Lung Transplantation Advanced Prediction Tool: Determining Recipient's Outcome for a Certain Donor

Pancreas Transplantation Outcome Predictions-PTOP: A Risk Prediction Tool for Pancreas and Pancreas-Kidney Transplants Based on a European Cohort

Background

For patients with complicated type 1 diabetes having, for example, hypoglycemia unawareness and end-stage renal disease because of diabetic nephropathy, combined pancreas and kidney transplantation (PKT) is the therapy of choice. However, the shortage of available grafts and complex impact of risk factors call for individualized, impartial predictions of PKT and pancreas transplantation (PT) outcomes to support physicians in graft acceptance decisions.

Methods

Based on a large European cohort with 3060 PKT and PT performed between 2006 and 2021, the 3 primary patient outcomes time to patient mortality, pancreas graft loss, and kidney graft loss were visualized using Kaplan-Meier survival curves. Multivariable Cox proportional hazards models were developed for 5- and 10-y prediction of outcomes based on 26 risk factors.

Results

Risk factors associated with increased mortality included previous kidney transplants, rescue allocations, longer waiting times, and simultaneous transplants of other organs. Increased pancreas graft loss was positively associated with higher recipient body mass index and donor age and negatively associated with simultaneous transplants of kidneys and other organs. Donor age was also associated with increased kidney graft losses. The multivariable Cox models reported median C-index values were 63% for patient mortality, 62% for pancreas loss, and 55% for kidney loss.

Conclusions

This study provides an online risk tool at https://riskcalc.org/ptop for individual 5- and 10-y post-PKT and PT patient outcomes based on parameters available at the time of graft offer to support critical organ acceptance decisions and encourage external validation in independent populations.

The Year in Cardiothoracic Transplant Anesthesia: Selected Highlights From 2022 Part I: Lung Transplantation

These highlights focus on the research in lung transplantation (LTX) that was published in 2022 and includes the assessment and optimization of candidates for LTX, donor optimization, the use of organs from donation after circulatory death, and outcomes when using marginal or novel donors; recipient factors affecting LTX, including age, disease, the use of extracorporeal life support; and special situations, such as coronavirus disease2019, pediatric LTX, and retransplantation. The remainder of the article focuses on the perioperative management of LTX, including the perioperative risk factors for acute renal failure (acute kidney injury); the incidence and management of phrenic nerve injury, delirium, and pain; and the postoperative management of hyperammonemia, early postoperative infections, and the use of donor-derived cell-free DNA to detect rejection.

Developing machine learning models to predict primary graft dysfunction after lung transplantation

Primary graft dysfunction (PGD) is the leading cause of morbidity and mortality in the first 30 days after lung transplantation. Risk factors for the development of PGD include donor and recipient characteristics, but how multiple variables interact to impact the development of PGD and how clinicians should consider these in making decisions about donor acceptance remain unclear. This was a single-center retrospective cohort study to develop and evaluate machine learning pipelines to predict the development of PGD grade 3 within the first 72 hours of transplantation using donor and recipient variables that are known at the time of donor offer acceptance. Among 576 bilateral lung recipients, 173 (30%) developed PGD grade 3. The cohort underwent a 75% to 25% train-test split, and lasso regression was used to identify 11 variables for model development. A K-nearest neighbor's model showing the best calibration and performance with relatively small confidence intervals was selected as the final predictive model with an area under the receiver operating characteristics curve of 0.65. Machine learning models can predict the risk for development of PGD grade 3 based on data available at the time of donor offer acceptance. This may improve donor-recipient matching and donor utilization in the future.

Machine Learning-Based Prognostic Model for Patients After Lung Transplantation

Importance

Although numerous prognostic factors have been found for patients after lung transplantation (LTx) over the years, an accurate prognostic tool for LTx recipients remains unavailable.

Objective

To develop and validate a prognostic model for predicting overall survival in patients after LTx using random survival forests (RSF), a machine learning algorithm.

Design, Setting, and Participants

This retrospective prognostic study included patients who underwent LTx between January 2017 and December 2020. The LTx recipients were randomly assigned to training and test sets in accordance with a ratio of 7:3. Feature selection was performed using variable importance with bootstrapping resampling. The prognostic model was fitted using the RSF algorithm, and a Cox regression model was set as a benchmark. The integrated area under the curve (iAUC) and integrated Brier score (iBS) were applied to assess model performance in the test set. Data were analyzed from January 2017 to December 2019.

Main Outcomes And Measures

Overall survival in patients after LTx.

Results

A total of 504 patients were eligible for this study, consisting of 353 patients in the training set (mean [SD] age, 55.03 [12.78] years; 235 [66.6%] male patients) and 151 patients in the test set (mean [SD] age, 56.79 [10.95] years; 99 [65.6%] male patients). According to the variable importance of each factor, 16 were selected for the final RSF model, and postoperative extracorporeal membrane oxygenation time was identified as the most valuable factor. The RSF model had excellent performance with an iAUC of 0.879 (95% CI, 0.832-0.921) and an iBS of 0.130 (95% CI, 0.106-0.154). The Cox regression model fitted by the same modeling factors to the RSF model was significantly inferior to the RSF model with an iAUC of 0.658 (95% CI, 0.572-0.747; P < .001) and an iBS of 0.205 (95% CI, 0.176-0.233; P < .001). According to the RSF model predictions, the patients after LTx were stratified into 2 prognostic groups displaying significant difference, with mean overall survival of 52.91 months (95% CI, 48.51-57.32) and 14.83 months (95% CI, 9.44-20.22; log-rank P < .001), respectively.

Conclusions and relevance

In this prognostic study, the findings first demonstrated that RSF could provide more accurate overall survival prediction and remarkable prognostic stratification than the Cox regression model for patients after LTx.

Machine learning-based techniques to improve lung transplantation outcomes and complications: a systematic review

BACKGROUND

Machine learning has been used to develop predictive models to support clinicians in making better and more reliable decisions. The high volume of collected data in the lung transplant process makes it possible to extract hidden patterns by applying machine learning methods. Our study aims to investigate the application of machine learning methods in lung transplantation.

METHOD

A systematic search was conducted in five electronic databases from January 2000 to June 2022. Then, the title, abstracts, and full text of extracted articles were screened based on the PRISMA checklist. Then, eligible articles were selected according to inclusion criteria. The information regarding developed models was extracted from reviewed articles using a data extraction sheet.

RESULTS

Searches yielded 414 citations. Of them, 136 studies were excluded after the title and abstract screening. Finally, 16 articles were determined as eligible studies that met our inclusion criteria. The objectives of eligible articles are classified into eight main categories. The applied machine learning methods include the Support vector machine (SVM) (n = 5, 31.25%) technique, logistic regression (n = 4, 25%), Random Forests (RF) (n = 4, 25%), Bayesian network (BN) (n = 3, 18.75%), linear regression (LR) (n = 3, 18.75%), Decision Tree (DT) (n = 3, 18.75%), neural networks (n = 3, 18.75%), Markov Model (n = 1, 6.25%), KNN (n = 1, 6.25%), K-means (n = 1, 6.25%), Gradient Boosting trees (XGBoost) (n = 1, 6.25%), and Convolutional Neural Network (CNN) (n = 1, 6.25%). Most studies (n = 11) employed more than one machine learning technique or combination of different techniques to make their models. The data obtained from pulmonary function tests were the most used as input variables in predictive model development. Most studies (n = 10) used only post-transplant patient information to develop their models. Also, UNOS was recognized as the most desirable data source in the reviewed articles. In most cases, clinicians succeeded to predict acute diseases incidence after lung transplantation (n = 4) or estimate survival rate (n = 4) by developing machine learning models.

CONCLUSION

The outcomes of these developed prediction models could aid clinicians to make better and more reliable decisions by extracting new knowledge from the huge volume of lung transplantation data.

Establishment of Difficult Caudal Epidural Blockade Prediction Model

Background

We aimed to develop a predictive difficult caudal epidural blockade (pDCEB) model when ultrasound was not available and verified the role of ultrasound in difficult caudal epidural blockade (CEB).

Methods

From October 2018 to March 2019, this study consisted of three phases. First, we prospectively enrolled 202 patients scheduled to undergo caudal epidural anesthesia and assessed risk factors by binary logistic regression to develop the predictive scoring system. Second, we enrolled 87 patients to validate it. The receiver operating characteristic (ROC) curve was used to evaluate the performance of the prediction model. Youden-index was used to determine the cut-off value. Third, we enrolled 68 patients with a high risk of difficult CEB (pDCEB score ≥3) and randomized them into ultrasound and landmark groups to verify the role of ultrasound.

Result

The rate of difficult CEB was 14.98% overall 289 patients. We found a correlation between unclear palpation of the sacral hiatus (OR 9.688) and cornua (OR 4.725), the number of the sacral hiatus by palpation ≥1 (OR 4.451), and history of difficult CEB (OR 39.282) with a higher possibility of difficult CEB. The area under the receiver operating characteristic curve of the pDCEB model involving the aforementioned factors was 0.889 (95% CI, 0.827-0.952) in the development cohort and 0.862 (95% CI, 0.747-0.977) in the validation cohort. For patients with a pDCEB score ≥3, a preprocedure ultrasound scan could reduce the incidence of difficult CEB (55.56% in the Landmark group vs. 9.38% in the ultrasound group, p < 0.001).

Conclusion

This novel pDCEB score, which takes into account palpation of the sacral hiatus/cornua, number of the sacral hiatus by palpation ≥1, and history of difficult CEB, showed a good predictive ability of difficult CEB. The findings suggested that performing an ultrasound scan is essential for patients with a pDCEB score ≥3. Trial registration: No: ChiCTR1800018871, Site URL: https://www.chictr.org.cn/edit.aspx?pid=31875&htm=4; Principal investigator: Jialian Zhao, Date of registration: 2018.10.14.