|
1
|
Kurbalija V, Geler Z, Stankov TV, Petrušić I, Ivanović M, Kononenko I, Semnic M, Daković M, Semnic R, Bosnić Z. Analysis of neuropsychological and neuroradiological features for diagnosis of Alzheimer's disease and mild cognitive impairment. Int J Med Inform 2023; 178:105195. [PMID: 37611363 DOI: 10.1016/j.ijmedinf.2023.105195] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2023] [Revised: 07/18/2023] [Accepted: 08/09/2023] [Indexed: 08/25/2023]
Abstract
BACKGROUND Age-related neurodegenerative diseases are constantly increasing with prediction that in 2050 over 60 % of population will suffer from some level of cognitive impairment. A cure for the Alzheimer's disease (AD) does not exist, so early diagnosis is of a great importance. Machine learning techniques can help in early diagnosis with deep medical data processing, disease understanding, intervention analysis and knowledge discovery for achieving better medical decision making. METHODS In this paper, we analyze the dataset consisting of 90 individuals and 482 input features. We investigate the achieved AD prediction performances using seven classifiers and five feature selection algorithms. We pay special focus on analyzing performance by utilizing only a subset of best ranked attributes to establish the minimum amount of input features that ensure acceptable performance. We also investigate the significance of neuropsychological (NP) and neuroradiological (NR) attributes for the AD diagnosis. RESULTS The accuracy for the whole set of attributes ranged between 66.22 % and 81.00 %, and the weighted average AUROC was between 76.3 % and 95.0 %. The best results were achieved by the naive Bayes classifier and the Relief feature selection algorithm. Additionally, Support Vector Machines classifier shows the most stable results since it depends the least on the feature selection algorithm which is used. As the main result of this paper, we compare the performance of models trained with automatically selected features to models trained with hand-selected features performed by medical experts (NP and NR features). CONCLUSIONS The results reveal that unlike the NR attributes, the NP attributes achieve a good performance that is comparable to the full set of attributes, which suggests that they possess a high predictive power for AD diagnosis.
Collapse
Affiliation(s)
- Vladimir Kurbalija
- University of Novi Sad, Faculty of Sciences, Department of Mathematics and Informatics, Trg D. Obradovića 4, 21000 Novi Sad, Serbia
| | - Zoltan Geler
- University of Novi Sad, Faculty of Philosophy, Department of Media Studies, Dr Zorana Đinđića 2, 21000 Novi Sad, Serbia.
| | - Tijana Vujanić Stankov
- University of Novi Sad, Faculty of Medicine, Department of Neurology, Hajduk Veljkova 3, 21000 Novi Sad, Serbia; University Clinical Centre of Vojvodina, Neurology Clinic, Hajduk Veljkova 1, 21000 Novi Sad, Serbia
| | - Igor Petrušić
- University of Belgrade, Faculty of Physical Chemistry, Laboratory for Advanced Analysis of Neuroimages, Studentski trg 12-16, 11000 Belgrade, Serbia
| | - Mirjana Ivanović
- University of Novi Sad, Faculty of Sciences, Department of Mathematics and Informatics, Trg D. Obradovića 4, 21000 Novi Sad, Serbia
| | - Igor Kononenko
- University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia
| | - Marija Semnic
- University of Novi Sad, Faculty of Medicine, Department of Neurology, Hajduk Veljkova 3, 21000 Novi Sad, Serbia; University Clinical Centre of Vojvodina, Neurology Clinic, Hajduk Veljkova 1, 21000 Novi Sad, Serbia
| | - Marko Daković
- University of Belgrade, Faculty of Physical Chemistry, Laboratory for Advanced Analysis of Neuroimages, Studentski trg 12-16, 11000 Belgrade, Serbia
| | - Robert Semnic
- Uppsala University, Department of Surgical Sciences, Radiology, P.O. Box 256, SE-751 05 Uppsala, Sweden
| | - Zoran Bosnić
- University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia
| |
Collapse
|
|
2
|
Stratification of Parkinson’s Disease Patients via Multi-view Clustering. Artif Intell Med 2021. [DOI: 10.1007/978-3-030-77211-6_25] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
|
|
4
|
Multi-view Clustering with mvReliefF for Parkinson’s Disease Patients Subgroup Detection. Artif Intell Med 2020. [DOI: 10.1007/978-3-030-59137-3_26] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|