LLM-Cardio: A Large Language Model-Based Assistant for Cardiovascular Health Inquiry and Diagnostic Support Using Wearable Data
Bibliographic record
Abstract
The global increase in cardiovascular disease (CVD) cases, along with the growing use of wearable health technologies, has created a demand for intelligent tools that support early diagnostic support and monitoring of heart conditions.This work introduces LLM-Cardio, an AI-driven cardiology assistant that combines wearable and clinical data with large language model (LLM) reasoning for personalized cardiovascular assessment.The system is powered by the Meta-Llama-3.1-8B-Instructmodel (4-bit), fine-tuned using the LoRA (Low-Rank Adaptation) method on a cardiology-specific dataset that includes structured medical records, diagnostic reports, clinical cases, and medical Q&A data.The system integrates streaming vital-sign data (simulated in this study) with an instruction-tuned LLM to deliver adaptive cardiovascular diagnostic support.A key contribution is the fine-tuning of a pretrained LLM on cardiology-specific datasets, including diagnostic reports, clinical cases, and medical Q&A data.Users can describe symptoms or ask cardiology-related questions and receive medically grounded, explainable responses, while simultaneously monitoring vital signs through a responsive mobile interface.Using BERTScore, the fine-tuned model achieved Precision=0.9463,Recall=0.9527,F1-score=0.9493, outperforming baseline generative models in semantic similarity on our test set.LLM-Cardio illustrates the potential of merging wearable technologies with AI reasoning for intelligent cardiac monitoring and diagnosis, and sets the groundwork for future integration with real devices and clinical validation toward proactive cardiovascular care.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".