1
|
Ameli A, Peña-Castillo L, Usefi H. Assessing the reproducibility of machine-learning-based biomarker discovery in Parkinson's disease. Comput Biol Med 2024; 174:108407. [PMID: 38603902 DOI: 10.1016/j.compbiomed.2024.108407] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2023] [Revised: 03/21/2024] [Accepted: 04/01/2024] [Indexed: 04/13/2024]
Abstract
Feature selection and machine learning algorithms can be used to analyze Single Nucleotide Polymorphisms (SNPs) data and identify potential disease biomarkers. Reproducibility of identified biomarkers is critical for them to be useful for clinical research; however, genotyping platforms and selection criteria for individuals to be genotyped affect the reproducibility of identified biomarkers. To assess biomarkers reproducibility, we collected five SNPs datasets from the database of Genotypes and Phenotypes (dbGaP) and explored several data integration strategies. While combining datasets can lead to a reduction in classification accuracy, it has the potential to improve the reproducibility of potential biomarkers. We evaluated the agreement among different strategies in terms of the SNPs that were identified as potential Parkinson's disease (PD) biomarkers. Our findings indicate that, on average, 93% of the SNPs identified in a single dataset fail to be identified in other datasets. However, through dataset integration, this lack of replication is reduced to 62%. We discovered fifty SNPs that were identified at least twice, which could potentially serve as novel PD biomarkers. These SNPs are indirectly linked to PD in the literature but have not been directly associated with PD before. These findings open up new potential avenues of investigation.
Collapse
Affiliation(s)
- Ali Ameli
- Department of Computer Science, Memorial University of Newfoundland, 230 Elizabeth Ave, St. John's, A1C5S7, NL, Canada
| | - Lourdes Peña-Castillo
- Department of Computer Science, Memorial University of Newfoundland, 230 Elizabeth Ave, St. John's, A1C5S7, NL, Canada; Department of Biology, Memorial University of Newfoundland, 230 Elizabeth Ave, St. John's, A1C5S7, NL, Canada.
| | - Hamid Usefi
- Department of Computer Science, Memorial University of Newfoundland, 230 Elizabeth Ave, St. John's, A1C5S7, NL, Canada; Department of Mathematics and Statistics, Memorial University of Newfoundland, 230 Elizabeth Ave, St. John's, A1C5S7, NL, Canada.
| |
Collapse
|
2
|
Pitton Rissardo J, Fornari Caprara AL. Cardiac 123I-Metaiodobenzylguanidine (MIBG) Scintigraphy in Parkinson's Disease: A Comprehensive Review. Brain Sci 2023; 13:1471. [PMID: 37891838 PMCID: PMC10605004 DOI: 10.3390/brainsci13101471] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Revised: 09/23/2023] [Accepted: 10/13/2023] [Indexed: 10/29/2023] Open
Abstract
Cardiac sympathetic denervation, as documented on 123I-metaiodobenzylguanidine (MIBG) myocardial scintigraphy, is relatively sensitive and specific for distinguishing Parkinson's disease (PD) from other neurodegenerative causes of parkinsonism. The present study aims to comprehensively review the literature regarding the use of cardiac MIBG in PD. MIBG is an analog to norepinephrine. They share the same uptake, storage, and release mechanisms. An abnormal result in the cardiac MIBG uptake in individuals with parkinsonism can be an additional criterion for diagnosing PD. However, a normal result of cardiac MIBG in individuals with suspicious parkinsonian syndrome does not exclude the diagnosis of PD. The findings of cardiac MIBG studies contributed to elucidating the pathophysiology of PD. We investigated the sensitivity and specificity of cardiac MIBG scintigraphy in PD. A total of 54 studies with 3114 individuals diagnosed with PD were included. The data were described as means with a Hoehn and Yahr stage of 2.5 and early and delayed registration H/M ratios of 1.70 and 1.51, respectively. The mean cutoff for the early and delayed phases were 1.89 and 1.86. The sensitivity for the early and delayed phases was 0.81 and 0.83, respectively. The specificity for the early and delayed phases were 0.86 and 0.80, respectively.
Collapse
|
3
|
De Feo MS, Frantellizzi V, Locuratolo N, Di Rocco A, Farcomeni A, Pauletti C, Marongiu A, Lazri J, Nuvoli S, Fattapposta F, De Vincentis G, Spanu A. Role of Functional Neuroimaging with 123I-MIBG and 123I-FP-CIT in De Novo Parkinson's Disease: A Multicenter Study. Life (Basel) 2023; 13:1786. [PMID: 37629643 PMCID: PMC10455638 DOI: 10.3390/life13081786] [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: 07/07/2023] [Revised: 08/10/2023] [Accepted: 08/19/2023] [Indexed: 08/27/2023] Open
Abstract
BACKGROUND Parkinson's disease is a progressive neurodegenerative disorder, with incidence and prevalence rates of 8-18 per 100,000 people per year and 0.3-1%, respectively. As parkinsonian symptoms do not appear until approximately 50-60% of the nigral DA-releasing neurons have been lost, the impact of routine structural imaging findings is minimal at early stages, making Parkinson's disease an ideal condition for the application of functional imaging techniques. The aim of this multicenter study is to assess whether 123I-FP-CIT (DAT-SPECT), 123I-MIBG (mIBG-scintigraphy) or an association of both exams presents the highest diagnostic accuracy in de novo PD patients. METHODS 288 consecutive patients with suspected diagnoses of Parkinson's disease or non- Parkinson's disease syndromes were analyzed in the present Italian multicenter retrospective study. All subjects were de novo, drug-naive patients and met the inclusion criteria of having undergone both DAT-SPECT and mIBG-scintigraphy within one month of each other. RESULTS The univariate analysis including age and both mIBG-SPECT and DAT-SPECT parameters showed that the only significant values for predicting Parkinson's disease in our population were eH/M, lH/M, ESS and LSS obtained from mIBG-scintigraphy (p < 0.001). CONCLUSIONS mIBG-scintigraphy shows higher diagnostic accuracy in de novo Parkinson's disease patients than DAT-SPECT, so given the superiority of the MIBG study, the combined use of both exams does not appear to be mandatory in the early phase of Parkinson's disease.
Collapse
Affiliation(s)
- Maria Silvia De Feo
- Department of Radiological Sciences, Oncology and Anatomo-Pathology, Sapienza, University of Rome, 00161 Rome, Italy (J.L.)
| | - Viviana Frantellizzi
- Department of Radiological Sciences, Oncology and Anatomo-Pathology, Sapienza, University of Rome, 00161 Rome, Italy (J.L.)
| | - Nicoletta Locuratolo
- Department of Human Neurosciences, Sapienza, University of Rome, 00161 Rome, Italy
- National Centre for Disease Prevention and Health Promotion, National Institute of Health, 00161 Rome, Italy
| | - Arianna Di Rocco
- Department of Radiological Sciences, Oncology and Anatomo-Pathology, Sapienza, University of Rome, 00161 Rome, Italy (J.L.)
| | - Alessio Farcomeni
- Department of Economics & Finance, University of Rome “Tor Vergata”, 00133 Rome, Italy
| | - Caterina Pauletti
- Department of Human Neurosciences, Sapienza, University of Rome, 00161 Rome, Italy
| | - Andrea Marongiu
- Department of Medical, Surgical and Experimental Sciences, University of Sassari, 07100 Sassari, Italy
| | - Julia Lazri
- Department of Radiological Sciences, Oncology and Anatomo-Pathology, Sapienza, University of Rome, 00161 Rome, Italy (J.L.)
| | - Susanna Nuvoli
- Department of Medical, Surgical and Experimental Sciences, University of Sassari, 07100 Sassari, Italy
| | | | - Giuseppe De Vincentis
- Department of Radiological Sciences, Oncology and Anatomo-Pathology, Sapienza, University of Rome, 00161 Rome, Italy (J.L.)
| | - Angela Spanu
- Department of Medical, Surgical and Experimental Sciences, University of Sassari, 07100 Sassari, Italy
| |
Collapse
|
4
|
Elshewey AM, Shams MY, El-Rashidy N, Elhady AM, Shohieb SM, Tarek Z. Bayesian Optimization with Support Vector Machine Model for Parkinson Disease Classification. SENSORS (BASEL, SWITZERLAND) 2023; 23:s23042085. [PMID: 36850682 PMCID: PMC9961102 DOI: 10.3390/s23042085] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/29/2023] [Revised: 02/08/2023] [Accepted: 02/10/2023] [Indexed: 05/31/2023]
Abstract
Parkinson's disease (PD) has become widespread these days all over the world. PD affects the nervous system of the human and also affects a lot of human body parts that are connected via nerves. In order to make a classification for people who suffer from PD and who do not suffer from the disease, an advanced model called Bayesian Optimization-Support Vector Machine (BO-SVM) is presented in this paper for making the classification process. Bayesian Optimization (BO) is a hyperparameter tuning technique for optimizing the hyperparameters of machine learning models in order to obtain better accuracy. In this paper, BO is used to optimize the hyperparameters for six machine learning models, namely, Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), Naive Bayes (NB), Ridge Classifier (RC), and Decision Tree (DT). The dataset used in this study consists of 23 features and 195 instances. The class label of the target feature is 1 and 0, where 1 refers to the person suffering from PD and 0 refers to the person who does not suffer from PD. Four evaluation metrics, namely, accuracy, F1-score, recall, and precision were computed to evaluate the performance of the classification models used in this paper. The performance of the six machine learning models was tested on the dataset before and after the process of hyperparameter tuning. The experimental results demonstrated that the SVM model achieved the best results when compared with other machine learning models before and after the process of hyperparameter tuning, with an accuracy of 92.3% obtained using BO.
Collapse
Affiliation(s)
- Ahmed M. Elshewey
- Computer Science Department, Faculty of Computers and Information, Suez University, Suez 43512, Egypt
| | - Mahmoud Y. Shams
- Faculty of Artificial Intelligence, Kafrelsheikh University, Kafrelsheikh 33516, Egypt
| | - Nora El-Rashidy
- Faculty of Artificial Intelligence, Kafrelsheikh University, Kafrelsheikh 33516, Egypt
| | | | - Samaa M. Shohieb
- Information Systems Department, Faculty of Computers and Information, Mansoura University, Mansoura 35561, Egypt
| | - Zahraa Tarek
- Computer Science Department, Faculty of Computers and Information, Mansoura University, Mansoura 35561, Egypt
| |
Collapse
|
5
|
Gopinath N. Artificial intelligence and neuroscience: An update on fascinating relationships. Process Biochem 2023. [DOI: 10.1016/j.procbio.2022.12.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
|
6
|
Li S, Yue L, Chen S, Wu Z, Zhang J, Hong R, Xie L, Peng K, Wang C, Lin A, Jin L, Guan Q. High clinical diagnostic accuracy of combined salivary gland and myocardial metaiodobenzylguanidine scintigraphy in the diagnosis of Parkinson's disease. Front Aging Neurosci 2023; 14:1066331. [PMID: 36711204 PMCID: PMC9875016 DOI: 10.3389/fnagi.2022.1066331] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Accepted: 12/22/2022] [Indexed: 01/13/2023] Open
Abstract
Background Decreased myocardial uptake of 131I-metaiodobenzylguanidine (MIBG) is known to be an important feature to diagnose Parkinson's disease (PD). However, the diagnosis accuracy of myocardial MIBG scintigraphy alone is often unsatisfying. Recent studies have found that the MIBG uptake of the major salivary glands was reduced in PD patients as well. Purpose To evaluate the diagnostic value of major salivary gland MIBG scintigraphy in PD, and explore the potential role of myocardial MIBG scintigraphy combined with salivary gland MIBG scintigraphy in distinguishing PD from non-PD (NPD). Methods Thirty-seven subjects were performed with 131I-MIBG scintigraphy. They were classified into the PD group (N = 18) and the NPD group (N = 19), based on clinical diagnostic criteria, DAT PET and 18F-FDG PET imaging findings. Images of salivary glands and myocardium were outlined to calculated the MIBG uptake ratios. Results The combination of left parotid and left submandibular gland early images had a good performance in distinguishing PD from NPD, with sensitivity, specificity, and accuracy of 50.00, 94.74, and 72.37%, respectively. Combining the major salivary gland and myocardial scintigraphy results in the early period showed a good diagnostic value with AUC, sensitivity and specificity of 0.877, 77.78, and 94.74%, respectively. Meanwhile, in the delayed period yield an excellent diagnostic value with AUC, sensitivity and specificity of 0.904, 88.89, and 84.21%, respectively. Conclusion 131I-MIBG salivary gland scintigraphy assisted in the diagnosis and differential diagnosis of PD. The combination of major salivary gland and myocardial 131I-MIBG scintigraphy further increased the accuracy of PD diagnosis.
Collapse
Affiliation(s)
- Shuangfang Li
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China,Department of Neurology and Neurological Rehabilitation, Shanghai YangZhi Rehabilitation Hospital (Shanghai Sunshine Rehabilitation Center), School of Medicine, Tongji University, Shanghai, China
| | - Lei Yue
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Shuzhen Chen
- Department of Nuclear Medicine, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Zhuang Wu
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Jingxing Zhang
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Ronghua Hong
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Ludi Xie
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Kangwen Peng
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Chenghong Wang
- Department of Nuclear Medicine, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Ao Lin
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China
| | - Lingjing Jin
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China,Department of Neurology and Neurological Rehabilitation, Shanghai YangZhi Rehabilitation Hospital (Shanghai Sunshine Rehabilitation Center), School of Medicine, Tongji University, Shanghai, China,Shanghai Clinical Research Center for Aging and Medicine, Shanghai, China,Lingjing Jin,
| | - Qiang Guan
- Neurotoxin Research Center of Key Laboratory of Spine and Spinal Cord Injury Repair and Regeneration of Ministry of Education, Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, Shanghai, China,*Correspondence: Qiang Guan,
| |
Collapse
|
7
|
Barukab O, Ahmad A, Khan T, Thayyil Kunhumuhammed MR. Analysis of Parkinson's Disease Using an Imbalanced-Speech Dataset by Employing Decision Tree Ensemble Methods. Diagnostics (Basel) 2022; 12:diagnostics12123000. [PMID: 36553007 PMCID: PMC9776735 DOI: 10.3390/diagnostics12123000] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/10/2022] [Revised: 11/07/2022] [Accepted: 11/24/2022] [Indexed: 12/05/2022] Open
Abstract
Parkinson's disease (PD) currently affects approximately 10 million people worldwide. The detection of PD positive subjects is vital in terms of disease prognostics, diagnostics, management and treatment. Different types of early symptoms, such as speech impairment and changes in writing, are associated with Parkinson disease. To classify potential patients of PD, many researchers used machine learning algorithms in various datasets related to this disease. In our research, we study the dataset of the PD vocal impairment feature, which is an imbalanced dataset. We propose comparative performance evaluation using various decision tree ensemble methods, with or without oversampling techniques. In addition, we compare the performance of classifiers with different sizes of ensembles and various ratios of the minority class and the majority class with oversampling and undersampling. Finally, we combine feature selection with best-performing ensemble classifiers. The result shows that AdaBoost, random forest, and decision tree developed for the RUSBoost imbalanced dataset perform well in performance metrics such as precision, recall, F1-score, area under the receiver operating characteristic curve (AUROC) and the geometric mean. Further, feature selection methods, namely lasso and information gain, were used to screen the 10 best features using the best ensemble classifiers. AdaBoost with information gain feature selection method is the best performing ensemble method with an F1-score of 0.903.
Collapse
Affiliation(s)
- Omar Barukab
- Department of Information Technology, Faculty of Computing and Information Technology in Rabigh (FCITR), King Abdulaziz University, Jeddah 21589, Saudi Arabia
- Correspondence:
| | - Amir Ahmad
- College of Information Technology, United Arab Emirates University, Al Ain P.O. Box 15551, United Arab Emirates
| | - Tabrej Khan
- Department of Information Systems, Faculty of Computing and Information Technology in Rabigh (FCITR), King Abdulaziz University, Jeddah 21589, Saudi Arabia
| | - Mujeeb Rahiman Thayyil Kunhumuhammed
- Department of Computer Science, Faculty of Computing and Information Technology in Rabigh (FCITR), King Abdulaziz University, Jeddah 21589, Saudi Arabia
| |
Collapse
|
8
|
Nuvoli S, Palumbo B, Marongiu A, Bianconi F, Spanu A. 123I-MIBG Cardiac Scintigraphy and Heart/Mediastinum Ratio in Neurodegenerative Disorders: Is Delayed Scan Really Necessary? Curr Radiopharm 2022; 15:257-258. [PMID: 35619294 DOI: 10.2174/1874471015666220520090630] [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: 10/19/2021] [Revised: 12/24/2021] [Accepted: 01/17/2022] [Indexed: 11/22/2022]
Affiliation(s)
- Susanna Nuvoli
- Department of Medical, Surgical and Experimental Sciences, Unit of Nuclear Medicine, Università degli Studi di Sassari, Sassari, Italy
| | - Barbara Palumbo
- Department of Medicine and Surgery, Section of Nuclear Medicine and Health Physics, Università degli Studi di Perugia, Perugia, Italy
| | - Andrea Marongiu
- Department of Medical, Surgical and Experimental Sciences, Unit of Nuclear Medicine, Università degli Studi di Sassari, Sassari, Italy
| | - Francesco Bianconi
- Department of Engineering, Università degli Studi di Perugia, Perugia, Italy
| | - Angela Spanu
- Department of Medical, Surgical and Experimental Sciences, Unit of Nuclear Medicine, Università degli Studi di Sassari, Sassari, Italy
| |
Collapse
|
9
|
Differential Diagnosis of Alzheimer Disease vs. Mild Cognitive Impairment Based on Left Temporal Lateral Lobe Hypomethabolism on 18F-FDG PET/CT and Automated Classifiers. Diagnostics (Basel) 2022; 12:diagnostics12102425. [PMID: 36292114 PMCID: PMC9601187 DOI: 10.3390/diagnostics12102425] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 09/22/2022] [Accepted: 10/04/2022] [Indexed: 11/17/2022] Open
Abstract
Purpose: We evaluate the ability of Artificial Intelligence with automatic classification methods applied to semi-quantitative data from brain 18F-FDG PET/CT to improve the differential diagnosis between Alzheimer Disease (AD) and Mild Cognitive Impairment (MCI). Procedures: We retrospectively analyzed a total of 150 consecutive patients who underwent diagnostic evaluation for suspected AD (n = 67) or MCI (n = 83). All patients received brain 18F-FDG PET/CT according to the international guidelines, and images were analyzed both Qualitatively (QL) and Quantitatively (QN), the latter by a fully automated post-processing software that produced a z score metabolic map of 25 anatomically different cortical regions. A subset of n = 122 cases with a confirmed diagnosis of AD (n = 53) or MDI (n = 69) by 18–24-month clinical follow-up was finally included in the study. Univariate analysis and three automated classification models (classification tree –ClT-, ridge classifier –RC- and linear Support Vector Machine –lSVM-) were considered to estimate the ability of the z scores to discriminate between AD and MCI cases in. Results: The univariate analysis returned 14 areas where the z scores were significantly different between AD and MCI groups, and the classification accuracy ranged between 74.59% and 76.23%, with ClT and RC providing the best results. The best classification strategy consisted of one single split with a cut-off value of ≈ −2.0 on the z score from temporal lateral left area: cases below this threshold were classified as AD and those above the threshold as MCI. Conclusions: Our findings confirm the usefulness of brain 18F-FDG PET/CT QL and QN analyses in differentiating AD from MCI. Moreover, the combined use of automated classifications models can improve the diagnostic process since its use allows identification of a specific hypometabolic area involved in AD cases in respect to MCI. This data improves the traditional 18F-FDG PET/CT image interpretation and the diagnostic assessment of cognitive disorders.
Collapse
|
10
|
Diagnostic classification of Parkinson’s disease based on non-motor manifestations and machine learning strategies. Neural Comput Appl 2022. [DOI: 10.1007/s00521-022-07256-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
Abstract
AbstractNon-motor manifestations of Parkinson’s disease (PD) appear early and have a significant impact on the quality of life of patients, but few studies have evaluated their predictive potential with machine learning algorithms. We evaluated 9 algorithms for discriminating PD patients from controls using a wide collection of non-motor clinical PD features from two databases: Biocruces (96 subjects) and PPMI (687 subjects). In addition, we evaluated whether the combination of both databases could improve the individual results. For each database 2 versions with different granularity were created and a feature selection process was performed. We observed that most of the algorithms were able to detect PD patients with high accuracy (>80%). Support Vector Machine and Multi-Layer Perceptron obtained the best performance, with an accuracy of 86.3% and 84.7%, respectively. Likewise, feature selection led to a significant reduction in the number of variables and to better performance. Besides, the enrichment of Biocruces database with data from PPMI moderately benefited the performance of the classification algorithms, especially the recall and to a lesser extent the accuracy, while the precision worsened slightly. The use of interpretable rules obtained by the RIPPER algorithm showed that simply using two variables (autonomic manifestations and olfactory dysfunction), it was possible to achieve an accuracy of 84.4%. Our study demonstrates that the analysis of non-motor parameters of PD through machine learning techniques can detect PD patients with high accuracy and recall, and allows us to select the most discriminative non-motor variables to create potential tools for PD screening.
Collapse
|
11
|
Boccalini C, Carli G, Vanoli EG, Cocco A, Albanese A, Garibotto V, Perani D. Manual and semi-automated approaches to MIBG myocardial scintigraphy in patients with Parkinson's disease. Front Med (Lausanne) 2022; 9:1073720. [PMID: 36530915 PMCID: PMC9755341 DOI: 10.3389/fmed.2022.1073720] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2022] [Accepted: 11/17/2022] [Indexed: 12/04/2022] Open
Abstract
Objective This study investigates the effects of manual and semi-automatic methods for assessing MIBG semi-quantitative indices in a clinical setting. Materials and methods We included 123I-MIBG scans obtained in 35 patients with idiopathic Parkinson's Disease. Early and late heart-to-mediastinum (H/M) ratios were calculated from 123I-MIBG images using regions of interest (ROIs) placed over the heart and the mediastinum. The ROIs were derived using two approaches: (i) manually drawn and (ii) semi-automatic fixed-size ROIs using anatomical landmarks. Expert, moderate-expert, and not expert raters applied the ROIs procedures and interpreted the 123I-MIBG images. We evaluated the inter and intra-rater agreements in assessing 123I-MIBG H/M ratios. Results A moderate agreement in the raters' classification of pathological and non-pathological scores emerged regarding early and late H/M ratio values (κ = 0.45 and 0.69 respectively), applying the manual method, while the early and late H/M ratios obtained with the semi-automatic method reached a good agreement among observers (κ = 0.78). Cohen-Kappa values revealed that the semi-automatic method improved the agreement between expert and inexpert raters: the agreement improved from a minimum of 0.29 (fair, for early H/M) and 0.69 (substantial, in late H/M) with the manual method, to 0.90 (perfect, in early H/M) and 0.87 (perfect, in late H/M) with the semi-automatic method. Conclusion The use of the semi-automatic method improves the agreement among raters in classifying' H/M ratios as pathological or non-pathological, namely for inexpert readers. These results have important implications for semi-quantitative assessment of 123I-MIBG images in clinical routine.
Collapse
Affiliation(s)
- Cecilia Boccalini
- School of Psychology, Vita-Salute San Raffaele University, Milan, Italy.,In vivo Human Molecular and Structural Neuroimaging Unit, Division of Neuroscience, Scientific Institute for Research, Hospitalization and Healthcare (IRCCS) San Raffaele Scientific Institute, Milan, Italy.,Laboratory of Neuroimaging and Innovative Molecular Tracers (NIMTlab), Geneva University Neurocenter and Faculty of Medicine, University of Geneva, Geneva, Switzerland
| | - Giulia Carli
- In vivo Human Molecular and Structural Neuroimaging Unit, Division of Neuroscience, Scientific Institute for Research, Hospitalization and Healthcare (IRCCS) San Raffaele Scientific Institute, Milan, Italy.,Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands
| | | | - Antoniangela Cocco
- Department of Neurology, Scientific Institute for Research, Hospitalization and Healthcare (IRCCS) Humanitas Research Hospital, Milan, Italy
| | - Alberto Albanese
- Department of Neurology, Scientific Institute for Research, Hospitalization and Healthcare (IRCCS) Humanitas Research Hospital, Milan, Italy.,Department of Neuroscience, Catholic University, Milan, Italy
| | - Valentina Garibotto
- Laboratory of Neuroimaging and Innovative Molecular Tracers (NIMTlab), Geneva University Neurocenter and Faculty of Medicine, University of Geneva, Geneva, Switzerland.,Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospitals, Geneva, Switzerland.,Center for Biomedical Imaging, Geneva, Switzerland
| | - Daniela Perani
- School of Psychology, Vita-Salute San Raffaele University, Milan, Italy.,In vivo Human Molecular and Structural Neuroimaging Unit, Division of Neuroscience, Scientific Institute for Research, Hospitalization and Healthcare (IRCCS) San Raffaele Scientific Institute, Milan, Italy.,Nuclear Medicine Unit, San Raffaele Hospital, Milan, Italy
| |
Collapse
|
12
|
Nuvoli S, Tanda G, Stazza ML, Palumbo B, Frantellizzi V, De Vincentis G, Spanu A, Madeddu G. 123I-Ioflupane SPECT and 18F-FDG PET Combined Use in the Characterization of Movement and Cognitive Associated Disorders in Neurodegenerative Diseases. Curr Alzheimer Res 2021; 18:196-207. [PMID: 34102975 DOI: 10.2174/1567205018666210608112302] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2020] [Revised: 03/21/2021] [Accepted: 04/21/2021] [Indexed: 11/22/2022]
Abstract
BACKGROUND Both movement (MD) and cognitive (CD) disorders can occur associated in some neurodegenerative diseases, such as Parkinson's disease (PD) and Alzheimer's disease (AD). OBJECTIVE We further investigated the usefulness of 123I-Ioflupane SPECT and 18F-FDG PET combined use in patients with these disorders in the early stage. METHODS We retrospectively enrolled twenty-five consecutive patients with MD and CD clinical symptoms of recent appearance. All patients had undergone neurologic examination, neuropsychological tests, and magnetic resonance imaging. 123I-Ioflupane SPECT was performed in all cases, followed by 18F-FDG PET two weeks later. In the two procedures, both qualitative (QL) and quantitative (QN) image analyses were determined. RESULTS In patients with both 123I-Ioflupane SPECT and 18F-FDG PET pathologic data, associated dopaminergic and cognitive impairments were confirmed in 56% of cases. Pathologic SPECT with normal PET in 16% of cases could diagnose MD and exclude an associated CD, despite clinical symptoms. On the contrary, normal SPECT with pathologic PET in 28% of cases could exclude basal ganglia damage while confirming CD. QN 123I-Ioflupane SPECT analysis showed better performance than QL since QN correctly characterized two cases of MD with normal QL. Moreover, correct classification of normal metabolism was made only by QN analysis of 18F-FDG PET in four cases, despite suspect areas of hypometabolism at QL. CONCLUSION The combined use of these imaging procedures proved a reliable diagnostic tool to accurately identify and characterize MD and CD in early stage. QN analysis was effective in supporting QL evaluation, and its routine use is suggested, especially with inconclusive QL.
Collapse
Affiliation(s)
- Susanna Nuvoli
- Unit of Nuclear Medicine, Department of Medical, Surgical and Experimental Sciences, University of Sassari, Sassari, Italy
| | - Giovanna Tanda
- Unit of Nuclear Medicine, Department of Medical, Surgical and Experimental Sciences, University of Sassari, Sassari, Italy
| | - Maria L Stazza
- Unit of Nuclear Medicine, Department of Medical, Surgical and Experimental Sciences, University of Sassari, Sassari, Italy
| | - Barbara Palumbo
- Section of Nuclear Medicine and Health Physics, Department of Surgical and Biomedical Sciences, University of Perugia, Perugia, Italy
| | | | | | - Angela Spanu
- Unit of Nuclear Medicine, Department of Medical, Surgical and Experimental Sciences, University of Sassari, Sassari, Italy
| | - Giuseppe Madeddu
- Unit of Nuclear Medicine, Department of Medical, Surgical and Experimental Sciences, University of Sassari, Sassari, Italy
| |
Collapse
|
13
|
Mei J, Desrosiers C, Frasnelli J. Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature. Front Aging Neurosci 2021; 13:633752. [PMID: 34025389 PMCID: PMC8134676 DOI: 10.3389/fnagi.2021.633752] [Citation(s) in RCA: 76] [Impact Index Per Article: 25.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2020] [Accepted: 03/22/2021] [Indexed: 12/26/2022] Open
Abstract
Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.
Collapse
Affiliation(s)
- Jie Mei
- Chemosensory Neuroanatomy Lab, Department of Anatomy, Université du Québec à Trois-Rivières (UQTR), Trois-Rivières, QC, Canada
| | - Christian Desrosiers
- Laboratoire d'Imagerie, de Vision et d'Intelligence Artificielle (LIVIA), Department of Software and IT Engineering, École de Technologie Supérieure, Montreal, QC, Canada
| | - Johannes Frasnelli
- Chemosensory Neuroanatomy Lab, Department of Anatomy, Université du Québec à Trois-Rivières (UQTR), Trois-Rivières, QC, Canada
- Centre de Recherche de l'Hôpital du Sacré-Coeur de Montréal, Centre Intégré Universitaire de Santé et de Services Sociaux du Nord-de-l'Île-de-Montréal (CIUSSS du Nord-de-l'Île-de-Montréal), Montreal, QC, Canada
| |
Collapse
|
14
|
Palumbo B, Bianconi F, Nuvoli S, Spanu A, Fravolini ML. Artificial intelligence techniques support nuclear medicine modalities to improve the diagnosis of Parkinson’s disease and Parkinsonian syndromes. Clin Transl Imaging 2020. [DOI: 10.1007/s40336-020-00404-x] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
Abstract
Purpose
The aim of this review is to discuss the most significant contributions about the role of Artificial Intelligence (AI) techniques to support the diagnosis of movement disorders through nuclear medicine modalities.
Methods
The work is based on a selection of papers available on PubMed, Scopus and Web of Sciences. Articles not written in English were not considered in this study.
Results
Many papers are available concerning the increasing contribution of machine learning techniques to classify Parkinson’s disease (PD), Parkinsonian syndromes and Essential Tremor (ET) using data derived from brain SPECT with dopamine transporter radiopharmaceuticals. Other papers investigate by AI techniques data obtained by 123I-MIBG myocardial scintigraphy to differentially diagnose PD and other Parkinsonian syndromes.
Conclusion
The recent literature provides strong evidence that AI techniques can play a fundamental role in the diagnosis of movement disorders by means of nuclear medicine modalities, therefore paving the way towards personalized medicine.
Collapse
|
15
|
Zukotynski K, Gaudet V, Uribe CF, Mathotaarachchi S, Smith KC, Rosa-Neto P, Bénard F, Black SE. Machine Learning in Nuclear Medicine: Part 2-Neural Networks and Clinical Aspects. J Nucl Med 2020; 62:22-29. [PMID: 32978286 DOI: 10.2967/jnumed.119.231837] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2020] [Accepted: 08/13/2020] [Indexed: 12/12/2022] Open
Abstract
This article is the second part in our machine learning series. Part 1 provided a general overview of machine learning in nuclear medicine. Part 2 focuses on neural networks. We start with an example illustrating how neural networks work and a discussion of potential applications. Recognizing that there is a spectrum of applications, we focus on recent publications in the areas of image reconstruction, low-dose PET, disease detection, and models used for diagnosis and outcome prediction. Finally, since the way machine learning algorithms are reported in the literature is extremely variable, we conclude with a call to arms regarding the need for standardized reporting of design and outcome metrics and we propose a basic checklist our community might follow going forward.
Collapse
Affiliation(s)
- Katherine Zukotynski
- Departments of Medicine and Radiology, McMaster University, Hamilton, Ontario, Canada
| | - Vincent Gaudet
- Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, Ontario, Canada
| | - Carlos F Uribe
- PET Functional Imaging, BC Cancer, Vancouver, British Columbia, Canada
| | | | - Kenneth C Smith
- Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario, Canada
| | - Pedro Rosa-Neto
- Translational Neuroimaging Lab, McGill University, Montreal, Quebec, Canada
| | - François Bénard
- PET Functional Imaging, BC Cancer, Vancouver, British Columbia, Canada.,Department of Radiology, University of British Columbia, Vancouver, British Columbia, Canada; and
| | - Sandra E Black
- Department of Medicine (Neurology), Sunnybrook Health Sciences Centre, University of Toronto, Toronto, Ontario, Canada
| |
Collapse
|