Enhancing Organ Allocation Efficiency: A Pilot Study Evaluating Artificial Intelligence-Assisted Assessment of Donor Kidney Pathology
Bibliographic record
Abstract
PURPOSE: The purpose of this study is to evaluate the effectiveness of an artificial intelligence (AI)-assisted review (AAR) system in improving diagnostic accuracy, efficiency, and concordance with expert assessments during the evaluation of donor kidney viability. METHODS: Sixty H&E-stained frozen-section kidney biopsy slides from explant kidneys obtained for organ donation were evaluated. A board-certified renal pathologist established ground truth (GT) through manual digital evaluation on the Techcyte Fusion Platform. The slides were independently reviewed by an AI algorithm, a board-certified pathologist (Reviewer 2 (R2)), and a board-certified transplant surgeon (Reviewer 1 (R1)). After a washout period, AI-assisted reads were performed. The performance of AAR and manual digital review (MDR) was compared to the GT for total and sclerotic glomeruli (SG) counts, as well as concordance with kidney viability thresholds (using a 20% SG cutoff rate). Secondary outcomes included comparisons of review times and concordance rates for AAR, MDR, and AI analysis alone with the GT. RESULTS: AAR demonstrated concordance with GT across parameters. For R1, coefficient of determination (COD) values for SG counts improved with AAR (0.833) compared to MDR (0.81). Agreement at the 20% SG threshold for kidney viability was 98.33% for both AAR and MDR. AAR reduced mean review times (minutes) by 54.83% compared to MDR, with per-slide review times decreasing from 17:09 (MDR) to 8:35 (AAR). Pearson correlation coefficients (PCC) and concordance correlation coefficients (CCC) for AAR were generally higher than MDR, particularly for the percentage of SG, indicating improved alignment with GT. Analyses revealed no systematic bias, with AAR aligning more closely with GT compared to MDR for both reviewers. CONCLUSION: The Techcyte algorithm reduces review time while maintaining accuracy and concordance with experts, promoting AI adoption to improve workflow efficiency and expedite transplantation decisions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".