International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 06 | Jun 2023
p-ISSN: 2395-0072
www.irjet.net
Explainable AI in Healthcare: Enhancing Transparency and Trust upon Legal and Ethical Consideration Mohammad Nazmul Alam1, Mandeep Kaur2, Md. Shahin Kabir3 1Assistant Professor, 2Assistant Professor, 3Assistant Professor, 1Department of Computer Applications, 2Department of Computer Applications, 3Department of Law
1Guru Kashi University, Bathinda, Punjab, India, 2Guru Kashi University, Bathinda, Punjab, India, 3Raffles
University, Rajasthan, India ---------------------------------------------------------------------***-------------------------------------------------------------------- Explore the concept of XAI and its significance in Abstract- As artificial intelligence (AI) continues to make significant advancements in healthcare, there is a growing need to ensure the transparency and trustworthiness of AIdriven clinical decision-making. Explainable AI (XAI) has emerged as a promising approach to address this challenge by providing clear and interpretable explanations for the predictions and recommendations made by AI algorithms. This research paper explores the application of XAI techniques in healthcare and examines their impact on improving patient outcomes, clinician trust, and regulatory compliance. Various XAI methods, such as rule-based models, decision trees, and model-agnostic techniques, are discussed in the context of healthcare research, and their potential benefits and limitations are explored. Additionally, ethical considerations, challenges, and future directions for integrating XAI into healthcare systems are also discussed.
II.
Healthcare, Decision making.
INTRODUCTION
Artificial intelligence (AI) has shown great potential in revolutionizing healthcare by enabling more accurate diagnoses, personalized treatments, and efficient healthcare delivery. However, the lack of transparency and interpretability in AI algorithms poses challenges for clinicians, patients, and regulatory bodies. Explainable AI (XAI) seeks to address these challenges by providing clear explanations for the decisions made by AI models, thereby increasing trust, understanding, and accountability in healthcare settings.
TABLE I. L ITERATURE REVIEW Author Year
The increasing adoption of AI in healthcare has raised concerns about the "black box" nature of these algorithms. Clinicians and patients often find it difficult to trust and rely on AI-driven recommendations without understanding the underlying reasoning. Moreover, regulatory bodies require transparency to ensure patient safety, ethical compliance, and regulatory standards. XAI offers a solution to bridge the gap between the inherent complexity of AI models and the need for understandable decision-making processes in healthcare. The primary objectives of this research paper are to:
© 2023, IRJET
|
Impact Factor value: 8.226
LITERATURE REVIEW
Explainable AI (XAI) has gained significant attention in healthcare due to its potential to enhance transparency, interpretability, and trust in AI-based systems used for clinical decision-making. This literature review aims to explore previous research focused on the development and application of XAI techniques in healthcare, specifically emphasizing the importance of transparency, trust, and considering legal and ethical considerations. By analyzing the selected research papers, this review aims to provide insights into the significance of XAI in healthcare and its impact on building trust among clinicians, patients, and AI systems [10-15].
Keywords: Explainable AI, Trust in AI, Transparency in AI, I.
healthcare. Investigate the different techniques and methods used for achieving explainability in AI models. Examine the applications of XAI in healthcare research and clinical practice. Discuss the evaluation and validation approaches for XAI in healthcare. Highlight the challenges and limitations associated with implementing XAI in healthcare settings. Suggest future directions for advancing XAI in healthcare research and practice.
|
and
Paper Title
Summary
Dosilovi6, F. K., Brci6, M., & Hlupi6, N. (n.d.)
Explainable Artificial Intelligence: A Survey.
The paper discusses the issue of lack of transparency and interpretability in many state-of-the-art machine learning models, which is a major drawback in applications such as healthcare and finance. The paper summarizes
ISO 9001:2008 Certified Journal
|
Page 828