Exploring the potential relationship between kidney disease index and cognitive dysfunction: a machine learning approach with NHANES data
Bibliographic record
Abstract
OBJECTIVE: This study investigates the relationship between the Kidney Disease Index (KDI) and cognitive function, evaluating its potential as a predictive marker for cognitive impairment in older adults. We also compare the performance of KDI with traditional kidney function markers, including estimated glomerular filtration rate (eGFR) and urine albumin-to-creatinine ratio (UACR), in predicting cognitive decline. METHODS: Data from the National Health and Nutrition Examination Survey (NHANES) involving participants aged 60 years or older were analyzed. Multivariable regression models were employed to assess the relationship between KDI, eGFR, UACR, and cognitive impairment. Restricted cubic splines (RCS) were used to explore the dose-response relationship between KDI levels and cognitive impairment, and interaction analyses were performed to assess how KDI impacts cognitive function across various demographic groups. Machine learning techniques, including LASSO, XGBoost, and random forests, were applied for feature selection and model validation to predict cognitive impairment. The performance of the predictive models was evaluated using receiver operating characteristic (ROC) curves and decision curve analysis (DCA). Calibration was assessed through calibration curves to ensure accurate prediction probabilities, while SHAP values were used to interpret the relative importance of KDI and other variables in predicting cognitive impairment. RESULTS: A higher KDI level may be significantly associated with lower cognitive scores and an increased risk of cognitive impairment. For each 0.1 unit increase in KDI, cognitive scores decrease by 0.17 points, and the probability of cognitive impairment increases by 15%. Machine learning confirmed that the AUC of KDI (> 0.7) is higher than that of eGFR and UACR, indicating that KDI may outperform eGFR and UACR in predicting cognitive impairment. The SHAP model further validated the predictive value of KDI. CONCLUSION: KDI may be a reliable and effective indicator for predicting cognitive function and the risk of cognitive impairment in the elderly. Research suggests that higher KDI levels may serve as a risk factor for cognitive decline, underscoring the importance of managing KDI for cognitive health, particularly in populations with chronic kidney disease (CKD). Future studies should focus on longitudinal research and clinical interventions to further validate the clinical utility of KDI and develop treatment strategies based on KDI.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".