Trustworthy and reliable AI for heart disease diagnosis: advancing ethical and explainable healthcare decision-making

Giovanah Gogi; Santosh Kumar Gurung; Alexander Gegov; Farzad Arabikhan; Alexandar Ichtev

doi:10.1109/IJCNN64981.2025.11229043

Trustworthy and reliable AI for heart disease diagnosis: advancing ethical and explainable healthcare decision-making

Giovanah Gogi
, Santosh Kumar Gurung
, Alexander Gegov
, Farzad Arabikhan
, Alexandar Ichtev

Technical University of Sofia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Downloads (Pure)

Abstract

The integration of artificial intelligence (AI) in healthcare decision-making has revolutionised the diagnosis and treatment of many diseases. However, challenges such as model interpretability, data quality, algorithmic bias, and ethical considerations remain a barrier. This paper presents a multi-algorithm approach for heart disease diagnosis that prioritises accuracy, explainability, and ethical AI principles. It also aligns with Explainable Artificial Intelligence (XAI) principles by highlighting ante-hoc transparency through careful feature selection and a tailored CNN model design for heart disease diagnosis. By leveraging interpretable AI techniques and addressing key challenges, this paper demonstrates how trustworthy and reliable AI systems can transform healthcare. Additionally, it explores the potential of post-hoc explainability techniques, such as SHAP and LIME, to clarify the model decisions and build trust among the healthcare professionals. This work bridges the gap between AI and the clinical practice.

Original language	English
Title of host publication	2025 International Joint Conference on Neural Networks (IJCNN)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	7
ISBN (Electronic)	9798331510428
ISBN (Print)	9798331510435
DOIs	https://doi.org/10.1109/IJCNN64981.2025.11229043
Publication status	Published - 14 Nov 2025
Event	2025 International Joint Conference on Neural Networks - Rome, Italy Duration: 30 Jun 2025 → 5 Jul 2025

Publication series

Name	IEEE IJCNN Proceedings
Publisher	IEEE
ISSN (Print)	2161-4393
ISSN (Electronic)	2161-4407

Conference

Conference	2025 International Joint Conference on Neural Networks
Country/Territory	Italy
City	Rome
Period	30/06/25 → 5/07/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

artificial intelligence
explainable artificial intelligence
machine learning
convolutional neural networks
cardiovascular disease
heart disease

Access to Document

10.1109/IJCNN64981.2025.11229043

2025 IJCNN Final Camera Ready paperAccepted author manuscript (Post-print), 312 KBLicence: CC BY

Cite this

Gogi, G., Gurung, S. K., Gegov, A., Arabikhan, F., & Ichtev, A. (2025). Trustworthy and reliable AI for heart disease diagnosis: advancing ethical and explainable healthcare decision-making. In 2025 International Joint Conference on Neural Networks (IJCNN) (IEEE IJCNN Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN64981.2025.11229043

@inproceedings{ce32d783fb4e4921b8cb9a99f0c56d33,

title = "Trustworthy and reliable AI for heart disease diagnosis: advancing ethical and explainable healthcare decision-making",

abstract = "The integration of artificial intelligence (AI) in healthcare decision-making has revolutionised the diagnosis and treatment of many diseases. However, challenges such as model interpretability, data quality, algorithmic bias, and ethical considerations remain a barrier. This paper presents a multi-algorithm approach for heart disease diagnosis that prioritises accuracy, explainability, and ethical AI principles. It also aligns with Explainable Artificial Intelligence (XAI) principles by highlighting ante-hoc transparency through careful feature selection and a tailored CNN model design for heart disease diagnosis. By leveraging interpretable AI techniques and addressing key challenges, this paper demonstrates how trustworthy and reliable AI systems can transform healthcare. Additionally, it explores the potential of post-hoc explainability techniques, such as SHAP and LIME, to clarify the model decisions and build trust among the healthcare professionals. This work bridges the gap between AI and the clinical practice.",

keywords = "artificial intelligence, explainable artificial intelligence, machine learning, convolutional neural networks, cardiovascular disease, heart disease",

author = "Giovanah Gogi and Gurung, \{Santosh Kumar\} and Alexander Gegov and Farzad Arabikhan and Alexandar Ichtev",

year = "2025",

month = nov,

day = "14",

doi = "10.1109/IJCNN64981.2025.11229043",

language = "English",

isbn = "9798331510435",

series = "IEEE IJCNN Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2025 International Joint Conference on Neural Networks (IJCNN)",

address = "United States",

note = "2025 International Joint Conference on Neural Networks ; Conference date: 30-06-2025 Through 05-07-2025",

}

Gogi, G, Gurung, SK, Gegov, A , Arabikhan, F & Ichtev, A 2025, Trustworthy and reliable AI for heart disease diagnosis: advancing ethical and explainable healthcare decision-making. in 2025 International Joint Conference on Neural Networks (IJCNN). IEEE IJCNN Proceedings, Institute of Electrical and Electronics Engineers Inc., 2025 International Joint Conference on Neural Networks, Rome, Italy, 30/06/25. https://doi.org/10.1109/IJCNN64981.2025.11229043

Trustworthy and reliable AI for heart disease diagnosis: advancing ethical and explainable healthcare decision-making. / Gogi, Giovanah; Gurung, Santosh Kumar; Gegov, Alexander et al.
2025 International Joint Conference on Neural Networks (IJCNN). Institute of Electrical and Electronics Engineers Inc., 2025. (IEEE IJCNN Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Trustworthy and reliable AI for heart disease diagnosis: advancing ethical and explainable healthcare decision-making

AU - Gogi, Giovanah

AU - Gurung, Santosh Kumar

AU - Gegov, Alexander

AU - Arabikhan, Farzad

AU - Ichtev, Alexandar

PY - 2025/11/14

Y1 - 2025/11/14

N2 - The integration of artificial intelligence (AI) in healthcare decision-making has revolutionised the diagnosis and treatment of many diseases. However, challenges such as model interpretability, data quality, algorithmic bias, and ethical considerations remain a barrier. This paper presents a multi-algorithm approach for heart disease diagnosis that prioritises accuracy, explainability, and ethical AI principles. It also aligns with Explainable Artificial Intelligence (XAI) principles by highlighting ante-hoc transparency through careful feature selection and a tailored CNN model design for heart disease diagnosis. By leveraging interpretable AI techniques and addressing key challenges, this paper demonstrates how trustworthy and reliable AI systems can transform healthcare. Additionally, it explores the potential of post-hoc explainability techniques, such as SHAP and LIME, to clarify the model decisions and build trust among the healthcare professionals. This work bridges the gap between AI and the clinical practice.

AB - The integration of artificial intelligence (AI) in healthcare decision-making has revolutionised the diagnosis and treatment of many diseases. However, challenges such as model interpretability, data quality, algorithmic bias, and ethical considerations remain a barrier. This paper presents a multi-algorithm approach for heart disease diagnosis that prioritises accuracy, explainability, and ethical AI principles. It also aligns with Explainable Artificial Intelligence (XAI) principles by highlighting ante-hoc transparency through careful feature selection and a tailored CNN model design for heart disease diagnosis. By leveraging interpretable AI techniques and addressing key challenges, this paper demonstrates how trustworthy and reliable AI systems can transform healthcare. Additionally, it explores the potential of post-hoc explainability techniques, such as SHAP and LIME, to clarify the model decisions and build trust among the healthcare professionals. This work bridges the gap between AI and the clinical practice.

KW - artificial intelligence

KW - explainable artificial intelligence

KW - machine learning

KW - convolutional neural networks

KW - cardiovascular disease

KW - heart disease

UR - https://2025.ijcnn.org/authors/important-dates

U2 - 10.1109/IJCNN64981.2025.11229043

DO - 10.1109/IJCNN64981.2025.11229043

M3 - Conference contribution

SN - 9798331510435

T3 - IEEE IJCNN Proceedings

BT - 2025 International Joint Conference on Neural Networks (IJCNN)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2025 International Joint Conference on Neural Networks

Y2 - 30 June 2025 through 5 July 2025

ER -

Trustworthy and reliable AI for heart disease diagnosis: advancing ethical and explainable healthcare decision-making

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this