The promise of machine learning applications in solid organ transplantation

Machine learning in solid organ transplantation: Charting the evolving landscape

BACKGROUND

Machine learning (ML), a major branch of artificial intelligence, has not only demonstrated the potential to significantly improve numerous sectors of healthcare but has also made significant contributions to the field of solid organ transplantation. ML provides revolutionary opportunities in areas such as donor-recipient matching, post-transplant monitoring, and patient care by automatically analyzing large amounts of data, identifying patterns, and forecasting outcomes.

AIM

To conduct a comprehensive bibliometric analysis of publications on the use of ML in transplantation to understand current research trends and their implications.

METHODS

On July 18, a thorough search strategy was used with the Web of Science database. ML and transplantation-related keywords were utilized. With the aid of the VOS viewer application, the identified articles were subjected to bibliometric variable analysis in order to determine publication counts, citation counts, contributing countries, and institutions, among other factors.

RESULTS

Of the 529 articles that were first identified, 427 were deemed relevant for bibliometric analysis. A surge in publications was observed over the last four years, especially after 2018, signifying growing interest in this area. With 209 publications, the United States emerged as the top contributor. Notably, the "Journal of Heart and Lung Transplantation" and the "American Journal of Transplantation" emerged as the leading journals, publishing the highest number of relevant articles. Frequent keyword searches revealed that patient survival, mortality, outcomes, allocation, and risk assessment were significant themes of focus.

CONCLUSION

The growing body of pertinent publications highlights ML's growing presence in the field of solid organ transplantation. This bibliometric analysis highlights the growing importance of ML in transplant research and highlights its exciting potential to change medical practices and enhance patient outcomes. Encouraging collaboration between significant contributors can potentially fast-track advancements in this interdisciplinary domain.

Knowledge domain and frontier trends of artificial intelligence applied in solid organ transplantation: A visualization analysis

BACKGROUND

Solid organ transplantation (SOT) is vital for end-stage organ failure but faces challenges like organ shortage and rejection. Artificial intelligence (AI) offers potential to improve outcomes through better matching, success prediction, and automation. However, the evolution of AI in SOT research remains underexplored. This study uses bibliometric analysis to identify trends, hotspots, and key contributors in the field.

METHODS

821 articles from the Web of Science Core Collection were exported for analysis. Microsoft Excel 2021 was used for descriptive statistics. VOSviewer, CiteSpace, Scimago Graphica, and Biblioshiny were used for bibliometric analysis. The ggalluvial package in R was utilized to create Sankey diagrams, and top articles were selected based on citation count.

RESULTS

This analysis reveals the rapid expansion of AI in SOT. Key areas include robotic surgery, organ allocation, outcome prediction, immunosuppression management, and precision medicine. Robotic surgery has improved transplant outcomes. AI algorithms optimize organ matching and enhance fairness. Machine learning models predict outcomes and guide treatment, while AI-based systems advance personalized immunosuppression. AI in precision medicine, including diagnostics and imaging, is crucial for transplant success.

CONCLUSION

This study highlights AI's transformative potential in SOT, with significant contributions from countries like the USA, Canada, and the UK. Key institutions such as the University of Toronto and the University of Pittsburgh have played vital roles. However, practical challenges like ethical issues, bias, and data integration remain. Fostering international and interdisciplinary collaborations is crucial for overcoming these challenges and accelerating AI's integration into clinical practice, ultimately improving patient outcomes.

The Heart of Transformation: Exploring Artificial Intelligence in Cardiovascular Disease

The application of artificial intelligence (AI) and machine learning (ML) in medicine and healthcare has been extensively explored across various areas. AI and ML can revolutionize cardiovascular disease management by significantly enhancing diagnostic accuracy, disease prediction, workflow optimization, and resource utilization. This review summarizes current advancements in AI and ML concerning cardiovascular disease, including their clinical investigation and use in primary cardiac imaging techniques, common cardiovascular disease categories, clinical research, patient care, and outcome prediction. We analyze and discuss commonly used AI and ML models, algorithms, and methodologies, highlighting their roles in improving clinical outcomes while addressing current limitations and future clinical applications. Furthermore, this review emphasizes the transformative potential of AI and ML in cardiovascular practice by improving clinical decision making, reducing human error, enhancing patient monitoring and support, and creating more efficient healthcare workflows for complex cardiovascular conditions.

Cherry on Top or Real Need? A Review of Explainable Machine Learning in Kidney Transplantation

Research on solid organ transplantation has taken advantage of the substantial acquisition of medical data and the use of artificial intelligence (AI) and machine learning (ML) to answer diagnostic, prognostic, and therapeutic questions for many years. Nevertheless, despite the question of whether AI models add value to traditional modeling approaches, such as regression models, their "black box" nature is one of the factors that have hindered the translation from research to clinical practice. Several techniques that make such models understandable to humans were developed with the promise of increasing transparency in the support of medical decision-making. These techniques should help AI to close the gap between theory and practice by yielding trust in the model by doctors and patients, allowing model auditing, and facilitating compliance with emergent AI regulations. But is this also happening in the field of kidney transplantation? This review reports the use and explanation of "black box" models to diagnose and predict kidney allograft rejection, delayed graft function, graft failure, and other related outcomes after kidney transplantation. In particular, we emphasize the discussion on the need (or not) to explain ML models for biological discovery and clinical implementation in kidney transplantation. We also discuss promising future research paths for these computational tools.

Model multifactor analysis of soil heavy metal pollution on plant germination in Southeast Chengdu, China: Based on redundancy analysis, factor detector, and XGBoost-SHAP

This study assessed the levels of soil heavy metal pollution in agricultural land in southeastern Chengdu and its effects on the germination stage of higher plants. Through extensive soil sampling and laboratory analyses, 15 soil environmental factors were measured, including soil density, porosity, pH, field moisture capacity (FMC), calcium carbonate (CaCO3), and heavy metals such as arsenic (As) and cadmium (Cd). Acute toxicity tests were performed on sorghum (Sorghum bicolor) and Brassica napus (Brassica napus var. napus). The results of the geo-accumulation index (Igeo) and enrichment factor (EF) analyses indicate a higher risk of pollution and enrichment of As and Cd in the study area, with relatively lower risks for other heavy metals. Additionally, the current soil heavy metal concentrations inhibited the growth of sorghum and Brassica napus shoots and roots during the germination stage. Redundancy analysis (RDA), factor detector, and XGBoost-SHAP models identified the As, Cd, FMC, and CaCO3 contents, soil density, and porosity as the primary factors influencing plant growth. Among these factors, FMC, porosity, and Cd were found to promote plant growth, whereas soil density and As demonstrated inhibitory effects. CaCO3 had a dual effect, initially promoting growth but later inhibiting it as its concentration increased. Further analysis revealed that Brassica napus is more sensitive to soil environmental factors than sorghum, particularly to Cd and As, while sorghum has greater tolerance. Moreover, roots were found to be more sensitive than shoots to soil environmental factors, with roots being influenced primarily by physical factors such as FMC and soil density, whereas shoots were affected primarily by chemical factors such as As and Cd. This study addresses the significant lack of data regarding the impact of soil heavy metal concentrations on plant growth in southeastern Chengdu, providing a scientific basis for regional environmental monitoring, soil remediation, and plant cultivation optimization.

The Use of Machine Learning in the Diagnosis of Kidney Allograft Rejection: Current Knowledge and Applications

Kidney allograft rejection is one of the main limitations to long-term kidney transplant survival. The diagnostic gold standard for detecting rejection is a kidney biopsy, an invasive procedure that can often give imprecise results due to complex diagnostic criteria and high interobserver variability. In recent years, several additional diagnostic approaches to rejection have been investigated, some of them with the aid of machine learning (ML). In this review, we addressed studies that investigated the detection of kidney allograft rejection over the last decade using various ML algorithms. Various ML techniques were used in three main categories: (a) histopathologic assessment of kidney tissue with the aim to improve the diagnostic accuracy of a kidney biopsy, (b) assessment of gene expression in rejected kidney tissue or peripheral blood and the development of diagnostic classifiers based on these data, (c) radiologic assessment of kidney tissue using diffusion-weighted magnetic resonance imaging and the construction of a computer-aided diagnostic system. In histopathology, ML algorithms could serve as a support to the pathologist to avoid misclassifications and overcome interobserver variability. Diagnostic platforms based on biopsy-based transcripts serve as a supplement to a kidney biopsy, especially in cases where histopathologic diagnosis is inconclusive. ML models based on radiologic evaluation or gene signature in peripheral blood may be useful in cases where kidney biopsy is contraindicated in addition to other non-invasive biomarkers. The implementation of ML-based diagnostic methods is usually slow and undertaken with caution considering ethical and legal issues. In summary, the approach to the diagnosis of rejection should be individualized and based on all available diagnostic tools (including ML-based), leaving the responsibility for over- and under-treatment in the hands of the clinician.

Advanced Prediction of Glomerular Filtration Rate After Kidney Transplantation Using Gradient Boosting Techniques

OBJECTIVES

Clinicians often face uncertainty when interpreting whether a decline in estimated glomerular filtration rate is within the patient's expected range of fluctuation or if the decline signals a substantial deviation. Thus, accurate predictions of glomerular filtration rate can be an early warning system, prompting timely interventions, such as biopsies to preclude early graft rejection and adjustments in immunosuppression. Traditional models, encompassing linear and conventional methods, typically struggle with variabilities and complexities in posttransplant data.

MATERIALS AND METHODS

We evaluated the efficacy of a gradient boosting model in predicting posttransplant glomerular filtration rate, to potentially enhance accuracy over traditional prediction approaches. Our patient dataset included 68 pediatric patients aged 1 to 18 years who underwent kidney transplant between 2017 and 2023 at Baskent University Hospital (Ankara, Turkey). The dataset comprised 2285 glomerular filtration rate measurements, along with patient demographics and transplant-related data. For our model, we included "days to transplant" (glomerular filtration rate values pretransplant), "days from transplant" (glomerular filtration rate values up to 7 days posttransplant), patient age, sex, and donor types. We divided the dataset into a training set (70%) and a test set (30%). To evaluate model performance, we used mean absolute error and root mean squared error, with a focus on the accuracy of glomerular filtration rate predictions at various posttransplant stages.

RESULTS

In the training set, the gradient boosting model demonstrated a significant improvement in prediction accuracy, achieving an mean absolute error of ~5.64 mL/min/1.73 m².

CONCLUSIONS

Our model underscored the promise of advanced machine learning techniques in refining prediction of glomerular filtration rate after kidney transplant. With its augmented precision, the model can support clinicians in making informed decisions regarding early biopsies and interventions, thus highlighting the vital role of sophisticated analytical methods in medical prognosis and the monitoring of pediatric patient care.

The emerging role of generative artificial intelligence in transplant medicine

Generative artificial intelligence (AI), a subset of machine learning that creates new content based on training data, has witnessed tremendous advances in recent years. Practical applications have been identified in health care in general, and there is significant opportunity in transplant medicine for generative AI to simplify tasks in research, medical education, and clinical practice. In addition, patients stand to benefit from patient education that is more readily provided by generative AI applications. This review aims to catalyze the development and adoption of generative AI in transplantation by introducing basic AI and generative AI concepts to the transplant clinician and summarizing its current and potential applications within the field. We provide an overview of applications to the clinician, researcher, educator, and patient. We also highlight the challenges involved in bringing these applications to the bedside and need for ongoing refinement of generative AI applications to sustainably augment the transplantation field.

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.

Predicting Donor Selection and Multi-Organ Transplantation within Organ Procurement Organizations Using Machine Learning

Organ procurement organizations (OPOs) play a crucial role in the field of organ transplantation, serving as key intermediaries in the process of organ donation. However, despite their vital function, there exists a pressing issue of transparency within the organ allocation process. This opacity not only impedes the overall effectiveness of OPOs but also raises ethical and societal concerns regarding organ distribution. This study utilizes the recently published ORCHID dataset, containing 133,101 records of organ donor referrals, to understand organ procurement and donor selection strategies in OPOs using machine learning (ML). We developed seven ML classification models to predict donor selection and the likelihood of at least four organs being suitable for transplantation, in line with established definitions of multi-organ transplantation. The models demonstrated variable recall values for donor selection, ranging between 0.62 and 0.80, while achieving consistently high performance across other evaluation metrics, notably with AUC values exceeding 0.95. Particularly in the context of multi-organ transplant predictions, the models exhibited remarkable effectiveness, with recall values spanning from 0.88 to 0.98 and AUC metrics consistently above 0.97. Administrative milestones and particular organ transplants were identified as key determinants in the organ allocation process. This study's findings suggest significant opportunities to improve organ allocation strategies by focusing on the optimization of administrative practices, highlighting their substantial impact on transplantation success rates.

Assessment of inflammatory suppression and fibroblast infiltration in tissue remodelling by supercritical CO2 acellular dermal matrix (scADM) utilizing Sprague Dawley models

Human skin-derived ECM aids cell functions but can trigger immune reactions; therefore it is addressed through decellularization. Acellular dermal matrices (ADMs), known for their regenerative properties, are used in tissue and organ regeneration. ADMs now play a key role in plastic and reconstructive surgery, enhancing aesthetics and reducing capsular contracture risk. Innovative decellularization with supercritical carbon dioxide preserves ECM quality for clinical use. The study investigated the cytotoxicity, biocompatibility, and anti-inflammatory properties of supercritical CO2 acellular dermal matrix (scADM) in vivo based on Sprague Dawley rat models. Initial experiments in vitro with fibroblast cells confirmed the non-toxic nature of scADM and demonstrated cell infiltration into scADMs after incubation. Subsequent tests in vitro revealed the ability of scADM to suppress inflammation induced by lipopolysaccharides (LPS) presenting by the reduction of pro-inflammatory cytokines TNF-α, IL-6, IL-1β, and MCP-1. In the in vivo model, histological assessment of implanted scADMs in 6 months revealed a decrease in inflammatory cells, confirmed further by the biomarkers of inflammation in immunofluorescence staining. Besides, an increase in fibroblast infiltration and collagen formation was observed in histological staining, which was supported by various biomarkers of fibroblasts. Moreover, the study demonstrated vascularization and macrophage polarization, depicting increased endothelial cell formation. Alteration of matrix metalloproteinases (MMPs) was analyzed by RT-PCR, indicating the reduction of MMP2, MMP3, and MMP9 levels over time. Simultaneously, an increase in collagen deposition of collagen I and collagen III was observed, verified in immunofluorescent staining, RT-PCR, and western blotting. Overall, the findings suggested that scADMs offer significant benefits in improving outcomes in implant-based procedures as well as soft tissue substitution.

The 2022 Banff Meeting Lung Report

The Lung Session of the 2022 16th Banff Foundation for Allograft Pathology Conference-held in Banff, Alberta-focused on non-rejection lung allograft pathology and novel technologies for the detection of allograft injury. A multidisciplinary panel reviewed the state-of-the-art of current histopathologic entities, serologic studies, and molecular practices, as well as novel applications of digital pathology with artificial intelligence, gene expression analysis, and quantitative image analysis of chest computerized tomography. Current states of need as well as prospective integration of the aforementioned tools and technologies for complete assessment of allograft injury and its impact on lung transplant outcomes were discussed. Key conclusions from the discussion were: (1) recognition of limitations in current standard of care assessment of lung allograft dysfunction; (2) agreement on the need for a consensus regarding the standardized approach to the collection and assessment of pathologic data, inclusive of all lesions associated with graft outcome (eg, non-rejection pathology); and (3) optimism regarding promising novel diagnostic modalities, especially minimally invasive, which should be integrated into large, prospective multicenter studies to further evaluate their utility in clinical practice for directing personalized therapies to improve graft outcomes.

Radiomics in Kidney Transplantation: A Scoping Review of Current Applications, Limitations, and Future Directions

Radiomics is increasingly applied to the diagnosis, management, and outcome prediction of various urological conditions. The purpose of this scoping review is to evaluate the current evidence of the application of radiomics in kidney transplantation, especially its utility in diagnostics and therapeutics. An electronic literature search on radiomics in the setting of transplantation was conducted on PubMed, EMBASE, and Scopus from inception to September 23, 2022. A total of 16 studies were included. The most widely studied clinical utility of radiomics in kidney transplantation is its use as an adjunct to diagnose rejection, potentially reducing the need for unnecessary biopsies or guiding decisions for earlier biopsies to optimize graft survival. Technology such as optical coherence tomography is a noninvasive procedure to build high-resolution optical cross-section images of the kidney cortex in situ and in real time, which can provide histopathological information of donor kidney candidates for transplantation, and to predict posttransplant function. This review shows that, although radiomics in kidney transplants is still in its infancy, it has the potential for large-scale implementation. Its greatest potential lies in the correlation with conventional established diagnostic evaluation for living donors and potential in predicting and detecting rejection postoperatively.

Recipient Pericardial Apolipoprotein Levels Might Be an Indicator of Worse Outcomes after Orthotopic Heart Transplantation

BACKGROUND

End-stage heart failure (ESHF) leads to hypoperfusion and edema formation throughout the body and is accompanied by neurohormonal and immunological alterations. Orthotopic heart transplantation (HTX) has been used as a beneficial option for ESHF. Due to the shortage of donor hearts, the ideal matching and timing of donors and recipients has become more important.

PURPOSE

In this study, our aim was to explore the relationship between the clinical outcomes of HTX and the cytokine and apolipoprotein profiles of the recipient pericardial fluid obtained at heart transplantation after opening the pericardial sac.

MATERIALS AND METHODS

The clinical data and the interleukin, adipokine, and lipoprotein levels in the pericardial fluid of twenty HTX recipients were investigated. Outcome variables included primer graft dysfunction (PGD), the need for post-transplantation mechanical cardiac support (MCS), International Society for Heart and Lung Transplantation grade ≥2R rejection, and mortality. Recipient risk scores were also investigated.

RESULTS

Leptin levels were significantly lower in patients with PGD than in those without PGD (median: 6.36 (IQR: 5.55-6.62) versus 7.54 (IQR = 6.71-10.44); p = 0.029). Higher ApoCII levels (median: 14.91 (IQR: 11.55-21.30) versus 10.31 (IQR = 10.02-13.07); p = 0.042) and ApoCIII levels (median: 60.32 (IQR: 43.00-81.66) versus 22.84 (IQR = 15.84-33.39); p = 0.005) were found in patients (n = 5) who died in the first 5 years after HTX. In patients who exhibited rejection (n = 4) in the first month after transplantation, the levels of adiponectin (median: 74.48 (IQR: 35.51-131.70) versus 29.96 (IQR: 19.86-42.28); p = 0.039), ApoCII (median: 20.11 (IQR: 13.06-23.54) versus 10.32 (IQR: 10.02-12.84); p = 0.007), and ApoCIII (median: 70.97 (IQR: 34.72-82.22) versus 26.33 (IQR: 17.18-40.17); p = 0.029) were higher than in the nonrejection group. Moreover, the pericardial thyroxine (T4) levels (median: 3.96 (IQR: 3.49-4.46) versus 4.69 (IQR: 4.23-5.77); p = 0.022) were lower in patients with rejection than in patients who did not develop rejection.

CONCLUSION

Our results indicate that apolipoproteins can facilitate the monitoring of rejection and could be a useful tool in the forecasting of early and late complications.

Leukotriene B4 receptor knockdown affects PI3K/AKT/mTOR signaling and apoptotic responses in colorectal cancer

Colorectal cancer (CRC) presents a landscape of intricate molecular dynamics. In this study, we focused on the role of the leukotriene B4 receptor (LTB4R) in CRC, exploring its significance in the disease's progression and potential therapeutic approaches. Using bioinformatics analysis of the GSE164191 and the Cancer Genome Atlas-colorectal adenocarcinoma (TCGA-COAD) datasets, we identified LTB4R as a hub gene influencing CRC prognosis. Subsequently, we examined the relationship between LTB4R expression, apoptosis, and the phosphoinositide 3-kinase/protein kinase B/mammalian target of rapamycin (PI3K/AKT/mTOR) signaling pathway through cellular and mice experiments. Our findings revealed that LTB4R is highly expressed in CRC samples and is pivotal for determining prognosis. In vitro experiments demonstrated that silencing LTB4R significantly impeded CRC cell viability, migration, invasion, and colony formation. Correspondingly, in vivo tests indicated that LTB4R knockdown led to markedly slower tumor growth in mice models. Further in-depth investigation revealed that LTB4R knockdown significantly amplified the apoptosis in CRC cells and upregulated the expression of apoptosis-related proteins, such as caspase-3 and caspase-9, while diminishing p53 expression. Interestingly, silencing LTB4R also resulted in a significant downregulation of the PI3K/AKT/mTOR signaling pathway. Moreover, pretreatment with the PI3K activator 740Y-P only partially attenuated the effects of LTB4R knockdown on CRC cell behavior, emphasizing LTB4R's dominant influence in CRC cell dynamics and signaling pathways. LTB4R stands out as a critical factor in CRC progression, profoundly affecting cellular behavior, apoptotic responses, and the PI3K/AKT/mTOR signaling pathway. These findings not only shed light on LTB4R's role in CRC but also establish it as a potential diagnostic biomarker and a promising target for therapeutic intervention.

Multi-Task Learning for Post-transplant Cause of Death Analysis: A Case Study on Liver Transplant

Organ transplant is the essential treatment method for some end-stage diseases, such as liver failure. Analyzing the post-transplant cause of death (CoD) after organ transplant provides a powerful tool for clinical decision making, including personalized treatment and organ allocation. However, traditional methods like Model for End-stage Liver Disease (MELD) score and conventional machine learning (ML) methods are limited in CoD analysis due to two major data and model-related challenges. To address this, we propose a novel framework called CoD-MTL leveraging multi-task learning to model the semantic relationships between various CoD prediction tasks jointly. Specifically, we develop a novel tree distillation strategy for multi-task learning, which combines the strength of both the tree model and multi-task learning. Experimental results are presented to show the precise and reliable CoD predictions of our framework. A case study is conducted to demonstrate the clinical importance of our method in the liver transplant.

Awareness, Attitudes, and Willingness: A Cross-Sectional Study of Organ Donation in Saudi Arabia

BACKGROUND

Organ transplantation is inherently dependent on the availability of organ donors. There is a noticeable paucity of literature addressing the rates of organ donation registration and the awareness of Islamic regulations (Fatwa) regarding organ donation within Saudi Arabia. Our study aimed to evaluate the level of organ donation registration, awareness of Islamic regulations, and knowledge of the Saudi Center for Organ Transplantation (SCOT) within the Saudi society.

METHODS

We conducted a cross-sectional survey from 30 March to 9 April 2023. This survey aimed to assess the awareness of Islamic (Fatwa) guidance on organ donation, the role of SCOT, and the rate of organ donation registration facilitated through the Tawakkalna app, the official health passport application in Saudi Arabia.

RESULTS

Out of 2329 respondents, 21% had registered as potential deceased organ donors, despite 87% acknowledging the importance of organ donation. Awareness of the Islamic Fatwa regarding organ donation was reported by 54.7% of respondents, and 37% recognized the Fatwa's acceptance of brain death criteria. The likelihood of registration as organ donors was higher among Saudi citizens under 45 years of age, females, healthcare workers (HCWs), individuals with higher education, relatives of patients awaiting organ donations, those informed about the Islamic Fatwas, and those willing to donate organs to friends. Conversely, being over the age of 25, Saudi nationality, employment as an HCW, awareness of SCOT, and prior organ donation registration were predictive of a heightened awareness of Islamic Fatwas. However, perceiving the importance of organ donation correlated with a lower awareness of the Fatwas. Significant positive correlations were found between awareness of SCOT, awareness of Fatwas, and registration for organ donation.

CONCLUSIONS

While the Saudi population exhibits a high regard for the importance of organ donation, this recognition is not adequately translated into registration rates. The discrepancy may be attributable to limited awareness of SCOT and the relevant Islamic Fatwas. It is imperative to initiate organ donation awareness campaigns that focus on religious authorization to boost organ donation rates and rectify prevalent misconceptions.

RapaLink-1 outperforms rapamycin in alleviating allogeneic graft rejection by inhibiting the mTORC1-4E-BP1 pathway in mice

Inhibition of mammalian target of rapamycin (mTOR), which is a component of both mTORC1 and mTORC2, leads to clinical benefits for organ transplant recipients. Pathways to inhibit mTOR include strengthening the association of FKBP12-mTOR or competing with ATP at the active site of mTOR, which have been applied to the design of first- and second-generation mTOR inhibitors, respectively. However, the clinical efficacy of these mTOR inhibitors may be limited by side effects, compensatory activation of kinases and attenuation of feedback inhibition of receptor expression. A new generation of mTOR inhibitors possess a core structure similar to rapamycin and covalently link to mTOR kinase inhibitors, resulting in moderate selectivity and potent inhibition of mTORC1. Since the immunosuppressive potential of this class of compounds remains unknown, our goal is to examine the therapeutic efficacy of a third-generation mTOR inhibitor in organ transplantation. In this study, RapaLink-1 outperformed rapamycin in inhibiting T-cell proliferation and significantly prolonged graft survival time. Mechanistically, the ameliorated rejection induced by RapaLink-1 is associated with a reduction in p-4E-BP1 in T cells, resulting in an elevation in Treg cells alongside a decline in Th1 and Th17 cells. For the first time, these studies demonstrate the effectiveness of third-generation mTOR inhibitors in inhibiting allograft rejection, highlighting the potential of this novel class of mTOR inhibitors for further investigation.

Application possibilities of artificial intelligence in facial vascularized composite allotransplantation-a narrative review

Facial vascularized composite allotransplantation (FVCA) is an emerging field of reconstructive surgery that represents a dogmatic shift in the surgical treatment of patients with severe facial disfigurements. While conventional reconstructive strategies were previously considered the goldstandard for patients with devastating facial trauma, FVCA has demonstrated promising short- and long-term outcomes. Yet, there remain several obstacles that complicate the integration of FVCA procedures into the standard workflow for facial trauma patients. Artificial intelligence (AI) has been shown to provide targeted and resource-effective solutions for persisting clinical challenges in various specialties. However, there is a paucity of studies elucidating the combination of FVCA and AI to overcome such hurdles. Here, we delineate the application possibilities of AI in the field of FVCA and discuss the use of AI technology for FVCA outcome simulation, diagnosis and prediction of rejection episodes, and malignancy screening. This line of research may serve as a fundament for future studies linking these two revolutionary biotechnologies.

Exploring the variable importance in random forests under correlations: a general concept applied to donor organ quality in post-transplant survival

Random Forests are a powerful and frequently applied Machine Learning tool. The permutation variable importance (VIMP) has been proposed to improve the explainability of such a pure prediction model. It describes the expected increase in prediction error after randomly permuting a variable and disturbing its association with the outcome. However, VIMPs measure a variable's marginal influence only, that can make its interpretation difficult or even misleading. In the present work we address the general need for improving the explainability of prediction models by exploring VIMPs in the presence of correlated variables. In particular, we propose to use a variable's residual information for investigating if its permutation importance partially or totally originates from correlated predictors. Hypotheses tests are derived by a resampling algorithm that can further support results by providing test decisions and p-values. In simulation studies we show that the proposed test controls type I error rates. When applying the methods to a Random Forest analysis of post-transplant survival after kidney transplantation, the importance of kidney donor quality for predicting post-transplant survival is shown to be high. However, the transplant allocation policy introduces correlations with other well-known predictors, which raises the concern that the importance of kidney donor quality may simply originate from these predictors. By using the proposed method, this concern is addressed and it is demonstrated that kidney donor quality plays an important role in post-transplant survival, regardless of correlations with other predictors.

Beyond Human Limits: Harnessing Artificial Intelligence to Optimize Immunosuppression in Kidney Transplantation

The field of kidney transplantation is being revolutionized by the integration of artificial intelligence (AI) and machine learning (ML) techniques. AI equips machines with human-like cognitive abilities, while ML enables computers to learn from data. Challenges in transplantation, such as organ allocation and prediction of allograft function or rejection, can be addressed through AI-powered algorithms. These algorithms can optimize immunosuppression protocols and improve patient care. This comprehensive literature review provides an overview of all the recent studies on the utilization of AI and ML techniques in the optimization of immunosuppression in kidney transplantation. By developing personalized and data-driven immunosuppression protocols, clinicians can make informed decisions and enhance patient care. However, there are limitations, such as data quality, small sample sizes, validation, computational complexity, and interpretability of ML models. Future research should validate and refine AI models for different populations and treatment durations. AI and ML have the potential to revolutionize kidney transplantation by optimizing immunosuppression and improving outcomes. AI-powered algorithms enable personalized and data-driven immunosuppression protocols, enhancing patient care and decision-making. Limitations include data quality, small sample sizes, validation, computational complexity, and interpretability of ML models. Further research is needed to validate and enhance AI models for different populations and longer-term dosing decisions.

Artificial Intelligence and Robotics in Transplant Surgery: Advancements and Future Directions

This editorial explores the transformative impact of artificial intelligence (AI) and robotics in transplant surgery. By merging robotic precision with AI analysis, this integration enhances organ transplantation outcomes. AI algorithms scrutinize patient data, elevating organ compatibility during allocation. Robotic systems such as the da Vinci Surgical System enable intricate operations with reduced complications and faster recovery. AI-driven post-transplant monitoring identifies early rejection signs, while tailored immunosuppressive regimens enhance patient care. Future prospects encompass predictive organ availability, telemedicine-enabled expertise dissemination, bioengineered organs, and personalized immunosuppression. Ethical considerations include privacy and algorithmic bias. In striking a balance, responsible AI and robotics application can revolutionize transplant surgery, offering a brighter future for patients in need.

Pancreas Rejection in the Artificial Intelligence Era: New Tool for Signal Patients at Risk

INTRODUCTION

Pancreas transplantation is currently the only treatment that can re-establish normal endocrine pancreatic function. Despite all efforts, pancreas allograft survival and rejection remain major clinical problems. The purpose of this study was to identify features that could signal patients at risk of pancreas allograft rejection.

METHODS

We collected 74 features from 79 patients who underwent simultaneous pancreas-kidney transplantation (SPK) and used two widely-applicable classification methods, the Naive Bayesian Classifier and Support Vector Machine, to build predictive models. We used the area under the receiver operating characteristic curve and classification accuracy to evaluate the predictive performance via leave-one-out cross-validation.

RESULTS

Rejection events were identified in 13 SPK patients (17.8%). In feature selection approach, it was possible to identify 10 features, namely: previous treatment for diabetes mellitus with long-term Insulin (U/I/day), type of dialysis (peritoneal dialysis, hemodialysis, or pre-emptive), de novo DSA, vPRA_Pre-Transplant (%), donor blood glucose, pancreas donor risk index (pDRI), recipient height, dialysis time (days), warm ischemia (minutes), recipient of intensive care (days). The results showed that the Naive Bayes and Support Vector Machine classifiers prediction performed very well, with an AUROC and classification accuracy of 0.97 and 0.87, respectively, in the first model and 0.96 and 0.94 in the second model.

CONCLUSION

Our results indicated that it is feasible to develop successful classifiers for the prediction of graft rejection. The Naive Bayesian generated nomogram can be used for rejection probability prediction, thus supporting clinical decision making.

Multicenter analysis of immunosuppressive medications on the risk of malignancy following adult solid organ transplantation

Objective

This study aimed to assess the risk of maintenance immunosuppression on the post-transplant risk of malignancy across all solid organ transplant types.

Methods

This is a retrospective cohort study from a multicenter hospital system in the United States. The electronic health record was queried from 2000 to 2021 for cases of solid organ transplant, immunosuppressive medications, and post-transplant malignancy.

Results

A total of 5,591 patients, 6,142 transplanted organs, and 517 post-transplant malignancies were identified. Skin cancer was the most common type of malignancy at 52.8%, whereas liver cancer was the first malignancy to present at a median time of 351 days post-transplant. Heart and lung transplant recipients had the highest rate of malignancy, but this finding was not significant upon adjusting for immunosuppressive medications (heart HR 0.96, 95% CI 0.72 - 1.3, p = 0.88; lung HR 1.01, 95% CI 0.77 - 1.33, p = 0.94). Random forest variable importance calculations and time-dependent multivariate cox proportional hazard analysis identified an increased risk of cancer in patients receiving immunosuppressive therapy with sirolimus (HR 1.41, 95% CI 1.05 - 1.9, p = 0.04), azathioprine (HR 2.1, 95% CI 1.58 - 2.79, p < 0.001), and cyclosporine (HR 1.59, 95% CI 1.17 - 2.17, p = 0.007), while tacrolimus (HR 0.59, 95% CI 0.44 - 0.81, p < 0.001) was associated with low rates of post-transplant neoplasia.

Conclusion

Our results show varying risks of immunosuppressive medications associated with the development of post-transplant malignancy, demonstrating the importance of cancer detection and surveillance strategies in solid organ transplant recipients.

HLA amino acid Mismatch-Based risk stratification of kidney allograft failure using a novel Machine learning algorithm

OBJECTIVE

While associations between HLA antigen-level mismatches (Ag-MM) and kidney allograft failure are well established, HLA amino acid-level mismatches (AA-MM) have been less explored. Ag-MM fails to consider the substantial variability in the number of MMs at polymorphic amino acid (AA) sites within any given Ag-MM category, which may conceal variable impact on allorecognition. In this study we aim to develop a novel Feature Inclusion Bin Evolver for Risk Stratification (FIBERS) and apply it to automatically discover bins of HLA amino acid mismatches that stratify donor-recipient pairs into low versus high graft survival risk groups.

METHODS

Using data from the Scientific Registry of Transplant Recipients, we applied FIBERS on a multiethnic population of 166,574 kidney transplants between 2000 and 2017. FIBERS was applied (1) across all HLA-A, B, C, DRB1, and DQB1 locus AA-MMs with comparison to 0-ABDR Ag-MM risk stratification, (2) on AA-MMs within each HLA locus individually, and (3) using cross validation to evaluate FIBERS generalizability. The predictive power of graft failure risk stratification was evaluated while adjusting for donor/recipient characteristics and HLA-A, B, C, DRB1, and DQB1 Ag-MMs as covariates.

RESULTS

FIBERS's best-performing bin (on AA-MMs across all loci) added significant predictive power (hazard ratio = 1.10, Bonferroni adj. p < 0.001) in stratifying graft failure risk (where low-risk is defined as zero AA-MMs and high-risk is one or more AA-MMs) even after adjusting for Ag-MMs and donor/recipient covariates. The best bin also categorized more than twice as many patients to the low-risk category, compared to traditional 0-ABDR Ag mismatching (∼24.4% vs ∼ 9.1%). When HLA loci were binned individually, the bin for DRB1 exhibited the strongest risk stratification; relative to zero AA-MM, one or more MMs in the bin yielded HR = 1.11, p < 0.005 in a fully adjusted Cox model. AA-MMs at HLA-DRB1 peptide contact sites contributed most to incremental risk of graft failure. Additionally, FIBERS points to possible risk associated with HLA-DQB1 AA-MMs at positions that determine specificity of peptide anchor residues and HLA-DQ heterodimer stability.

CONCLUSION

FIBERS's performance suggests potential for discovery of HLA immunogenetics-based risk stratification of kidney graft failure that outperforms traditional assessment.

Development of a calculated panel reactive antibody calculator for the United Arab Emirates: a proof of concept study

Calculated panel reactive antibody (CPRA) is used to help increase sensitized patient's access to transplantation. United Arab Emirates (UAE) has a diverse resident population hence we developed a UAE-CPRA calculator based on HLA antigen frequencies of the different ethnic groups that represent the UAE population. HLA antigen frequencies at serological split antigen level for HLA-A, -B, -C, -DRB1 and -DQB1 of 1002 healthy unrelated donors were performed. We subsequently compared the performance of the UAE CPRA calculator with the Organ Procurement and Transplantation Network (OPTN) and the Canadian CPRA calculators in 110 Kidney Transplant waitlist patients from January 2016 to December 2018. Lin's concordance correlation coefficient showed a moderate agreement between the UAE and OPTN calculator (Rc = 0.949, 95% CI 0.929-0.963) and the UAE and Canadian calculators (Rc = 0.952, 95% CI 0.932-0.965). While there continued to be a moderate agreement (Rc = 0.937, UAE versus OPTN calculator) in the lower sensitized group, a poor agreement (Rc = 0.555, UAE versus OPTN calculator) was observed in the higher sensitized group. In this study, we provide a template for countries to develop their own population-specific CPRA calculator. Implementation of the CPRA algorithm based on HLA frequencies of the multi-ethnic UAE population will be more fitting to increase access to transplantation and improve transplant outcomes. Our study demonstrates that the CPRA calculators developed using the data from the western population had poor correlation in our higher sensitized patients disadvantaging them in potential organ allocations systems. We plan to further refine this calculator by using high resolution HLA typing to address the problem of a genetically diverse population.

Enhanced survival prediction using explainable artificial intelligence in heart transplantation

The most limiting factor in heart transplantation is the lack of donor organs. With enhanced prediction of outcome, it may be possible to increase the life-years from the organs that become available. Applications of machine learning to tabular data, typical of clinical decision support, pose the practical question of interpretation, which has technical and potential ethical implications. In particular, there is an issue of principle about the predictability of complex data and whether this is inherent in the data or strongly dependent on the choice of machine learning model, leading to the so-called accuracy-interpretability trade-off. We model 1-year mortality in heart transplantation data with a self-explaining neural network, which is benchmarked against a deep learning model on the same development data, in an external validation study with two data sets: (1) UNOS transplants in 2017-2018 (n = 4750) for which the self-explaining and deep learning models are comparable in their AUROC 0.628 [0.602,0.654] cf. 0.635 [0.609,0.662] and (2) Scandinavian transplants during 1997-2018 (n = 2293), showing good calibration with AUROCs of 0.626 [0.588,0.665] and 0.634 [0.570, 0.698], respectively, with and without missing data (n = 982). This shows that for tabular data, predictive models can be transparent and capture important nonlinearities, retaining full predictive performance.