Machine Learning to identify factors that affect Human Systolic Blood Pressure
Bibliographic record
Abstract
This paper employs different machine learning algorithms to perform a regression study to predict systolic blood pressure (SBP) levels. We used blood pressure dataset of Dr. Raymond Lam, GlaxoSmithKline, Toronto, Ontario, Canada in this study. There are 500 patients in the dataset, 250 have normal blood pressure level and the other 250 have hypertension. There are 500 predictors in the dataset. 17 predictors are patients' non-genomic information and the rest are 483 genetic markers. In this paper, we have selected only the following 13 factors as predictors in this study to reduce the complexity of the problem. The predictors included in this study are 'gender', 'married', 'smoke', 'exercise level', 'age', 'weight', 'height', 'alcohol consumption', 'treatment for hypertension', 'stress level', 'salt intake level', 'income' and 'education level'. The regression model that gave the lowest root mean square error in SBP of 25.68 for the 13 predictors is Gaussian Process Regression using the squared exponential function in the regression model. Although the RMS value was quite high, it was sufficient to draw some conclusions and identify the factors that do affect the SBP level.
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| 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".