Advanced Prediction and Classification of Liver Cirrhosis using Machine Learning Techniques

Abstract

Liver cirrhosis is a life-threatening condition caused by long-term liver damage and scarring. Early detection is crucial but traditional diagnostic methods like biopsies and imaging have limitations in accuracy and invasiveness. Machine learning (ML) offers promising solutions by analyzing large medical datasets to predict disease progression. Techniques such as decision trees, random forests, SVMs, and neural networks help identify patterns in medical history, lab results, and demographics to assess cirrhosis risk and severity. ML models, when integrated with real-time health monitoring, enable early abnormality detection, reducing advanced cases requiring transplants. Additionally, predictive models assist in developing personalized treatment plans and targeted therapeutic interventions, improving patient outcomes and advancing liver disease management

Introduction

Liver disease, especially cirrhosis, is a serious global health issue often diagnosed too late. Traditional diagnostic methods like biopsies and imaging are invasive and sometimes inaccurate. This project uses machine learning (ML) techniques—including Random Forest, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN)—to predict liver cirrhosis early and accurately by analyzing patient data such as medical history, liver function tests, and demographics.

Compared to traditional methods, ML models showed higher accuracy (up to 92.4% with Random Forest), better precision, and faster processing times, improving diagnostic efficiency and enabling early interventions. The system consists of four main steps: data collection, preprocessing (cleaning and normalization), model training, and prediction generation. Key features impacting predictions include liver enzyme levels (AST, ALT), age, and clinical history.

The system delivers timely, accurate predictions that support healthcare professionals in risk classification and personalized treatment planning. It is deployed using the Flask web framework and offers a secure, scalable web API to integrate with healthcare systems and applications, facilitating real-time liver disease diagnosis and management.

Conclusion

The liver patient dataset was utilized to implement advanced prediction and classification algorithms, significantly reducing the workload on doctors by automating liver disease diagnosis. Machine learning techniques were applied to analyze the patient’s overall liver condition, improving diagnostic precision. A liver condition persisting for at least six months is classified as chronic, requiring continuous monitoring and timely intervention. The dataset comprises both positive and negative cases, helping to train models that can distinguish between healthy and diseased liver conditions effectively. A confusion matrix visually represents the classifier\'s performance in predicting liver disease by displaying true positives, true negatives, false positives, and false negatives. With a well-structured training dataset, the proposed classification techniques enhance accuracy and reliability. By leveraging machine learning classifiers, the system efficiently categorizes good and bad values, demonstrating high predictive accuracy and aiding in early detection and treatment planning.

References

[1] C. Huang and R. Ogawa, ‘‘The vascular involvement in soft tissue fibrosis Lessons learned from pathological scarring’’, Int. J. Mol. Sci., vol. 21, no. 7, p. 2542, Apr. 2020, doi: 10.3390/ijms21072542. [2] D. Q. Huang, N. A. Terrault, F. Tacke, L. L. Gluud, M. Arrese, E. Bugianesi, and R. Loomba, ‘‘Global epidemiology of cirrhosis— Aetiology, trends and predictions,’’NatureRev.GastroenterologyHepatology,vol.20,no.6,pp.388– 398, Jun. 2023. [3] D.W.Crabb,G.Y.Im,G.Szabo,J.L.Mellinger,andM.R.Lucey,‘‘Diagnosis and treatment of alcohol-associated liver diseases: 2019 practice guidance from theAmericanAssociationfortheStudyofLiverDiseases,’’Hepatology,vol.71, no. 1, pp. 306–333, Jan. 2020, doi: 10.1002/hep.30866. [4] J. F. Creeden, D. M. Gordon, D. E. Stec, and T. D. Hinds, ‘‘Bilirubin as a metabolic hormone: The physiological relevance of low levels,’’ Amer. J. Physiol.-Endocrinol.Metabolism,vol.320,no.2,pp.E191–E207,Feb.2021,doi: 10.1152/ajpendo.00405.2020. [5] J.Trebicka,P.Bork,A.Krag,andM.Arumugam,‘‘Utilizingthegutmicrobiome in decompensated cirrhosis and acute-on-chronic liver failure,’’ Nature Rev. Gastroenterology Hepatology, vol. 18, no. 3, pp. 167–180, Nov. 2020, doi: 10.1038/s41575-020-00376-3. [6] L. Fabris and M. Strazzabosco, ‘‘Rare and undiagnosed liver diseases: Challenges and opportunities,’’ Transl. Gastroenterol. Hepatol., vol. 6, p. 18, Apr. 2021, doi: 10.21037/tgh-2020-05. [7] M. P. Diaz-Soto and G. Garcia-Tsao, ‘‘Management of varices and variceal haemorrhage in liver cirrhosis: A recent update,’’ Therapeutic Adv. Gastroenterology, vol. 15, Jan. 2022, Art. no. 175628482211017, doi: 10.1177/17562848221101712. [8] N.V.Bergasa,ApproachtoPatientWithLiverDisease.London,U.K.:Springer, 2022, pp. 5–26, doi: 10.1007/978-1-4471-4715-2_2. [9] N. Tanwar and K. F. Rahman, ‘‘Machine learning in liver disease diagnosis: Currentprogressandfutureopportunities,’’IOPConf.Ser.,Mater.Sci.Eng.,vol. 1022, no. 1, Jan. 2021, Art. no. 012029. [Online]. [10] P.Ginès,A.Krag,J.G.Abraldes,E.Solà,N.Fabrellas,andP.S.Kamath,‘‘Liver cirrhosis,’’ Lancet, vol. 398, no. 10308, pp. 1359–1376, 2021.

Copyright

Copyright © 2025 Mr. G. Raghul, S. I. Rohith Narendhiran, C. Udhaya Kumar, A. Noorul Ashfaq, P. Ganesh, S. Sakthimurugan . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.