Enhancing Framingham Cardiovascular Risk Score Transparency through Logic-Based XAI

Emannuel L. de A. Bezerra; Luiz H. T. Viana; Vinícius P. Chagas; Diogo E. Rolim; Thiago Alves Rocha; Carlos H. L. Cavalcante

cs.LOFeb 25, 2026

Enhancing Framingham Cardiovascular Risk Score Transparency through Logic-Based XAI

Authors: Emannuel L. de A. Bezerra, Luiz H. T. Viana, Vinícius P. Chagas, Diogo E. Rolim, Thiago Alves Rocha, Carlos H. L. Cavalcante

Organizations: Instituto Federal do Ceará (IFCE), Maracanaú, Ceará Brazil

Abstract

Cardiovascular disease (CVD) remains one of the leading global health challenges, accounting for more than 19 million deaths worldwide. To address this, several tools that aim to predict CVD risk and support clinical decision making have been developed. In particular, the Framingham Risk Score (FRS) is one of the most widely used and recommended worldwide. However, it does not explain why a patient was assigned to a particular risk category nor how it can be reduced. Due to this lack of transparency, we present a logical explainer for the FRS. Based on first-order logic and explainable artificial intelligence (XAI) fundaments, the explainer is capable of identifying a minimal set of patient attributes that are sufficient to explain a given risk classification. Our explainer also produces actionable scenarios that illustrate which modifiable variables would reduce a patient's risk category. We evaluated all possible input combinations of the FRS (over 22,000 samples) and tested them with our explainer, successfully identifying important risk factors and suggesting focused interventions for each case. The results may improve clinician trust and facilitate a wider implementation of CVD risk assessment by converting opaque scores into transparent and prescriptive insights, particularly in areas with restricted access to specialists.

Figures & tables

Points	Risk (%)
$\leq-3$ or less	$<1$
$-2$	1.1
$-1$	1.4
0	1.6
1	1.9
2	2.3

Table 2: Risk percentage according to total points for male [ 7 ]

Feature	#Values (Male)	#Values (Female)
Age	10	10
HDL	5	5
Total ChoL	5	5
SBP	5	6
Treatment for SBP	2	2
Smoker	2	2

Table 3: Number of possible values for each feature after continuous-features quantization for males and famale

Number of Features	Abductive (%)
3	4.00
4	18.14
5	25.15
6	35.97
7	16.05
8	0.70

Table 4: Distribution of abductive explanation sparsity over all FRS inputs

Feature	Count	% of all samples
Age	21 593	98.2%
Systolic blood pressure	20 329	92.4%
Smoker status	15 662	71.2%
HDL cholesterol	14 588	66.3%
Total cholesterol	13 095	59.5%
Treatment for SBP	11 257	51.2%

Table 5: Feature presence in abductive explanations over all inputs

Number of Features	Counterfactual (%)
1	47.17
2	35.07
3	13.06
4	3.32
5	0.54
6	0.84

Table 6: Distribution of counterfactual explanation sparsity over Moderate-Risk and High-Risk FRS inputs

Feature	Count	%
Systolic blood pressure	8 330	43.7%
Total cholesterol	8 019	42.1%
Treatment for SBP	5 958	31.3%
HDL cholesterol	4 983	26.2%
Smoker status	2 450	12.9%
Sex, age	0	0.0%

Table 7: Feature presence in counterfactual explanations (excluding low-risk)

Explainable Artificial Intelligence

Explainable artificial intelligence develops ways to make AI decisions understandable, testable, and useful to people.

See all 320 papers

Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy
Feb 25, 2026Vinícius P. Chagas, Luiz H. T. Viana, Mac M. da S. Carlos +4Clinical Risk Prediction Mortality Prediction
Federal Institute of Education and Technology of Ceara, Maracanau, Ceara, Brazil · Universidade Feferal do Ceará (UFC), CE · Edson Saad Heart Institute – Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports
Jun 9, 2026Olga Shakhmatova, Dmitrii Kriukov, Daniil Larionov +10Clinical Risk Prediction Cardiovascular Risk Prediction
National Medical Research Center of Cardiology named after Academician E.I. Chazov, Moscow, Russia · Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia · Artificial Intelligence Research Institute (AIRI), Moscow, Russia +8
Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models
Sep 10, 2026Raad Bin Tareaf, Murad Al-Rajab, Samia Loucif +2Data Leakage Tabular Foundation Models
Data Science and AI Cluster, XU Exponential University of Applied Sciences, Potsdam, Germany · German University of Digital Science, Potsdam, Germany · College of Engineering, Abu Dhabi University, Abu Dhabi, United Arab Emirates +2

Feb 25, 2026J/K move · Enter open · S save

Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy

Vinícius P. Chagas, Luiz H. T. Viana, Mac M. da S. Carlos, João P. V. Madeiro+3

Federal Institute of Education and Technology of Ceara, Maracanau, Ceara, Brazil · Universidade Feferal do Ceará (UFC), CE · Edson Saad Heart Institute – Federal University of Rio de Janeiro, Rio de Janeiro, Brazil

Clinical Risk Prediction Mortality Prediction Explainable Artificial Intelligence Explainability Evaluation

Open paper AskPDF arXiv

Sudden cardiac death (SCD) is unpredictable, and its prediction in Chagas cardiomyopathy (CC) remains a significant challenge, especially in patients not classified as high risk. While AI and machine learning models improve risk stratification, their adoption is hindered by a lack of transparency, as they are often perceived as black boxes with unclear decision-making processes. Some approaches apply heuristic explanations without correctness guarantees, leading to mistakes in the decision-making process. To address this, we apply a logic-based explainability method with correctness guarantees to the problem of SCD prediction in CC. This explainability method, applied to an AI classifier with over 95% accuracy and recall, demonstrated strong predictive performance and 100% explanation fidelity. When compared to state-of-the-art heuristic methods, it showed superior consistency and robustness. This approach enhances clinical trust, facilitates the integration of AI-driven tools into practice, and promotes large-scale deployment, particularly in endemic regions where it is most needed.

Abstract

Explainable Artificial Intelligence

Explore similar work

Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy

Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports

Target leakage, not model class, explains reported accuracy in survey-based cardiovascular screening: a leakage-tiered audit of glass-box and tabular foundation models