A Novel Explainable Deep Learning STING Kernel Approach for Multivariate Time Series Imputation in Healthcare
Bibliographic record
Abstract
Multivariate time series (MTS) data is crucial in fields such as healthcare, finance, and traffic management, particularly for forecasting clinical outcomes like mortality rates, disease risks, and hospital stay durations.In healthcare, imputing missing values from complex MTS datasets can enhance critical care management and enable personalized treatments.This study focuses on imputing missing values in health-related data, especially intravenous vital signs and data essential to physicians' decision-making.To address limitations of existing imputation methods, we introduce a novel approach: the STING Kernel Deep Level (SKDL), coupled with an explainable framework.SKDL is designed to improve accuracy and effectively handle categorical outputs.Our evaluation using the MIMIC-IV dataset shows that SKDL outperforms traditional imputation methods such as Mean Imputation, k-Nearest Neighbors (KNN), and standard GAN-based approaches, based on performance metrics including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R Squared.SKDL achieved an MAE of 0.0870, MSE of 0.0175, RMSE of 0.0040, and R Squared of 0.3367, indicating strong accuracy.Furthermore, the integration of Explainable AI (XAI) enables interpretability by visualizing imputation rationale, helping clinicians verify that the predicted values align with physiological expectations, thereby reinforcing trust in the imputation process.These results suggest that SKDL, with its interpretable design, provides a reliable solution for missing data imputation and supports more consistent and transparent clinical decisionmaking.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".