Interpretable and Interactive Deep Survival Analysis with Time-dependent EXtreme Gradient Integration
Bibliographic record
Abstract
Accurate prediction of time-to-event outcomes, commonly known as survival analysis, is vital in high-stakes domains such as healthcare and business, where timely and trustworthy insights can have profound implications. Traditional survival analysis methods either provide predictions without clear explanations or offer interpretability without a mechanism to integrate expert insights. In many real-world scenarios, decision-makers require models that are both transparent and capable of interactively incorporating domain knowledge to refine predictions. The key challenge we address is how to simultaneously achieve accurate time-to-event forecasting, clear interpretability, and interactive integration of expert feedback. We propose the Interpretable and Interactive Deep Discrete-Time Survival Analysis framework, an approach that is both data-driven and knowledge-driven. Furthermore, it embeds expert knowledge into the model, dynamically aligns feature contributions with evolving risk patterns, and actively engages experts to guide the learning process interactively. This interactive strategy not only enhances predictive performance but also produces explanations that clearly reflect the critical factors identified by domain experts. Extensive evaluations on diverse clinical and business datasets demonstrate that our method captures feature importance and yields robust and reliable predictions that stand in contrast to conventional black-box models. These results indicate that bridging interpretability with interactive expert engagement can significantly improve decision support systems. By integrating accurate forecasting with human-aligned, interactive explanations, our framework offers a promising direction for developing more transparent and trusted models across a wide range of disciplines.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 teacher head, 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".