TY - JOUR
T1 - On the road to explainable AI in drug-drug interactions prediction
T2 - A systematic review
AU - Vo, Thanh Hoa
AU - Nguyen, Ngan Thi Kim
AU - Kha, Quang Hien
AU - Le, Nguyen Quoc Khanh
N1 - Funding Information:
This work was supported by the Ministry of Science and Technology, Taiwan [grant number MOST110-2221-E-038-001-MY2].
Publisher Copyright:
© 2022 The Author(s)
PY - 2022/1
Y1 - 2022/1
N2 - Over the past decade, polypharmacy instances have been common in multi-diseases treatment. However, unwanted drug-drug interactions (DDIs) that might cause unexpected adverse drug events (ADEs) in multiple regimens therapy remain a significant issue. Since artificial intelligence (AI) is ubiquitous today, many AI prediction models have been developed to predict DDIs to support clinicians in pharmacotherapy-related decisions. However, even though DDI prediction models have great potential for assisting physicians in polypharmacy decisions, there are still concerns regarding the reliability of AI models due to their black-box nature. Building AI models with explainable mechanisms can augment their transparency to address the above issue. Explainable AI (XAI) promotes safety and clarity by showing how decisions are made in AI models, especially in critical tasks like DDI predictions. In this review, a comprehensive overview of AI-based DDI prediction, including the publicly available source for AI-DDIs studies, the methods used in data manipulation and feature preprocessing, the XAI mechanisms to promote trust of AI, especially for critical tasks as DDIs prediction, the modeling methods, is provided. Limitations and the future directions of XAI in DDIs are also discussed.
AB - Over the past decade, polypharmacy instances have been common in multi-diseases treatment. However, unwanted drug-drug interactions (DDIs) that might cause unexpected adverse drug events (ADEs) in multiple regimens therapy remain a significant issue. Since artificial intelligence (AI) is ubiquitous today, many AI prediction models have been developed to predict DDIs to support clinicians in pharmacotherapy-related decisions. However, even though DDI prediction models have great potential for assisting physicians in polypharmacy decisions, there are still concerns regarding the reliability of AI models due to their black-box nature. Building AI models with explainable mechanisms can augment their transparency to address the above issue. Explainable AI (XAI) promotes safety and clarity by showing how decisions are made in AI models, especially in critical tasks like DDI predictions. In this review, a comprehensive overview of AI-based DDI prediction, including the publicly available source for AI-DDIs studies, the methods used in data manipulation and feature preprocessing, the XAI mechanisms to promote trust of AI, especially for critical tasks as DDIs prediction, the modeling methods, is provided. Limitations and the future directions of XAI in DDIs are also discussed.
KW - Chemical structures
KW - Deep learning
KW - Drug-drug interaction
KW - Explainable artificial intelligence
KW - Machine learning
KW - Natural language processing
UR - http://www.scopus.com/inward/record.url?scp=85129638986&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129638986&partnerID=8YFLogxK
U2 - 10.1016/j.csbj.2022.04.021
DO - 10.1016/j.csbj.2022.04.021
M3 - Review article
AN - SCOPUS:85129638986
SN - 2001-0370
VL - 20
SP - 2112
EP - 2123
JO - Computational and Structural Biotechnology Journal
JF - Computational and Structural Biotechnology Journal
ER -