Age, sex, hypertension and the sensitivity and specificity of traditional, new and a machine learning ECG criteria for prediction of left ventricular hypertrophy
Bibliographic record
Abstract
OBJECTIVE: To evaluate the impact of age, sex and hypertension to improve ECG diagnosis of Left Ventricular Hypertrophy (LVH). METHODS: The study evaluated 14 different QRS voltage criteria as well as our recently proposed criteria of S in V3 plus S in V4 in a population of 159 patients, of whom 14.5 % had echocardiographic evidence of LVH. Statistical analyses assessed the influence of age, sex, and hypertension on the sensitivity and specificity of each criterion. In addition, a machine learning model was used for enhanced diagnostic accuracy. RESULTS: The new SV3 + SV4 criterion had the highest F1 and AUC scores. Among traditional ECG criteria, the Peguero criterion showed the highest sensitivity (0.438), while Wilson and Mazeloni criteria demonstrated the highest specificity (0.9412). The new SV3 + SV4 criterion with sex-specific cut offs achieves a sensitivity of 0.500 and specificity of 0.809 in females, while in males, sensitivity reached 0.556 with specificity at 0.910. Multiple regression analysis indicated that age, sex, and hypertension significantly improved the diagnostic performance of specific criteria, including Sokolow-Lyon, Romhilt voltage, Murphy, and Grant criteria. However, other criteria were not impacted by considering age, sex, or hypertension. ML analysis improved diagnostic accuracy with clinical variables, with the highest performance in males with the addition of age (accuracy 0.959, sensitivity 0.556, and specificity 1.00). CONCLUSION: Considering age, sex, and hypertension can enhance the diagnostic performance of certain ECG criteria and especially in a ML model for LVH. Findings support a more individualized approach for LVH diagnosis in diverse patient populations.
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 | 0.003 | 0.013 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| 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 | 0.000 |
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".