Fatty Liver Disease Prediction Based on Multi-Layer Random Forest Model

Heart disease is one amongst the key causes of death now-a-days. Prediction of the center sickness is troublesome, time overwhelming and expensive, therefore we tend to try to beat it. This analysis is to assist individuals, as we all know prediction of upset may be a vital challenge and it’s expensive that most of the individuals can’t afford and lacking behind due to these, therefore to assist them for obtaining done this tests in low value, we tend to try to develop cardiovascular disease prediction system victimization machine learning. As there square measure several systems designed for machine-controlled coronary failure testing however it's some drawbacks like over fitting that we tend to try to beat in our system and implementing system which is able to show smart performance and have high accuracy as compared to alternative systems. Experiment is performed victimization on-line clinical coronary failure dataset. The projected methodology is a smaller amount complicated with high accuracy of report. They contributes towards study square measure as follows: one. AN intelligent learning system RSA-RF is projected for the machine-controlled detection of coronary failure. The projected RSA-RF model was projected and developed for the primary time for the center failure detection. Previously, RSA algorithms have shown winning applications in looking best hyper parameters of a model. This paper presents its application in looking best set of options. 2. The developed learning system improves coronary failure prediction of typical random forest model by three.3% and shows higher performance than eleven recently projected strategies and alternative state of the art machine learning models for coronary failure detection. Moreover, the projected methodology shows lower time complexness because it reduces the amount of options[1].

Download Full-text

Diagnostic Value of Magnetic Resonance Elastography Radiomics Analysis for the Assessment of Hepatic Fibrosis in Patients With Nonalcoholic Fatty Liver Disease

10.21203/rs.3.rs-798827/v1 ◽

2021 ◽

Author(s):

Ki Choon Sim ◽

Min Ju Kim ◽

Yongwon Cho ◽

Hyun Jin Kim ◽

Beom Jin Park ◽

...

Keyword(s):

Liver Disease ◽

Magnetic Resonance ◽

Random Forest ◽

Fatty Liver ◽

Hepatic Fibrosis ◽

Fatty Liver Disease ◽

Diagnostic Performance ◽

Fibrosis Stage ◽

Nonalcoholic Fatty Liver ◽

Clinically Significant

Abstract Background: To investigate the diagnostic performance of radiomics analysis using magnetic resonance elastography (MRE) toward assessing hepatic fibrosis in patients with nonalcoholic fatty liver disease (NAFLD). Methods: A total of 100 patients with suspected NAFLD were retrospectively enrolled. All patients underwent a liver parenchymal biopsy. MRE was performed using a 3.0-T scanner. Following three-dimensional (3D) segmentation of MRE images, 834 radiomic features were analyzed using a commercial program. Radiologic features, such as median and mean values of two-dimensional (2D) or 3D regions of interest (ROIs) and variable clinical features, were analyzed. A random forest regressor was employed to extract important radiomic, radiological, and clinical features. A random forest classifier model was trained to use these features to classify the fibrosis stage. The area under the receiver operating characteristic curve (AUC) was evaluated using a classifier for fibrosis stage diagnosis. Results: The pathological hepatic fibrosis stage was classified as low-grade fibrosis (stages F0–F1, n = 82) or clinically significant fibrosis (stages F2–F4, n = 18). Eight important features were extracted from radiomics analysis, with the two most important being wavelet-HHL gray level dependence matrix (GLDM)-dependence non-uniformity-normalized and wavelet-HHL GLDM-dependence entropy. The median value of the 2D ROI was identified as the most important radiologic feature. Platelet count was identified as an important clinical feature. The AUC of the classifier using radiomics was comparable to that of radiologic measures (0.97 ± 0.07 vs. 0.96 ± 0.06). Conclusions: MRE radiomics analysis provides diagnostic performance comparable to conventional MRE analysis for the assessment of clinically significant hepatic fibrosis in patients with NAFLD.

Download Full-text

Fatty Liver Disease Prediction Using Supervised Learning

Communications in Computer and Information Science - Advanced Informatics for Computing Research ◽

10.1007/978-981-16-3660-8_54 ◽

2021 ◽

pp. 577-587

Author(s):

Vala Harshitha Rao ◽

Dheeraj Sundaragiri ◽

Prasanta Kumar Sahoo

Keyword(s):

Liver Disease ◽

Fatty Liver ◽

Supervised Learning ◽

Fatty Liver Disease ◽

Disease Prediction

Download Full-text

Nine Markers to Predict Nonalcoholic Fatty Liver Disease for a Chinese Diabetic Population

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2021.3343 ◽

2021 ◽

Vol 11 (3) ◽

pp. 730-735

Author(s):

Jiandun Li ◽

Dingyu Yang ◽

Ting Chen ◽

Tao Li ◽

Peng Jiang ◽

...

Keyword(s):

Liver Disease ◽

Random Forest ◽

Fatty Liver ◽

Nonalcoholic Fatty Liver Disease ◽

Fatty Liver Disease ◽

Low Density Lipoprotein ◽

Density Lipoprotein ◽

Diabetic Patients ◽

Nonalcoholic Fatty Liver ◽

Diabetic Population

Background: Nonalcoholic fatty liver disease (NAFLD) increases the possibility to suffer from liver or cardiovascular disease. Although hepatic biopsy is well acknowledged as the standard diagnosis, it is difficult to implement because of its intrusiveness and cost concerns. Moreover, overweight people or diabetic patients are always NAFLD-positive, but not absolute. Therefore, to distinguish whether a diabetic case has NAFLD via nonintrusive indicators is of great significance for further interventions. Objective: With 8499 diabetic patients hosted by Shanghai Sixth People’s Hospital, we try to rank the impacts of multiple routine indicators (features) on NAFLD, and further predict NAFLD within this diabetic population. Methods: We first rank dozens of related features according to their contributions in NAFLD prediction, and then we prune several trivial features to simplify the prediction. Additionally, three classification algorithms are considered and compared, e.g., C4.5, Naïve Bayes and Random Forest. Results: The experiment shows that Random Forest outperforms the rest (accuracy 85.1%, recall 90.98% and AUC 0.631). Conclusions: We find that the top nine markers together can effectively tell NAFLD out of this diabetic population. They are triglyceride (TG), low density lipoprotein (LDL), insulin (INS), hbA1C, high-density lipoprotein (HDL), fasting plasma glucose (FPG), age, total cholesterol (TC) and duration.

Download Full-text

Heart Disease Prediction Using Hybrid Random Forest Model Integrated with Linear Model

10.3233/apc210160 ◽

2021 ◽

Author(s):

Jaishri Pandhari Wankhede ◽

Palaniappan S ◽

Magesh Kumar S

Keyword(s):

Heart Disease ◽

Random Forest ◽

Linear Model ◽

Early Stage ◽

Estimation Procedure ◽

Prediction Performance ◽

Random Forest Model ◽

Disease Prediction ◽

Forest Model ◽

Simple Estimation

The objective of the paper is to throw light on few existing heart disease predicting approaches and proposes a Hybrid Random Forest Model Integrated with Linear Model (HRFMILM) for predicting and identifying the HDs at an early stage. Even though the linear model has simple estimation procedure, it is very sensitive to outliers and may lead to overfitting process. On the other hand, averaging in Random Forest Model (RFM) improves the overall accuracy and reduces the possibility of overfitting. The dataset is collected from standard UCI repository. Experimental results concluded that the integration of Linear Model with RFM makes the simple estimation procedure with improved overall accuracy than the respective models. Further, the proposed method compares the prediction performance of few existing approaches in terms of parameters, namely, precision, recall and F1-score.

Download Full-text