A Molecular Nearest-Neighbours Approach to Diagnosis and Prognosis in Kidney Transplant Biopsies.
Bibliographic record
Abstract
While assessment of the conventional and molecular phenotype of a biopsy provides diagnostic information, it stops short of providing a sense of what is likely to happen. We used a molecular nearest-neighbours approach to predict diagnoses and prognoses in a series of kidney transplant biopsies-for-cause. We have previously developed univariate molecular classifiers for various kidney pathologies. In the present study, we combined the molecular scores for ABMR, TCMR, rejection, fibrosis, loss of solute carriers, and injury/repair, in a reference set of 538 biopsies. These scores were then reduced into 3-dimensional space via principal components analysis (PCA). As new cases presented, their molecular scores were projected into this space.Figure: No Caption available.The histologic diagnosis of each new sample's 50 nearest neighbours was then obtained, along with their 1- and 3-year survival rates. Three-dimensional Euclidean distance was used to define proximity.Table: No Caption available.The clinical application of the nearest neighbours is illustrated by two cases. Case 1 received a live donor transplant 64 days earlier and had stable but impaired function. The biopsy showed no rejection and relatively little AKI. Most neighbours had been diagnosed with no rejection, and 98% survived to at least one year. Case 2 illustrates a much more troubled kidney, presenting with rising creatinine 9.8 years post transplant and suspected recurrent disease. Many of its nearest neighbours had rejection, with 1- and 3-year survival of 71% and 45% respectively. This illustrates how the nearest neighbours approach, by comparing new patients with a large reference set of similar cases, can provide the clinician with a sense of the impact of these molecular phenotypes. DISCLOSURES:Halloran, P.: Other, Astellas, lecturing, Novartis, lecturing, One Lambda, lecturing.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".