MACHINE LEARNING CLASSIFICATION ON BLOOD PRESSURE VARIATION FOR THE RISK OF COGNITIVE IMPAIRMENT: A CROSS-SECTIONAL STUDY FROM A BLOOD PRESSURE MANAGEMENT COHORT IN HONG KONG
Bibliographic record
Abstract
Objective: The evidence for the association between blood pressure variability (BPV) with cognitive impairment is still uncertain in the Asia population. This study explored whether a machine learning classification on BPV is associated with cognitive impairment among the elderly in Hong Kong. Design and method: Random samples of 573 participants were selected from a community-based cohort for blood pressure management in July 2021. Participants regularly measured blood pressure. K-means clustering methods were applied to group the standard deviation of BPV into high, medium, and low variations. This method considered both systolic and diastolic blood pressure variations. For cognitive functions, participants were assessed by the shorted version of the Montreal Cognitive Assessment Version, i.e., 5-min MoCA (Hong Kong validated version). Mild cognitive impairment (MCI) was defined with adjustment of age and education according to the 5-min MoCA. BPV was defined as the standard deviation of systolic and diastolic blood pressure values. Logistic and quantile regression models were conducted to explore the association of MCI with systolic or diastolic BPV and a combined BPV classification. Odds ratios (OR) were adjusted for age, gender, educational background social economic status, and other medical histories, including hypertension, hyperlipidemia, diabetes, and stroke. Results: The 573 participants had a mean age of 72 years with 86% of females. The median follow-up period was eight months with a median number of 19 blood pressure records. Systolic BPV increases the risk of MCI (adjusted OR, 95% CI = 1.18, 1.05 to 1.31), but not diastolic BPV. The quantile regression found that the magnitude of association is more substantial among the population with lower cognitive function (Figure 1). With reference to the machine learning classification, participants with high BPV were shown to have a 5.5 times higher risk of MCI than those with low BPV. Conclusions: Participants with higher systolic BPV are shown to be associated with poorer cognitive function, and therefore, long-term management of blood pressure variability is also important to reduce the risk of cognitive impairment.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".