A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features
IntroductionAlzheimer’s disease (AD) even nowadays remains a complex neurodegenerative disease and its diagnosis relies mainly on cognitive tests which have many limitations. On the other hand, qualitative imaging will not provide an early diagnosis because the radiologist will perceive brain atroph...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Aging Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnagi.2023.1149871/full |
| _version_ | 1797809881493798912 |
|---|---|
| author | Stephanos Leandrou Demetris Lamnisos Haralabos Bougias Nikolaos Stogiannos Nikolaos Stogiannos Nikolaos Stogiannos Eleni Georgiadou K. G. Achilleos Constantinos S. Pattichis Constantinos S. Pattichis Alzheimer’s Disease Neuroimaging Initiative |
| author_facet | Stephanos Leandrou Demetris Lamnisos Haralabos Bougias Nikolaos Stogiannos Nikolaos Stogiannos Nikolaos Stogiannos Eleni Georgiadou K. G. Achilleos Constantinos S. Pattichis Constantinos S. Pattichis Alzheimer’s Disease Neuroimaging Initiative |
| author_sort | Stephanos Leandrou |
| collection | DOAJ |
| description | IntroductionAlzheimer’s disease (AD) even nowadays remains a complex neurodegenerative disease and its diagnosis relies mainly on cognitive tests which have many limitations. On the other hand, qualitative imaging will not provide an early diagnosis because the radiologist will perceive brain atrophy on a late disease stage. Therefore, the main objective of this study is to investigate the necessity of quantitative imaging in the assessment of AD by using machine learning (ML) methods. Nowadays, ML methods are used to address high dimensional data, integrate data from different sources, model the etiological and clinical heterogeneity, and discover new biomarkers in the assessment of AD.MethodsIn this study radiomic features from both entorhinal cortex and hippocampus were extracted from 194 normal controls (NC), 284 mild cognitive impairment (MCI) and 130 AD subjects. Texture analysis evaluates statistical properties of the image intensities which might represent changes in MRI image pixel intensity due to the pathophysiology of a disease. Therefore, this quantitative method could detect smaller-scale changes of neurodegeneration. Then the radiomics signatures extracted by texture analysis and baseline neuropsychological scales, were used to build an XGBoost integrated model which has been trained and integrated.ResultsThe model was explained by using the Shapley values produced by the SHAP (SHapley Additive exPlanations) method. XGBoost produced a f1-score of 0.949, 0.818, and 0.810 between NC vs. AD, MC vs. MCI, and MCI vs. AD, respectively.DiscussionThese directions have the potential to help to the earlier diagnosis and to a better manage of the disease progression and therefore, develop novel treatment strategies. This study clearly showed the importance of explainable ML approach in the assessment of AD. |
| first_indexed | 2024-03-13T07:00:38Z |
| format | Article |
| id | doaj.art-e92ba47486e4415fb40d10c7738700ae |
| institution | Directory Open Access Journal |
| issn | 1663-4365 |
| language | English |
| last_indexed | 2024-03-13T07:00:38Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging Neuroscience |
| spelling | doaj.art-e92ba47486e4415fb40d10c7738700ae2023-06-07T04:29:27ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652023-06-011510.3389/fnagi.2023.11498711149871A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic featuresStephanos Leandrou0Demetris Lamnisos1Haralabos Bougias2Nikolaos Stogiannos3Nikolaos Stogiannos4Nikolaos Stogiannos5Eleni Georgiadou6K. G. Achilleos7Constantinos S. Pattichis8Constantinos S. Pattichis9Alzheimer’s Disease Neuroimaging InitiativeSchool of Sciences, European University Cyprus, Nicosia, CyprusSchool of Sciences, European University Cyprus, Nicosia, CyprusUniversity Hospital of Ioannina, Ioannina, GreeceDiscipline of Medical Imaging and Radiation Therapy, University College Cork, Cork, IrelandDivision of Midwifery and Radiography, City, University of London, London, United KingdomMedical Imaging Department, Corfu General Hospital, Corfu, GreeceMetaxa Anticancer Hospital, Athens, GreeceDepartment of Computer Science and Biomedical Engineering Research Centre, University of Cyprus, Nicosia, CyprusDepartment of Computer Science and Biomedical Engineering Research Centre, University of Cyprus, Nicosia, CyprusCYENS Centre of Excellence, Nicosia, CyprusIntroductionAlzheimer’s disease (AD) even nowadays remains a complex neurodegenerative disease and its diagnosis relies mainly on cognitive tests which have many limitations. On the other hand, qualitative imaging will not provide an early diagnosis because the radiologist will perceive brain atrophy on a late disease stage. Therefore, the main objective of this study is to investigate the necessity of quantitative imaging in the assessment of AD by using machine learning (ML) methods. Nowadays, ML methods are used to address high dimensional data, integrate data from different sources, model the etiological and clinical heterogeneity, and discover new biomarkers in the assessment of AD.MethodsIn this study radiomic features from both entorhinal cortex and hippocampus were extracted from 194 normal controls (NC), 284 mild cognitive impairment (MCI) and 130 AD subjects. Texture analysis evaluates statistical properties of the image intensities which might represent changes in MRI image pixel intensity due to the pathophysiology of a disease. Therefore, this quantitative method could detect smaller-scale changes of neurodegeneration. Then the radiomics signatures extracted by texture analysis and baseline neuropsychological scales, were used to build an XGBoost integrated model which has been trained and integrated.ResultsThe model was explained by using the Shapley values produced by the SHAP (SHapley Additive exPlanations) method. XGBoost produced a f1-score of 0.949, 0.818, and 0.810 between NC vs. AD, MC vs. MCI, and MCI vs. AD, respectively.DiscussionThese directions have the potential to help to the earlier diagnosis and to a better manage of the disease progression and therefore, develop novel treatment strategies. This study clearly showed the importance of explainable ML approach in the assessment of AD.https://www.frontiersin.org/articles/10.3389/fnagi.2023.1149871/fullAlzheimer’s diseaseMRImachine learning (ML)radiomicexplainability and interpretability |
| spellingShingle | Stephanos Leandrou Demetris Lamnisos Haralabos Bougias Nikolaos Stogiannos Nikolaos Stogiannos Nikolaos Stogiannos Eleni Georgiadou K. G. Achilleos Constantinos S. Pattichis Constantinos S. Pattichis Alzheimer’s Disease Neuroimaging Initiative A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features Frontiers in Aging Neuroscience Alzheimer’s disease MRI machine learning (ML) radiomic explainability and interpretability |
| title | A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features |
| title_full | A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features |
| title_fullStr | A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features |
| title_full_unstemmed | A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features |
| title_short | A cross-sectional study of explainable machine learning in Alzheimer’s disease: diagnostic classification using MR radiomic features |
| title_sort | cross sectional study of explainable machine learning in alzheimer s disease diagnostic classification using mr radiomic features |
| topic | Alzheimer’s disease MRI machine learning (ML) radiomic explainability and interpretability |
| url | https://www.frontiersin.org/articles/10.3389/fnagi.2023.1149871/full |
| work_keys_str_mv | AT stephanosleandrou acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT demetrislamnisos acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT haralabosbougias acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT nikolaosstogiannos acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT nikolaosstogiannos acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT nikolaosstogiannos acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT elenigeorgiadou acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT kgachilleos acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT constantinosspattichis acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT constantinosspattichis acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT alzheimersdiseaseneuroimaginginitiative acrosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT stephanosleandrou crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT demetrislamnisos crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT haralabosbougias crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT nikolaosstogiannos crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT nikolaosstogiannos crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT nikolaosstogiannos crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT elenigeorgiadou crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT kgachilleos crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT constantinosspattichis crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT constantinosspattichis crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures AT alzheimersdiseaseneuroimaginginitiative crosssectionalstudyofexplainablemachinelearninginalzheimersdiseasediagnosticclassificationusingmrradiomicfeatures |