Redefining biomaterial biocompatibility: challenges for artificial intelligence and text mining

• Published in: Trends in biotechnology (Regular ed.) Vol. 42; no. 4; pp. 402 - 417
• Main Authors: Mateu-Sanz, Miguel, Fuenteslópez, Carla V., Uribe-Gomez, Juan, Haugen, Håvard Jostein, Pandit, Abhay, Ginebra, Maria-Pau, Hakimi, Osnat, Krallinger, Martin, Samara, Athina
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01-04-2024; Elsevier Limited
• Subjects: Artificial intelligence; Automation; Big Data; Biocompatibility; biomaterial; Biomaterials; Biomedical materials; Clinical trials; Data mining; Datasets; Electronic health records; Electronic medical records; international organization for standardization (ISO); Language; Market entry; Medical equipment; Medical research; Medical technology; natural language processing; Ontology; Product development; R&D; Regulatory approval; Research & development; databases; international organization for standardization (ISO); biomaterial; natural language processing; biocompatibility; data mining; artificial intelligence
• ISSN: 0167-7799; 1879-3096
• DOI: 10.1016/j.tibtech.2023.09.015

Biomaterials designed to interact with living systems should be evaluated for their biocompatibility; however, current definitions of biocompatibility are ambiguous and not well delimited.The need for a consensus on the definition of biocompatibility complicates the understanding of its practical requirements, rendering data extraction difficult.A working definition of biocompatibility will enable the use of computational tools to extract relevant information and perform reasoning.Analyzing the international standards allowed us to include relevant specifications in the working definition of biocompatibility and identify useful vocabularies for text mining.Charting the key elements and gaps in existing biocompatibility definitions enabled us to narrow down a unified and implementable working definition matching automated data extraction requirement.
The surge in ‘Big data’ has significantly influenced biomaterials research and development, with vast data volumes emerging from clinical trials, scientific literature, electronic health records, and other sources. Biocompatibility is essential in developing safe medical devices and biomaterials to perform as intended without provoking adverse reactions. Therefore, establishing an artificial intelligence (AI)-driven biocompatibility definition has become decisive for automating data extraction and profiling safety effectiveness. This definition should both reflect the attributes related to biocompatibility and be compatible with computational data-mining methods. Here, we discuss the need for a comprehensive and contemporary definition of biocompatibility and the challenges in developing one. We also identify the key elements that comprise biocompatibility, and propose an integrated biocompatibility definition that enables data-mining approaches.
The surge in ‘Big data’ has significantly influenced biomaterials research and development, with vast data volumes emerging from clinical trials, scientific literature, electronic health records, and other sources. Biocompatibility is essential in developing safe medical devices and biomaterials to perform as intended without provoking adverse reactions. Therefore, establishing an artificial intelligence (AI)-driven biocompatibility definition has become decisive for automating data extraction and profiling safety effectiveness. This definition should both reflect the attributes related to biocompatibility and be compatible with computational data-mining methods. Here, we discuss the need for a comprehensive and contemporary definition of biocompatibility and the challenges in developing one. We also identify the key elements that comprise biocompatibility, and propose an integrated biocompatibility definition that enables data-mining approaches.