A Population Health Survey-Based Prediction Equation for Incident CKD: The CKD Population Risk Tool CKDPort/PREDICT-CKD LIFESTYLE
Bibliographic record
Abstract
Background: Chronic kidney disease awareness among the general public is less than 10%. Patients' health behaviours are known to be associated with CKD development and disease progression. Prediction tools that engage the general public with their self-reported health information could increase awareness, identify modifiable lifestyle risk factors, empower patients, and prevent disease. The study objective was to develop and validate a population health survey-based prediction equation to determine the risk of incident CKD in the general public. Methods: Participants who completed the Canadian Community Health Survey (CCHS) were linked to laboratory and hospital admission data between 2000 and 2015 in Ontario, Canada. The primary outcome was incident CKD (eGFR < 60 ml/min/1.73m2) with up to 8 years of follow-up. Models accounted for the competing risk of all-cause mortality. The CCHS is a random, comprehensive, prospective, general population survey that captures information on demographics, co-morbid illnesses, lifestyle and behaviours, diet, body mass index and mood. External validation was performed using data from the UK Biobank. Results: From 22,200 eligible adults, 1,981 (8.9%) developed incident CKD during a mean follow-up time of 8 years. Domains included in the final reduced model were baseline eGFR, smoking, alcohol, physical activity, education, mood, fruit and vegetable intake, diabetes, hypertension, heart and lung disease, urinary incontinence, cancer, and BMI. The model demonstrated excellent discrimination in individuals with and without a baseline eGFR measure (5-year c-statistic with baseline eGFR: 0.84 95%CI 0.82-0.85, without 0.81 95%CI 0.80-0.82), was well calibrated (Brier score at 5-years with baseline eGFR: 0.07 95%CI 0.007-0.08, without 0.08 95%CI 0.07-0.08), and was consistent in a sensitivity analysis using 2 measures of eGFR > 90 days apart to define the outcome. The model was consistent with external validation. Conclusions: Lifestyle and health behaviour information from population-based health surveys can predict incident CKD in the population with excellent discrimination and can be used to improve public engagement in CKD awareness.
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 | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".