Machine Learning Models to Predict Major Adverse Cardiovascular Events After Orthotopic Liver Transplantation: A Cohort Study

LightGBM outperforms other machine learning techniques in predicting graft failure after liver transplantation: Creation of a predictive model through large-scale analysis

BACKGROUND

The incidence of graft failure following liver transplantation (LTx) is consistent. While traditional risk scores for LTx have limited accuracy, the potential of machine learning (ML) in this area remains uncertain, despite its promise in other transplant domains. This study aims to determine ML's predictive limitations in LTx by replicating methods used in previous heart transplant research.

METHODS

This study utilized the UNOS STAR database, selecting 64,384 adult patients who underwent LTx between 2010 and 2020. Gradient boosting models (XGBoost and LightGBM) were used to predict 14, 30, and 90-day graft failure compared to conventional logistic regression model. Models were evaluated using both shuffled and rolling cross-validation (CV) methodologies. Model performance was assessed using the AUC across validation iterations.

RESULTS

In a study comparing predictive models for 14-day, 30-day and 90-day graft survival, LightGBM consistently outperformed other models, achieving the highest AUC of.740,.722, and.700 in shuffled CV methods. However, in rolling CV the accuracy of the model declined across every ML algorithm. The analysis revealed influential factors for graft survival prediction across all models, including total bilirubin, medical condition, recipient age, and donor AST, among others. Several features like donor age and recipient diabetes history were important in two out of three models.

CONCLUSIONS

LightGBM enhances short-term graft survival predictions post-LTx. However, due to changing medical practices and selection criteria, continuous model evaluation is essential. Future studies should focus on temporal variations, clinical implications, and ensure model transparency for broader medical utility.

Predicting major adverse cardiovascular events after orthotopic liver transplantation using a supervised machine learning model: A cohort study

BACKGROUND

Liver transplant (LT) patients have become older and sicker. The rate of post-LT major adverse cardiovascular events (MACE) has increased, and this in turn raises 30-d post-LT mortality. Noninvasive cardiac stress testing loses accuracy when applied to pre-LT cirrhotic patients.

AIM

To assess the feasibility and accuracy of a machine learning model used to predict post-LT MACE in a regional cohort.

METHODS

This retrospective cohort study involved 575 LT patients from a Southern Brazilian academic center. We developed a predictive model for post-LT MACE (defined as a composite outcome of stroke, new-onset heart failure, severe arrhythmia, and myocardial infarction) using the extreme gradient boosting (XGBoost) machine learning model. We addressed missing data (below 20%) for relevant variables using the k-nearest neighbor imputation method, calculating the mean from the ten nearest neighbors for each case. The modeling dataset included 83 features, encompassing patient and laboratory data, cirrhosis complications, and pre-LT cardiac assessments. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC). We also employed Shapley additive explanations (SHAP) to interpret feature impacts. The dataset was split into training (75%) and testing (25%) sets. Calibration was evaluated using the Brier score. We followed Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis guidelines for reporting. Scikit-learn and SHAP in Python 3 were used for all analyses. The supplementary material includes code for model development and a user-friendly online MACE prediction calculator.

RESULTS

Of the 537 included patients, 23 (4.46%) developed in-hospital MACE, with a mean age at transplantation of 52.9 years. The majority, 66.1%, were male. The XGBoost model achieved an impressive AUROC of 0.89 during the training stage. This model exhibited accuracy, precision, recall, and F1-score values of 0.84, 0.85, 0.80, and 0.79, respectively. Calibration, as assessed by the Brier score, indicated excellent model calibration with a score of 0.07. Furthermore, SHAP values highlighted the significance of certain variables in predicting postoperative MACE, with negative noninvasive cardiac stress testing, use of nonselective beta-blockers, direct bilirubin levels, blood type O, and dynamic alterations on myocardial perfusion scintigraphy being the most influential factors at the cohort-wide level. These results highlight the predictive capability of our XGBoost model in assessing the risk of post-LT MACE, making it a valuable tool for clinical practice.

CONCLUSION

Our study successfully assessed the feasibility and accuracy of the XGBoost machine learning model in predicting post-LT MACE, using both cardiovascular and hepatic variables. The model demonstrated impressive performance, aligning with literature findings, and exhibited excellent calibration. Notably, our cautious approach to prevent overfitting and data leakage suggests the stability of results when applied to prospective data, reinforcing the model's value as a reliable tool for predicting post-LT MACE in clinical practice.

Machine learning prediction of major adverse cardiac events after elective bariatric surgery

BACKGROUND

Machine learning (ML) is an emerging technology with the potential to predict and improve clinical outcomes including adverse events, based on complex pattern recognition. Major adverse cardiac events (MACE) after bariatric surgery have an incidence of 0.1% but carry significant morbidity and mortality. Prior studies have investigated these events using traditional statistical methods, however, studies reporting ML for MACE prediction in bariatric surgery remain limited. As such, the objective of this study was to evaluate and compare MACE prediction models in bariatric surgery using traditional statistical methods and ML.

METHODS

Cross-sectional study of the MBSAQIP database, from 2015 to 2019. A binary-outcome MACE prediction model was generated using three different modeling methods: (1) main-effects-only logistic regression, (2) neural network with a single hidden layer, and (3) XGBoost model with a max depth of 3. The same set of predictor variables and random split of the total data (50/50) were used to train and validate each model. Overall performance was compared based on the area under the receiver operating curve (AUC).

RESULTS

A total of 755,506 patients were included, of which 0.1% experienced MACE. Of the total sample, 79.6% were female, 47.8% had hypertension, 26.2% had diabetes, 23.7% had hyperlipidemia, 8.4% used tobacco within 1 year, 1.9% had previous percutaneous cardiac intervention, 1.2% had a history of myocardial infarction, 1.1% had previous cardiac surgery, and 0.6% had renal insufficiency. The AUC for the three different MACE prediction models was: 0.790 for logistic regression, 0.798 for neural network and 0.787 for XGBoost. While the AUC implies similar discriminant function, the risk prediction histogram for the neural network shifted in a smoother fashion.

CONCLUSION

The ML models developed achieved good discriminant function in predicting MACE. ML can help clinicians with patient selection and identify individuals who may be at elevated risk for MACE after bariatric surgery.

Clinical Deployment of Machine Learning Tools in Transplant Medicine: What Does the Future Hold?

Medical applications of machine learning (ML) have shown promise in analyzing patient data to support clinical decision-making and provide patient-specific outcomes. In transplantation, several applications of ML exist which include pretransplant: patient prioritization, donor-recipient matching, organ allocation, and posttransplant outcomes. Numerous studies have shown the development and utility of ML models, which have the potential to augment transplant medicine. Despite increasing efforts to develop robust ML models for clinical use, very few of these tools are deployed in the healthcare setting. Here, we summarize the current applications of ML in transplant and discuss a potential clinical deployment framework using examples in organ transplantation. We identified that creating an interdisciplinary team, curating a reliable dataset, addressing the barriers to implementation, and understanding current clinical evaluation models could help in deploying ML models into the transplant clinic setting.

Screening Modalities for Coronary Artery Disease in Liver Transplant Candidates: A Review of the Literature

Patients with cirrhosis undergoing liver transplant (LT) are at high risk of postoperative cardiopulmonary complications. It is known that patients with coronary artery disease (CAD) have greater rates of post-LT morbidity and mortality than patients without CAD. Thus, identifying significant CAD in LT candidates is of the utmost importance to optimize survival posttransplant. Consensus is lacking on the ideal screening test for CAD in LT candidates. Traditional exercise and many pharmacologic stress tests are impractical and inaccurate in patients with cirrhosis due to their unique physiology. The purpose of this review is to describe different screening modalities for CAD among LT candidates. The background, diagnostic accuracy, and limitations of each screening modality are described to achieve this goal.

Reappraisal of Donor Age in Liver Transplantation: NASH as a Potential Target to Safely Utilize Old Liver Grafts

BACKGROUND

With the chronic shortage of donated organs, expanding the indications for liver transplantation (LT) from older donors is critical. Nonalcoholic steatohepatitis (NASH) stands out because of its unique systemic pathogenesis and high recurrence rate, both of which might make donor selection less decisive. The present study aims to investigate the usefulness of old donors in LT for NASH patients.

METHODS

The retrospective cohort study was conducted using the Scientific Registry Transplant Recipient database. The cohort was divided into 3 categories according to donor age: young (aged 16-35), middle-aged (36-59), and old donors (60-). Multivariable and Kaplan-Meier analyses were performed to compare the risk of donor age on graft survival (GS).

RESULTS

A total of 67 973 primary adult donation-after-brain-death LTs (2002-2016) were eligible for analysis. The multivariable analysis showed a reduced impact of donor age on GS for the NASH cohort (adjusted hazard ratio = 1.13, 95% confidence interval, 1.00-1.27), comparing old to middle-aged donors. If the cohort was limited to NASH recipients plus 1 of the following, recipient age ≥60, body mass index <30, or Model of End Stage Liver Disease score <30, adjusted hazard ratios were even smaller (0.99 [0.84-1.15], 0.92 [0.75-1.13], or 1.04 [0.91-1.19], respectively). Kaplan-Meier analysis revealed no significant differences in overall GS between old- and middle-aged donors in these subgroups (P = 0.86, 0.28, and 0.11, respectively).

CONCLUSIONS

Donor age was less influential for overall GS in NASH cohort. Remarkably, old donors were equivalent to middle-aged donors in subgroups of recipient age ≥60, recipient body mass index <30, or Model of End Stage Liver Disease score <30.

Artificial Intelligence-enabled Decision Support in Surgery: State-of-the-art and Future Directions

OBJECTIVE

To summarize state-of-the-art artificial intelligence-enabled decision support in surgery and to quantify deficiencies in scientific rigor and reporting.

BACKGROUND

To positively affect surgical care, decision-support models must exceed current reporting guideline requirements by performing external and real-time validation, enrolling adequate sample sizes, reporting model precision, assessing performance across vulnerable populations, and achieving clinical implementation; the degree to which published models meet these criteria is unknown.

METHODS

Embase, PubMed, and MEDLINE databases were searched from their inception to September 21, 2022 for articles describing artificial intelligence-enabled decision support in surgery that uses preoperative or intraoperative data elements to predict complications within 90 days of surgery. Scientific rigor and reporting criteria were assessed and reported according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews guidelines.

RESULTS

Sample size ranged from 163-2,882,526, with 8/36 articles (22.2%) featuring sample sizes of less than 2000; 7 of these 8 articles (87.5%) had below-average (<0.83) area under the receiver operating characteristic or accuracy. Overall, 29 articles (80.6%) performed internal validation only, 5 (13.8%) performed external validation, and 2 (5.6%) performed real-time validation. Twenty-three articles (63.9%) reported precision. No articles reported performance across sociodemographic categories. Thirteen articles (36.1%) presented a framework that could be used for clinical implementation; none assessed clinical implementation efficacy.

CONCLUSIONS

Artificial intelligence-enabled decision support in surgery is limited by reliance on internal validation, small sample sizes that risk overfitting and sacrifice predictive performance, and failure to report confidence intervals, precision, equity analyses, and clinical implementation. Researchers should strive to improve scientific quality.

Artificial intelligence, machine learning, and deep learning in liver transplantation

Liver transplantation (LT) is a life-saving treatment for individuals with end-stage liver disease. The management of LT recipients is complex, predominantly because of the need to consider demographic, clinical, laboratory, pathology, imaging, and omics data in the development of an appropriate treatment plan. Current methods to collate clinical information are susceptible to some degree of subjectivity; thus, clinical decision-making in LT could benefit from the data-driven approach offered by artificial intelligence (AI). Machine learning and deep learning could be applied in both the pre- and post-LT settings. Some examples of AI applications pre-transplant include optimising transplant candidacy decision-making and donor-recipient matching to reduce waitlist mortality and improve post-transplant outcomes. In the post-LT setting, AI could help guide the management of LT recipients, particularly by predicting patient and graft survival, along with identifying risk factors for disease recurrence and other associated complications. Although AI shows promise in medicine, there are limitations to its clinical deployment which include dataset imbalances for model training, data privacy issues, and a lack of available research practices to benchmark model performance in the real world. Overall, AI tools have the potential to enhance personalised clinical decision-making, especially in the context of liver transplant medicine.

Non-Alcoholic Fatty Liver Disease, Heart Failure, and Long-Term Mortality: Insights From the National Health and Nutrition Examination Survey

OBJECTIVE

To evaluate the association between non-alcoholic fatty liver disease (NAFLD), heart failure (HF), and all-cause mortality.

BACKGROUND

Both NAFLD and HF are increasing in prevalence due to shared risk factors.

METHODS

We used data from the National Health and Nutrition Examination Survey (NHANES) 2005-2018 to identify non-pregnant individuals aged ≥20 years with HF and NAFLD and linked with the cause of death data from the National Center for Health Statistics. The associations between NAFLD, HF, and all-cause mortality were assessed using logistic regression and Cox proportional hazard modeling as appropriate.

RESULTS

There were 82,358,893 weighted eligible participants of whom 3,833,667 (4.7%) had NAFLD. The mean (SE) age was 51.5 (0.35) years, 45.1% women, 63.0% Non-Hispanic White and 11.8% Non-Hispanic Black. Cardiovascular comorbidities were more common in participants with NAFLD; they were more likely to have hypertension (81.7% vs 53.5%), diabetes (65.1% vs 17.1%), stroke (7.3% vs 4.1%), coronary artery disease (14.9% vs 8.4%), or HF (10.5% v s 3.5%) compared with participants without NAFLD. In multivariate logistic regression models adjusting for age, race/ethnicity and sex, participants with NAFLD were 3.5 times more likely to have HF [aOR, 95% CI: 3.47 (1.98-6.06)]. Older age, male sex, presence of diabetes and coronary artery disease were associated with higher odds of HF in participants with established NAFLD. At the end of the follow-up period, participants with NAFLD had higher all-cause mortality compared with participants without NAFLD [HR(95% CI): 1.93 (1.24-2.99), p<0.001].

CONCLUSION

In this analysis of US adults, ambulatory participants with NAFLD were ∼3.5 times more likely to have HF, and twice as likely to experience mortality compared with participants without NAFLD. Further studies are needed to identify the possible linkage between NAFLD and HF beyond the shared risk factor pathogenesis.

Application of machine learning in liver transplantation: a review

BACKGROUND

Machine learning (ML) has been increasingly applied in the health-care and liver transplant setting. The demand for liver transplantation continues to expand on an international scale, and with advanced aging and complex comorbidities, many challenges throughout the transplantation decision-making process must be better addressed. There exist massive datasets with hidden, non-linear relationships between demographic, clinical, laboratory, genetic, and imaging parameters that conventional methods fail to capitalize on when reviewing their predictive potential. Pre-transplant challenges include addressing efficacies of liver segmentation, hepatic steatosis assessment, and graft allocation. Post-transplant applications include predicting patient survival, graft rejection and failure, and post-operative morbidity risk.

AIM

In this review, we describe a comprehensive summary of ML applications in liver transplantation including the clinical context and how to overcome challenges for clinical implementation.

METHODS

Twenty-nine articles were identified from Ovid MEDLINE, MEDLINE Epub Ahead of Print and In-Process and Other Non-Indexed Citations, Embase, Cochrane Database of Systematic Reviews, and Cochrane Central Register of Controlled Trials.

CONCLUSION

ML is vastly interrogated in liver transplantation with promising applications in pre- and post-transplant settings. Although challenges exist including site-specific training requirements, the demand for more multi-center studies, and optimization hurdles for clinical interpretability, the powerful potential of ML merits further exploration to enhance patient care.