An official website of the United States government
Purpose: The equitable distribution of donor kidneys is crucial to maximizing transplant success rates and addressing disparities in healthcare data. This study examines potential gender bias in the Deceased Donor Organ Allocation Model (DDOA) by using machine learning and AI to analyze its impact on kidney discard decisions to ensure fairness in accordance with medical ethics. Methods: The study employs the Deceased Donor Organ Allocation Model (DDOA) model (https://ddoa.mst.hekademeia.org/#/kidney) to predict the discard probability of deceased donor kidneys using donor characteristic from the OPTN Deceased Donor Dataset (2016-2023). Using the SRTR SAF dictionary, the dataset consists of 18,029 donor records, where gender was assessed for its effect on discard probability. ANOVA and t-test determines whether there is a statistically significant difference between the discard percentages for female and male donors by changing the donor gender data alone. If the p-value obtained from the t-test is less than the significance level (typically 0.05), we reject the null hypothesis and conclude that there is a significant difference. Otherwise, we fail to reject the null hypothesis. Results: Figure 1 visualizes the differences in discard percentages between female and male donor kidneys, with an unbiased allocation system expected to show no difference (i.e., a value of zero). To assess the presence of gender bias, statistical analyses, including t-tests and ANOVA were performed. The t-test comparing female and male kidney discard rates yielded a t-statistic of 29.690228, with a p-value of 3.586956e-189 < 0.05 significance threshold. This result leads to the rejection of the null hypothesis, indicating a significant difference was found between the mean when altering only the donor gender attribute in the DDOA model making it play a significant role in discard decisions. Conclusions: The study highlights that a significant difference was found between the mean by altering only the donor gender attribute, contributing to kidney discard rates in the DDOA model. These findings reinforce the need for greater transparency in organ allocation models and a reconsideration of the demographic criteria used in the evaluation process. Future research should refine algorithms to minimize biases in organ allocation and investigate kidney discard disparities in transplantation.
more »
« less
This content will become publicly available on August 1, 2026
Assessment of Potential Bias in Kidney Transplant Acceptance Decision Using the Deceased Donor-Recipient Attributes Matching AI Model
Purpose: AI models for kidney transplant acceptance must be rigorously evaluated for bias to ensure equitable healthcare access. This study investigates demographic and clinical biases in the Final Acceptance Model (FAM), a donor-recipient matching deep learning model that complements surgeons’ decision-making process in predicting whether to accept available kidneys for their patients with end of stage renal disorder. Methods: AI models for kidney transplant acceptance must be rigorously evaluated for bias to ensure equitable healthcare access. This study investigates demographic and clinical biases in the Final Acceptance Model (FAM), a donor-recipient matching deep learning model that complements surgeons’ decision-making process in predicting whether to accept available kidneys for their patients with end of stage renal disorder. Results: There is no significant racial bias in the model’s predictions (p=1.0), indicating consistent outcome across all racial combinations between donors and recipients. Gender-related effects as shown in Figure 1, while statistically significant (p=0.008), showed minimal practical impact with mean differences below 1% in prediction probabilities. Significant difference Clinical factors involving diabetes and hypertension showed significant difference (p=4.21e-19). The combined presence of diabetes and hypertension in donors showed the largest effect on predictions (mean difference up to -0.0173, p<0.05), followed by diabetes-only conditions in donors (mean difference up to -0.0166, p<0.05). These variations in clinical factor predictions showed bias against groups with comorbidities. Conclusions: The biases observed in the model highlight the need to improve the algorithm to ensure absolute fairness in prediction.
more »
« less
- Award ID(s):
- 2222801
- PAR ID:
- 10629354
- Publisher / Repository:
- Elsevier
- Date Published:
- Journal Name:
- American Journal of Transplantation
- Volume:
- 25
- Issue:
- S1
- ISSN:
- 1600-6135
- Page Range / eLocation ID:
- S368
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
(TSFAM) model, an adaptive human-AI teaming framework designed to enhance hard-to-place kidney acceptance decision-making by integrating transplant surgeons’ individualized expertise with advanced AI analytics (Figure 1). Methods: TSFAM is an innovative solution for complex issues in kidney transplant decision-making support. It employs fuzzy associative memory to capture and codify unique decision-making rules of transplant surgeons. Using the Deceased Donor Organ Assessment (DDOA) and Final Acceptance AI models designed to evaluate hard-to-place kidneys, TSFAM integrates fuzzy logic with deep learning techniques to manage inherent uncertainties in donor organ assessments. Surgeon-specifi c ontologies and membership functions are extracted through interviews. Similar to how a pain scale is used for understanding patients, an ontology ambiguity scale is used to develop surgeon rules (Figure 2). Fuzzy logic captures ambiguity and enables the model to adapt to evolving clinical, environmental, and policy conditions. The structured incorporation of human expertise ensures decision support remains closely aligned with local clinical practices and global best evidence. Results: This novel framework incorporates human expertise into AI decisionmaking tools to support donor organ acceptance in transplantation. Integrating surgeon-defi ned criteria into a robust decision-support tool enhances accuracy and transparency of organ allocation decision-making support. TSFAM bridges the gap between data-driven models and nuanced judgment required in complex clinical scenarios, fostering trust and promoting responsible AI adoption. Conclusions: TSFAM fuses deep learning analytics with subtleties of human expertise for a promising pathway to improve decision-making support in transplant surgery. The framework enhances clinical assessment and sets a precedent for future systems prioritizing human-AI collaboration. Prospective studies will focus on clinical implementation with dynamic interfaces for a more patient-centered, evidencebased model in organ transplantation. The intent is for this approach to be adaptable to individual case scenarios and the diverse needs of key transplant team membersmore » « less
-
Background.In rodents, hydrogen sulfide (H2S) reduces ischemia-reperfusion injury and improves renal graft function after transplantation. Here, we hypothesized that the benefits of H2S are conserved in pigs, a more clinically relevant model. Methods.Adult porcine kidneys retrieved immediately or after 60 min of warm ischemia (WI) were exposed to 100 µM sodium hydrosulfide (NaHS) (1) during the hypothermic ex vivo perfusion only, (2) during WI only, and (3) during both WI and ex vivo perfusion. Kidney perfusion was evaluated with dynamic contrast-enhanced MRI. MRI spectroscopy was further employed to assess energy metabolites including ATP. Renal biopsies were collected at various time points for histopathological analysis. Results.Perfusion for 4 h pig kidneys with Belzer MPS UW + NaHS resulted in similar renal perfusion and ATP levels than perfusion with UW alone. Similarly, no difference was observed when NaHS was administered in the renal artery before ischemia. After autotransplantation, no improvement in histologic lesions or cortical/medullary kidney perfusion was observed upon H2S administration. In addition, AMP and ATP levels were identical in both groups. Conclusions.In conclusion, treatment of porcine kidney grafts using NaHS did not result in a significant reduction of ischemia-reperfusion injury or improvement of kidney metabolism. Future studies will need to define the benefits of H2S in human, possibly using other molecules as H2S donors.more » « less
-
Key PointsA2 to B incompatible transplantation is not fully practiced in the country, and further policies should encourage centers to perform more blood incompatible transplants.Centers that currently practice A2 to B incompatible transplants should give priority to blood type B patients who are willing to accept an A organ. This will benefit Asian and Black patients. BackgroundThe rate of A2 to B incompatible (ABO-i) kidney transplant continues to be low despite measures in the new kidney allocation system (KAS) to facilitate such transplants. This study shows how the number of ABO-i transplants could increase if KAS policies were used to their fullest extent through a boost in ABO-i priority points. MethodTransplant outcomes were predicted using the Kidney Pancreas Simulated Allocation Model, preloaded with national data of 2010. We used this simulation to compare KAS with a new intervention in which priority equal to cPRA=100 has been given to blood type B candidates who are willing to accept an A blood type organ. ResultsThe number of Black recipients increased by 375 (from 35% of the total recipient population to 38.7%), the number of blood type B Blacks increased by 65 (from 8% of the total recipient population to 9%), and the number of blood type B Black patients receiving blood type A kidneys increased by 49 (from 2% of the total recipient population to 2.5%). The same change occurred for Asians, particularly blood type B Asians (from 0.54% of the total recipient population to 0.7%). The average wait time notably decreased by 27 days for blood type B Black patients. In the proposed scenario, 263 blood type B Black patients received a blood type A organ (2.5% of the total recipient population) while only 181 (1.1%) of such transplants were performed in 2021. These results signify a considerable opportunity loss of ABO-i transplants for Black patients. ConclusionsIf this policy was universally adopted, we would expect to see an overall increase in A2 to B transplantation, but in reality, not all centers perform ABO-i transplantation. Thus, adopting this policy would incentivize other centers to perform more subtyping of A-type kidneys, and it would increase access to organs for blood type B Asian and Black patients in centers where ABO-i transplantation already takes place.more » « less
-
Background:It is a major clinical challenge to ensure the long-term function of transplanted kidneys. Specifically, the injury associated with cold storage of kidneys compromises the long-term function of the grafts after transplantation. Therefore, the molecular mechanisms underlying cold-storage–related kidney injury are attractive therapeutic targets to prevent injury and improve long-term graft function. Previously, we found that constitutive proteasome function was compromised in rat kidneys after cold storage followed by transplantation. Here, we evaluated the role of the immunoproteasome (iproteasome), a proteasome variant, during cold storage (CS) followed by transplantation. Methods:Established in vivo rat kidney transplant model with or without CS containing vehicle or iproteasome inhibitor (ONX 0914) was used in this study. Theiproteasome function was performed using rat kidney homogenates and fluorescent-based peptide substrate specific to β5i subunit. Western blotting and quantitative RT-PCR were used to assess the subunit expression/level of theiproteasome (β5i) subunit. Results:We demonstrated a decrease in the abundance of the β5i subunit of theiproteasome in kidneys during CS, but β5i levels increased in kidneys after CS and transplant. Despite the increase in β5i levels and its peptidase activity within kidneys, inhibiting β5i during CS did not improve graft function after transplantation. Summary:These results suggest that the pharmacological inhibition of immunoproteasome function during CS does not improve graft function or outcome. In light of these findings, future studies targeting immunoproteasomes during both CS and transplantation may define the role of immunoproteasomes on short- and long-term kidney transplant outcomes.more » « less
