Development and validation of a risk prediction model for amnestic mild cognitive impairment in older adults residing in communities
Bibliographic record
Abstract
Abstract Background Amnestic mild cognitive impairment (aMCI) is the most common subtype of MCI with a much higher risk of Alzheimer’s disease (AD) transition. this study aimed to develop and validate a non-invasive and affordable initial diagnostic instrument based on neuropsychological assessment and routine physical examination that will identify individuals with potentially reversible aMCI. Methods Data was obtained from Brain Health Cognitive Management Team in Wuhan (https://hbtcm.66nao.com/admin/). A total of 1007 community elders aged over 65 years were recruited and randomly allocated to either a training or validation set at a 7:3 ratio. Ten questionnaires were used to comprehensively collect data including the demography information, chronic disease history, hobbies, and cognitive assessment results of the elderly; Combined with the physical examination results such as blood pressure, blood sugar, blood lipids, blood routine, liver and kidney function, and urine routine, a risk prediction model was constructed with a multivariate logistic regression, and the performance of the model was assessed with respect to its discrimination, calibration, and clinical usefulness, the results were quantified and visualized through the Area Under the Curve (AUC), Calibration Curve (CC), and Decision Curve Analysis (DCA), respectively. Results The mean age was 71 years old (ranged from 67 to74), and females accounted for 59.48% in all 1007 participants, among them, aMCI (n = 401). Among all predictors, Diastolic Blood Pressure (DBP), Pulse (P), Hemoglobin (HGB) were lower in the validation set than the training set; the validation set had higher prevalence of diabetes and gastroenteropathy (P < 0.05). The optimal model ultimately includes 11 significant variables: Montreal Cognitive Assessment (MoCA), Mini-Mental State Examination (MMSE), Instrumental Activities of Daily Living (IADL), center, education, job, planting flowers/keeping pets, singing, Num. of hobbies, Urine Occult Blood (UOB), Urine Protein (UP). The AUC was 0.787 (95% CI: 0.753–0.821) in the training set, and the AUC of 0.780 (95% CI: 0.728–0.832) was verified internally by bootstrapping in the validation set, indicating that the diagnostic model has a good discrimination. Model diagnostics showed good calibration (Hosmer Lemeshow test, X2 = 9.4759, P = 0.304, P＞0.05) and good agreement of the CC in both training and validation sets. The DCA showed a favorable net benefit for clinical use (if the predicted risk of aMCI is greater than 45.9%, divide elder individuals into high-risk groups to manage, resulting in a net benefit rate of 14% among the modeled population). Conclusions This multivariate prediction model can effectively identify older adults at high risk for aMCI, assist in early screening and targeted management of primary healthcare, and promote healthy aging.
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 | 0.008 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".