scholarly journals Current and Next Visit Prediction for Fatty Liver Disease with a Large-Scale Dataset (Preprint)

2020 ◽  
Author(s):  
ChengTse Wu ◽  
Ta-Wei Chu ◽  
Jyh-Shing Roger Jang
Keyword(s):  
Feature Selection ◽  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Large Scale ◽  
Prediction Models ◽  
Short Term Memory ◽  
Support Vector ◽  
Test Accuracy ◽  
Forward Selection

BACKGROUND Fatty liver disease (FLD) arises from the accumulation of fat in the liver and may cause liver inflammation which, according to past research it is shown that if not actively well-controlled, may develop into liver fibrosis, cirrhosis, or even hepatocellular carcinoma in the future. OBJECTIVE We describe the construction of machine-learning models for current-visit prediction (CVP) which can help physicians obtain more information for accurate diagnosis, and next-visit prediction (NVP) which can help physicians deal provide potential high-risk patients with advice to effectively prevent or delay health deterioration. METHODS The large-scale and high-dimensional dataset used in this study comes from the MJ Health Research Foundation in Taipei. The models we created use sequence forward selection (SFS) and one-pass ranking (OPR) for feature selection. For current-visit prediction (CVP), we explored multiple models including Adaboost, support vector machine (SVM), logistic regression (LR), random forest (RF), Gaussian Naïve Bayes (GNB), decision trees C4.5 (C4.5), and classification & regression trees (CART). For next-visit prediction (NVP), we used long short-term memory (LSTM) as a sequence classifier that uses various input sets for prediction. Model performance is evaluated based on two criteria: the accuracy of the test set, and the IoU and coverage between the features selected by OPR/SFS and by domain experts. RESULTS The dataset respectively includes 34,856 and 31,394 unique visits by male and female patients during 2009∼2016. The test accuracy results of CVP for Adaboost, SVM, LR, RF, GNB, C4.5, and CART were respectively 84.28, 83.84, 82.22, 82.21, 76.03, 75.78, and 75.53%. The test accuracy results of NVP of LSTM with fixed and variable intervals were respectively 78.20% and 76.79%. The proposed two paradigms of LSTM respectively achieved 39.29% and 41.21% error reduction when compared with a baseline model of simple induction. CONCLUSIONS This study explores a large fatty liver disease (FLD) dataset with high dimensionality. We have developed prediction models that can use for CVP and NVP for FLD prediction. We have also implemented efficient feature selection schemes for CVP and NVP to compare the automatically selected features with expert-selected features.

scholarly journals Predicting and elucidating the etiology of fatty liver disease using a machine learning-based approach: an IMI DIRECT study

2020 ◽  
Author(s):  
Naeimeh Atabaki-Pasdar ◽  
Mattias Ohlsson ◽  
Ana Viñuela ◽  
Francesca Frau ◽  
Hugo Pomares-Millan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Prediction Models ◽  
Cell Function ◽  
Area Under The Curve ◽  
Liver Fat ◽  
Irreversible Damage ◽  
Alcoholic Fatty Liver

ABSTRACTBackgroundNon-alcoholic fatty liver disease (NAFLD) is highly prevalent and causes serious health complications in type 2 diabetes (T2D) and beyond. Early diagnosis of NAFLD is important, as this can help prevent irreversible damage to the liver and ultimately hepatocellular carcinomas.Methods and FindingsUtilizing the baseline data from the IMI DIRECT participants (n=1514) we sought to expand etiological understanding and develop a diagnostic tool for NAFLD using machine learning. Multi-omic (genetic, transcriptomic, proteomic, and metabolomic) and clinical (liver enzymes and other serological biomarkers, anthropometry, and measures of beta-cell function, insulin sensitivity, and lifestyle) data comprised the key input variables. The models were trained on MRI image-derived liver fat content (<5% or ≥5%). We applied LASSO (least absolute shrinkage and selection operator) to select features from the different layers of omics data and Random Forest analysis to develop the models. The prediction models included clinical and omics variables separately or in combination. A model including all omics and clinical variables yielded a cross-validated receiver operator characteristic area under the curve (ROCAUC) of 0.84 (95% confidence interval (CI)=0.82, 0.86), which compared with a ROCAUC of 0.82 (95% CI=0.81, 0.83) for a model including nine clinically-accessible variables. The IMI DIRECT prediction models out-performed existing non-invasive NAFLD prediction tools.ConclusionsWe have developed clinically useful liver fat prediction models (see: www.predictliverfat.org) and identified biological features that appear to affect liver fat accumulation.

Serum SHBG Is Associated With the Development and Regression of Nonalcoholic Fatty Liver Disease: A Prospective Study

2019 ◽  
Vol 105 (3) ◽  
pp. e791-e804
Author(s):  
Xu Wang ◽  
Jiewen Xie ◽  
Juan Pang ◽  
Hanyue Zhang ◽  
Xu Chen ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Liver Disease ◽  
Fatty Liver ◽  
Nonalcoholic Fatty Liver Disease ◽  
Fatty Liver Disease ◽  
Prediction Models ◽  
Stepwise Logistic Regression ◽  
Stepwise Logistic Regression Analysis ◽  
Nonalcoholic Fatty Liver ◽  
Potential Biomarker

Abstract Context SHBG, a homodimeric glycoprotein produced by hepatocytes has been shown to be associated with metabolic disorders. Whether circulating SHBG levels are predictive of later risk of nonalcoholic fatty liver disease (NAFLD) remains unknown. In this study, we prospectively investigated the association between SHBG and NAFLD progression through a community-based cohort comprising 3389 Chinese adults. Methods NAFLD was diagnosed using abdominal ultrasonography. Serum SHBG levels were measured by chemiluminescent enzyme immunometric assay, and their relationship with NAFLD development and regression was investigated after a mean follow-up of 3.09 years using multivariable logistic regression. Results Basal SHBG was negatively associated with NAFLD development, with a fully adjusted odds ratio (OR) and its 95% confidence interval (CI) of 0.22 (0.12-0.40) (P &lt; .001). In contrast, basal SHBG was positively associated with NAFLD regression, with a fully adjusted OR of 4.83 (2.38-9.81) (P &lt; .001). Multiple-stepwise logistic regression analysis showed that SHBG concentration was an independent predictor of NAFLD development (OR, 0.28 [0.18-0.45]; P &lt; .001) and regression (OR, 3.89 [2.43-6.22]; P &lt; .001). In addition, the area under the receiver operating characteristic curves were 0.764 (95% CI, 0.740-0.787) and 0.762 (95% CI, 0.738-0.785) for the prediction models of NAFLD development and regression, respectively. Conclusions Serum SHBG concentration is associated with the development and regression of NAFLD; moreover, it can be a potential biomarker for predicting NAFLD progression, and also a novel preventive and therapeutic target for NAFLD.

scholarly journals Inverse Association between Hepatitis B Virus Infection and Fatty Liver Disease: A Large-Scale Study in Populations Seeking for Check-Up

PLoS ONE ◽  
2013 ◽  
Vol 8 (8) ◽  
pp. e72049 ◽  
Author(s):  
Yuan-Lung Cheng ◽  
Yuan-Jen Wang ◽  
Wei-Yu Kao ◽  
Ping-Hsien Chen ◽  
Teh-Ia Huo ◽  
...  
Keyword(s):  
Liver Disease ◽  
Hepatitis B Virus ◽  
Virus Infection ◽  
Hepatitis B ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Large Scale ◽  
Inverse Association ◽  
Hepatitis B Virus Infection ◽  
B Virus

scholarly journals External validation of non-invasive prediction models for identifying ultrasonography-diagnosed fatty liver disease in a Chinese population

Medicine ◽  
2017 ◽  
Vol 96 (30) ◽  
pp. e7610 ◽  
Author(s):  
Ya-Nan Shen ◽  
Ming-Xing Yu ◽  
Qian Gao ◽  
Yan-Yan Li ◽  
Jian-Jun Huang ◽  
...  
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Chinese Population ◽  
Prediction Models ◽  
External Validation ◽  
Non Invasive

scholarly journals Pediatric Fatty Liver and Obesity: Not Always Justa Matter of Non-Alcoholic Fatty Liver Disease

Children ◽  
2018 ◽  
Vol 5 (12) ◽  
pp. 169
Author(s):  
Renata Alfani ◽  
Edoardo Vassallo ◽  
Anna De Anseris ◽  
Lucia Nazzaro ◽  
Ida D'Acunzo ◽  
...  
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Large Scale ◽  
Correct Diagnosis ◽  
Diagnostic Algorithm ◽  
Liver Imaging ◽  
Dietary Counseling ◽  
Alcoholic Fatty Liver ◽  
Alcoholic Fatty Liver Disease

Obesity-related non-alcoholic fatty liver disease (NAFLD) represents the most common cause of pediatric liver disease due to overweight/obesity large-scale epidemics. In clinical practice, diagnosis is usually based on clinical features, blood tests, and liver imaging. Here, we underline the need to make a correct differential diagnosis for a number of genetic, metabolic, gastrointestinal, nutritional, endocrine, muscular, and systemic disorders, and for iatrogenic/viral/autoimmune hepatitis as well. This is all the more important for patients who are not in the NAFLD classical age range and for those for whom a satisfactory response of liver test abnormalities to weight loss after dietary counseling and physical activity measures cannot be obtained or verified due to poor compliance. A correct diagnosis may be life-saving, as some of these conditions which appear similar to NAFLD have a specific therapy. In this study, the characteristics of the main conditions which require consideration are summarized, and a practical diagnostic algorithm is discussed.

scholarly journals External Validation and Clinical Utility of Non-Invasive Prediction Models for Non-Alcoholic Fatty Liver Disease in Malaysia

2020 ◽  
Author(s):  
Mohd Azri Mohd Suan ◽  
Huan Keat Chan ◽  
Shahrul Aiman Soelar ◽  
Muhammad Radzi Abu Hassan
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Prediction Models ◽  
Predictive Performance ◽  
Public Healthcare ◽  
Discriminative Performance ◽  
Alcoholic Fatty Liver ◽  
Liver Elastography ◽  
Alcoholic Fatty Liver Disease

Abstract Background: Many prediction models have been developed to detect non-alcoholic fatty liver disease (NAFLD). The drawbacks of many of models are the use of parameters that are not routinely measured locally. This study aimed to evaluate the external validity of a series of prediction models for NAFLD, which were selected based on the routinely measured and tested clinical parameters in public healthcare centers in Malaysia. Methods: A literature search of articles that described the prediction models for NAFLD on adult subjects between 2000 and 2019 was conducted. The validation cohort comprised patients who underwent liver elastography using the Fibroscan® device in a public tertiary care center between January 2017 and December 2019. Both the discrimination and calibration of each model were assessed to determine their predictive performance. Results: Out of the 404 patients undergoing liver elastography, 280 were diagnosed with NAFLD (69.3%). Six prediction models were identified from the existing literature and evaluated. The calibration assessment demonstrated that although three of the models overestimated the NAFLD risk, updating the models generally improved their calibration performance. The discriminative performance of the selected models ranged from 0.717 to 0.783. With a specificity level of 90% and 80%, the sensitivity of all the models fell between 31.1%–48.9% and 46.4%–66.8%, respectively. The Framingham Steatosis Index (FSI) model demonstrated a better predictive performance compared to the other models. Conclusions: The FSI model demonstrates an acceptable predictive performance. Its application in clinical practice could promote the screening and early treatment of NAFLD in the Malaysian population.

scholarly journals Dynamics of Serum Retinol and Alpha-Tocopherol Levels According to Non-Alcoholic Fatty Liver Disease Status

Nutrients ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 1720
Author(s):  
Dongsub Jeon ◽  
Minkook Son ◽  
Juhyun Shim
Keyword(s):  
Liver Disease ◽  
Fatty Liver ◽  
Fatty Liver Disease ◽  
Prediction Models ◽  
Serum Levels ◽  
Alpha Tocopherol ◽  
Advanced Fibrosis ◽  
Serum Retinol ◽  
Alcoholic Fatty Liver ◽  
Alcoholic Fatty Liver Disease

The available data on the association between micronutrients in the blood and non-alcoholic fatty liver disease (NAFLD) are limited. To investigate the clinical implications of this relationship, we sought to identify the difference in the serum levels of vitamins A and E according to NAFLD status using data from the seventh Korea National Health and Nutrition Examination Survey. In this cross-sectional study of the Korean population, NAFLD and its severity were defined using prediction models. Differences in the prevalence and severity of NAFLD were analyzed according to serum retinol (vitamin A) and alpha (α)-tocopherol (vitamin E) levels. Serum levels of retinol and α-tocopherol were positively correlated with the prevalence of NAFLD. In most prediction models of the NAFLD subjects, serum retinol deficiency was significantly correlated with advanced fibrosis, while serum α-tocopherol levels did not differ between individuals with or without advanced fibrosis. Similar trends were also noted with cholesterol-adjusted levels of α-tocopherol. In summary, while circulating concentrations of retinol and α-tocopherol were positively associated with the presence of NAFLD, advanced liver fibrosis was only correlated with serum retinol levels. Our findings could provide insight into NAFLD patient care at a micronutrient level.

Sign in / Sign up

Export Citation Format

Share Document