Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson’s disease

Zhang, Jing

doi:10.1038/s41531-021-00266-8

Cited by 45 publications

(10 citation statements)

References 104 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More research is urgently needed to establish a reliable risk model for predicting EAOC in patients with endometriosis. 27 To our delight, machine learning has been widely used in clinical differentiation and early diagnosis, such as Parkinson's disease, 28 diabetic kidney disease, 29 non‐alcoholic fatty liver disease, 30 and prostate cancer diagnosis. 31 Compared with traditional methods, the use of machine learning algorithms has advantages for modeling and validation.…”

Section: Discussionmentioning

confidence: 99%

The application of risk models based on machine learning to predict endometriosis‐associated ovarian cancer in patients with endometriosis

Chao

Wang

Lang

et al. 2022

Acta Obstet Gynecol Scand

View full text Add to dashboard Cite

Introduction:There is currently no satisfactory model for predicting malignant transformation of endometriosis. The aim of this study was to construct and evaluate a risk model incorporating noninvasive clinical parameters to predict endometriosisassociated ovarian cancer (EAOC) in patients with endometriosis. Material and Methods:We enrolled 6809 patients with endometriosis confirmed by pathology, and randomly allocated them to training (n = 4766) and testing cohorts (n = 2043). The proportion of patients with EAOC in each cohort was similar. We extracted a total of 94 demographic and clinicopathologic features from the medical records using natural language processing. We used a machine learning methodgradient-boosting decision tree -to construct a predictive model for EAOC and to evaluate the accuracy of the model. We also constructed a multivariate logistic regression model inclusive of the EAOC-associated risk factors using a back stepwise procedure. Then we compared the performance of the two risk-predicting models using DeLong's test. Results:The occurrence of EAOC was 1.84% in this study. The logistic regression model comprised 10 selected features and demonstrated good discrimination in the testing cohort, with an area under the curve (AUC) of 0.891 (95% confidence interval[CI] 0.821-0.960), sensitivity of 88.9%, and specificity of 76.7%. The risk model based on machine learning had an AUC of 0.942 (95% CI 0.914-0.969), sensitivity of 86.8%, and specificity of 86.7%. The machine learning-based risk model performed better than the logistic regression model in DeLong's test (p = 0.036). Furthermore, in a prospective dataset, the machine learning-based risk model had an AUC of 0.8758, a sensitivity of 94.4%, and a specificity of 73.8%. Conclusions:The machine learning-based risk model was constructed to predict EAOC and had high sensitivity and specificity. This model could be of considerable use in helping reduce medical costs and designing follow-up schedules.

show abstract

Section: Discussionmentioning

confidence: 99%

The application of risk models based on machine learning to predict endometriosis‐associated ovarian cancer in patients with endometriosis

Chao

Wang

Lang

et al. 2022

Acta Obstet Gynecol Scand

View full text Add to dashboard Cite

show abstract

“…Furthermore, the availability of more massive and representative data of the PD patients will allow the use of additional modelling algorithms. Deep learning methods as conventional neural network would likely being suitable to extract potential features from the T1 and R2* maps [37]. The second is the definition of acceptable margins errors for the estimated values according to the considered clinical application.…”

Section: Discussionmentioning

confidence: 99%

Can Dopamine Responsiveness Be Predicted in Parkinson’s Disease Without an Acute Administration Test?

Betrouni

Moreau

Rolland

et al. 2022

Journal of Parkinson’s Disease

View full text Add to dashboard Cite

Background: Dopamine responsiveness (dopa-sensitivity) is an important parameter in the management of patients with Parkinson’s disease (PD). For quantification of this parameter, patients undergo a challenge test with acute Levodopa administration after drug withdrawal, which may lead to patient discomfort and use of significant resources. Objective: Our objective was to develop a predictive model combining clinical scores and imaging. Methods: 350 patients, recruited by 13 specialist French centers and considered for deep brain stimulation, underwent an acute L-dopa challenge (dopa-sensitivity > 30%), full assessment, and MRI investigations, including T1w and R2* images. Data were randomly divided into a learning base from 10 centers and data from the remaining centers for testing. A machine selection approach was applied to choose the optimal variables and these were then used in regression modeling. Complexity of the modelling was incremental, while the first model considered only clinical variables, the subsequent included imaging features. The performances were evaluated by comparing the estimated values and actual values Results: Whatever the model, the variables age, sex, disease duration, and motor scores were selected as contributors. The first model used them and the coefficients of determination (R2) was 0.60 for the testing set and 0.69 in the learning set (p < 0.001). The models that added imaging features enhanced the performances: with T1w (R2 = 0.65 and 0.76, p < 0.001) and with R2* (R2 = 0.60 and 0.72, p < 0.001). Conclusion: These results suggest that modeling is potentially a simple way to estimate dopa-sensitivity, but requires confirmation in a larger population, including patients with dopa-sensitivity < 30%

show abstract

“…Despite that, if someone wants to deploy imaging for early diagnosis, then it is necessitated to build some machine learning models (e.g., Deep learning methods such as Convolution Neural Networks etc.) for analyzing the whole brain regions that can be used for early diagnosis and predict the disease condition better than the existing models [12].…”

Section: Brain Imagingmentioning

confidence: 99%

Early Diagnosis of Parkinson’s Disease: Utility of Animal Models

Neha¹,

Ahmad²,

Kumari³

et al. 2023

Parkinson’s Disease - Animal Models, Current Therapies and Clinical Trials

View full text Add to dashboard Cite

The effectiveness of the treatment strategies for Parkinson’s disease (PD) is highly dependent on the time of therapeutic intervention. This makes early diagnosis of PD an essential factor for its treatment; however, the complexities of the symptoms make it difficult to diagnose at an early stage. Moreover, by the time the symptoms start to appear, the disease has already been propagated in the patients. Even for the researchers, it is difficult to understand the important early diagnostic biomarkers due to the unavailability of the patients at the early stage, that is, before the manifestation of visible symptoms. The solution to this problem appears to develop animal models and monitor them from the early days to discover the diagnostic biomarkers. In this chapter, we shall discuss the use of animal models in the research intended to discover early diagnostic biomarkers for PD and why it is important to use animal models.

show abstract

Mining imaging and clinical data with machine learning approaches for the diagnosis and early detection of Parkinson’s disease

Cited by 45 publications

References 104 publications

The application of risk models based on machine learning to predict endometriosis‐associated ovarian cancer in patients with endometriosis

The application of risk models based on machine learning to predict endometriosis‐associated ovarian cancer in patients with endometriosis

Can Dopamine Responsiveness Be Predicted in Parkinson’s Disease Without an Acute Administration Test?

Early Diagnosis of Parkinson’s Disease: Utility of Animal Models

Contact Info

Product

Resources

About