On the road to explainable AI in drug-drug interactions prediction: A systematic review
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...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-01-01
|
Series: | Computational and Structural Biotechnology Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037022001386 |
_version_ | 1797978218560487424 |
---|---|
author | Thanh Hoa Vo Ngan Thi Kim Nguyen Quang Hien Kha Nguyen Quoc Khanh Le |
author_facet | Thanh Hoa Vo Ngan Thi Kim Nguyen Quang Hien Kha Nguyen Quoc Khanh Le |
author_sort | Thanh Hoa Vo |
collection | DOAJ |
description | 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. |
first_indexed | 2024-04-11T05:19:29Z |
format | Article |
id | doaj.art-5f8e6fb777fd40d0af821ff69c0cbd93 |
institution | Directory Open Access Journal |
issn | 2001-0370 |
language | English |
last_indexed | 2024-04-11T05:19:29Z |
publishDate | 2022-01-01 |
publisher | Elsevier |
record_format | Article |
series | Computational and Structural Biotechnology Journal |
spelling | doaj.art-5f8e6fb777fd40d0af821ff69c0cbd932022-12-24T04:52:08ZengElsevierComputational and Structural Biotechnology Journal2001-03702022-01-012021122123On the road to explainable AI in drug-drug interactions prediction: A systematic reviewThanh Hoa Vo0Ngan Thi Kim Nguyen1Quang Hien Kha2Nguyen Quoc Khanh Le3Master Program in Clinical Genomics and Proteomics, College of Pharmacy, Taipei Medical University, Taipei 110, TaiwanSchool of Nutrition and Health Sciences, College of Nutrition, Taipei Medical University, Taipei 11031, TaiwanInternational Master/Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei 110, TaiwanProfessional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei 106, Taiwan; Research Center for Artificial Intelligence in Medicine, Taipei Medical University, Taipei 106, Taiwan; Translational Imaging Research Center, Taipei Medical University Hospital, Taipei 110, Taiwan; Corresponding author at: Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei 106, Taiwan.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.http://www.sciencedirect.com/science/article/pii/S2001037022001386Explainable artificial intelligenceDrug-drug interactionMachine learningDeep learningChemical structuresNatural language processing |
spellingShingle | Thanh Hoa Vo Ngan Thi Kim Nguyen Quang Hien Kha Nguyen Quoc Khanh Le On the road to explainable AI in drug-drug interactions prediction: A systematic review Computational and Structural Biotechnology Journal Explainable artificial intelligence Drug-drug interaction Machine learning Deep learning Chemical structures Natural language processing |
title | On the road to explainable AI in drug-drug interactions prediction: A systematic review |
title_full | On the road to explainable AI in drug-drug interactions prediction: A systematic review |
title_fullStr | On the road to explainable AI in drug-drug interactions prediction: A systematic review |
title_full_unstemmed | On the road to explainable AI in drug-drug interactions prediction: A systematic review |
title_short | On the road to explainable AI in drug-drug interactions prediction: A systematic review |
title_sort | on the road to explainable ai in drug drug interactions prediction a systematic review |
topic | Explainable artificial intelligence Drug-drug interaction Machine learning Deep learning Chemical structures Natural language processing |
url | http://www.sciencedirect.com/science/article/pii/S2001037022001386 |
work_keys_str_mv | AT thanhhoavo ontheroadtoexplainableaiindrugdruginteractionspredictionasystematicreview AT nganthikimnguyen ontheroadtoexplainableaiindrugdruginteractionspredictionasystematicreview AT quanghienkha ontheroadtoexplainableaiindrugdruginteractionspredictionasystematicreview AT nguyenquockhanhle ontheroadtoexplainableaiindrugdruginteractionspredictionasystematicreview |