGRbXIF8upqbKpca5_3k0PrRNc-rz3mzbEqLJqT1fzunyif0YaXZtIwPD1e5euisO0EQqOrx9N2cJw5U2zu370AaFXLDAxSSitMtfdYGyliyzzkxqjC-Z_AQsz7kzvrY_4hVDbmMKp0YPM1uI4K2ZyLAWYhf9vFgme9RUGqKnk08XZJDyLbYd8VRAj20PP-5PPq3ZskFsiUnu77j8Lpv1d_18NzktN21KGudkfJ_dc7sKb2jR8IDdwuohu3PotPCIfbOg8C6AwutA8fvnr9pzcPA6OHgNHDwLB-8yHDwLh8fs68H-eO-D75pq-CpOYOFjKUow1V8LXSQFciUAAVQWI88hKVJODiWUUVCEAaaYgc5FqsjL0UWRBbnO4iesV00rfMY8nZWJIgsQa-AJAs_LKAEVc4S4MATmPgtbqcmZrZ0i26TCU7mWtDSSllbSfSZa8cqWG0yrmSRcbDCWXzcWa_d11jKUdSQDeQUrffauG-k8T-tRbjjv6xYHkoyzOXHLK5wuaxmTYxiao37os6cWIJ0kkiAJAVJ4_g9v_ILdXX9-L1lvMV_iK3Zb_Vic1PMdtsUnsOPg_weGhcH- |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Speech+signals-based+Parkinson%E2%80%99s+disease+diagnosis+using+hybrid+autoencoder-LSTM+models&rft.jtitle=Computers+in+biology+and+medicine&rft.au=Tekindor%2C+Ay%C5%9Fe+Nur&rft.au=Akman+Ayd%C4%B1n%2C+Eda&rft.date=2025-07-01&rft.pub=Elsevier+Ltd&rft.issn=0010-4825&rft.volume=193&rft_id=info:doi/10.1016%2Fj.compbiomed.2025.110334&rft.externalDocID=S0010482525006857 |
| thumbnail_m | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F00104825%2FS0010482525X00093%2Fcov150h.gif |