1
|
Wu Y, Cheng Y, Xiao Y, Shang H, Ou R. The Role of Machine Learning in Cognitive Impairment in Parkinson Disease: Systematic Review and Meta-Analysis. J Med Internet Res 2025; 27:e59649. [PMID: 40153789 PMCID: PMC11992493 DOI: 10.2196/59649] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2024] [Revised: 11/04/2024] [Accepted: 01/30/2025] [Indexed: 03/30/2025] Open
Abstract
BACKGROUND Parkinson disease (PD) is a common neurodegenerative disease characterized by both motor and nonmotor symptoms. Cognitive impairment often occurs early in the disease and can persist throughout its progression, severely impacting patients' quality of life. The utilization of machine learning (ML) has recently shown promise in identifying cognitive impairment in patients with PD. OBJECTIVE This study aims to summarize different ML models applied to cognitive impairment in patients with PD and to identify determinants for improving diagnosis and predictive power for early detection of cognitive impairment. METHODS PubMed, Cochrane, Embase, and Web of Science were searched for relevant articles on March 2, 2024. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Bivariate meta-analysis was used to estimate pooled sensitivity and specificity results, presented as odds ratio (OR) and 95% CI. A summary receiver operator characteristic (SROC) curve was used. RESULTS A total of 38 articles met the criteria, involving 8564 patients with PD and 1134 healthy controls. Overall, 120 models reported sensitivity and specificity, with mean values of 71.07% (SD 13.72%) and 77.01% (SD 14.31%), respectively. Predictors commonly used in ML models included clinical features, neuroimaging features, and other variables. No significant heterogeneity was observed in the bivariate meta-analysis, which included 12 studies. Using sensitivity as the metric, the combined sensitivity and specificity were 0.76 (95% CI 0.67-0.83) and 0.83 (95% CI 0.76-0.88), respectively. When specificity was used, the combined values were 0.77 (95% CI 0.65-0.86) and 0.76 (95% CI 0.63-0.85), respectively. The area under the curves of the SROC were 0.87 (95% CI 0.83-0.89) and 0.83 (95% CI 0.80-0.86) respectively. CONCLUSIONS Our findings provide a comprehensive summary of various ML models and demonstrate the effectiveness of ML as a tool for diagnosing and predicting cognitive impairment in patients with PD. TRIAL REGISTRATION PROSPERO CRD42023480196; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023480196.
Collapse
Affiliation(s)
- Yanyun Wu
- Department of Neurology, West China Hospital of Sichuan University, Chengdu, China
| | - Yangfan Cheng
- Department of Neurology, West China Hospital of Sichuan University, Chengdu, China
| | - Yi Xiao
- Department of Neurology, West China Hospital of Sichuan University, Chengdu, China
| | - Huifang Shang
- Department of Neurology, West China Hospital of Sichuan University, Chengdu, China
| | - Ruwei Ou
- Department of Neurology, West China Hospital of Sichuan University, Chengdu, China
| |
Collapse
|
2
|
Dzialas V, Doering E, Eich H, Strafella AP, Vaillancourt DE, Simonyan K, van Eimeren T, International Parkinson Movement Disorders Society‐Neuroimaging Study Group. Houston, We Have AI Problem! Quality Issues with Neuroimaging-Based Artificial Intelligence in Parkinson's Disease: A Systematic Review. Mov Disord 2024; 39:2130-2143. [PMID: 39235364 PMCID: PMC11657025 DOI: 10.1002/mds.30002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/20/2024] [Revised: 08/07/2024] [Accepted: 08/08/2024] [Indexed: 09/06/2024] Open
Abstract
In recent years, many neuroimaging studies have applied artificial intelligence (AI) to facilitate existing challenges in Parkinson's disease (PD) diagnosis, prognosis, and intervention. The aim of this systematic review was to provide an overview of neuroimaging-based AI studies and to assess their methodological quality. A PubMed search yielded 810 studies, of which 244 that investigated the utility of neuroimaging-based AI for PD diagnosis, prognosis, or intervention were included. We systematically categorized studies by outcomes and rated them with respect to five minimal quality criteria (MQC) pertaining to data splitting, data leakage, model complexity, performance reporting, and indication of biological plausibility. We found that the majority of studies aimed to distinguish PD patients from healthy controls (54%) or atypical parkinsonian syndromes (25%), whereas prognostic or interventional studies were sparse. Only 20% of evaluated studies passed all five MQC, with data leakage, non-minimal model complexity, and reporting of biological plausibility as the primary factors for quality loss. Data leakage was associated with a significant inflation of accuracies. Very few studies employed external test sets (8%), where accuracy was significantly lower, and 19% of studies did not account for data imbalance. Adherence to MQC was low across all observed years and journal impact factors. This review outlines that AI has been applied to a wide variety of research questions pertaining to PD; however, the number of studies failing to pass the MQC is alarming. Therefore, we provide recommendations to enhance the interpretability, generalizability, and clinical utility of future AI applications using neuroimaging in PD. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.
Collapse
Affiliation(s)
- Verena Dzialas
- Department of Nuclear Medicine, Faculty of Medicine and University HospitalUniversity of CologneCologneGermany
- Faculty of Mathematics and Natural SciencesUniversity of CologneCologneGermany
| | - Elena Doering
- Department of Nuclear Medicine, Faculty of Medicine and University HospitalUniversity of CologneCologneGermany
- German Center for Neurodegenerative Diseases (DZNE)BonnGermany
| | - Helena Eich
- Department of Nuclear Medicine, Faculty of Medicine and University HospitalUniversity of CologneCologneGermany
| | - Antonio P. Strafella
- Edmond J. Safra Parkinson Disease Program, Neurology Division, Krembil Brain InstituteUniversity Health NetworkTorontoCanada
- Brain Health Imaging Centre, Centre for Addiction and Mental HealthUniversity of TorontoTorontoCanada
- Temerty Faculty of MedicineUniversity of TorontoTorontoCanada
| | - David E. Vaillancourt
- Department of Applied Physiology and KinesiologyUniversity of FloridaGainesvilleFloridaUSA
| | - Kristina Simonyan
- Department of Otolaryngology—Head and Neck SurgeryHarvard Medical School and Massachusetts Eye and EarBostonMassachusettsUSA
- Department of NeurologyMassachusetts General HospitalBostonMassachusettsUSA
| | - Thilo van Eimeren
- Department of Nuclear Medicine, Faculty of Medicine and University HospitalUniversity of CologneCologneGermany
- Department of Neurology, Faculty of Medicine and University HospitalUniversity of CologneCologneGermany
| | | |
Collapse
|
3
|
Christidi F, Drouka A, Brikou D, Mamalaki E, Ntanasi E, Karavasilis E, Velonakis G, Angelopoulou G, Tsapanou A, Gu Y, Yannakoulia M, Scarmeas N. The Association between Individual Food Groups, Limbic System White Matter Tracts, and Episodic Memory: Initial Data from the Aiginition Longitudinal Biomarker Investigation of Neurodegeneration (ALBION) Study. Nutrients 2024; 16:2766. [PMID: 39203902 PMCID: PMC11357525 DOI: 10.3390/nu16162766] [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: 07/22/2024] [Revised: 08/14/2024] [Accepted: 08/17/2024] [Indexed: 09/03/2024] Open
Abstract
(1) Background: Many studies link food intake with clinical cognitive outcomes, but evidence for brain biomarkers, such as memory-related limbic white matter (WM) tracts, is limited. We examined the association between food groups, limbic WM tracts integrity, and memory performance in community-dwelling individuals. (2) Methods: We included 117 non-demented individuals (ALBION study). Verbal and visual episodic memory tests were administered, and a composite z-score was calculated. Diffusion tensor imaging tractography was applied for limbic WM tracts (fornix-FX, cingulum bundle-CB, uncinate fasciculus-UF, hippocampal perforant pathway zone-hPPZ). Food intake was evaluated through four 24-h recalls. We applied linear regression models adjusted for demographics and energy intake. (3) Results: We found significant associations between (a) higher low-to-moderate alcohol intake and higher FX fractional anisotropy (FA), (b) higher full-fat dairy intake and lower hPPZ FA, and (c) higher red meat and cold cuts intake and lower hPPZ FA. None of the food groups was associated with memory performance. (4) Conclusions: Despite non-significant associations between food groups and memory, possibly due to participants' cognitive profile and/or compensatory mechanisms, the study documented a possible beneficial role of low-to-moderate alcohol and a harmful role of full-fat dairy and red meat and cold cuts on limbic WM tracts.
Collapse
Affiliation(s)
- Foteini Christidi
- First Department of Neurology, Aiginition Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece (G.A.)
- Computational Neuroimaging Group (CNG), School of Medicine, Trinity College Dublin, D08 NHY1 Dublin, Ireland
| | - Archontoula Drouka
- Department of Nutrition and Dietetics, Harokopio University, 17671 Athens, Greece
| | - Dora Brikou
- Department of Nutrition and Dietetics, Harokopio University, 17671 Athens, Greece
| | - Eirini Mamalaki
- Department of Nutrition and Dietetics, Harokopio University, 17671 Athens, Greece
| | - Eva Ntanasi
- First Department of Neurology, Aiginition Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece (G.A.)
| | - Efstratios Karavasilis
- Research Unit of Radiology and Medical Imaging, 2nd Department of Radiology, Attikon General University Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece
- School of Medicine, Democritus University of Alexandroupolis, 68100 Alexandroupolis, Greece
| | - Georgios Velonakis
- Research Unit of Radiology and Medical Imaging, 2nd Department of Radiology, Attikon General University Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece
| | - Georgia Angelopoulou
- First Department of Neurology, Aiginition Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece (G.A.)
| | - Angeliki Tsapanou
- First Department of Neurology, Aiginition Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece (G.A.)
- Taub Institute for Research in Alzheimer’s Disease and the Aging Brain, The Gertrude H. Sergievsky Center, Columbia University, New York, NY 10032, USA;
| | - Yian Gu
- Taub Institute for Research in Alzheimer’s Disease and the Aging Brain, The Gertrude H. Sergievsky Center, Columbia University, New York, NY 10032, USA;
| | - Mary Yannakoulia
- Department of Nutrition and Dietetics, Harokopio University, 17671 Athens, Greece
| | - Nikolaos Scarmeas
- First Department of Neurology, Aiginition Hospital, School of Medicine, National and Kapodistrian University of Athens, 11528 Athens, Greece (G.A.)
- Taub Institute for Research in Alzheimer’s Disease and the Aging Brain, The Gertrude H. Sergievsky Center, Columbia University, New York, NY 10032, USA;
| |
Collapse
|
4
|
Pang H, Wang J, Yu Z, Yu H, Li X, Bu S, Zhao M, Jiang Y, Liu Y, Fan G. Glymphatic function from diffusion-tensor MRI to predict conversion from mild cognitive impairment to dementia in Parkinson's disease. J Neurol 2024; 271:5598-5609. [PMID: 38913186 PMCID: PMC11319419 DOI: 10.1007/s00415-024-12525-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2024] [Revised: 06/10/2024] [Accepted: 06/15/2024] [Indexed: 06/25/2024]
Abstract
BACKGROUND Although brain glymphatic dysfunction is a contributing factor to the cognitive deficits in Parkinson's disease (PD), its role in the longitudinal progression of cognitive dysfunction remains unknown. OBJECTIVE To investigate the glymphatic function in PD with mild cognitive impairment (MCI) that progresses to dementia (PDD) and to determine its predictive value in identifying individuals at high risk for developing dementia. METHODS We included 64 patients with PD meeting criteria for MCI and categorized them as either progressed to PDD (converters) (n = 29) or did not progress to PDD (nonconverters) (n = 35), depending on whether they developed dementia during follow-up. Meanwhile, 35 age- and gender-matched healthy controls (HC) were included. Bilateral diffusion-tensor imaging analysis along the perivascular space (DTI-ALPS) indices and enlarged perivascular spaces (EPVS) volume fraction in bilateral centrum semiovale, basal ganglia (BG), and midbrain were compared among the three groups. Correlations among the DTI-ALPS index and EPVS, as well as cognitive performance were analyzed. Additionally, we investigated the mediation effect of EPVS on DTI-ALPS and cognitive function. RESULTS PDD converters had lower cognitive composites scores in the executive domains than did nonconverters (P < 0.001). Besides, PDD converters had a significantly lower DTI-ALPS index in the left hemisphere (P < 0.001) and a larger volume fraction of BG-PVS (P = 0.03) compared to HC and PDD nonconverters. Lower DTI-ALPS index and increased BG-PVS volume fraction were associated with worse performance in the global cognitive performance and executive function. However, there was no significant mediating effect. Receiver operating characteristic analysis revealed that the DTI-ALPS could effectively identify PDD converters with an area under the curve (AUC) of 0.850. CONCLUSION The reduction of glymphatic activity, measured by the DTI-ALPS, could potentially be used as a non-invasive indicator in forecasting high risk of dementia conversion before the onset of dementia in PD patients.
Collapse
Affiliation(s)
- Huize Pang
- Department of Radiology, First Affiliated Hospital of China Medical University, Shenyang, Liaoning, China
| | - Juzhou Wang
- Department of Radiology, First Affiliated Hospital of China Medical University, Shenyang, Liaoning, China
| | - Ziyang Yu
- School of Medicine, Xiamen University, Xiamen, Fujian, China
| | - Hongmei Yu
- Department of Neurology, First Affiliated Hospital of China Medical University, Shenyang, Liaoning, China
| | - Xiaolu Li
- Department of Radiology, First Affiliated Hospital of China Medical University, Shenyang, Liaoning, China
| | - Shuting Bu
- Department of Radiology, First Affiliated Hospital of China Medical University, Shenyang, Liaoning, China
| | - Mengwan Zhao
- Department of Radiology, First Affiliated Hospital of China Medical University, Shenyang, Liaoning, China
| | - Yueluan Jiang
- MR Research Collaboration, Siemens Healthineers, Beijing, China
| | - Yu Liu
- Department of Radiology, First Affiliated Hospital of China Medical University, Shenyang, Liaoning, China
| | - Guoguang Fan
- Department of Radiology, First Affiliated Hospital of China Medical University, Shenyang, Liaoning, China.
| |
Collapse
|
5
|
Altham C, Zhang H, Pereira E. Machine learning for the detection and diagnosis of cognitive impairment in Parkinson's Disease: A systematic review. PLoS One 2024; 19:e0303644. [PMID: 38753740 PMCID: PMC11098383 DOI: 10.1371/journal.pone.0303644] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2024] [Accepted: 04/29/2024] [Indexed: 05/18/2024] Open
Abstract
BACKGROUND Parkinson's Disease is the second most common neurological disease in over 60s. Cognitive impairment is a major clinical symptom, with risk of severe dysfunction up to 20 years post-diagnosis. Processes for detection and diagnosis of cognitive impairments are not sufficient to predict decline at an early stage for significant impact. Ageing populations, neurologist shortages and subjective interpretations reduce the effectiveness of decisions and diagnoses. Researchers are now utilising machine learning for detection and diagnosis of cognitive impairment based on symptom presentation and clinical investigation. This work aims to provide an overview of published studies applying machine learning to detecting and diagnosing cognitive impairment, evaluate the feasibility of implemented methods, their impacts, and provide suitable recommendations for methods, modalities and outcomes. METHODS To provide an overview of the machine learning techniques, data sources and modalities used for detection and diagnosis of cognitive impairment in Parkinson's Disease, we conducted a review of studies published on the PubMed, IEEE Xplore, Scopus and ScienceDirect databases. 70 studies were included in this review, with the most relevant information extracted from each. From each study, strategy, modalities, sources, methods and outcomes were extracted. RESULTS Literatures demonstrate that machine learning techniques have potential to provide considerable insight into investigation of cognitive impairment in Parkinson's Disease. Our review demonstrates the versatility of machine learning in analysing a wide range of different modalities for the detection and diagnosis of cognitive impairment in Parkinson's Disease, including imaging, EEG, speech and more, yielding notable diagnostic accuracy. CONCLUSIONS Machine learning based interventions have the potential to glean meaningful insight from data, and may offer non-invasive means of enhancing cognitive impairment assessment, providing clear and formidable potential for implementation of machine learning into clinical practice.
Collapse
Affiliation(s)
- Callum Altham
- Department of Computer Science, Edge Hill University, Ormskirk, Lancashire, United Kingdom
| | - Huaizhong Zhang
- Department of Computer Science, Edge Hill University, Ormskirk, Lancashire, United Kingdom
| | - Ella Pereira
- Department of Computer Science, Edge Hill University, Ormskirk, Lancashire, United Kingdom
| |
Collapse
|
6
|
Müller HP, Kassubek J. Toward diffusion tensor imaging as a biomarker in neurodegenerative diseases: technical considerations to optimize recordings and data processing. Front Hum Neurosci 2024; 18:1378896. [PMID: 38628970 PMCID: PMC11018884 DOI: 10.3389/fnhum.2024.1378896] [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: 01/30/2024] [Accepted: 02/26/2024] [Indexed: 04/19/2024] Open
Abstract
Neuroimaging biomarkers have shown high potential to map the disease processes in the application to neurodegenerative diseases (NDD), e.g., diffusion tensor imaging (DTI). For DTI, the implementation of a standardized scanning and analysis cascade in clinical trials has potential to be further optimized. Over the last few years, various approaches to improve DTI applications to NDD have been developed. The core issue of this review was to address considerations and limitations of DTI in NDD: we discuss suggestions for improvements of DTI applications to NDD. Based on this technical approach, a set of recommendations was proposed for a standardized DTI scan protocol and an analysis cascade of DTI data pre-and postprocessing and statistical analysis. In summary, considering advantages and limitations of the DTI in NDD we suggest improvements for a standardized framework for a DTI-based protocol to be applied to future imaging studies in NDD, towards the goal to proceed to establish DTI as a biomarker in clinical trials in neurodegeneration.
Collapse
|