Measuring the effect of the COVID-19 pandemic on solid organ transplantation

A machine-learning approach to human ex vivo lung perfusion predicts transplantation outcomes and promotes organ utilization

Ex vivo lung perfusion (EVLP) is a data-intensive platform used for the assessment of isolated lungs outside the body for transplantation; however, the integration of artificial intelligence to rapidly interpret the large constellation of clinical data generated during ex vivo assessment remains an unmet need. We developed a machine-learning model, termed InsighTx, to predict post-transplant outcomes using n = 725 EVLP cases. InsighTx model AUROC (area under the receiver operating characteristic curve) was 79 ± 3%, 75 ± 4%, and 85 ± 3% in training and independent test datasets, respectively. Excellent performance was observed in predicting unsuitable lungs for transplantation (AUROC: 90 ± 4%) and transplants with good outcomes (AUROC: 80 ± 4%). In a retrospective and blinded implementation study by EVLP specialists at our institution, InsighTx increased the likelihood of transplanting suitable donor lungs [odds ratio=13; 95% CI:4-45] and decreased the likelihood of transplanting unsuitable donor lungs [odds ratio=0.4; 95%CI:0.16-0.98]. Herein, we provide strong rationale for the adoption of machine-learning algorithms to optimize EVLP assessments and show that InsighTx could potentially lead to a safe increase in transplantation rates.

The effect of the COVID-19 pandemic on deceased and living organ donors in the United States of America

A life-saving treatment, solid organ transplantation (SOT) has transformed the survival and quality of life of patients with end-organ dysfunction. The coronavirus disease (COVID-19) pandemic has impacted the practice of deceased and living donations worldwide by various resource shifting, including healthcare personnel and equipment such as ventilators and bed space. Our work explores the COVID-19 pandemic and global transplant data to create a statistical model for deducing the impact of COVID-19 on living donor and deceased donor transplants in the United States of America (USA). In severely impacted regions, transplant centers need to carefully balance the risks and benefits of performing a transplant during the COVID-19 pandemic. In our statistical model, the COVID cases are used as an explanatory variable (input) to living or deceased donor transplants (output). The model is shown to be statistically accurate for both estimation of the correlation structure, and prediction of future donors. The provided predictions are to be taken as probabilistic assertions, so that for each instant where the prediction is calculated, a statistical measure of accuracy (confidence interval) is provided. The method is tested on both low and high frequency data, that notoriously exhibit a different behavior.

Challenges in liver transplantation in the context of a major pandemic

Coronavirus disease-2019 (COVID-19) has led to a temporary suspension of liver transplant activity across the world and the remodeling of care for patients on the waiting list and transplant recipients with the increasing use of remote consultations. Emerging evidence shows that patients with more advanced liver disease are at increased risk of severe COVID-19 and death, whereas transplant recipients have similar risk with the general population which is mainly driven by age and metabolic comorbidities. Tacrolimus immunosuppression might have a protective role in the post-transplant population. Vaccines that have become rapidly available seem to be safe in liver patients, but the antibody response in transplant patients is likely suboptimal. Most transplant centers were gradually able to resume activity soon after the onset of the pandemic and after modifying their pathways to optimize safety for patients and workforce. Preliminary evidence regarding utilizing grafts from positive donors and/or transplanting recently recovered or infected recipients under certain circumstances is encouraging and may allow offering life-saving transplant to patients at the greatest need. This review summarizes the currently available data on liver transplantation in the context of a major pandemic and discusses areas of uncertainty and future challenges. Lessons learnt from the COVID-19 pandemic might provide invaluable guidance for future pandemics.