The enlightening role of explainable artificial intelligence in medical & healthcare domains: A systematic literature review

Просветительская роль объяснимого искусственного интеллекта в медицине и здравоохранении: систематический обзор литературы
Ali Shariq Imran, Subhan Ali, Filza Akhlaq, Zenun Kastrati, Sher Muhammad Daudpota, Muhammad Moosa
2023-10-04

Explainable artificial intelligenceLIMEMedical machine learningModel interpretabilitySHAP
In domains such as medical and healthcare, the interpretability and explainability of machine learning and artificial intelligence systems are crucial for building trust in their results. Errors caused by these systems, such as incorrect diagnoses or treatments, can have severe and even life-threatening consequences for patients. To address this issue, Explainable Artificial Intelligence (XAI) has emerged as a popular area of research, focused on understanding the black-box nature of complex and hard-to-interpret machine learning models. While humans can increase the accuracy of these models through technical expertise, understanding how these models actually function during training can be difficult or even impossible. XAI algorithms such as Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) can provide explanations for these models, improving trust in their predictions by providing feature importance and increasing confidence in the systems. Many articles have been published that propose solutions to medical problems by using machine learning models alongside XAI algorithms to provide interpretability and explainability. In our study, we identified 454 articles published from 2018-2022 and analyzed 93 of them to explore the use of these techniques in the medical domain.
1
Explainable artificial intelligence addresses the opacity of complex machine-learning models by clarifying how their predictions are produced.
2
Interpretability and explainability are especially critical in healthcare because erroneous AI diagnoses or treatments can cause severe or life-threatening patient consequences.
3
LIME and SHAP are highlighted as model-agnostic XAI methods that explain predictions through feature importance, potentially increasing trust and confidence in healthcare AI systems.
4
The reviewed literature commonly combines machine-learning models with XAI techniques to provide interpretability for medical problem-solving.
5
The systematic review identified 454 relevant articles published between 2018 and 2022 and analyzed 93 studies on XAI applications in medicine.

machine learning and artificial intelligence systems used in medical and healthcare domains

the interpretability and explainability of these systems, including how XAI methods improve trust in their predictions

Publication Details
Publication Date
2023-10-04
Journal
Publisher
ISSN
Cited by
385
Access Type
Author Information
Authors
Ali Shariq Imran
Subhan Ali
Filza Akhlaq
Zenun Kastrati
Sher Muhammad Daudpota
Muhammad Moosa
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%