Diagnosis of Alzheimer's disease using universum support vector machine based recursive feature elimination (USVM-RFE)

Richhariya, Bharat; Tanveer, M.; Rashid, Ashraf Haroon

doi:10.1016/j.bspc.2020.101903

Cited by 123 publications

(41 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sum normalized data were subjected to log transformation and auto-scaling was applied for each metabolite. A recursive feature elimination (RFE) method using logistic regression was applied to each pair-wise comparison (LRRK2 control vs. LRRK2 PD, sPD control vs. SPD, and LRRK2 PD vs. sPD) to find the most discriminative variables [20][21][22]. Feature selection using the RFE method and subsequent model training were performed using 60% of the data.…”

Section: Machine Learning-based Regression Analysismentioning

confidence: 99%

Metabolic Profiling of CSF from People Suffering from Sporadic and LRRK2 Parkinson’s Disease: A Pilot Study

Yılmaz

Ugur

Ustun

et al. 2020

Cells

View full text Add to dashboard Cite

CSF from unique groups of Parkinson’s disease (PD) patients was biochemically profiled to identify previously unreported metabolic pathways linked to PD pathogenesis, and novel biochemical biomarkers of the disease were characterized. Utilizing both 1H NMR and DI-LC-MS/MS we quantitatively profiled CSF from patients with sporadic PD (n = 20) and those who are genetically predisposed (LRRK2) to the disease (n = 20), and compared those results with age and gender-matched controls (n = 20). Further, we systematically evaluated the utility of several machine learning techniques for the diagnosis of PD. 1H NMR and mass spectrometry-based metabolomics, in combination with bioinformatic analyses, provided useful information highlighting previously unreported biochemical pathways and CSF-based biomarkers associated with both sporadic PD (sPD) and LRRK2 PD. Results of this metabolomics study further support our group’s previous findings identifying bile acid metabolism as one of the major aberrant biochemical pathways in PD patients. This study demonstrates that a combination of two complimentary techniques can provide a much more holistic view of the CSF metabolome, and by association, the brain metabolome. Future studies for the prediction of those at risk of developing PD should investigate the clinical utility of these CSF-based biomarkers in more accessible biomatrices. Further, it is essential that we determine whether the biochemical pathways highlighted here are recapitulated in the brains of PD patients with the aim of identifying potential therapeutic targets.

show abstract

Section: Machine Learning-based Regression Analysismentioning

confidence: 99%

Metabolic Profiling of CSF from People Suffering from Sporadic and LRRK2 Parkinson’s Disease: A Pilot Study

Yılmaz

Ugur

Ustun

et al. 2020

Cells

View full text Add to dashboard Cite

show abstract

“…The RFE algorithm has been widely used in medical diagnosis and mineral element mapping [76,77]. We try to use this method to process a large number of spectral data and spectral indexes and prove that the SOM prediction accuracy can be improved with RFE.…”

Section: Advantages Of Recursive Feature Eliminationmentioning

confidence: 99%

Soil Organic Matter Prediction Model with Satellite Hyperspectral Image Based on Optimized Denoising Method

Meng

Bao

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

In order to improve the signal-to-noise ratio of the hyperspectral sensors and exploit the potential of satellite hyperspectral data for predicting soil properties, we took MingShui County as the study area, which the study area is approximately 1481 km2, and we selected Gaofen-5 (GF-5) satellite hyperspectral image of the study area to explore an applicable and accurate denoising method that can effectively improve the prediction accuracy of soil organic matter (SOM) content. First, fractional-order derivative (FOD) processing is performed on the original reflectance (OR) to evaluate the optimal FOD. Second, singular value decomposition (SVD), Fourier transform (FT) and discrete wavelet transform (DWT) are used to denoise the OR and optimal FOD reflectance. Third, the spectral indexes of the reflectance under different denoising methods are extracted by optimal band combination algorithm, and the input variables of different denoising methods are selected by the recursive feature elimination (RFE) algorithm. Finally, the SOM content is predicted by a random forest prediction model. The results reveal that 0.6-order reflectance describes more useful details in satellite hyperspectral data. Five spectral indexes extracted from the reflectance under different denoising methods have a strong correlation with the SOM content, which is helpful for realizing high-accuracy SOM predictions. All three denoising methods can reduce the noise in hyperspectral data, and the accuracies of the different denoising methods are ranked DWT > FT > SVD, where 0.6-order-DWT has the highest accuracy (R2 = 0.84, RMSE = 3.36 g kg−1, and RPIQ = 1.71). This paper is relatively novel, in that GF-5 satellite hyperspectral data based on different denoising methods are used to predict SOM, and the results provide a highly robust and novel method for mapping the spatial distribution of SOM content at the regional scale.

show abstract

“…The algorithm calculates a rank score and eliminates the lowest-ranking features. Previous studies showed significant performance improvements by employing RFE, including predicting mental states (brain activity) [31,32], Parkinson [33], skin disease [34], autism [35], Alzheimer [36], and T2D [37]. They showed that SVM-RFE achieved superior performance than several comparison methods.…”

Section: Recursive Feature Eliminationmentioning

confidence: 99%

Deep Neural Network for Predicting Diabetic Retinopathy from Risk Factors

et al. 2020

View full text Add to dashboard Cite

Extracting information from individual risk factors provides an effective way to identify diabetes risk and associated complications, such as retinopathy, at an early stage. Deep learning and machine learning algorithms are being utilized to extract information from individual risk factors to improve early-stage diagnosis. This study proposes a deep neural network (DNN) combined with recursive feature elimination (RFE) to provide early prediction of diabetic retinopathy (DR) based on individual risk factors. The proposed model uses RFE to remove irrelevant features and DNN to classify the diseases. A publicly available dataset was utilized to predict DR during initial stages, for the proposed and several current best-practice models. The proposed model achieved 82.033% prediction accuracy, which was a significantly better performance than the current models. Thus, important risk factors for retinopathy can be successfully extracted using RFE. In addition, to evaluate the proposed prediction model robustness and generalization, we compared it with other machine learning models and datasets (nephropathy and hypertension–diabetes). The proposed prediction model will help improve early-stage retinopathy diagnosis based on individual risk factors.

show abstract

Diagnosis of Alzheimer's disease using universum support vector machine based recursive feature elimination (USVM-RFE)

Cited by 123 publications

References 47 publications

Metabolic Profiling of CSF from People Suffering from Sporadic and LRRK2 Parkinson’s Disease: A Pilot Study

Metabolic Profiling of CSF from People Suffering from Sporadic and LRRK2 Parkinson’s Disease: A Pilot Study

Soil Organic Matter Prediction Model with Satellite Hyperspectral Image Based on Optimized Denoising Method

Deep Neural Network for Predicting Diabetic Retinopathy from Risk Factors

Contact Info

Product

Resources

About