Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical Insights
ABSTRACT Background While automated methods for differential diagnosis of parkinsonian syndromes based on MRI imaging have been introduced, their implementation in clinical practice still underlies considerable challenges. Objective To assess whether the performance of classifiers based on imaging d...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Brain and Behavior |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/brb3.70274 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832582646666887168 |
|---|---|
| author | Tobias Meindl Alexander Hapfelmeier Tobias Mantel Angela Jochim Jonas Deppe Silke Zwirner Jan S. Kirschke Yong Li Bernhard Haslinger |
| author_facet | Tobias Meindl Alexander Hapfelmeier Tobias Mantel Angela Jochim Jonas Deppe Silke Zwirner Jan S. Kirschke Yong Li Bernhard Haslinger |
| author_sort | Tobias Meindl |
| collection | DOAJ |
| description | ABSTRACT Background While automated methods for differential diagnosis of parkinsonian syndromes based on MRI imaging have been introduced, their implementation in clinical practice still underlies considerable challenges. Objective To assess whether the performance of classifiers based on imaging derived biomarkers is improved with the addition of basic clinical information and to provide a practical solution to address the insecurity of classification results due to the uncertain clinical diagnosis they are based on. Methods Retro‐ and prospectively collected data from multimodal MRI and standardized clinical datasets of 229 patients with PD (n = 167), PSP (n = 44), or MSA (n = 18) underwent multinomial classification in a benchmark study comparing the performance of nine machine learning methods. A predictor space of imaging variables, either with or without clinical information, was investigated. Classification results were assessed using multiclass AUCs. Individual predicted probabilities were visualized to address diagnostic uncertainty. Results Clinical diagnosis was accurately confirmed using machine learning models with only small differences when using imaging and clinical signs versus imaging variables only (expected multiclass AUC of 0.95 vs. 0.92). Still, multinomial classification is hampered by imbalanced class frequencies. The most discriminatory variables were responsiveness to levodopa, vertical gaze palsy, and the volumes of subcortical structures, including the red nucleus. Conclusion Machine‐learning‐assisted classification of MR‐imaging biomarkers gathered in routine care can assist in the diagnosis of parkinsonian syndromes as part of the diagnostic workup. We provide a visual method that aids the interpretation of neuroimaging‐based classification results of the three main parkinsonian syndromes, improving clinical interpretability. |
| format | Article |
| id | doaj-art-7db5c458e64447b69785e6202f72c728 |
| institution | Kabale University |
| issn | 2162-3279 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Brain and Behavior |
| spelling | doaj-art-7db5c458e64447b69785e6202f72c7282025-01-29T13:36:40ZengWileyBrain and Behavior2162-32792025-01-01151n/an/a10.1002/brb3.70274Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical InsightsTobias Meindl0Alexander Hapfelmeier1Tobias Mantel2Angela Jochim3Jonas Deppe4Silke Zwirner5Jan S. Kirschke6Yong Li7Bernhard Haslinger8Department of Neurology, Klinikum rechts der Isar Technical University of Munich Munich GermanyInstitute of AI and Informatics in Medicine, School of Medicine Technical University of Munich Munich GermanyDepartment of Neurology, Klinikum rechts der Isar Technical University of Munich Munich GermanyDepartment of Neurology, Klinikum rechts der Isar Technical University of Munich Munich GermanyDepartment of Neurology, Klinikum rechts der Isar Technical University of Munich Munich GermanyDepartment of Neurology, Klinikum rechts der Isar Technical University of Munich Munich GermanyDepartment of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar Technical University Munich Munich GermanyDepartment of Neurology, Klinikum rechts der Isar Technical University of Munich Munich GermanyDepartment of Neurology, Klinikum rechts der Isar Technical University of Munich Munich GermanyABSTRACT Background While automated methods for differential diagnosis of parkinsonian syndromes based on MRI imaging have been introduced, their implementation in clinical practice still underlies considerable challenges. Objective To assess whether the performance of classifiers based on imaging derived biomarkers is improved with the addition of basic clinical information and to provide a practical solution to address the insecurity of classification results due to the uncertain clinical diagnosis they are based on. Methods Retro‐ and prospectively collected data from multimodal MRI and standardized clinical datasets of 229 patients with PD (n = 167), PSP (n = 44), or MSA (n = 18) underwent multinomial classification in a benchmark study comparing the performance of nine machine learning methods. A predictor space of imaging variables, either with or without clinical information, was investigated. Classification results were assessed using multiclass AUCs. Individual predicted probabilities were visualized to address diagnostic uncertainty. Results Clinical diagnosis was accurately confirmed using machine learning models with only small differences when using imaging and clinical signs versus imaging variables only (expected multiclass AUC of 0.95 vs. 0.92). Still, multinomial classification is hampered by imbalanced class frequencies. The most discriminatory variables were responsiveness to levodopa, vertical gaze palsy, and the volumes of subcortical structures, including the red nucleus. Conclusion Machine‐learning‐assisted classification of MR‐imaging biomarkers gathered in routine care can assist in the diagnosis of parkinsonian syndromes as part of the diagnostic workup. We provide a visual method that aids the interpretation of neuroimaging‐based classification results of the three main parkinsonian syndromes, improving clinical interpretability.https://doi.org/10.1002/brb3.70274automated diagnosisdecision supportMRImultiple system atrophyParkinson's diseaseprogressive supranuclear palsy |
| spellingShingle | Tobias Meindl Alexander Hapfelmeier Tobias Mantel Angela Jochim Jonas Deppe Silke Zwirner Jan S. Kirschke Yong Li Bernhard Haslinger Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical Insights Brain and Behavior automated diagnosis decision support MRI multiple system atrophy Parkinson's disease progressive supranuclear palsy |
| title | Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical Insights |
| title_full | Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical Insights |
| title_fullStr | Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical Insights |
| title_full_unstemmed | Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical Insights |
| title_short | Assisted Parkinsonism Diagnosis Using Multimodal MRI—The Role of Clinical Insights |
| title_sort | assisted parkinsonism diagnosis using multimodal mri the role of clinical insights |
| topic | automated diagnosis decision support MRI multiple system atrophy Parkinson's disease progressive supranuclear palsy |
| url | https://doi.org/10.1002/brb3.70274 |
| work_keys_str_mv | AT tobiasmeindl assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights AT alexanderhapfelmeier assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights AT tobiasmantel assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights AT angelajochim assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights AT jonasdeppe assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights AT silkezwirner assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights AT janskirschke assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights AT yongli assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights AT bernhardhaslinger assistedparkinsonismdiagnosisusingmultimodalmritheroleofclinicalinsights |