{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:21:38Z","timestamp":1793132498103,"version":"4.5.0"},"reference-count":57,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T00:00:00Z","timestamp":1756166400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Alzheimer\u2019s Disease poses a significant challenge as a progressive and irreversible neurological condition striking the elderly population. Its incurable nature correlates with a significant rise in death rates. However, early detection can slow its progression and facilitate prompt intervention, thereby mitigating mortality risks. Functional Magnetic Resonance Imaging (fMRI) provides valuable insights into the functional changes within distinct brain regions associated with the disease. The recent research efforts have extracted functional connectivity measures for the classification. These handcrafted functional connectivity features are usually not robust and are computationally intensive. To address the issue, this study introduces an integrated deep-learning framework based on CNN and LSTM networks. This framework autonomously learns both intra-volume and inter-volume features critical for classification tasks. CNNs facilitate feature extraction, while LSTM networks govern the selection of significant features for classification. The key aim of this study is to classify Alzheimer\u2019s disease and its prodromal stage, Mild Cognitive Impairment (MCI). MCI is further categorized as early MCI (EMCI) and late MCI (LMCI). We have evaluated the framework in three dimensions, binary classification, multi-class classification with 3-classes, and multi-class classification with 4-classes. For each dimension, multiple classifications were performed. The results depict the proposed CNN-LSTM framework to attain 99% accuracy and 100% average area under the curve for the majority of the classification.<\/jats:p>","DOI":"10.1371\/journal.pone.0317968","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T17:37:31Z","timestamp":1756229851000},"page":"e0317968","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing the early detection of Alzheimer\u2019s disease using an integrated CNN-LSTM framework: A robust approach for fMRI-based multi-stage classification"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6610-9290","authenticated-orcid":true,"given":"Saima","family":"Farhan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasin Ul","family":"Haq","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Momina Abdul","family":"Khaliq","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seemal","family":"Afza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5269-0427","authenticated-orcid":true,"given":"Fahad","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4299-7756","authenticated-orcid":true,"given":"Tariq","family":"Mahmood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amjad","family":"Rehman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,8,26]]},"reference":[{"key":"pone.0317968.ref001","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.media.2018.03.013","article-title":"Integration of temporal and spatial properties of dynamic connectivity networks for automatic diagnosis of brain disease","volume":"47","author":"B Jie","year":"2018","journal-title":"Med Image Anal."},{"issue":"5","key":"pone.0317968.ref002","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1093\/ageing\/19.5.341","article-title":"Cause of death in Alzheimer\u2019s disease","volume":"19","author":"A Burns","year":"1990","journal-title":"Age Ageing."},{"issue":"5","key":"pone.0317968.ref003","first-page":"3708","article-title":"Alzheimer\u2019s disease facts and figures","volume":"20","author":"Association Alzheimer\u2019s","year":"2024","journal-title":"Alzheimer\u2019s Dementia."},{"key":"pone.0317968.ref004","unstructured":"Heron M. Deaths: Leading causes for 2016 ; 2018."},{"issue":"19","key":"pone.0317968.ref005","doi-asserted-by":"crossref","first-page":"1778","DOI":"10.1212\/WNL.0b013e31828726f5","article-title":"Alzheimer disease in the United States 2010 -2050) estimated using the 2010 census","volume":"80","author":"LE Hebert","year":"2013","journal-title":"Neurology."},{"key":"pone.0317968.ref006","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1212\/CON.0000000000000313","article-title":"Mild cognitive impairment","volume":"22","author":"RC Petersen","year":"2016","journal-title":"Continuum (Minneap Minn)."},{"key":"pone.0317968.ref007","doi-asserted-by":"crossref","first-page":"31","DOI":"10.3389\/fncom.2018.00031","article-title":"Classification of Alzheimer\u2019s disease, mild cognitive impairment, and normal controls with subnetwork selection and graph kernel principal component analysis based on minimum spanning tree brain functional network","volume":"12","author":"X Cui","year":"2018","journal-title":"Front Comput Neurosci."},{"issue":"2","key":"pone.0317968.ref008","doi-asserted-by":"crossref","first-page":"144","DOI":"10.3988\/jcn.2017.13.2.144","article-title":"Morphological and microstructural changes of the hippocampus in early MCI: A study utilizing the Alzheimer\u2019s disease neuroimaging initiative database","volume":"13","author":"P Lee","year":"2017","journal-title":"J Clin Neurol."},{"issue":"3","key":"pone.0317968.ref009","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s40708-015-0019-x","article-title":"Multimodal neuroimaging computing: A review of the applications in neuropsychiatric disorders","volume":"2","author":"S Liu","year":"2015","journal-title":"Brain Inform."},{"issue":"4","key":"pone.0317968.ref010","first-page":"2725","article-title":"In vivo imaging techniques: A new era for histochemical analysis","volume":"60","author":"A Busato","year":"2016","journal-title":"Eur J Histochem."},{"key":"pone.0317968.ref011","unstructured":"Farhan S, Fahiem MA, Tahir F, Tauseef H. A comparative study of neuroimaging and pattern recognition techniques for estimation of Alzheimer\u2019s disease. 2013."},{"issue":"1","key":"pone.0317968.ref012","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1016\/j.neuroimage.2010.11.049","article-title":"Functional connectivity of the insula in the resting brain","volume":"55","author":"F Cauda","year":"2011","journal-title":"Neuroimage."},{"key":"pone.0317968.ref013","unstructured":"Mohri M, Rostamizadeh A, Talwalkar A. Foundations of machine learning; 2018."},{"issue":"7","key":"pone.0317968.ref014","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1016\/j.cell.2018.05.015","article-title":"Next-generation machine learning for biological networks","volume":"173","author":"DM Camacho","year":"2018","journal-title":"Cell."},{"issue":"3","key":"pone.0317968.ref015","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.neulet.2009.06.052","article-title":"SVM-based computer-aided diagnosis of the Alzheimer\u2019s disease using t-test NMSE feature selection with feature correlation weighting","volume":"461","author":"R Chaves","year":"2009","journal-title":"Neurosci Lett."},{"key":"pone.0317968.ref016","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.compbiomed.2017.02.011","article-title":"Classification of Alzheimer\u2019s disease and prediction of mild cognitive impairment-to-Alzheimer\u2019s conversion from structural magnetic resource imaging using feature ranking and a genetic algorithm","volume":"83","author":"I Beheshti","year":"2017","journal-title":"Comput Biol Med."},{"key":"pone.0317968.ref017","first-page":"2477","article-title":"Classification of Alzheimer\u2019s disease from FDG-PET images using favourite class ensembles","volume":"2013","author":"C Cabral","year":"2013","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc."},{"key":"pone.0317968.ref018","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.patcog.2016.10.009","article-title":"Multi-modal classification of Alzheimer\u2019s disease using nonlinear graph fusion","volume":"63","author":"T Tong","year":"2017","journal-title":"Pattern Recogn."},{"key":"pone.0317968.ref019","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.neuroimage.2018.08.042","article-title":"Reproducible evaluation of classification methods in Alzheimer\u2019s disease: Framework and application to MRI and PET data","volume":"183","author":"J Samper-Gonz\u00e1lez","year":"2018","journal-title":"Neuroimage."},{"key":"pone.0317968.ref020","doi-asserted-by":"crossref","unstructured":"Samper-Gonz\u00e1lez J. Yet another ADNI machine learning paper? Paving the way towards fully-reproducible research on classification of Alzheimer\u2019s disease. Springer; 2017. p. 53\u201360.","DOI":"10.1007\/978-3-319-67389-9_7"},{"key":"pone.0317968.ref021","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.compbiomed.2018.09.004","article-title":"Predicting conversion from MCI to AD by integrating rs-fMRI and structural MRI","volume":"102","author":"SH Hojjati","year":"2018","journal-title":"Comput Biol Med."},{"issue":"3","key":"pone.0317968.ref022","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1007\/s11682-015-9448-7","article-title":"Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer\u2019s disease","volume":"10","author":"A Khazaee","year":"2016","journal-title":"Brain Imaging Behav."},{"key":"pone.0317968.ref023","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"G Litjens","year":"2017","journal-title":"Med Image Anal."},{"key":"pone.0317968.ref024","doi-asserted-by":"crossref","unstructured":"Islam J, Zhang Y. A novel deep learning based multi-class classification method for Alzheimer\u2019s disease detection using brain MRI data. Springer. 2017. p. 213\u201322.","DOI":"10.1007\/978-3-319-70772-3_20"},{"key":"pone.0317968.ref025","doi-asserted-by":"crossref","unstructured":"Korolev S, Safiullin A, Belyaev M, Dodonova Y. Residual and plain convolutional neural networks for 3D brain MRI classification. In: 2017 IEEE 14th international symposium on biomedical imaging (ISBI 2017), 2017. 835\u20138. https:\/\/doi.org\/10.1109\/isbi.2017.7950647","DOI":"10.1109\/ISBI.2017.7950647"},{"issue":"3","key":"pone.0317968.ref026","first-page":"584","article-title":"Alzheimer\u2019s disease diagnostics by a 3D deeply supervised adaptable convolutional network","volume":"23","author":"E Hosseini-Asl","year":"2018","journal-title":"Front Biosci (Landmark Ed)."},{"key":"pone.0317968.ref027","doi-asserted-by":"crossref","first-page":"8","DOI":"10.3389\/fnagi.2019.00008","article-title":"Evaluation of functional decline in Alzheimer\u2019s dementia using 3D Deep learning and group ICA for rs-fMRI measurements","volume":"11","author":"MNI Qureshi","year":"2019","journal-title":"Front Aging Neurosci."},{"key":"pone.0317968.ref028","doi-asserted-by":"crossref","unstructured":"Hon M, Khan N. Towards Alzheimer\u2019s disease classification through transfer learning; 2017.","DOI":"10.1109\/BIBM.2017.8217822"},{"issue":"6","key":"pone.0317968.ref029","article-title":"Automatic classification of medical image modality and anatomical location using convolutional neural network","volume":"16","author":"C-H Chiang","year":"2021","journal-title":"PLoS One."},{"issue":"08","key":"pone.0317968.ref030","article-title":"Development of convolutional neural network model for classification of cardiomegaly X-ray images","volume":"22","author":"M-J Kim","year":"2022","journal-title":"J Mech Med Biol."},{"issue":"6","key":"pone.0317968.ref031","first-page":"885","article-title":"Comparison of medical image classification accuracy among three machine learning methods","volume":"26","author":"T Maruyama","year":"2018","journal-title":"J Xray Sci Technol."},{"issue":"1","key":"pone.0317968.ref032","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.2019190177","article-title":"The importance of image resolution in building deep learning models for medical imaging","volume":"2","author":"P Lakhani","year":"2020","journal-title":"Radiol Artif Intell."},{"key":"pone.0317968.ref033","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","article-title":"Recent advances in convolutional neural networks","volume":"77","author":"J Gu","year":"2018","journal-title":"Pattern Recogn."},{"key":"pone.0317968.ref034","unstructured":"Hagan M, Demuth H, Beale M, Jes\u00fas OD. Neural network design; 1996."},{"key":"pone.0317968.ref035","unstructured":"Haykin S. Neural networks; 1994."},{"issue":"2","key":"pone.0317968.ref036","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Y Bengio","year":"1994","journal-title":"IEEE Trans Neural Netw."},{"issue":"02","key":"pone.0317968.ref037","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1142\/S0218488598000094","article-title":"The vanishing gradient problem during learning recurrent neural nets and problem solutions","volume":"06","author":"S Hochreiter","year":"1998","journal-title":"Int J Unc Fuzz Knowl Based Syst."},{"issue":"8","key":"pone.0317968.ref038","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Computat."},{"key":"pone.0317968.ref039","doi-asserted-by":"crossref","unstructured":"Stratified cross validation. Encyclopedia of Machine Learning and Data Mining. Boston, MA: Springer US; 2017. p. 1191.","DOI":"10.1007\/978-1-4899-7687-1_788"},{"issue":"1","key":"pone.0317968.ref040","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1109\/TCBB.2012.141","article-title":"The receiver operational characteristic for binary classification with multiple indices and its application to the neuroimaging study of Alzheimer\u2019s disease","volume":"10","author":"X Wu","year":"2013","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform."},{"key":"pone.0317968.ref041","doi-asserted-by":"crossref","unstructured":"Unknown. ROC Curve. Encyclopedia of machine learning and data mining. Boston, MA: Springer US; 2017. p. 1116.","DOI":"10.1007\/978-1-4899-7687-1_735"},{"key":"pone.0317968.ref042","unstructured":"Zeugmann T. Boston, MA: Springer US; 2011. p. 781."},{"key":"pone.0317968.ref043","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization; 2014."},{"key":"pone.0317968.ref044","doi-asserted-by":"crossref","first-page":"60","DOI":"10.3389\/fninf.2018.00060","article-title":"Analysis of Alzheimer\u2019s disease based on the random neural network cluster in fMRI","volume":"12","author":"X Bi","year":"2018","journal-title":"Front Neuroinform."},{"issue":"3","key":"pone.0317968.ref045","article-title":"Random support vector machine cluster analysis of resting-state fMRI in Alzheimer\u2019s disease","volume":"13","author":"X-A Bi","year":"2018","journal-title":"PLoS One."},{"issue":"11","key":"pone.0317968.ref046","doi-asserted-by":"crossref","first-page":"2132","DOI":"10.1016\/j.clinph.2015.02.060","article-title":"Identifying patients with Alzheimer\u2019s disease using resting-state fMRI and graph theory","volume":"126","author":"A Khazaee","year":"2015","journal-title":"Clin Neurophysiol."},{"key":"pone.0317968.ref047","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1016\/j.bbr.2016.06.043","article-title":"Classification of patients with MCI and AD from healthy controls using directed graph measures of resting-state fMRI","volume":"322","author":"A Khazaee","year":"2017","journal-title":"Behav Brain Res."},{"issue":"2","key":"pone.0317968.ref048","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0212582","article-title":"Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer\u2019s dementia diagnosis using multi-measure rs-fMRI spatial patterns","volume":"14","author":"DT Nguyen","year":"2019","journal-title":"PLoS One."},{"key":"pone.0317968.ref049","doi-asserted-by":"crossref","unstructured":"Sarraf S, DeSouza DD, Anderson J, for the Alzheimer\u2019s Disease Neuroimaging Initiative GT. DeepAD: Alzheimer\u2019s disease classification via deep convolutional neural networks using MRI and fMRI. bioRxiv; 2017. p. 070441.","DOI":"10.1101\/070441"},{"key":"pone.0317968.ref050","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1186\/s12859-018-2528-0","article-title":"Classifying early and late mild cognitive impairment stages of Alzheimer\u2019s disease by fusing default mode networks extracted with multiple seeds","volume":"19","author":"S Pei","year":"2018","journal-title":"BMC Bioinform."},{"key":"pone.0317968.ref051","doi-asserted-by":"crossref","first-page":"716","DOI":"10.3389\/fnins.2018.00716","article-title":"Analysis of progression toward Alzheimer\u2019s disease based on evolutionary weighted random support vector machine cluster","volume":"12","author":"X Bi","year":"2018","journal-title":"Front Neurosci."},{"issue":"12","key":"pone.0317968.ref052","doi-asserted-by":"crossref","first-page":"4609","DOI":"10.3390\/s22124609","article-title":"Early-stage Alzheimer\u2019s disease categorization using PET neuroimaging modality and convolutional neural networks in the 2D and 3D domains","volume":"22","author":"AB Tufail","year":"2022","journal-title":"Sensors (Basel)."},{"key":"pone.0317968.ref053","doi-asserted-by":"crossref","unstructured":"Jie B, Liu M, Lian C, Shi F, Shen D. Developing novel weighted correlation kernels for convolutional neural networks to extract hierarchical functional connectivities from fMRI for disease diagnosis. In: Machine learning in medical imaging: 9th international workshop, MLMI 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedings 9, 2018. 1\u20139.","DOI":"10.1007\/978-3-030-00919-9_1"},{"key":"pone.0317968.ref054","doi-asserted-by":"crossref","unstructured":"Kazemi Y, Houghten S. A deep learning pipeline to classify different stages of Alzheimer\u2019s disease from fMRI data. In: 2018 IEEE conference on computational intelligence in bioinformatics and computational biology (CIBCB); 2018. p. 1\u20138. https:\/\/doi.org\/10.1109\/cibcb.2018.8404980","DOI":"10.1109\/CIBCB.2018.8404980"},{"issue":"2","key":"pone.0317968.ref055","doi-asserted-by":"crossref","first-page":"469","DOI":"10.3390\/electronics12020469","article-title":"A novel framework for classification of different Alzheimer\u2019s disease stages using CNN model","volume":"12","author":"G Mohi ud din dar","year":"2023","journal-title":"Electronics."},{"issue":"22","key":"pone.0317968.ref056","doi-asserted-by":"crossref","first-page":"14695","DOI":"10.3390\/su142214695","article-title":"On disharmony in batch normalization and dropout methods for early categorization of Alzheimer\u2019s disease","volume":"14","author":"AB Tufail","year":"2022","journal-title":"Sustainability."},{"key":"pone.0317968.ref057","doi-asserted-by":"crossref","first-page":"35","DOI":"10.3389\/fninf.2018.00035","article-title":"Classification of Alzheimer\u2019s disease by combination of convolutional and recurrent neural networks using FDG-PET images","volume":"12","author":"M Liu","year":"2018","journal-title":"Front Neuroinform."}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T17:37:40Z","timestamp":1756229860000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317968"}},"subtitle":[],"editor":[{"given":"Usman","family":"Ghafoor","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,26]]},"references-count":57,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,26]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0317968","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,26]]}}}