Blended Ensemble Learning Prediction Model for Strengthening Diagnosis and Treatment of Chronic Diabetes Disease

Mahesh, T R; Kumar, Dhilip; Kumar, V. Vinoth; Asghar, Junaid; Bazezew, Mekecha Banchigize; Natarajan, Rajesh; Vivek, V.

doi:10.1155/2022/4451792

Cited by 36 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RNNs, unlike regular NNs, may analyze data objects where actually, the activation at each step is dependent on the previous step. CNN relies on "discrete convolution" since it makes use of spatial data [8] among picture pixels. As a result, it is assumed that the image is grayscale.…”

Section: Related Workmentioning

confidence: 99%

Performance Analysis of XGBoost Ensemble Methods for Survivability with the Classification of Breast Cancer

et al. 2022

Self Cite

View full text Add to dashboard Cite

Breast cancer (BC) disease is the most common and rapidly spreading disease across the globe. This disease can be prevented if identified early, and this eventually reduces the death rate. Machine learning (ML) is the most frequently utilized technology in research. Cancer patients can benefit from early detection and diagnosis. Using machine learning approaches, this research proposes an improved way of detecting breast cancer. To deal with the problem of imbalanced data in the class and noise, the Synthetic Minority Oversampling Technique (SMOTE) has been used. There are two steps in the suggested task. In the first phase, SMOTE is utilized to decrease the influence of imbalance data issues, and subsequently, in the next phase, data is classified using the Naive Bayes classifier, decision trees classifier, Random Forest, and their ensembles. According to the experimental analysis, the XGBoost-Random Forest ensemble classifier outperforms with 98.20% accuracy in the early detection of breast cancer.

show abstract

Section: Related Workmentioning

confidence: 99%

Performance Analysis of XGBoost Ensemble Methods for Survivability with the Classification of Breast Cancer

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…An effective DWT-SVD is deployed with selfadaptive differential evolution (SDE) algorithm for image watermarking scheme, SDE adjusts the mutation factor F and the crossover rate Cr dynamically in order to balance an individual's exploration and exploitation capability for different evolving phases to achieve invisibility [18][19][20]. In [21][22][23][24], comparative analysis of image compression is done by three transform methods, which are Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Hybrid (DCT + DWT) Transform, thereby achieving better invisibility property and good PSNR ratio.…”

Section: Related Workmentioning

confidence: 99%

Efficient Hybrid Blind Watermarking in DWT‐DCT‐SVD with Dual Biometric Features for Images

Mokashi

Bhat

Pujari

et al. 2022

Contrast Media & Molecular Imaging

Self Cite

View full text Add to dashboard Cite

In the modern era of virtual computers over the notional environment of computer networks, the protection of influential documents is a major concern. To bring out this motto, digital watermarking with biometric features plays a crucial part. It utilizes advanced technology of cuffing data into digital media, i.e., text, image, video, or audio files. The strategy of cuffing an image inside another image by applying biometric features namely signature and fingerprint using watermarking techniques is the key purpose of this study. To accomplish this, a combined watermarking strategy consisting of Discrete Wavelet Transform, Discrete Cosine Transform, and Singular Value Decomposition (DWT-DCT-SVD) is projected for authentication of image that is foolproof against attacks. Here, singular values of watermark1 (fingerprint) and watermark2 (signature) are obtained by applying DWT-DCT-SVD. Affixing both the singular values of watermarks, we acquire the transformed watermark. Later, the same is applied to cover image to extract the singular values. Then we add these values to the cover image and transformed watermark to obtain a final watermarked image containing both signature and fingerprint. To upgrade the reliability, sturdiness, and originality of the image, a fusion of watermarking techniques along with dual biometric features is exhibited. The experimental results conveyed that the proposed scheme achieved an average PSNR value of about 40 dB, an average SSIM value of 0.99, and an embedded watermark resilient to various attacks in the watermarked image.

show abstract

“…Thus, leveraging machine learning for T2DM screening has emerged as a notable approach in auxiliary diagnostics, enhancing both the accuracy and efficiency of diagnoses. Currently, machine learning models such as the random forest (RF) ( 8 – 10 ), support vector machine (SVM) ( 8 , 11 ), logistic regression (LR) ( 11 – 13 ), and eXtreme gradient boosting (XGBoost) ( 9 , 14 ) have been developed for constructing accurate system of T2DM prediction. Some studies have also employed machine learning techniques to identify indicators associated with T2DM, such as the white blood cell (WBC) ( 15 ), urinary and dietary metal exposure ( 16 ) and serum calcium ( 17 ).…”

Section: Introductionmentioning

confidence: 99%

Identifying diagnostic indicators for type 2 diabetes mellitus from physical examination using interpretable machine learning approach

Lv,

Luo,

Huang

et al. 2024

Front. Endocrinol.

View full text Add to dashboard Cite

BackgroundIdentification of patients at risk for type 2 diabetes mellitus (T2DM) can not only prevent complications and reduce suffering but also ease the health care burden. While routine physical examination can provide useful information for diagnosis, manual exploration of routine physical examination records is not feasible due to the high prevalence of T2DM.ObjectivesWe aim to build interpretable machine learning models for T2DM diagnosis and uncover important diagnostic indicators from physical examination, including age- and sex-related indicators.MethodsIn this study, we present three weighted diversity density (WDD)-based algorithms for T2DM screening that use physical examination indicators, the algorithms are highly transparent and interpretable, two of which are missing value tolerant algorithms.PatientsRegarding the dataset, we collected 43 physical examination indicator data from 11,071 cases of T2DM patients and 126,622 healthy controls at the Affiliated Hospital of Southwest Medical University. After data processing, we used a data matrix containing 16004 EHRs and 43 clinical indicators for modelling.ResultsThe indicators were ranked according to their model weights, and the top 25% of indicators were found to be directly or indirectly related to T2DM. We further investigated the clinical characteristics of different age and sex groups, and found that the algorithms can detect relevant indicators specific to these groups. The algorithms performed well in T2DM screening, with the highest area under the receiver operating characteristic curve (AUC) reaching 0.9185.ConclusionThis work utilized the interpretable WDD-based algorithms to construct T2DM diagnostic models based on physical examination indicators. By modeling data grouped by age and sex, we identified several predictive markers related to age and sex, uncovering characteristic differences among various groups of T2DM patients.

show abstract

Blended Ensemble Learning Prediction Model for Strengthening Diagnosis and Treatment of Chronic Diabetes Disease

Cited by 36 publications

References 18 publications

Performance Analysis of XGBoost Ensemble Methods for Survivability with the Classification of Breast Cancer

Performance Analysis of XGBoost Ensemble Methods for Survivability with the Classification of Breast Cancer

Efficient Hybrid Blind Watermarking in DWT‐DCT‐SVD with Dual Biometric Features for Images

Identifying diagnostic indicators for type 2 diabetes mellitus from physical examination using interpretable machine learning approach

Contact Info

Product

Resources

About