Using Machine Learning to Detect Factors That Affect Homocysteine in Healthy Elderly Taiwanese Men
Bibliographic record
Abstract
Background: Homocysteine (Hcy) is a sulfur-containing amino acid crucial for various physiological processes, with elevated levels linked to cardiovascular and neurological adverse conditions. Various factors contribute to high Hcy, and past studies of impact factors relied on traditional statistical methods. Recently, machine learning (ML) techniques have greatly improved and are now widely applied in medical research. This study used four ML methods to identify key factors influencing Hcy in healthy elderly Taiwanese men, comparing their accuracy using multiple linear regression (MLR). The study seeks to improve Hcy prediction accuracy and provide insights into relevant impact factors. Methods: A total of 468 healthy elderly men were studied in terms of 33 parameters using four ML methods: random forest (RF), stochastic gradient boosting (SGB), eXtreme gradient boosting (XGBoost), and elastic net (EN). MLR served as a benchmark. Model performance was assessed using SMAPE, RAE, RRSE, and RMSE. Results: All ML methods demonstrated lower prediction errors than MLR, indicating higher accuracy. By averaging the importance scores from the four ML models, C-reactive protein (CRP) emerged as the leading impact factor for Hcy, followed by GPT, WBC, LDH, eGFR, and sport volume (SV). Conclusions: Machine learning methods outperformed MLR in predicting Hcy levels in healthy elderly Taiwanese men. CRP was identified as the most crucial factor, followed by GPT/ALT, WBC, LDH, and eGFR.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 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".