Abstract FR435: Artificial Intelligence-Enhanced Electrocardiography for the Detection and Prediction of Arterial Hypertension: A Systematic Review
Bibliographic record
Abstract
Background: Early detection and prediction of arterial hypertension (HTN) are vital to reduce cardiovascular morbidity and mortality. AI has enhanced ECG diagnostic capabilities, enabling detection of latent cardiovascular abnormalities. Aims: This systematic review evaluates current evidence on AI-enhanced ECG for detection and prediction of HTN in in both clinical and subclinical populations. Methods: A search was conducted on April 28, 2025, in PubMed, Scopus, and Web of Science. Gray literature and study reference lists, plus the first 10 pages of Google Scholar, were screened. The review followed PRISMA 2020 guidelines. Bias risk was assessed using PROBAST (for prediction models) and QUADAS-2 (for diagnostic studies). Two reviewers independently performed study selection and data extraction after pilot training. Results: A total of 26 studies were included: 16 focused on detection and 10 on prediction of HTN using AI-enhanced ECG. Overall, 96% reported successful outcomes, underscoring the strong diagnostic and prognostic potential of this approach. Among detection studies, 94% successfully identified hypertensive individuals, classified blood pressure (BP) levels, or evaluated cardiovascular risk. Most were retrospective in design (75%), with internal validation in 44% and external validation in 19%. Sample sizes ranged from 100 to over 120,000, including healthy and cardiovascular patients. Commonly used algorithms included deep Learning, random forest, and ensemble methods, often using single-lead ECG data, highlighting the feasibility of wearable technologies. QUADAS-2 identified 56% of studies had low risk of bias. All prediction studies achieved accurate estimation of systolic/diastolic BP or predicted future HTN onset. Designs were 40% experimental and 50% retrospective. All studies reported internal validation, and 50% included external validation. AI models such as CNNs, ResNet-LSTM, and U-Net were used across clinical and community-based populations, with follow-up periods of up to 6.8 years. Populations were predominantly normotensive or mixed. PROBAST assessments showed 60% low and 40% moderate risk of bias. Conclusion: AI-enhanced ECG is a promising, non-invasive tool for early detection and prediction of HTN. However, external validation and clinical trials are needed to support integration and generalizability.
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 | 0.006 | 0.028 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.009 | 0.007 |
| Bibliometrics | 0.008 | 0.008 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 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".