Data mining of routine laboratory tests can predict liver disease progression in Egyptian diabetic patients with hepatitis C virus (G4) infection: a cohort study of 71 806 patients

Saad, Yasmin; Awad, Abobakr; Alakel, Wafaa; Doss, Wahid; Awad, Tahany; Mabrouk, Mahasen

doi:10.1097/meg.0000000000001008

Cited by 7 publications

(5 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…J48 (C4.5) is the most widely used decision-tree algorithm, also known as a statistical classifier. J48 can handle both numerical and categorical data ( 32 ), is easy to implement, and deals with both noise and missing values ( 33 ). However, the performance of J48 is not good for a small data set ( 33 ).…”

Section: Discussionmentioning

confidence: 99%

Association of Gender, Diagnosis, and Obesity With Retention Rate of Secukinumab in Spondyloarthropathies: Results Form a Multicenter Real-World Study

García-Dorta

León-Suárez

Peña³

et al. 2022

Front. Med.

View full text Add to dashboard Cite

Background: Secukinumab has been shown effective for psoriatic arthritis (PsA) and axial spondylarthritis (AxSpA) in randomized trials. The aim of this study was to analyze baseline patient and disease characteristics associated with a better retention rate of secukinumab under real-world conditions.Patients and Methods: Real-life, prospective multicenter observational study involving 138 patients, 61 PsA and 77 AxSpA, who were analyzed at baseline, 6, 12 months and subsequently every year after starting secukinumab regardless of the line of treatment. Demographics and disease characteristics, measures of activity, secukinumab use, and adverse events were collected. Drug survival was analyzed using Kaplan-Meier curves and factors associated with discontinuation were evaluated using Cox regression. The machine-learning J48 decision tree classifier was also applied.Results: During the 1st year of treatment, 75% of patients persisted with secukinumab, but accrued 71% (n = 32) in total losses (n = 45). The backward stepwise (Wald) method selected diagnosis, obesity, and gender as relevant variables, the latter when analyzing the interactions. At 1 year of follow-up, the Cox model showed the best retention rate in the groups of AxSpa women (95%, 95% CI 93–97%) and PsA men (89%, 95% CI 84–93%), with the worst retention in PsA women (66%, 95% CI 54–79%). The J48 predicted secukinumab retention with an accuracy of 77.2%. No unexpected safety issues were observed.Conclusions: Secukinumab shows the best retention rate at 1 year of treatment in AxSpA women and in PsA men, independently of factors such as the time of disease evolution, the line of treatment or the initial dose of the drug.

show abstract

Section: Discussionmentioning

confidence: 99%

Association of Gender, Diagnosis, and Obesity With Retention Rate of Secukinumab in Spondyloarthropathies: Results Form a Multicenter Real-World Study

García-Dorta

León-Suárez

Peña³

et al. 2022

Front. Med.

View full text Add to dashboard Cite

show abstract

“…J48 Algorithm J48 (C4.5) is the most commonly used decision trees algorithm and is an extension of Quinlan's earlier ID3 Algorithm that is known to have a reasonable accuracy rate in bio-medical applications [4]. It has the capability to handle both numerical and categorical data [17]. It is also named as statistical classi er [18].…”

Section: Multiclass/ Multinomial Classi Cationmentioning

confidence: 99%

Chronic Kidney Disease Diagnosis using Decision Tree Algorithms

Ilyas

Ali

Ponum

et al. 2020

Preprint

View full text Add to dashboard Cite

Chronic Kidney Disease (CKD), i.e., gradual decrease in the renal function spanning over a duration of several months to years without any major symptoms, is a life-threatening disease. It progresses in six stages according to the severity level. It is categorized into various stages based on the Glomerular Filtration Rate (GFR), which in turn utilizes several attributes, like age, sex, race and Serum Creatinine. Among multiple available models for estimating GFR value, Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI), which is a linear model, has been found to be quite efficient because it allows detecting all CKD stages i.e., early stage to the last stage of kidney failure. Early detection and cure of CKD is extremely desirable as it can lead to the prevention of unwanted consequences. Machine learning are being extensively advocated for early detection of symptoms and diagnosis of several diseases recently. With the same motivation, the aim of this study is to predict the various stages of CKD using machine learning classification algorithms on the dataset obtained from the medical records of affected people. In particular, we have used the Random Forest and J48 algorithms to obtain a sustainable and practicable model to detect various stages of CKD with comprehensive medical accuracy. Comparative analysis of the results revealed that J48 predicted CKD in all stages better than random forest with a 85.5% accuracy. The study also showed that J48 shows improved performance over Random Forest, so, it may be used to build an automated system for the detection of severity of CKD.

show abstract

“…J48 (C4.5) is the most commonly used decision tree algorithm that is an extension of Quinlan’s earlier ID3 Algorithm - known to have a reasonable accuracy rate in bio-medical applications [ 12 , 13 ]. It has the capability to handle both numerical and categorical data [ 14 ]. It is also named as statistical classifier [ 15 ].…”

Section: Methodsmentioning

confidence: 99%

Chronic kidney disease diagnosis using decision tree algorithms

et al. 2021

View full text Add to dashboard Cite

Background Chronic Kidney Disease (CKD), i.e., gradual decrease in the renal function spanning over a duration of several months to years without any major symptoms, is a life-threatening disease. It progresses in six stages according to the severity level. It is categorized into various stages based on the Glomerular Filtration Rate (GFR), which in turn utilizes several attributes, like age, sex, race and Serum Creatinine. Among multiple available models for estimating GFR value, Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI), which is a linear model, has been found to be quite efficient because it allows detecting all CKD stages. Methods Early detection and cure of CKD is extremely desirable as it can lead to the prevention of unwanted consequences. Machine learning methods are being extensively advocated for early detection of symptoms and diagnosis of several diseases recently. With the same motivation, the aim of this study is to predict the various stages of CKD using machine learning classification algorithms on the dataset obtained from the medical records of affected people. Specifically, we have used the Random Forest and J48 algorithms to obtain a sustainable and practicable model to detect various stages of CKD with comprehensive medical accuracy. Results Comparative analysis of the results revealed that J48 predicted CKD in all stages better than random forest with an accuracy of 85.5%. The study also showed that J48 shows improved performance over Random Forest. Conclusions The study concluded that it may be used to build an automated system for the detection of severity of CKD.

show abstract

Data mining of routine laboratory tests can predict liver disease progression in Egyptian diabetic patients with hepatitis C virus (G4) infection: a cohort study of 71 806 patients

Cited by 7 publications

References 47 publications

Association of Gender, Diagnosis, and Obesity With Retention Rate of Secukinumab in Spondyloarthropathies: Results Form a Multicenter Real-World Study

Association of Gender, Diagnosis, and Obesity With Retention Rate of Secukinumab in Spondyloarthropathies: Results Form a Multicenter Real-World Study

Chronic Kidney Disease Diagnosis using Decision Tree Algorithms

Chronic kidney disease diagnosis using decision tree algorithms

Contact Info

Product

Resources

About