The practical implementation of artificial intelligence technologies in medicine
By J. He, Sally L. Baxter, Jie Xu, Jiming Xu, Xingtao Zhou, Kang Zhang. 2019
1,892 citations recorded by the source corpus.
The development of artificial intelligence (AI)-based technologies in medicine is advancing rapidly, but real-world clinical implementation has not yet become a reality. Here we review some of the key practical issues surrounding the implementation of AI into existing clinical workflows, including data sharing and privacy, transparency of algorithms, data standardization, and interoperability across multiple platforms, and concern for patient safety. We summarize the current regulatory environment in the United States and highlight comparisons with other regions in the world, notably Europe and China. To bring the full potential of AI to the clinic, practical and regulatory changes need to be made in health systems globally.
Subfields: Artificial Intelligence, Health Informatics, Radiology, Nuclear Medicine and Imaging
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Jessica Morley
- Luciano Floridi
- Josh Cowls
- Marzyeh Ghassemi
- Anna Goldenberg
- Joseph D. Futoma
- Mariarosaria Taddeo
- Suchi Saria
In Health Informatics
- Jessica Morley
- Luciano Floridi
- Mariarosaria Taddeo
- Zeeshan Ahmed
- Saman Zeeshan
- Khalid Mohamed
- Xinqi Dong
- Finale Doshi-Velez
In Radiology, Nuclear Medicine and Imaging
- Anil V. Parwani
- Pouyan Esmaeilzadeh
- Zeeshan Ahmed
- Khalid Mohamed
- Xinqi Dong
- Saman Zeeshan
- Hock Hai Teo
- John P. A. Ioannidis
Citations in the corpus
- The ethics of AI in health care: A mapping review. (2020, background): “In their overview of patient-safety issues with AI in healthcare, He et al. (2019) state that those working in the field are trying to establish a systems-wide approach that does not attribute blame to individuals or individual companies, but conclude that where liability will ultimately rest…”
- Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension (2020, neutral): “14 While AI systems have been researched for some time, recent advances in deep learning and neural networks have gained considerable interest for their potential in health applications.”
- Use of AI-based tools for healthcare purposes: a survey study from consumers’ perspectives (2020, background): “1 Research model and quality of autonomous operations an essential factor affecting the use of AI devices [27].”
- "The human body is a black box": supporting clinical decision-making with deep learning (2019, background): “Many experts cite explainable machine learning as the answer to protecting patient safety and ensuring professional accountability [24, 49].”
- Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the Digital Pathology Association (2019, background): “Most importantly, the laboratory accreditation landscape must become flexible enough to accommodate novel scoring and deep learning methods that promise to improve accuracy and reproducibility [55,57].”
- MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care (2020, background): “There is a global consensus that AI solutions must be fair and nondiscriminatory and that AI solutions in health care should have a positive impact across all sectors of social and economic life.(2,14,15) However, through a lack of incentives, restrictions around data sharing and data privacy, and t”
- Role of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review (2020, background): “However, their implementation in real-life clinical practice is not widespread [1,7].”
- The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies (2020, methodology): “Lack of transparency is identified as one of the key barriers to implementation [5,6].”
- Artificial intelligence and machine learning in precision and genomic medicine (2021, background): “Since artificial intelligence has incorporated high-performance computing, we can determine and anticipate disease risk based on patients' data [20].”
- Artificial intelligence in drug development (2025, positive): “246), we can be judiciously optimistic about AI’s promise for accelerating drug development and benefiting human health.”
- Do no harm: a roadmap for responsible machine learning for health care (2019, methodology): “Third, statistical analysis should consider clinically relevant evaluation metrics, as recently described 3 .”
- The Recent Progress and Applications of Digital Technologies in Healthcare: A Review (2020, background): “Moreover, it could contribute to the optimization of treat-ment processes thus leading to an increase in therapeutic e ffi - ciency, patient satisfaction, and lower costs [6].”