pith. sign in

arxiv: 2606.26561 · v1 · pith:S6HSQJGBnew · submitted 2026-06-25 · 💻 cs.AI · cs.LG

Explainable Ensemble-Based Machine Learning Models for Detecting the Presence of Cirrhosis in Hepatitis C Patients

Abrar Alotaibi , Lujain Alnajrani , Nawal Alsheikh , Alhatoon Alanazy , Salam Alshammasi , Meshael Almusairii , Shoog Alrassan , Aisha Alansari This is my paper

Pith reviewed 2026-06-26 05:17 UTC · model grok-4.3

classification 💻 cs.AI cs.LG
keywords machine learninghepatitis Ccirrhosis detectionextra treesensemble modelsmedical diagnosisdisease classificationfeature selection
0
0 comments X

The pith

An Extra Trees model detects cirrhosis in hepatitis C patients at 96.92 percent accuracy using 16 features.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper trains four ensemble machine learning models on data from 2038 Egyptian patients with hepatitis C to identify cirrhosis. The Extra Trees model reaches 96.92 percent accuracy, 94 percent recall, 99.81 percent precision, and 96 percent AUC while using only 16 of the original 28 patient attributes. This result matters because cirrhosis often develops silently over years and leads to liver failure or other severe issues, so an accurate detection tool could support earlier intervention. The study positions the model as a practical aid for diagnosis where symptoms are absent for decades.

Core claim

Four machine learning algorithms were trained on a dataset of 28 attributes from 2038 Egyptian patients with hepatitis C. The Extra Trees model achieved an accuracy of 96.92 percent, recall of 94.00 percent, precision of 99.81 percent, and area under the receiver operating characteristic curve of 96 percent using only 16 of the 28 features, outperforming Random Forest, Gradient Boosting Machine, and Extreme Gradient Boosting.

What carries the argument

The Extra Trees ensemble classifier, which constructs multiple decision trees on random subsets of features and data to classify patients as having cirrhosis or not based on the reduced 16-attribute input.

If this is right

  • Hepatitis C patients could be screened for cirrhosis risk using fewer laboratory tests since only 16 features suffice.
  • High precision reduces the chance of false positive diagnoses that might lead to unnecessary follow-up procedures.
  • The same modeling approach could be applied to track disease progression if additional time-series data were collected.
  • Early identification supports treatment focused on slowing liver damage before failure occurs.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The title mentions explainable models, so the feature importance outputs from Extra Trees could reveal which lab values most influence cirrhosis predictions for clinicians.
  • Performance may drop if applied to populations with different age distributions, viral genotypes, or comorbidities not captured in the Egyptian data.
  • Similar ensemble methods might be tested on datasets for other liver conditions such as fibrosis staging or hepatocellular carcinoma risk.

Load-bearing premise

The dataset of 2038 Egyptian patients represents the broader hepatitis C population and performance on internal data splits will hold for new patients in other clinical settings.

What would settle it

Running the trained Extra Trees model on an independent set of hepatitis C patient records from a different country or clinic and measuring accuracy below 85 percent.

Figures

Figures reproduced from arXiv: 2606.26561 by Abrar Alotaibi, Aisha Alansari, Alhatoon Alanazy, Lujain Alnajrani, Meshael Almusairii, Nawal Alsheikh, Salam Alshammasi, Shoog Alrassan.

Figure 1
Figure 1. Figure 1: Framework of the study. 3.1. Dataset Description and Analysis The present study is based on the HCV dataset from the UCI ML repository [23]. This dataset includes 29 features of 1385 Egyptian patients, including the target class, who had HCV therapy for approximately 18 months. There are four identifiable stages of hepatitis C virus (HCV) included in the dataset: portal fibrosis without septa, portal fibro… view at source ↗
Figure 2
Figure 2. Figure 2: Distribution of samples for the four stages of HCV. Tables 1 and 2 outline the statistical analysis of the numerical and categorical attrib￾utes. The tables show that the dataset has a nearly equal distribution of cases for each categorical feature, which may guarantee the model's generalizability utilizing those fea￾tures. Moreover, some outliers are indicated from the statistical analysis applied to the … view at source ↗
Figure 3
Figure 3. Figure 3: Confusion matrices: (a) RF, (b) GBM, (c) XGBoost, (d) ET. According to the findings illustrated in [PITH_FULL_IMAGE:figures/full_fig_p011_3.png] view at source ↗
Figure 3
Figure 3. Figure 3: Confusion matrices: (a) RF, (b) GBM, (c) XGBoost, (d) ET. According to the findings illustrated in [PITH_FULL_IMAGE:figures/full_fig_p012_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: AUC-ROC values (a) RF, (b) GBM, (c) XGBoost, (d) ET. 5. Explainable Artificial Intelligence ML has gained widespread popularity and has been applied to numerous domains and use cases. However, specific measures need to be implemented to ensure that society accepts and trusts ML-powered systems. To build this trust, it is necessary to visualize and explain how ML models make their decisions. XAI can be used… view at source ↗
Figure 4
Figure 4. Figure 4: AUC-ROC values (a) RF, (b) GBM, (c) XGBoost, (d) ET. 5. Explainable Artificial Intelligence ML has gained widespread popularity and has been applied to numerous domains and use cases. However, specific measures need to be implemented to ensure that society accepts and trusts ML-powered systems. To build this trust, it is necessary to visualize and explain how ML models make their decisions. XAI can be used… view at source ↗
Figure 5
Figure 5. Figure 5: Shapley values for the ET model. 5.2. Local Interpretable Model-Agnostic Explanations LIME is a commonly used algorithm that provides the ability to interpret machine learning models by creating a comprehensive explanation for a single prediction. LIME’s prediction is based on a simpler interpretable model, such as a linear classifier. In this technique, random perturbation is used to simulate data around … view at source ↗
Figure 6
Figure 6. Figure 6: LIME predictions for the ET model (a) positive, (b) negative. 6. Conclusions and Recommendations Cirrhosis, caused by extensive liver fibrosis or scarring, is frequently discovered after decompensation when its associated consequences have occurred. The performance of current non-invasive testing for the early detection of advanced liver cirrhosis is poor, with many categories being uncertain. Healthcare p… view at source ↗
read the original abstract

Hepatitis C is a liver infection caused by a virus, which results in mild to severe inflammation of the liver. Over many years, hepatitis C gradually damages the liver, often leading to permanent scarring, known as cirrhosis. Patients sometimes have moderate or no symptoms of liver illness for decades before developing cirrhosis. Cirrhosis typically worsens to the point of liver failure. Patients with cirrhosis may also experience brain and nerve system damage, as well as gastrointestinal hemorrhage. Treatment for cirrhosis focuses on preventing further progression of the disease. Detecting cirrhosis earlier is therefore crucial for avoiding complications. Machine learning (ML) has been shown to be effective at providing precise and accurate information for use in diagnosing several diseases. Despite this, no studies have so far used ML to detect cirrhosis in patients with hepatitis C. This study obtained a dataset consisting of 28 attributes of 2038 Egyptian patients from the ML Repository of the University of California at Irvine. Four ML algorithms were trained on the dataset to diagnose cirrhosis in hepatitis C patients: a Random Forest, a Gradient Boosting Machine, an Extreme Gradient Boosting, and an Extra Trees model. The Extra Trees model outperformed the other models achieving an accuracy of 96.92%, a recall of 94.00%, a precision of 99.81%, and an area under the receiver operating characteristic curve of 96% using only 16 of the 28 features.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript applies four ensemble ML classifiers (Random Forest, Gradient Boosting Machine, XGBoost, Extra Trees) to a UCI dataset of 2038 Egyptian hepatitis C patients described by 28 attributes. It reports that the Extra Trees model, after reduction to 16 features, attains 96.92% accuracy, 94.00% recall, 99.81% precision and 96% AUC, outperforming the other three models, and positions the work as the first ML study for cirrhosis detection in this population.

Significance. If the evaluation pipeline is free of leakage and the performance generalizes, the result would supply a concrete, high-precision screening signal that could be integrated into hepatitis C management workflows. The emphasis on a modest feature subset is practically useful, but the lack of external validation or nested validation details currently prevents the numbers from being treated as evidence of clinical utility.

major comments (2)
  1. [Methods] Methods / experimental setup: the manuscript supplies no information on whether the reduction from 28 to 16 features, or any hyperparameter search, was performed inside or outside the train-test split (or inside CV folds). If selection occurred on the full data, the headline Extra Trees metrics (Abstract) are consistent with optimistic bias and cannot be interpreted as generalization performance.
  2. Results / evaluation protocol: no description is given of the train-test procedure, number of folds, stratification for class balance, or whether performance was averaged over multiple splits. Without these details the reported 96.92% accuracy and 99.81% precision cannot be assessed for robustness (Abstract and Results).
minor comments (2)
  1. [Abstract] The title advertises 'explainable' models yet the abstract and results contain no SHAP values, feature-importance tables, or other interpretability outputs; this mismatch should be resolved or the title adjusted.
  2. [Dataset] The dataset description states 2038 patients but does not report the cirrhosis prevalence or any class-imbalance statistics; adding these numbers would clarify the difficulty of the task.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their detailed review and constructive comments on our manuscript. We address each major comment below and will revise the manuscript to incorporate the suggested clarifications.

read point-by-point responses

  1. Referee: [Methods] Methods / experimental setup: the manuscript supplies no information on whether the reduction from 28 to 16 features, or any hyperparameter search, was performed inside or outside the train-test split (or inside CV folds). If selection occurred on the full data, the headline Extra Trees metrics (Abstract) are consistent with optimistic bias and cannot be interpreted as generalization performance.

    Authors: The referee correctly identifies a lack of detail in the current manuscript regarding the feature selection and hyperparameter tuning process. We will revise the Methods section to explicitly describe that both the feature reduction to 16 features and any hyperparameter optimization were performed within the cross-validation folds to prevent data leakage and ensure unbiased performance estimates. revision: yes

  2. Referee: [—] Results / evaluation protocol: no description is given of the train-test procedure, number of folds, stratification for class balance, or whether performance was averaged over multiple splits. Without these details the reported 96.92% accuracy and 99.81% precision cannot be assessed for robustness (Abstract and Results).

    Authors: We agree that the evaluation protocol details are essential for assessing the robustness of the results. In the revised manuscript, we will provide a complete description of the train-test split procedure, the number of folds used in cross-validation, the use of stratification to maintain class balance, and confirmation that performance metrics were averaged across multiple splits or folds. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical ML metrics on fixed dataset

full rationale

The paper reports only empirical performance numbers (accuracy, precision, etc.) obtained by training standard classifiers on the UCI hepatitis C dataset. No equations, closed-form derivations, fitted parameters renamed as predictions, or self-citation chains appear in the provided text. The central claim is a set of measured results on held-out data, not a reduction of any quantity to its own inputs by construction. This matches the default expectation of no significant circularity.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 0 invented entities

The central claim rests on the assumption that internal performance metrics on this single dataset will translate to clinical utility, plus the choice of which 16 features to retain after training.

free parameters (1)
  • number of retained features = 16
    Reduced from 28 to 16, value chosen to optimize reported metrics
axioms (2)
  • domain assumption Patient records in the UCI dataset are independent and identically distributed
    Required for standard supervised learning assumptions to hold
  • domain assumption The 28 attributes contain sufficient signal for cirrhosis classification
    Implicit in training any model on these inputs

pith-pipeline@v0.9.1-grok · 5826 in / 1258 out tokens · 32821 ms · 2026-06-26T05:17:34.085998+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

40 extracted references · 1 linked inside Pith

  1. [1]

    Available online: https://www.who.int/news-room/fact-sheets/detail/hepatitis-c (accessed on 10 November 2022)

    Hepatitism, C. Available online: https://www.who.int/news-room/fact-sheets/detail/hepatitis-c (accessed on 10 November 2022)

    2022

  2. [2]

    Characterizing hepatitis C virus epidemiology in Egypt: Systematic reviews, meta-analyses, and meta-regressions

    Kouyoumjian, S.P .; Chemaitelly, H.; Abu-Raddad, L.J. Characterizing hepatitis C virus epidemiology in Egypt: Systematic reviews, meta-analyses, and meta-regressions. Sci. Rep. 2018, 8, 1661. [CrossRef]

    2018

  3. [3]

    Hepatitis C in Egypt—Past, present, and future

    Elgharably, A.; Gomaa, A.I.; Crossey, M.M.E.; Norsworthy, P .J.; Waked, I.; Taylor-Robinson, S.D. Hepatitis C in Egypt—Past, present, and future. Int. J. Gen. Med. 2016, 10, 1–6. [CrossRef]

    2016

  4. [4]

    Liver cirrhosis

    Pinzani, M.; Rosselli, M.; Zuckermann, M. Liver cirrhosis. Best Pract. Res. Clin. Gastroenterol. 2011, 25, 281–290. [CrossRef]

    2011

  5. [5]

    The global, regional, and national burden of cirrhosis by cause in 195 countries and territories, 1990–2017: A systematic analysis for the Global Burden of Disease Study 2017

    Sepanlou, S.G.; Safiri, S.; Bisignano, C.; Ikuta, K.S.; Merat, S.; Saberifiroozi, M.; Poustchi, H.; Tsoi, D.; Colombara, D.V .; Abdoli, A.; et al. The global, regional, and national burden of cirrhosis by cause in 195 countries and territories, 1990–2017: A systematic analysis for the Global Burden of Disease Study 2017. Lancet Gastroenterol. Hepatol. 2020,...

    1990

  6. [6]

    Understanding the Complexities of Cirrhosis

    Muir, A.J. Understanding the Complexities of Cirrhosis. Clin. Ther. 2015, 37, 1822–1836. [CrossRef]

    2015

  7. [7]

    Evaluation of Aspartate Aminotransferase-to-Platelet Ratio Index as a Non-Invasive Marker for Liver Cirrhosis

    Jain, P .; Tripathi, B.K.; Gupta, B.; Bhandari, B.; Jalan, D. Evaluation of Aspartate Aminotransferase-to-Platelet Ratio Index as a Non-Invasive Marker for Liver Cirrhosis. J. Clin. Diagn. Res. 2015, 9, OC22–OC24. [CrossRef]

    2015

  8. [8]

    Cirrhosis and Chronic Liver Failure: Part I

    Heidelbaugh, J.J.; Bruderly, M. Cirrhosis and Chronic Liver Failure: Part I. Diagnosis and Evaluation. Am. Fam. Physician 2006, 74, 756–762. Available online: https://www.aafp.org/pubs/afp/issues/2006/0901/p756.html (accessed on 9 May 2023)

    2006

  9. [9]

    Limitations of non-invasive tests for assessment of liver fibrosis

    Patel, K.; Sebastiani, G. Limitations of non-invasive tests for assessment of liver fibrosis. JHEP Rep. 2020, 2, 100067. [CrossRef]

    2020

  10. [10]

    Fibrotest for evaluating fibrosis in non-alcoholic fatty liver disease patients: A systematic review and meta-analysis.J

    Vali, Y .; Lee, J.; Boursier, J.; Spijker, R.; V erheij, J.; Brosnan, M.J.; Anstee, Q.M.; Bossuyt, P .M.; Zafarmand, M.H. Fibrotest for evaluating fibrosis in non-alcoholic fatty liver disease patients: A systematic review and meta-analysis.J. Clin. Med. 2021, 10, 2415. [CrossRef]

    2021

  11. [11]

    Fibroscan (Transient Elastography) for the Measurement of Liver Fibrosis

    Afdhal, N.H. Fibroscan (Transient Elastography) for the Measurement of Liver Fibrosis. Gastroenterol. Hepatol. 2012, 8, 605

    2012

  12. [12]

    The impact of artificial intelligence in medicine on the future role of the physician

    Ahuja, A.S. The impact of artificial intelligence in medicine on the future role of the physician. PeerJ 2019, 7, e7702. [CrossRef]

    2019

  13. [13]

    The Assessment of Diagnostic Accuracy of Real Time Shear Wave Elastography in Detecting Liver Cirrhosis Keeping Histopathology as Reference Standard

    Saleem, S.; Slehria, A.U.R.; Rauf, M.H.; Sohail, M.; Taufiq, N.; Khan, M.U. The Assessment of Diagnostic Accuracy of Real Time Shear Wave Elastography in Detecting Liver Cirrhosis Keeping Histopathology as Reference Standard. Pak. Armed Forces Med. J. 2022, 72, 590–593. [CrossRef]

    2022

  14. [14]

    Explainable Artificial Intelligence: An Updated Perspective

    Krajna, A.; Kovac, M.; Brcic, M.; Sarcevic, A. Explainable Artificial Intelligence: An Updated Perspective. In Proceedings of the 2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO), Opatija, Croatia, 23–27 May 2022; pp. 859–864. [CrossRef]

    2022

  15. [15]

    Explainable artificial intelligence: A survey

    Dosilovic, F.K.; Brcic, M.; Hlupic, N. Explainable artificial intelligence: A survey. In Proceedings of the 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia, 21–25 May 2018; pp. 210–215. [CrossRef]

    2018

  16. [16]

    Statistical Machine Learning Approaches to Liver Disease Prediction

    Mostafa, F.; Hasan, E.; Williamson, M.; Khan, H.; Statistical, H.; Jaeschke, H.W. Statistical Machine Learning Approaches to Liver Disease Prediction. Livers 2021, 1, 294–312. [CrossRef] Computation 2023, 11, 104 17 of 17

    2021

  17. [17]

    Available online: https://archive.ics.uci.edu/ml/datasets/HCV+data (accessed on 9 May 2023)

    UCI Machine Learning Repository: HCV Data Data Set. Available online: https://archive.ics.uci.edu/ml/datasets/HCV+data (accessed on 9 May 2023)

    2023

  18. [18]

    Machine Learning Models for Diagnostic Classification of Hepatitis C Tests

    Oladimeji, O.O.; Oladimeji, A.; Olayanju, O. Machine Learning Models for Diagnostic Classification of Hepatitis C Tests. Front. Health Inform. 2021, 10, 70. [CrossRef]

    2021

  19. [19]

    Applying data mining techniques to classify patients with suspected hepatitis C virus infection

    Safdari, R.; Deghatipour, A.; Gholamzadeh, M.; Maghooli, K. Applying data mining techniques to classify patients with suspected hepatitis C virus infection. Intell. Med. 2022, 2, 193–198. [CrossRef]

    2022

  20. [20]

    A Comparative Study on Hepatitis C Predictions Using Machine Learning Algorithms

    Septina, P .L.; Sihotang, J.I. A Comparative Study on Hepatitis C Predictions Using Machine Learning Algorithms. 8ISC Proc. T echnol.2022, 33–42

    2022

  21. [21]

    Hepatitis C Virus Detection Model by Using Random Forest, Logistic-Regression and ABC Algorithm

    Li, T.H.S.; Chiu, H.J.; Kuo, P .H. Hepatitis C Virus Detection Model by Using Random Forest, Logistic-Regression and ABC Algorithm. IEEE Access 2022, 10, 91045–91058. [CrossRef]

    2022

  22. [22]

    Hep-Pred: Hepatitis C Staging Prediction Using Fine Gaussian SVM

    Ghazal, T.M.; Anam, M.; Hasan, M.K.; Hussain, M.; Farooq, M.S.; Ali, H.M.A.; Ahmad, M.; Soomro, T.R. Hep-Pred: Hepatitis C Staging Prediction Using Fine Gaussian SVM. Comput. Mater. Contin. 2021, 69, 191–203. [CrossRef]

    2021

  23. [23]

    Available online: https://archive.ics

    UCI Machine Learning Repository: Hepatitis C Virus (HCV) for Egyptian patients Data Set. Available online: https://archive.ics. uci.edu/ml/datasets/Hepatitis+C+Virus+%28HCV%29+for+Egyptian+patients (accessed on 9 May 2023)

    2023

  24. [24]

    Diagnosing the Stage of Hepatitis C Using Machine Learning

    Butt, M.B.; Alfayad, M.; Saqib, S.; Khan, M.A.; Ahmad, M.; Khan, M.A.; Elmitwally, N.S. Diagnosing the Stage of Hepatitis C Using Machine Learning. J. Healthc. Eng. 2021, 2021, 8062410. [CrossRef]

    2021

  25. [25]

    Mamdouh, H.; Shams, M.Y.; Abd El-Hafeez, T. Hepatitis C Virus Prediction Based on Machine Learning Framework: A Real-world Case Study in Egypt Hepatitis C Virus Prediction based on Machine Learning Framework: A Real-World Case Study in Egypt. Knowl. Inf. Syst. 2022, 65, 2595–2617. [CrossRef]

    2022

  26. [26]

    Prediction and Staging of Hepatic Fibrosis in Children with Hepatitis C Virus: A Machine Learning Approach

    Barakat, N.H.; Barakat, S.H.; Ahmed, N. Prediction and Staging of Hepatic Fibrosis in Children with Hepatitis C Virus: A Machine Learning Approach. Healthc. Inform. Res. 2019, 25, 173–181. [CrossRef] [PubMed]

    2019

  27. [27]

    Machine Learning Model for Diagnosing the Stage of Liver Fibrosis in Patients With Chronic Viral Hepatitis C

    Tsvetkov, V .; Tokin, I.; Lioznov, D. Machine Learning Model for Diagnosing the Stage of Liver Fibrosis in Patients With Chronic Viral Hepatitis C. Preprints.org 2021, 2021020488. [CrossRef]

    2021

  28. [28]

    A novel model based on non invasive methods for prediction of liver fibrosis

    Nasr, M.; El-Bahnasy, K.; Hamdy, M.; Kamal, S.M. A novel model based on non invasive methods for prediction of liver fibrosis. In Proceedings of the 2017 13th International Computer Engineering Conference (ICENCO), Cairo, Egypt, 27–28 December 2017; pp. 276–281. [CrossRef]

    2017

  29. [29]

    Random Forests; Chapman and Hall/CRC: Boca Raton, FL, USA, 2019; pp

    Breiman, B.; Greenwell, B. Random Forests; Chapman and Hall/CRC: Boca Raton, FL, USA, 2019; pp. 1–122. [CrossRef]

    2019

  30. [30]

    Available online: https://data-flair.training/blogs/artificial-neural-networks-for-machine-learning/amp/ (accessed on 9 May 2023)

    Artificial Neural Networks for Machine Learning—Every Aspect You Need to Know About—DataFlair. Available online: https://data-flair.training/blogs/artificial-neural-networks-for-machine-learning/amp/ (accessed on 9 May 2023)

    2023

  31. [31]

    Majority vote of diverse classifiers for late fusion

    Morvant, E.; Habrard, A.; Ayache, S. Majority vote of diverse classifiers for late fusion. Lect. Notes Comput. Sci. Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinform. 2014, 8621, 153–162. [CrossRef]

    2014

  32. [32]

    Available online: https://analyticsindiamag.com/story-of-gradient- boosting-how-it-evolved-over-years/ (accessed on 9 May 2023)

    Story of Gradient Boosting: How It Evolved over Years. Available online: https://analyticsindiamag.com/story-of-gradient- boosting-how-it-evolved-over-years/ (accessed on 9 May 2023)

    2023

  33. [33]

    Research on travel time prediction model of freeway based on gradient boosting decision tree

    Cheng, J.; Li, G.; Chen, X. Research on travel time prediction model of freeway based on gradient boosting decision tree. IEEE Access 2019, 7, 7466–7480. [CrossRef]

    2019

  34. [34]

    xgboost: EXtreme Gradient Boosting

    Chen, T.; He, T. xgboost: EXtreme Gradient Boosting. 2022. Available online: https://cran.r-project.org/web/packages/xgboost/ vignettes/xgboost.pdf (accessed on 18 June 2022)

    2022

  35. [35]

    IBLP: An XGBoost-Based Predictor for Identifying Bioluminescent Proteins

    Zhang, D.; Chen, H.D.; Zulfiqar, H.; Yuan, S.S.; Huang, Q.L.; Zhang, Z.Y.; Deng, K.J. IBLP: An XGBoost-Based Predictor for Identifying Bioluminescent Proteins. Comput. Math. Methods Med. 2021, 2021, 6664362. [CrossRef]

    2021

  36. [36]

    Extremely randomized trees

    Geurts, P .; Ernst, D.; Wehenkel, L. Extremely randomized trees. Mach Learn 2006, 63, 3–42. [CrossRef]

    2006

  37. [37]

    Extra Trees Ensemble: A Machine Learning Model for Predicting Blast-Induced Ground Vibration Based on the Bagging and Sibling of Random Forest Algorithm

    Bui, X.N.; Nguyen, H.; Soukhanouvong, P . Extra Trees Ensemble: A Machine Learning Model for Predicting Blast-Induced Ground Vibration Based on the Bagging and Sibling of Random Forest Algorithm. Lect. Notes Civ. Eng. 2022, 228, 643–652. [CrossRef]

    2022

  38. [38]

    Floating Variants—Mlxtend

    SequentialFeatureSelector: The Popular forward and Backward Feature Selection Approaches Incl. Floating Variants—Mlxtend. Available online: http://rasbt.github.io/mlxtend/user_guide/feature_selection/SequentialFeatureSelector/ (accessed on 8 May 2022)

    2022

  39. [39]

    Interpretable Machine Learning—A Brief History, State-of-the-Art and Challenges

    Molnar, C.; Casalicchio, G.; Bischl, B. Interpretable Machine Learning—A Brief History, State-of-the-Art and Challenges. Commun. Comput. Inf. Sci. 2020, 1323, 417–431. [CrossRef]

    2020

  40. [40]

    DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer- Aided Diagnosis Systems

    Zafar, M.R.; Khan, N.M. DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer- Aided Diagnosis Systems. arXiv 2019, arXiv:1906.10263. Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the ...

    Pith/arXiv arXiv 2019