Integration of clinical and imaging data to predict death in hemodialysis patients
Bibliographic record
Abstract
In a prior publication, we demonstrated that a model integrating clinical and simple imaging data predicted the presence and severity of coronary artery calcification in prevalent hemodialysis patients. Herein we report the ability of the same model to predict all-cause death. We assessed all-cause mortality in 141 consecutive maintenance hemodialysis patients from two dialysis centers followed for a median of 79 months from enrollment. Patients were risk stratified according to a simple cardiovascular calcification index (CCI) that included patient's age, dialysis vintage, calcification of the cardiac valves, and abdominal aorta. The mean patients' age was 55 ± 14 years. Abdominal aorta calcification was present in 57% of the patients, and 44% and 38% had aortic and mitral valve calcification, respectively. During follow-up, 75 deaths (93 deaths per 1000 person-years) were recorded. The CCI was linearly associated with risk of death, such that the unadjusted hazard risk (HR) increased by 12% for each point increase in CCI (P < 0.001). Further adjustments for age, sex, study center, diabetes mellitus, history of cardiovascular disease, hypertension, congestive heart failure, left ventricular hypertrophy, systolic, and diastolic blood pressure did not substantially change the strength of this association (HR 1.10; 95%CI: 1.00-1.21; P = 0.03). The CCI is a simple clinical model that can be used to risk stratify maintenance hemodialysis patients.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 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".