Application of explainable AI for nonlinear variable interactions in allogeneic hematopoietic cell transplantation survival prediction
Bibliographic record
Abstract
Allogeneic hematopoietic cell transplantation presents a potentially curative treatment for hematologic malignancies, yet carries associated risks and complications. Machine learning (ML) models excel at uncovering high-dimensional relationships, enhancing predictive accuracy. We developed ML models to predict the survival outcomes and through the application of SHAP, an explainable artificial intelligence (XAI) technique, enabled the identification of new and clinically relevant feature-outcome relationships. In particular, through this ML+XAI framework, we identified clear interaction between CD34+ cell dose of peripheral blood stem cell grafts and patient age at allo-HCT for acute leukemia patients.In addition, we developed ANI-SHAP (automated nonlinear interactions with SHAP), an automated Python-based algorithm package designed to improve the efficacy and accessibility of interaction analysis, which is the first to focus on exploring nonlinear interactions, the type of interaction that traditional statistical methods often fail to capture. The new ML + XAI framework, along with ANI-SHAP, can improve the exploration of feature-feature relationships, creating a more streamlined pipeline for further investigation.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".