Integrating Machine Learning Ensembles and Large Language Models for Heart Disease Prediction Using Voting Fusion

Md. Tahsin Amin; Tanim Ahmmod; Zannatul Ferdus; Talukder Naemul Hasan Naem; Ehsanul Ferdous; Arpita Bhattacharjee; Ishmam Ahmed Solaiman; Nahiyan Bin Noor

cs.LGFeb 25, 2026

Integrating Machine Learning Ensembles and Large Language Models for Heart Disease Prediction Using Voting Fusion

Authors: Md. Tahsin Amin, Tanim Ahmmod, Zannatul Ferdus, Talukder Naemul Hasan Naem, Ehsanul Ferdous, Arpita Bhattacharjee, Ishmam Ahmed Solaiman, Nahiyan Bin Noor

Organizations: Faculty of Computer Science & Engineering, Patuakhali Science & Technology University, Bangladesh · Dept. of Electrical & Electronic Engineering, Rajshahi University of Engineering & Technology, Bangladesh · Dept. of Industrial & Production Engineering, Ahsanullah University of Science & Technology, Bangladesh · Dept. of Computer Science & Engineering, National Institute of Technology, Silchar, India · University of Arkansas at Little Rock, Little Rock, Arkansas, USA · Institute for Digital Health & Innovation, University of Arkansas for Medical Sciences, Arkansas, USA

Abstract

Cardiovascular disease is the primary cause of death globally, necessitating early identification, precise risk classification, and dependable decision-support technologies. The advent of large language models (LLMs) provides new zero-shot and few-shot reasoning capabilities, even though machine learning (ML) algorithms, especially ensemble approaches like Random Forest, XGBoost, LightGBM, and CatBoost, are excellent at modeling complex, non-linear patient data and routinely beat logistic regression. This research predicts cardiovascular disease using a merged dataset of 1,190 patient records, comparing traditional machine learning models (95.78% accuracy, ROC-AUC 0.96) with open-source large language models via OpenRouter APIs. Finally, a hybrid fusion of the ML ensemble and LLM reasoning under Gemini 2.5 Flash achieved the best results (96.62% accuracy, 0.97 AUC), showing that LLMs (78.9 % accuracy) work best when combined with ML models rather than used alone. Results show that ML ensembles achieved the highest performance (95.78% accuracy, ROC-AUC 0.96), while LLMs performed moderately in zero-shot (78.9%) and slightly better in few-shot (72.6%) settings. The proposed hybrid method enhanced the strength in uncertain situations, illustrating that ensemble ML is considered the best structured tabular prediction case, but it can be integrated with hybrid ML-LLM systems to provide a minor increase and open the way to more reliable clinical decision-support tools.

Figures & tables

Attribute	Values / Range
Age	Continuous
Sex	Male / Female
Chest Pain Type	TA, ATA, NAP, ASY
Resting BP	Continuous
Cholesterol	Continuous
Fasting BS	1 = Yes, 0 = No

TABLE I: Dataset Attribution

Fig. 2: Proposed Hybrid ML–LLM Fusion Framework

Fig. 3: Model test accuracy comparison for all machine learning models

Fig. 4: ROC curves comparison for all machine learning models

Model	Accuracy (%)
CatBoost)	92.44
Random Forest	92.02
XGBoost	90.76
LightGBM	90.34
Gradient Boosting	89.92
SVM	85.02

TABLE II: Performance of Individual Machine Learning Models

Ensemble Strategy	Accuracy (%)	AUC
Soft Voting (Weighted))	95.23	0.96
Hard Voting	93.78	0.98

TABLE III: Ensemble Model Results

Panel of Figure 8 — Fig. 5: Confusion matrices of ensemble predictions: soft voting (left) and hard voting (right)

Model Name	Accuracy (%)	Accuracy (%)
Qwen 3 Coder	81.34	72.94
X AI Grok Code Fast 1	81.18	71.51
Z AI GLM 4.5 Air	80.08	72.94
Meta Llama 4 Maverick	79.24	76.20
Moonshot AI Kimi K2	78.82	75.29
OpenAI GPT 5	77.39	52.86

TABLE IV: Performance of LLMs with Zero-Shot and Few-Shot Prompting

Method	Accuracy	AUC
Zero soft voting	0.789	0.804
Zero hard voting	0.776	0.782
Few soft voting	0.726	0.727
Few hard voting	0.722	0.729

TABLE V: LLM Model Voting Results

Fig. 6: Confusion matrices of LLM voting results under (a) Zero Shot(Soft vote), (b) Zero Shot (Hard vote), (c) Few Shot (Soft vote) and (d) Few Shot (Hard vote)

Ref.	Model / Approach	Accuracy (%)
[16]	Feature-Selected Stacking Ensemble	82.56
[18]	AdaBoost Decision Fusion (ABDF)	83.0
[14]	Data Mining Model (10-fold CV)	86.3
[15]	Firefly + Stacking Ensemble	86.79
[25]	Stacking Ensemble & Voting Ensemble	91.0
[17]	VAE + DNN Stacked Ensemble (HDPM)	92.3

TABLE VI: Comparative Performance of Ensemble-Based CVD Prediction Methods

Fig. 7: Confusion matrices of fusion Pipeline

Fig. 8: ROC Curves of Comparison Across Model.

Explore similar work

LLMs for Cardiovascular Risk Prediction from Structured Clinical Data
Apr 21, 2026Jeba Maliha, Md Rafiul KabirMedical LLMs Clinical Risk Prediction
Central Michigan University, Mount Pleasant, MI, USA
Evaluating LLM-Generated Rules for Heart Disease Prediction
Aug 11, 2026Feisal Alaswad, Batoul Aljaddouh, Maher Alrahhal +2Clinical Risk Prediction Interpretable ML
Department of Computing Technologies, SRM Institute of Science and Technology, Kattankulathur, Chennai, India · Department of Computer Science, Amity University Dubai, Dubai, UAE · College of Computing and Informatics, University of Sharjah,Sharjah, UAE
Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure
Mar 18, 2024Ziyi Chen, Mengyuan Zhang, Mustafa Mohammed Ahmed +4Healthcare Oncology
Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL, USA · Division of Cardiovascular Medicine, Department of Medicine, College of Medicine, University of Florida, Gainesville, FL, USA · Division of Hematology & Oncology, Department of Medicine, College of Medicine, University of Florida, Gainesville, FL, USA

Apr 21, 2026J/K move · Enter open · S save

LLMs for Cardiovascular Risk Prediction from Structured Clinical Data

Jeba Maliha, Md Rafiul Kabir

Central Michigan University, Mount Pleasant, MI, USA

Medical LLMs Clinical Risk Prediction

Open paper AskPDF arXiv

Coronary artery disease (CAD) remains one of the leading causes of death globally, highlighting the need for reliable predictive systems to support early diagnosis and risk assessment. While traditional machine learning models perform well on structured clinical data, large language models (LLMs) present new possibilities to interpret medical information expressed in natural language. In this work, we develop a hybrid framework that bridges structured clinical data and natural-language representations for CAD prediction. Using a publicly available dataset of 1,190 patient records with 11 clinical attributes, structured variables are converted into interpretable feature representations and synthetic clinical narratives using LLMs. A validation pipeline performs reverse extraction of clinical variables and computes a consistency score with the original records, achieving an average fidelity of 94.61%. We then evaluate four conventional machine learning models and compare their performance with LLM-based classification under zero-shot and few-shot prompting settings. We use two LLMs here, GPT and Gemini. Experimental results show that Random Forest achieves the highest accuracy. Despite this advantage, LLM-based classification remains beneficial in real-world clinical settings. This is because LLMs operate directly on natural language patient descriptions, meaning that sensitive numerical patient data such as exact lab values, blood pressure readings, and diagnostic codes are kept private. Findings suggest that combining structured clinical data with LLM-generated narratives can enable new directions for hybrid clinical prediction systems.

Abstract

Explore similar work

LLMs for Cardiovascular Risk Prediction from Structured Clinical Data

Evaluating LLM-Generated Rules for Heart Disease Prediction

Narrative Feature or Structured Feature? A Study of Large Language Models to Identify Cancer Patients at Risk of Heart Failure