Artificial intelligence for prediction of donor liver allograft steatosis and early post-transplantation graft failure

Ethical frontiers in liver transplantation

Liver transplantation represents a pivotal intervention in the management of end-stage liver disease, offering a lifeline to countless patients. Despite significant strides in surgical techniques and organ procurement, ethical dilemmas and debates continue to underscore this life-saving procedure. Navigating the ethical terrain surrounding this complex procedure is hence paramount. Dissecting the nuances of ethical principles of justice, autonomy and beneficence that underpin transplant protocols worldwide, we explore the modern challenges that plaques the world of liver transplantation. We investigate the ethical dimensions of organ transplantation, focusing on allocation, emerging technologies, and decision-making processes. PubMed, Scopus, Web of Science, Embase and Central were searched from database inception to February 29, 2024 using the following keywords: “liver transplant”, “transplantation”, “liver donation”, “liver recipient”, “organ donation” and “ethics”. Information from relevant articles surrounding ethical discussions in the realm of liver transplantation, especially with regards to organ recipients and allocation, organ donation, transplant tourism, new age technologies and developments, were extracted. From the definition of death to the long term follow up of organ recipients, liver transplantation has many ethical quandaries. With new transplant techniques, societal acceptance and perceptions also play a pivotal role. Cultural, religious and regional factors including but not limited to beliefs, wealth and accessibility are extremely influential in public attitudes towards donation, xenotransplantation, stem cell research, and adopting artificial intelligence. Understanding and addressing these perspectives whilst upholding bioethical principles is essential to ensure just distribution and fair allocation of resources. Robust regulatory oversight for ethical sourcing of organs, ensuring good patient selection and transplant techniques, and high-quality long-term surveillance to mitigate risks is essential. Efforts to promote equitable access to transplantation as well as prioritizing patients with true needs are essential to address disparities. In conclusion, liver transplantation is often the beacon of hope for individuals suffering from end-stage liver disease and improves quality of life. The ethics related to transplantation are complex and multifaceted, considering not just the donor and the recipient, but also the society as a whole.

Artificial intelligence-aided steatosis assessment in donor livers according to the Banff consensus recommendations

OBJECTIVES

Severe macrovesicular steatosis in donor livers is associated with primary graft dysfunction. The Banff Working Group on Liver Allograft Pathology has proposed recommendations for steatosis assessment of donor liver biopsy specimens with a consensus for defining "large droplet fat" (LDF) and a 3-step algorithmic approach.

METHODS

We retrieved slides and initial pathology reports from potential liver donor biopsy specimens from 2010 to 2021. Following the Banff approach, we reevaluated LDF steatosis and employed a computer-assisted manual quantification protocol and artificial intelligence (AI) model for analysis.

RESULTS

In a total of 113 slides from 88 donors, no to mild (<33%) macrovesicular steatosis was reported in 88.5% (100/113) of slides; 8.8% (10/113) was reported as at least moderate steatosis (≥33%) initially. Subsequent pathology evaluation, following the Banff recommendation, revealed that all slides had LDF below 33%, a finding confirmed through computer-assisted manual quantification and an AI model. Correlation coefficients between pathologist and computer-assisted manual quantification, between computer-assisted manual quantification and the AI model, and between the AI model and pathologist were 0.94, 0.88, and 0.81, respectively (P < .0001 for all).

CONCLUSIONS

The 3-step approach proposed by the Banff Working Group on Liver Allograft Pathology may be followed when evaluating steatosis in donor livers. The AI model can provide a rapid and objective assessment of liver steatosis.

Overcoming the hurdles of steatotic grafts in liver transplantation: Insights into survival and prognostic factors

With increasing metabolic dysfunction-associated steatotic liver disease, the use of steatotic grafts in liver transplantation (LT) and their impact on postoperative graft survival (GS) needs further exploration. Analyzing adult LT recipient data (2002-2022) from the United Network for Organ Sharing database, outcomes of LT using steatotic (≥30% macrosteatosis) and nonsteatotic donor livers, donors after circulatory death, and standard-risk older donors (age 45-50) were compared. GS predictors were evaluated using Kaplan-Meier and Cox regression analyses. Of the 35,345 LT donors, 8.9% (3,155) were fatty livers. The initial 30-day postoperative period revealed significant challenges with fatty livers, demonstrating inferior GS. However, the GS discrepancy between fatty and nonfatty livers subsided over time ( p = 0.10 at 5 y). Long-term GS outcomes showed comparable or even superior results in fatty livers relative to nonsteatotic livers, conditional on surviving the initial 90 postoperative days ( p = 0.90 at 1 y) or 1 year ( p = 0.03 at 5 y). In the multivariable Cox regression analysis, the high body surface area (BSA) ratio (≥1.1) (HR 1.42, p = 0.02), calculated as donor BSA divided by recipient BSA, long cold ischemic time (≥6.5 h) (HR 1.72, p < 0.01), and recipient medical condition (intensive care unit hospitalization) (HR 2.53, p < 0.01) emerged as significant adverse prognostic factors. Young (<40 y) fatty donors showed a high BSA ratio, diabetes, and intensive care unit hospitalization as significant indicators of a worse prognosis ( p < 0.01). Our study emphasizes the initial postoperative 30-day survival challenge in LT using fatty livers. However, with careful donor-recipient matching, for example, avoiding the use of steatotic donors with long cold ischemic time and high BSA ratios for recipients in the intensive care unit, it is possible to enhance immediate GS, and in a longer time, outcomes comparable to those using nonfatty livers, donors after circulatory death livers, or standard-risk older donors can be anticipated. These novel insights into decision-making criteria for steatotic liver use provide invaluable guidance for clinicians.

Artificial Intelligence Advances in Transplant Pathology

Transplant pathology plays a critical role in ensuring that transplanted organs function properly and the immune systems of the recipients do not reject them. To improve outcomes for transplant recipients, accurate diagnosis and timely treatment are essential. Recent advances in artificial intelligence (AI)-empowered digital pathology could help monitor allograft rejection and weaning of immunosuppressive drugs. To explore the role of AI in transplant pathology, we conducted a systematic search of electronic databases from January 2010 to April 2023. The PRISMA checklist was used as a guide for screening article titles, abstracts, and full texts, and we selected articles that met our inclusion criteria. Through this search, we identified 68 articles from multiple databases. After careful screening, only 14 articles were included based on title and abstract. Our review focuses on the AI approaches applied to four transplant organs: heart, lungs, liver, and kidneys. Specifically, we found that several deep learning-based AI models have been developed to analyze digital pathology slides of biopsy specimens from transplant organs. The use of AI models could improve clinicians' decision-making capabilities and reduce diagnostic variability. In conclusion, our review highlights the advancements and limitations of AI in transplant pathology. We believe that these AI technologies have the potential to significantly improve transplant outcomes and pave the way for future advancements in this field.

Development of a portable device to quantify hepatic steatosis in potential donor livers

An accurate estimation of liver fat content is necessary to predict how a donated liver will function after transplantation. Currently, a pathologist needs to be available at all hours of the day, even at remote hospitals, when an organ donor is procured. Even among expert pathologists, the estimation of liver fat content is operator-dependent. Here we describe the development of a low-cost, end-to-end artificial intelligence platform to evaluate liver fat content on a donor liver biopsy slide in real-time. The hardware includes a high-resolution camera, display, and GPU to acquire and process donor liver biopsy slides. A deep learning model was trained to label and quantify fat globules in liver tissue. The algorithm was deployed on the device to enable real-time quantification and characterization of fat content for transplant decision-making. This information is displayed on the device and can also be sent to a cloud platform for further analysis.

Impact of Donor Liver Macrovesicular Steatosis on Deceased Donor Yield and Posttransplant Outcome

BACKGROUND

The Scientific Registry of Transplant Recipients (SRTR) had not traditionally considered biopsy results in risk-adjustment models, yet biopsy results may influence outcomes and thus decisions regarding organ acceptance.

METHODS

Using SRTR data, which includes data on all donors, waitlisted candidates, and transplant recipients in the United States, we assessed (1) the impact of macrovesicular steatosis on deceased donor yield (defined as number of livers transplanted per donor) and 1-y posttransplant graft failure and (2) the effect of incorporating this variable into existing SRTR risk-adjustment models.

RESULTS

There were 21 559 donors with any recovered organ and 17 801 liver transplant recipients included for analysis. Increasing levels of macrovesicular steatosis on donor liver biopsy predicted lower organ yield: ≥31% macrovesicular steatosis on liver biopsy was associated with 87% to 95% lower odds of utilization, with 55% of these livers being discarded. The hazard ratio for graft failure with these livers was 1.53, compared with those with no pretransplant liver biopsy and 0% to 10% steatosis. There was minimal change on organ procurement organization-specific deceased donor yield or program-specific posttransplant outcome assessments when macrovesicular steatosis was added to the risk-adjustment models.

CONCLUSIONS

Donor livers with macrovesicular steatosis are disproportionately not transplanted relative to their risk for graft failure. To avoid undue risk aversion, SRTR now accounts for macrovesicular steatosis in the SRTR risk-adjustment models to help facilitate use of these higher-risk organs. Increased recognition of this variable may also encourage further efforts to standardize the reporting of liver biopsy results.

A Novel Digital Algorithm for Identifying Liver Steatosis Using Smartphone-Captured Images

Access to lifesaving liver transplantation is limited by a severe organ shortage. One factor contributing to the shortage is the high rate of discard in livers with histologic steatosis. Livers with <30% macrosteatosis are generally considered safe for transplant. However, histologic assessment of steatosis by a pathologist remains subjective and is often limited by image quality. Here, we address this bottleneck by creating an automated digital algorithm for calculating histologic steatosis using only images of liver biopsy histology obtained with a smartphone.

Clinical Applications of Artificial Intelligence-An Updated Overview

Artificial intelligence has the potential to revolutionize modern society in all its aspects. Encouraged by the variety and vast amount of data that can be gathered from patients (e.g., medical images, text, and electronic health records), researchers have recently increased their interest in developing AI solutions for clinical care. Moreover, a diverse repertoire of methods can be chosen towards creating performant models for use in medical applications, ranging from disease prediction, diagnosis, and prognosis to opting for the most appropriate treatment for an individual patient. In this respect, the present paper aims to review the advancements reported at the convergence of AI and clinical care. Thus, this work presents AI clinical applications in a comprehensive manner, discussing the recent literature studies classified according to medical specialties. In addition, the challenges and limitations hindering AI integration in the clinical setting are further pointed out.