ALL Metrics
-
Views
-
Downloads
Get PDF
Get XML
Cite
Export
Track
Review

Artificial Intelligence in Cirrhosis: Diagnosis, Screening, and Evaluation for Liver Transplantation

[version 1; peer review: awaiting peer review]
PUBLISHED 01 Sep 2025
Author details Author details
OPEN PEER REVIEW
REVIEWER STATUS AWAITING PEER REVIEW

This article is included in the Artificial Intelligence and Machine Learning gateway.

Abstract

Artificial Intelligence (AI) is increasingly transforming the care of patients with cirrhosis and those undergoing liver transplantation (LT) through enhanced diagnostic accuracy, improved prognostication, and optimized resource utilization. Our review focuses on the growing application of AI, particularly machine learning (ML), in various stages of liver disease care. AI algorithms are more accurate than conventional methods in diagnosing, screening, and predicting the prognosis of cirrhosis. AI also enhances LT candidate selection by predicting pre- and post-transplant outcomes, such as survival, complications, and graft function, as well as identifying new biomarkers for individualized clinical decision-making. Artificial Intelligence has also played an essential role in revolutionizing donor-recipient matching and organ allocation for liver transplantation. Among the limitations, including data heterogeneity, interpretability, and absence of external validation, day-to-day clinical adoption is restricted. In the near future, AI can significantly contribute to diagnosis, prognosis, and decision-making in the context of cirrhosis and liver transplantation. As it becomes further developed and validated, it could serve as an impetus for the advancement of precision medicine in hepatology.

Keywords

Artificial Intelligence, Machine Learning, Cirrhosis, Liver Transplantation

Introduction

Given its ability to integrate complex data, the use of Artificial Intelligence (AI) in medicine has been increasing. It is expected that ML can reveal associations in large datasets.1 Recently, ML has been used to facilitate decisions regarding diagnosis, therapy, and prognostication.1 In hepatology, artificial intelligence, particularly ML and natural language processing (NLP), has proven helpful in obtaining insights from electronic health records (EHRs) that go beyond traditional structured data, enabling improved disease surveillance, prognosis modeling, and assessment of response to treatment.2 AI models have been used previously to assess the severity and prognosis of nonalcoholic fatty liver disease (NAFLD) and hepatocellular carcinoma.3,4 Researchers are now testing ML in organ allocation, predicting transplant outcomes, and stratifying high-risk patients.5 Moreover, with the growing population of older people, the gap between demand and supply of grafts is widening.6 AI can help bridge this gap by maximizing donor organ allocation and allowing for judicious use of “extended criteria donors“ — patients who are not acceptable as standard donors due to such conditions as advanced age, mild liver steatosis, or other comorbidities — and helping avoid the utilization of grafts with borderline fat load or risk of infection.7 A summary of key studies applying AI in cirrhosis and liver transplantation is presented in Table 1. One of the key metrics used to evaluate the performance of these predictive models is the Area Under the Curve (AUC), which reflects a model’s ability to distinguish between outcomes—an AUC closer to 1.0 indicates excellent discriminative performance.

Table 1. Key studies evaluating the applications of artificial intelligence in cirrhosis, including diagnosis, prognosis, and liver transplantation assessment.

Application AuthorsRole of AI model Accuracy
Diagnosis of cirrhosisSalvi et al.7Designed HEPASS (HEPatic Adaptive Steatosis Segmentation) to detect micro and macrosteatosis from images of histology specimensAccuracy = 97%
Yu et al.10Segmentation of portal tract imagesAUC = 0.89
Wada et al.12Analyzed liver CT of patients awaiting liver transplant or hepatectomy scans to detect cirrhosisAUC = 0.882 (F0 vs ≥ F1)
0.873 (≤F1 vs ≥ F2)
0.848 (≤F2 vs ≥ F3)
0.891 (≤F3 vs F4)
Sharma et al.13Analyzed 3s scans taken using handheld near-infrared-spectroscopy (NIRS)Accuracy = 96.3
AUC = 0.98
Prognosis/Predicting survival and complicationsKazemi et al.28Identification of factors affecting post-transplant survivalAUC = 0.90
Yu et al.29Predict post-transplant survival at 1, 3, and 12 months post-transplantAUC = 0.80 (1 month)
AUC = 0.85 (3 months)
AUC = 0.81 (12 months)
Azhie et al.32Used a long short-term memory (LSTM) AI model to predict graft fibrosisAUC = 0.798
Chen et al.36,37Predict sepsis and pneumoniaAUC = 0.73
He et al.38Predict AKI after donation after cardiac death liver transplantation (DCDLT)AUC = 0.85
Zhang et al.40Used SHapley Additive exPlanations (SHAP) to predict post-LT AKIAUC = 0.75
Fodor et al.41Hyperspectral imaging of bile ducts to predict biliary complicationsAccuracy = 90%
Jain et al.42Used gradient-boosted modeling (GBM), XGBoost, to predict major adverse cardiovascular events (MACE) post-LTAUC = 0.71
Ge et al.46Designed an Expert-Augmented Machine Learning (EAML) model to predict outcomes after liver transplant in acute-on-chronic liver failure patientsAUC=0.70 for 1-year mortality
AUC = 0.68 for death within 3 months
Donor-recipient matchingBörner et al.62Used ML with easily interpretable data to match donors with recipientsAUC = 0.94
Mark et al.63Found a higher 5-year survival rate in patients who received a transplant with a risk of infection transmission vs those who waited for a standard liver transplantRoot mean
square errors (RMSE) of ML model = 9.0
vs. random
guessing from a normal distribution = 23.6
Zhang et al.64Used Deep Learning to find a higher 3-year survival rate in patients who received a steatotic liver transplant vs those who waited for a standard liverBalanced accuracy = 86.41%
Lusnig et al.66Found that employed privacy-conscious collaborative ML superior to traditional methods for assessing hepatic steatosisAccuracy > 97%
Frey et al.67Classify macrosteatosis > 30% in donor liversAUC = 0.71
Sun et al.68Evaluate the percentage of steatosis in frozen sections of liver biopsyr = 0.85 and ICC = 0.85
Cesaretti et al.69Used ML to classify hepatic steatosis as more or less than 30% in intraoperative pictures clicked with a smartphone and graft biopsiesAccuracy = 98% (smartphone images)
Accuracy = 89% (graft biopsy features)

Applications of AI in diagnosis

Medical imaging analysis

Deep learning models: Deep learning algorithms have demonstrated tremendous potential for improving diagnostic accuracy for cirrhosis by analyzing medical images and histologic data with minimal human intervention. By offering reproducible and objective assessments critical to early diagnosis and disease monitoring, these systems are being increasingly applied in clinical research. For instance, Ahn et al. developed a deep learning model to generate an ACE (AI-Cirrhosis-ECG) score, which identified patients with cirrhosis based on ECG findings (AUC = 0.91).8 Building on this, a follow-up study evaluated the ACE score’s ability to detect hepatic decompensation, revealing high discriminative performance with an AUC of 0.933 (95% CI: 0.923–0.942).9 In another area of histologic examination, the HEPASS (HEPatic Adaptive Steatosis Segmentation) algorithm was developed as a fully automated deep learning program to quantify liver steatosis in H&E-stained biopsy specimens. It utilizes object detection and semantic segmentation to identify both microsteatosis and macrosteatosis regardless of size, shape, or staining intensity. This model enables accurate, reproducible, and user-independent assessment and is the first to automatically measure both types of liver fat with high precision7 ( Table 1). In addition, liver fibrosis—an essential predictor of disease progression and mortality—is best assessed by histopathologic biopsy but remains limited by observer variability in manual methods. To address this, a model named MUSA-UNet (Multiple Up-sampling and Spatial Attention guided UNet) was developed to automatically and accurately segment portal tract regions in whole-slide liver biopsy images using deep learning. This model outperforms traditional methods by enabling standardized and efficient assessment of fibrosis, demonstrating strong potential to support AI-aided diagnosis of cirrhosis10 ( Table 1).

Radiomics: The combination of Computed Tomography (CT) imaging with laboratory and demographic data has been shown to improve the prediction of undiagnosed cirrhosis, outperforming the Fibrosis-4 (Fib-4) score or morphomics when used alone, with an AUC of 0.85.11 Building on imaging-based approaches, deep learning-based spectral CT—a novel form of rapid kilovolt-switching CT (FKSCT)—enables higher energy separation and neural network-based computerized image reconstruction. This technique allows accurate quantification of iodine density and extracellular volume fraction (ECV) in liver parenchyma, which correlates strongly with the extent of fibrosis. As a noninvasive radiomic technique, it has the potential to be valuable in AI-assisted staging and diagnosis of liver fibrosis12 ( Table 1). Complementing these imaging advancements, a point-of-care near-infrared spectroscopy (NIRS) device integrated with machine learning can quickly and accurately diagnose liver fibrosis from freshly excised tissue specimens. It offers a biopsy-free solution that holds promise for real-time monitoring of fibrosis in assessing liver transplantation13 ( Table 1). Similarly, a radiomics-based machine learning model utilizing diffusion-weighted MRI (DWI) was developed to non-invasively identify liver fibrosis and early-stage cirrhosis. Built on a support vector machine (SVM), the model achieved high accuracy (AUC 0.948 for healthy vs. abnormal liver and AUC 0.968 for fibrosis vs. cirrhosis). The technique surpasses current Magnetic resonance imaging (MRI) and deep learning techniques and has high potential for early and accurate diagnosis of cirrhosis.14 Further expanding AI applications, a recent innovation explored the use of ChatGPT-4 in liver ultrasound radiomics, demonstrating its ability to outline significant texture features and classify fibrosis, steatosis, and normal liver tissue with an accuracy of up to 76%. Although it was slightly less sensitive than standard software, it significantly reduced the analysis time by 40%, allowing for efficient high-throughput evaluation. This suggests that ChatGPT-4 has the potential to be a fast and scalable tool in AI-assisted liver disease diagnosis.15

Pattern recognition

AI-based pattern recognition and omics analysis are emerging as powerful tools in improving the diagnosis and outcome prediction in liver cirrhosis. In one study, Guo et al. used various ML models to evaluate laboratory data and related diagnoses to predict mortality in liver cirrhosis. All ML models outperformed the traditional Model for End-Stage Liver Disease–Sodium (MELD-NA) scores. A deep neural network (DNN) demonstrated AUC values of 0.88 for 90-day mortality, 0.86 for 180-day mortality, and 0.85 for 1-year mortality.16 In parallel, omics technologies hold tremendous potential in detecting and monitoring early liver fibrosis, with the possibility of delaying disease progression, lowering the risk of developing end-stage liver diseases such as hepatocellular carcinoma, and, eventually, mortality. While conventional statistical methods have traditionally been the foundation, artificial intelligence (AI) methods—especially data-driven AI—have become increasingly applied to omics data analysis. Deep learning (DL), a subset of AI that entails multilayered neural networks, is demonstrating itself to be particularly well-suited for recognizing complex patterns in high-dimensional omics data and is seeing growing applications in this field.17

Natural Language Processing (NLP)

Electronic Health Records (EHRs) analysis: NLP tools can analyze electronic health records to identify patients with undiagnosed cirrhosis by extracting relevant information from clinical notes, lab results, and imaging reports. Vleck et al. utilized natural language processing (NLP) to extract vast amounts of clinical information from electronic health records (EHRs) by mapping patient data to Systematized Nomenclature of Medicine – Clinical Terms (SNOMED CT) expressions. This method outperformed traditional methods, such as ICD codes and free-text search, in identifying and tracking the progression of NAFLD into nonalcoholic steatohepatitis (NASH) or cirrhosis. It showed superior precision, recall, and F1 scores, indicating high diagnostic accuracy. Their combination with ICD codes improved sensitivity without losing specificity. Findings highlight the strength of NLP in improving cirrhosis detection through EHR mining.18

Screening

Predictive modelling

Risk stratification: To support early identification and individualized management in chronic liver diseases, machine learning models have been increasingly applied for risk stratification by predicting disease progression and clinical outcomes. An ensemble machine learning model has been developed to predict outcomes in Alpha-1 antitrypsin deficiency-associated liver disease (AATD-LD), demonstrating Area Under the Receiver Operating Characteristic Curve (AUROC) values of 68.1% for all-cause mortality, 75.9% for liver-related death, and 91.2% for liver transplantation, indicating strong predictive capability.19 In patients with Primary Sclerosing Cholangitis (PSC), artificial intelligence has been utilized to analyze digitized histological slides, with a particular emphasis on cytokeratin 7 (K7) expression. It predicted a composite end-liver transplant, liver-related mortality, or cholangiocarcinoma, with an AUC of 0.81.20 Another AI-based model combined Magnetic Resonance Cholangiopancreatography+ (MRCP+) imaging with clinical markers such as bilirubin and aspartate aminotransferase (AST) levels to predict the risk of transplant or death in PSC, achieving superior performance compared to the Mayo risk score, with an AUC of 0.86.21 Additionally, gradient boosting algorithms have been utilized to classify disease severity in NAFLD, with AUROC values of 0.90 for NAFLD detection, 0.82 for NASH, and 0.84 for advanced fibrosis, supporting the role of AI in noninvasive disease staging.22

Biomarker analysis

Advanced algorithms: AI can analyze EHR data to identify early signs of liver disease, enabling timely screening and monitoring. A machine learning model was developed using serum, stool samples, and portal venous blood to investigate changes in the gut microbiome and enterohepatic bile acid circulation, identifying a combinatorial biomarker panel (AUC = 0.92) for submassive hepatic necrosis (SMHN). This panel integrated selected bacterial species and bile acid markers from multiple sources, offering substantial predictive value through a multi-omics machine learning approach.23

Evaluation for liver transplantation

Patient selection

Predictive analytics: Artificial intelligence models can predict outcomes of liver transplantation based on a range of patient-specific factors, aiding in the selection of suitable candidates. One study compared deep learning models with the MELD-sodium score and demonstrated that deep learning was superior in predicting pretransplant mortality, achieving an AUC of 0.936.24 Another machine learning model, the Optimized Prediction of Mortality (OPOM), outperformed MELD in predicting mortality, particularly among patients with higher disease severity. OPOM showed greater accuracy in identifying the sickest candidates, significantly reduced waitlist and post-transplant deaths, and maintained overall transplant volume, supporting a more effective “sickest-first” allocation approach.25 In pediatric transplant centers, a Random Forest (RF) model was employed to identify the important predictors of mortality, and changes in creatinine and listing status were identified as the most significant factors. These high-risk feature identifications would improve survival by prioritizing the most vulnerable children for transplantation.26 Additionally, an artificial intelligence model was developed to predict harmful alcohol use after liver transplantation for alcoholic hepatitis using psychosocial variables such as lack of a primary support person, caregiving responsibilities, and prior opioid use. These factors were key to delineating personalized risk profiles, and the model demonstrated outstanding predictive capability, with an AUC of 0.93, and outstanding performance in both training and external validation, supporting its utility in guiding post-transplant care.27

Survival prediction: Several studies have used ML to predict post-transplant survival. Kazemi et al. applied a data mining approach to 902 adult liver transplant recipients and identified key pre-, peri-, and post-transplant factors—such as graft failure, infections, and vascular complications—as major determinants of survival. Their model highlighted how machine learning can uncover clinically relevant predictors that align closely with real-world outcomes, supporting its role in refining prognostic assessment28 ( Table 1). One study applied an RF model to identify recipient weight, BMI, age, and INR as relevant predictors of survival, factors that were not highlighted by traditional models29 ( Table 1). In another large-scale analysis using a U.S. transplant database, machine learning models, including random survival forests and neural networks, were employed for post-transplant survival prediction. Among these, partial logistic artificial neural networks (PLANN) demonstrated the most accurate long-term calibration and outperformed Cox models in predicting long-term survival. Key predictors identified included re-transplantation, donor age, life support, and Intensive Care Unit (ICU) admission before transplant, supporting their utility for personalized graft survival assessment.30

Additionally, a scoring system was developed using ML to predict 90-day, 1-year, and 5-year post-transplant survival based solely on preoperative characteristics. This model identified age, MELD score, BMI, diabetes, and dialysis as strong predictors of 3-month mortality, achieving an AUC of 0.95.31 ML approaches have also been employed to predict graft dysfunction32 ( Table 1). For example, Lin et al. employed AI to graft proteomics and perfusate metabolomics to predict early allograft dysfunction (EAD), reaching an AUC of 0.83.33 In the pediatric setting, analysis of the Studies in Pediatric Liver Transplantation (SPLIT) registry using Random Forest Analyses (RFA) evaluated whether demographic and biochemical factors one year after pediatric liver transplant could influence outcomes at three years. Predictors of adverse outcomes included racial factors, longer surgery duration, early biliary and vascular complications, and location within UNOS regions 2 and 5, with an accuracy of 0.71.34 Similarly, a systematic review of studies using artificial neural networks (ANN) to predict graft survival found that ANN models outperformed traditional tools like the balance of risk (BAR), donor risk index (DRI), and Survival Outcome Following Liver Transplantation (SOFT), with ANN achieving AUCs between 0.82 and 0.84.35

Complications of liver transplant: Various studies have employed AI to predict the probability of sepsis, pneumonia, Acute Kidney Injury (AKI), biliary, and cardiovascular complications post-LT3638,4042 ( Table 1).39 These complications are potential causes of mortality post-transplant, and accurate prediction of their risk may help stratify patients appropriately to improve outcomes. One study identified raised preoperative indirect bilirubin, lower intraoperative urine output, longer anesthesia duration, lower preoperative platelet count, and graft steatosis classified as nonalcoholic steatohepatitis, Clinical Research Network grade 1 (NASH CRN1), as predictors of acute kidney injury (AKI)40 ( Table 1). Similarly, infectious complications can pose a risk after LT. Colonization with Carbapenem-resistant Enterobacterales (CRE) at the time of liver transplant can increase the risk of post-transplant infections. Use of certain antibiotics, hepato-renal syndrome, and poor chronic liver failure sequential organ failure assessment (CLIF-SOFA) scores are associated with CRE.43 An ML model was designed to predict CRE colonization with a sensitivity of 66%, a specificity of 83%, and a negative predictive value of 97%.43 This could help tailor antibiotic prophylaxis at the time of liver transplant. Another study proposed an ultrasound-spectrogram fusion network that achieves greater accuracy, sensitivity, and specificity for the early and rapid detection of allograft dysfunction (EAD), surpassing radiologists and providing clinically helpful results. The four-ultrasound-image and clinical-data-fused model achieved an AUC of 0.968 (95% CI: 0.940–0.991), with approximately 30% greater performance on all metrics compared to radiologists. Furthermore, AI assistance significantly improved diagnostic performance (P < 0.050) for both less experienced and experienced clinicians.44

In addition, Wehrle et al. used ML to study the outcomes of combined LT and cardiac surgery, which is regarded as a hazardous procedure. The model identified risk factors such as preoperative kidney dysfunction and Coronary Artery Bypass Grafting (CABG) surgery as predictors of mortality.45 This could help in risk stratification and appropriately assess the safety of this procedure for each patient.

Liver transplant in patients with comorbidities: LT remains the curative option for acute on chronic liver failure (ACLF). Ge et al. and Yang et al. used ML to predict outcomes in the same way. Yang et al. found RF (AUC = 0.94) to be the most accurate among ML methods, while MELD (AUC = 0.70) proved to be an accurate traditional method for predicting the short-term survival of ACLF patients after LT46 ( Table 1).47 Several studies have been conducted to evaluate the prognosis after LT among patients with pre-existing comorbidities. ML was used in one study to predict post-LT survival among patients with diabetes mellitus (DM) and concluded that patients with pre-existing DM had poorer outcomes compared to non-diabetics.48

Furthermore, higher serum creatinine, blood pressure, and sirolimus therapy were linked with higher mortality.48 In another study, a deep learning model was trained to predict outcomes in Hepatitis C patients undergoing LT. The model demonstrated 100% accuracy in predicting postoperative complications, supporting its use in risk stratification and tailored monitoring for this population.49 Ischaemic-type biliary lesions (ITBL), a potential complication post-LT, were also evaluated using AI. A convolutional neural network (CNN) was applied to detect and denoise CT angiography (CTA) images, thereby improving their quality and facilitating the accurate identification of hepatic artery lesions and thrombosis. Early CTA abnormalities were associated with the later development of ITBL.50

Thus, it can be inferred that AI has been used extensively and shown promising capability to predict patient mortality and post-LT survival.

Preoperative assessment

Comprehensive evaluation: Preoperative assessment is one of the most critical parts of liver transplantation, and AI-based models have increasingly assisted in making it efficient and precise. An RF model was developed to predict 30-day survival after liver transplantation using preoperative blood investigations, with an AUC of 0.71. An imputation method proposed for handling missing data outperformed existing alternatives.51 Machine learning was also applied to evaluate the validity of the Global Leadership Initiative on Malnutrition (GLIM) criteria in cirrhotic patients, identifying midarm muscle circumference as a strong predictor of malnutrition and 1-year mortality. Another application of ML involved identifying patients at high risk of graft-versus-host disease post-transplant who may require closer monitoring.52,53 Given the cardiovascular demands of liver transplantation, a machine learning algorithm was used to non-invasively compute CT-derived fractional flow reserve (CT-FFR), offering 85% accuracy in ruling out coronary artery disease and potentially reducing reliance on invasive coronary angiography.54 In pediatric liver transplant recipients, transcriptomic signatures were integrated with protein interactome data through ML to identify targets for personalized antirejection therapies.55 Deep learning has also been used to predict long-term survival post-transplant, with AUCs ranging from 0.69 to 0.85 for infection-related and graft rejection-related deaths, respectively.56 As sarcopenia is known to increase post-transplant mortality risk, deep learning models were developed to assess muscle mass from CT scans. These tools showed equal predictive accuracy compared to manual assessments and helped associate sarcopenia with poor survival and increased risk of post-transplant diabetes.5759 Transfer learning, combined with the SHapley Additive exPlanation (SHAP) algorithm, was utilized to enhance the prediction of post-LT complications, yielding high precision, recall, and F1 scores.39 Finally, the GraftIQ model—a fusion of a multiclass neural network and clinical expertise—achieved an AUC of 0.902, outperforming other ML models and showing strong potential as a decision support tool by accurately discriminating between graft etiologies and identifying high-risk patients for targeted interventions.60

Resource allocation

Optimizing organ allocation: ML models have been used for the accurate matching of donors with recipients61,62 ( Table 1). Briceño et al. found both ANN and RF superior to traditional methods, such as the Model for End-Stage Liver Disease (MELD) score. While RF models were able to assess the significance of different variables to build a decision tree, ANN models were better for analyzing large groups (Success rate > 80%).61

Several possible donor livers carry a risk of transmitting diseases, and it is essential to weigh the risks of receiving a potentially unhealthy liver against the dangers of waiting longer for a standard transplant63,64 ( Table 1). A novel study utilized a deep learning model (Dl4jMLP) to analyze over 350,000 UNOS entries and predict short- and long-term survival after liver transplantation, incorporating 23 significant clinical factors. The model showed exceptional performance in both living donor (99.91%) and deceased donor (99.86%) recipients. The long-term survival prediction was above 98% within one year. Interestingly, there was no significant difference by donor type, dispelling assumptions in favor of living donors and facilitating broader use of deceased donor grafts. Deep learning outperformed traditional methods in terms of prediction accuracy.65 ML has also been used to assess hepatic steatosis6668 ( Table 1). In most studies, ML is superior to pathologists’ assessments68,69 ( Table 1).70,71 Narayan et al. developed a computer vision artificial intelligence (CVAI) program. They found an association between donor liver steatosis and EAD that remained significant after adjusting for age, diabetes, MELD score, and other factors (2.9% vs 1.9%, p = 0.02). Additionally, CVAI showed slightly better calibration than pathologists in detecting steatosis.70 The Banff Liver Working Group released recommendations to assess steatosis in biopsies of donor livers. However, they have not been implemented widely so far. Gambella et al. developed a CNN to assess steatosis and compared it with pathologists’ scores. They found that CNN and the scores assigned by pathologists showed greater overlap when the Banff approach was employed compared to pre-Banff recommendations.71 Contrary to the majority of literature, a study in the Republic of Korea used various ML models as well as logistic regression to assess for macrovesicular steatosis and found logistic regression to be the most accurate, with an accuracy of 80%.72 Another study applied AI by integrating transcriptomics and histopathology to evaluate biopsies from donor livers that were initially rejected for transplantation. Findings revealed that many of these rejected livers shared transcriptomic profiles with accepted organs, suggesting they might be viable for transplant.6 These insights highlight AI’s potential to expand the donor pool and enhance organ allocation decisions.

Discussion

Liver transplant is likely an appropriate field for ML since prognosticating cirrhosis involves various factors and comorbidities such as infections, kidney disease, encephalopathy, etc.73 Classically, the Model for End-Stage Liver Disease (MELD) has been used to make decisions regarding LT. However, it does not cover post-transplant outcomes and donor-recipient matching, gaps that researchers are attempting to bridge using ML.74

Given their high accuracy and low cost, ML models have emerged as valuable tools in the diagnosis of liver disease, assessing digital histology images and CT scans to distinguish between fibrosis, as well as analyzing EHRs to detect undiagnosed cirrhosis.7,10,18 AI can help develop predictive models to identify individuals at high risk for cirrhosis based on demographic data, lifestyle factors, and medical history.23 This could permit targeted screening and early intervention. ML algorithms have also been used to recognize patterns and prognosticate cirrhosis with greater accuracy than the MELD score.75

Some of the most significant applications of AI are in evaluating liver transplant candidates and allocating organs for transplantation. ML has proven effective in predicting pre-transplant mortality for both adult and pediatric candidates, with an accuracy surpassing MELD.34 Allocation of organs is based on principles of urgency, utility, and survival benefit, aimed at avoiding futile transplants. While MELD 3.0 prioritizes the sickest patients (urgency), it ignores post-transplant survival (utility). An ideal system would achieve an optimal survival advantage by considering both waitlist and transplanted patient results in a balanced manner. Despite efforts to develop such models, none have been widely utilized due to various limitations, including the improper estimation of survival advantage and the nonconsideration of other primary outcomes and risk factors. Progressing towards a benefit-based allocation model remains a challenge in liver transplantation.76 Identifying factors that predispose patients to adverse outcomes may enable appropriate risk stratification. Similarly, ML can predict post-transplant survival and help prioritize patients who would benefit most from the procedure. AI models have also been used to enhance the diagnosis of post-transplant pneumonia, sepsis, ACE, and Hepatic artery thrombosis (HAT), which can lead to mortality or graft failure.36,37 AI may eventually play a key role in determining transplant eligibility and guiding post-LT management. Moreover, AI can integrate data from multiple sources (e.g., imaging, lab tests, clinical history) to provide a comprehensive assessment of a patient’s condition, ensuring a thorough evaluation before transplantation.69

Notably, AI can aid in optimizing organ allocation by predicting graft survival and efficiently matching donors with recipients. ML models have largely proven better than MELD at predicting survival after organ allocation.62 AI can accurately identify the risk-benefit ratio of accepting a steatotic or possibly infectious graft versus waiting for a transplant.63,64 The swift and accurate results yielded by AI may help expand the pool of donor livers and provide a solution to the unmet demand for liver transplants.

Conclusion

Machine learning (ML) is a potentially significant area in the field of liver transplantation (LT) for the foreseeable future, given its promise for decision-making that may be superior to or even surpass existing algorithms. However, there are challenges to its incorporation into clinical medicines. Machine learning may be less effective when the clinical population differs from the one on which the model was trained. Clinicians are understandably reluctant to leave decisions to autonomous models without a transparent thought process. Unsuitable measures of performance, lack of interpretability, privacy issues, lack of reproducibility, and imbalances in datasets that are used to train AI models have also been cited as shortcomings of ML.77,78 Multicenter randomized clinical trials are warranted to better evaluate the role of AI in cirrhosis and liver transplantation.

Comments on this article Comments (0)

Version 1
VERSION 1 PUBLISHED 01 Sep 2025
Comment
Author details Author details
Competing interests
Grant information
Copyright
Download
 
Export To
metrics
Views Downloads
F1000Research - -
PubMed Central
Data from PMC are received and updated monthly.
- -
Citations
CITE
how to cite this article
Elmahdy M, Ali R, Khanna T et al. Artificial Intelligence in Cirrhosis: Diagnosis, Screening, and Evaluation for Liver Transplantation [version 1; peer review: awaiting peer review]. F1000Research 2025, 14:844 (https://doi.org/10.12688/f1000research.168817.1)
NOTE: If applicable, it is important to ensure the information in square brackets after the title is included in all citations of this article.
track
receive updates on this article
Track an article to receive email alerts on any updates to this article.

Open Peer Review

Current Reviewer Status:
AWAITING PEER REVIEW
AWAITING PEER REVIEW
?
Key to Reviewer Statuses VIEW
ApprovedThe paper is scientifically sound in its current form and only minor, if any, improvements are suggested
Approved with reservations A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.
Not approvedFundamental flaws in the paper seriously undermine the findings and conclusions

Comments on this article Comments (0)

Version 1
VERSION 1 PUBLISHED 01 Sep 2025
Comment
Alongside their report, reviewers assign a status to the article:
Approved - the paper is scientifically sound in its current form and only minor, if any, improvements are suggested
Approved with reservations - A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.
Not approved - fundamental flaws in the paper seriously undermine the findings and conclusions
Sign In
If you've forgotten your password, please enter your email address below and we'll send you instructions on how to reset your password.

The email address should be the one you originally registered with F1000.

Email address not valid, please try again

You registered with F1000 via Google, so we cannot reset your password.

To sign in, please click here.

If you still need help with your Google account password, please click here.

You registered with F1000 via Facebook, so we cannot reset your password.

To sign in, please click here.

If you still need help with your Facebook account password, please click here.

Code not correct, please try again
Email us for further assistance.
Server error, please try again.