Derivation and Validation of a Risk Index to Predict All-Cause Mortality in Type 2 Diabetes Mellitus
Bibliographic record
Abstract
Background: Type 2 Diabetes Mellitus with severe complications have higher risk of mortality. An easy-to-use risk index to quantify the risk of mortality would help clinicians identify patients who might benefit from more intensive therapy. The study aims to develop a risk index to predict all-cause mortality for a cohort of T2DM patients seen at primary care clinics in Singapore. Methods: In a retrospective cohort study, 28 patient-level variables were extracted from an automated clinical and administrative registry for T2DM who had at least 2 visits to the same National Healthcare Group Polyclinic in 2007. Demographic characteristics, inpatient and outpatient diagnoses, laboratory results and prescription were included. Mortality data were provided by the Ministry of Health. We used a split-sample design to derive and validate an index to predict the risk of death within 2 years of the index attendance. The c-statistic was used to assess model discrimination. Results: Out of the 59,747 patients in the study, 2,977 (5%) patients died during the 2-year follow up. Age (“A”); diabetes-related complications (Diabetes Complication Severity Index) (“C”); and cancer history (“C”) were found to independently predict all-cause mortality (from which the mnemonic “ACC” was derived). The ACC risk index ranged from 0 to 20 with expected risk of mortality of 0.3% to 80.6%. The discriminatory accuracy of the ACC risk index for the validation data is excellent (c-statistic 0.83, 95% CI 0.82 - 0.84). Conclusion: A simple risk index for all-cause mortality was successfully developed, and validated using routinely collected registry data. The risk index can be used to stratify T2 DM patients into varying risk of mortality. Further external validation of the risk index is needed before using it in a clinical setting. doi:10.4021/jem67w
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 | 0.013 | 0.033 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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 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".