Accurate Prediction of Advanced Liver Fibrosis Using the Decision Tree Learning Algorithm in Chronic Hepatitis C Egyptian Patients

Hashem, Somaya; Esmat, Gamal; Elakel, Wafaa; Habashy, Shahira M.; Raouf, Safaa Abdel; Darweesh, Samar K; Soliman, Mohamad; ElHefnawi, Mahmoud; Eladawy, Mohamed; ElHefnawi, Mahmoud

doi:10.1155/2016/2636390

Cited by 30 publications

(15 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The severity of hepatic fibrosis was associated with elevated serum AFP level in accordance with other studies (17,18). PLT and serum albumin level were also found to be independent predictors of fibrosis (17,39), however, multivariate analysis in our study revealed only age and PLT as the independent predictors of advanced fibrosis.…”

Section: Discussioncontrasting

confidence: 65%

See 1 more Smart Citation

Data Mining and Machine Learning Algorithms Using <i>IL28B</i> Genotype and Biochemical Markers Best Predicted Advanced Liver Fibrosis in Chronic Hepatitis C

et al. 2018

View full text Add to dashboard Cite

Section: Discussioncontrasting

confidence: 65%

“…An alternative way to build a decision tree is to grow a large tree, and then prune it by removing the nodes that provide less additional information. Pruning enhances tree comprehensibility while maintaining (or rather improving) its accuracy and should be performed in a bottom-up fashion (47,48 (39).…”

Section: Discussionmentioning

confidence: 99%

Data Mining and Machine Learning Algorithms Using <i>IL28B</i> Genotype and Biochemical Markers Best Predicted Advanced Liver Fibrosis in Chronic Hepatitis C

et al. 2018

View full text Add to dashboard Cite

“…Furthermore, these data are stored in large sets on powerful computers owned by the companies we deal with every day that they understand our mind for purchase. The same goes for physicians and researchers who understand each disease behavior [24][25][26][27][28][29][30][31] .…”

Section: Discussionmentioning

confidence: 99%

Ongoing transmission of HCV: Should cesarean section be justified? Data mining discovery

Elrazek

Saab

Foad

et al. 2017

Journal of Translational Internal Medicine

View full text Add to dashboard Cite

Background and Objectives:Over the past few decades, cesarean section (CS) rates are steadily increasing in most of the middle-and high-income countries. However, most of the pregnant women (particularly undergoing CS) are not screened for hepatitis C virus (HCV); hence, neonates born to HCV-positive mother could be a source of future HCV infection. In this study, the role of the CS and other surgical interventions in HCV transmission in Egypt, the highest endemic country of HCV-4, was investigated. Methods: From January to June 2016, a prospective cohort study was conducted among 3,836 pregnant women in both urban and rural areas across Egypt for HCV screening in both mothers and neonates born to HCV-positive mother. All pregnant women were screened during third trimester or just before delivery, neonates born to HCV-positive mothers were evaluated within 24-h postdelivery to record vertical transmission cases. Data mining (DM)-driven computational analysis was used to quantify the findings. Results: Among 3,836 randomized pregnant women, HCV genotype 4 was identified in 80 women (2.08%). Out of 80 HCV-infected women, 18 have experienced surgical intervention (22.5%) and 62 CS (77.5%). HCV vertical transmission was identified in 10 neonates, 10/80 (12.5%). Conclusion: Screening women who had experienced surgical intervention or CS during child bearing period and before pregnancy might prevent HCV mother-to-child transmission (MTCT). CS should be ethically justified to decrease global HCV transmission.

show abstract

“…We further addressed the issue of performance evaluation of decision tree classifiers, where we assessed the correctly classified instances, recall, precession, and area under the curve [14]. Hashem, et al used the decision tree learning algorithm to provide an accurate prediction of advanced Liver fibrosis in CHC [15].…”

Section: Related Workmentioning

confidence: 99%

Attribute Reduction and Decision Tree Pruning to Simplify Liver Fibrosis Prediction Algorithms A Cohort Study

Mabrouk¹,

Awad²,

Shousha³

et al. 2019

9th International Conference on Computer Science, Engineering and Applications (CCSEA 2019)

View full text Add to dashboard Cite

Background: Assessment of liver fibrosis is a vital need for enabling therapeutic decisions and prognostic evaluations of chronic hepatitis. Liver biopsy is considered the definitive investigation for assessing the stage of liver fibrosis but it carries several limitations. FIB-4 and APRI also have a limited accuracy. The National Committee for Control of Viral Hepatitis (NCCVH) in Egypt has supplied a valuable pool of electronic patients' data that data mining techniques can analyze to disclose hidden patterns, trends leading to the evolution of predictive algorithms. Aim: to collaborate with physicians to develop a novel reliable, easy to comprehend noninvasive model to predict the stage of liver fibrosis utilizing routine workup, without imposing extra costs for additional examinations especially in areas with limited resources like Egypt. Methods: This multi-centered retrospective study included baseline demographic, laboratory, and histopathological data of 69106 patients with chronic hepatitis C. We started by data collection preprocessing, cleansing and formatting for knowledge discovery of useful information from Electronic Health Records EHRs. Data mining has been used to build a decision tree (Reduced Error Pruning tree (REP tree)) with 10-fold internal cross-validation. Histopathology results were used to assess accuracy for fibrosis stages. Machine learning feature selection and reduction (CfsSubseteval / best first) reduced the initial number of input features (N=15) to the most relevant ones (N=6) for developing the prediction model. Results: In this study, 32419 patients had F(0-1), 25073 had F(2) and 11615 had F(3-4). FIB-4 and APRI revalidation in our study showed low accuracy and high discordance with biopsy results, with overall AUC 0.68 and 0.58 respectively. Out of 15 attributes machine learning selected Age, AFP, AST, glucose, albumin, and platelet as the most relevant attributes. Results for REP tree indicated an overall classification accuracy up to 70% and ROC Area 0.74 which was not nearly affected by attribute reduction, and pruning. However attribute reduction, and 316 Computer Science & Information Technology (CS & IT) tree pruning were associated with simpler model easy to understand by physician with less time for execution. Conclusion: This study we had the chance to study a large cohort of 69106 chronic hepatitis patients with available liver biopsy results to revise and validate the accuracy of FIB-4 and APRI. This study represents the collaboration between computer scientist and hepatologists to provide clinicians with an accurate novel and reliable, noninvasive model to predict the stage of liver fibrosis.

show abstract

Accurate Prediction of Advanced Liver Fibrosis Using the Decision Tree Learning Algorithm in Chronic Hepatitis C Egyptian Patients

Cited by 30 publications

References 18 publications

Data Mining and Machine Learning Algorithms Using <i>IL28B</i> Genotype and Biochemical Markers Best Predicted Advanced Liver Fibrosis in Chronic Hepatitis C

Data Mining and Machine Learning Algorithms Using <i>IL28B</i> Genotype and Biochemical Markers Best Predicted Advanced Liver Fibrosis in Chronic Hepatitis C

Ongoing transmission of HCV: Should cesarean section be justified? Data mining discovery

Attribute Reduction and Decision Tree Pruning to Simplify Liver Fibrosis Prediction Algorithms A Cohort Study

Contact Info

Product

Resources

About