MaltSci 麦伴科研

Appearance

Curated Papers > Highly Cited Authoritative Literature on "AI Drug Discovery"

The practical implementation of artificial intelligence technologies in medicine. ​

Literature Information ​

DOI10.1038/s41591-018-0307-0
PMID30617336
JournalNature medicine
Impact Factor50.0
JCR QuartileQ1
Publication Year2019
Times Cited661
KeywordsArtificial Intelligence, Medicine, Clinical Implementation, Data Sharing, Patient Safety
Literature TypeJournal Article, Research Support, Non-U.S. Gov't, Review
ISSN1078-8956
Pages30-36
Issue25(1)
AuthorsJianxing He, Sally L Baxter, Jie Xu, Jiming Xu, Xingtao Zhou, Kang Zhang

TL;DR ​

This paper reviews the challenges of integrating AI technologies into clinical practice, addressing issues such as data privacy, algorithm transparency, and patient safety, while comparing the regulatory landscapes in the U.S., Europe, and China. The findings underscore the need for standardized protocols and greater interoperability to ensure effective and safe AI implementation in healthcare settings.

Search for more papers on MaltSci.com ​

Artificial Intelligence · Medicine · Clinical Implementation · Data Sharing · Patient Safety

Abstract ​

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.

MaltSci.com AI Research Service ​

Intelligent ReadingAnswer any question about the paper and explain complex charts and formulas
Locate StatementsFind traces of a specific claim within the paper
Add to KBasePerform data extraction, report drafting, and advanced knowledge mining

Primary Questions Addressed ​

  1. What are the most significant barriers to achieving widespread adoption of AI technologies in clinical settings?
  2. How do regulatory frameworks in Europe and China differ from those in the United States regarding AI in healthcare?
  3. What role does patient safety play in the development and implementation of AI algorithms in medicine?
  4. How can data standardization and interoperability be improved to facilitate the integration of AI technologies into healthcare systems?
  5. What measures can be taken to enhance transparency in AI algorithms used in medical applications?

Key Findings ​

Research Background and Purpose ​

The rapid advancement of artificial intelligence (AI) technologies in medicine presents significant opportunities for enhancing healthcare delivery. However, the transition from development to practical implementation within clinical workflows remains a challenge. This paper reviews key issues surrounding the integration of AI into healthcare, focusing on data sharing, algorithm transparency, data standardization, interoperability, and patient safety, while also comparing the regulatory environments in the United States, Europe, and China.

Main Methods/Materials/Experimental Design ​

The authors conducted a comprehensive review of the current state of AI in healthcare, highlighting the following key areas:

  1. Data Sharing: Emphasizes the necessity for anonymized and de-identified data across institutions and countries, which requires new consent processes and robust cybersecurity measures.
  2. Transparency: Discusses the importance of clear labeling of training data and algorithm interpretability to ensure accuracy and mitigate bias.
  3. Patient Safety: Addresses the need for regulatory frameworks that ensure the safety and efficacy of AI technologies, along with accountability mechanisms for adverse events.
  4. Data Standardization and Interoperability: Stresses the need for common formats for data across different systems to facilitate effective AI integration.
  5. Regulatory Environment: Examines the existing regulatory frameworks in the U.S. (FDA), Europe (GDPR), and China, highlighting their approaches to AI in healthcare.
Mermaid diagram

Key Results and Findings ​

  • AI Implementation: AI technologies have shown potential in various applications, such as diagnostics and treatment recommendations, but widespread clinical use remains limited.
  • Regulatory Challenges: The FDA has developed a new category for software as medical devices (SaMD), recognizing the unique challenges posed by AI technologies. However, the traditional regulatory processes are often not suited for the rapid evolution of software.
  • Global Comparison: Different regions have varying regulatory approaches; for instance, the EU's GDPR imposes stricter data protection regulations that may impact AI deployment.

Main Conclusions/Significance/Innovation ​

The authors conclude that while AI has the potential to revolutionize healthcare, significant hurdles must be addressed to facilitate its integration into clinical practice. This includes developing standardized data formats, ensuring algorithm transparency, establishing regulatory frameworks that promote innovation while safeguarding patient safety, and fostering a workforce that is educated in AI technologies. The paper highlights the importance of collaboration among stakeholders, including policymakers, healthcare providers, and AI developers, to realize the full potential of AI in medicine.

Research Limitations and Future Directions ​

  • Limitations: The paper primarily discusses theoretical frameworks and does not present empirical data from AI implementations, which may limit the applicability of its conclusions.
  • Future Directions: Future research should focus on real-world applications of AI in diverse clinical settings, the development of best practices for data sharing and algorithm transparency, and ongoing education for healthcare professionals to adapt to AI advancements. The authors advocate for interdisciplinary collaboration to ensure that AI technologies meet clinical needs effectively.

Literatures Citing This Work ​

  1. Artificial Intelligence vs. Natural Stupidity: Evaluating AI readiness for the Vietnamese Medical Information System. - Quan-Hoang Vuong;Manh-Tung Ho;Thu-Trang Vuong;Viet-Phuong La;Manh-Toan Ho;Kien-Cuong P Nghiem;Bach Xuan Tran;Hai-Ha Giang;Thu-Vu Giang;Carl Latkin;Hong-Kong T Nguyen;Cyrus S H Ho;Roger C M Ho - Journal of clinical medicine (2019)
  2. Are There New Biomarkers in Tissue and Liquid Biopsies for the Early Detection of Non-Small Cell Lung Cancer? - Fiorella Calabrese;Francesca Lunardi;Federica Pezzuto;Francesco Fortarezza;Stefania Edith Vuljan;Charles Marquette;Paul Hofman - Journal of clinical medicine (2019)
  3. Artificial Intelligence in Clinical Health Care Applications: Viewpoint. - Michael van Hartskamp;Sergio Consoli;Wim Verhaegh;Milan Petkovic;Anja van de Stolpe - Interactive journal of medical research (2019)
  4. Remote Control of Greenhouse Vegetable Production with Artificial Intelligence-Greenhouse Climate, Irrigation, and Crop Production. - Silke Hemming;Feije de Zwart;Anne Elings;Isabella Righini;Anna Petropoulou - Sensors (Basel, Switzerland) (2019)
  5. Discovering Clinical Information Models Online to Promote Interoperability of Electronic Health Records: A Feasibility Study of OpenEHR. - Lin Yang;Xiaoshuo Huang;Jiao Li - Journal of medical Internet research (2019)
  6. Automated Classification of Malignant and Benign Breast Cancer Lesions Using Neural Networks on Digitized Mammograms. - Mohammed M Abdelsamea;Marghny H Mohamed;Mohamed Bamatraf - Cancer informatics (2019)
  7. Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the Digital Pathology Association. - Esther Abels;Liron Pantanowitz;Famke Aeffner;Mark D Zarella;Jeroen van der Laak;Marilyn M Bui;Venkata Np Vemuri;Anil V Parwani;Jeff Gibbs;Emmanuel Agosto-Arroyo;Andrew H Beck;Cleopatra Kozlowski - The Journal of pathology (2019)
  8. Artificial Intelligence Screening for Diabetic Retinopathy: the Real-World Emerging Application. - Valentina Bellemo;Gilbert Lim;Tyler Hyungtaek Rim;Gavin S W Tan;Carol Y Cheung;SriniVas Sadda;Ming-Guang He;Adnan Tufail;Mong Li Lee;Wynne Hsu;Daniel Shu Wei Ting - Current diabetes reports (2019)
  9. Predictive analytics in health care: how can we know it works? - Ben Van Calster;Laure Wynants;Dirk Timmerman;Ewout W Steyerberg;Gary S Collins - Journal of the American Medical Informatics Association : JAMIA (2019)
  10. Looking beyond the hype: Applied AI and machine learning in translational medicine. - Tzen S Toh;Frank Dondelinger;Dennis Wang - EBioMedicine (2019)

... (651 more literatures)

© 2025 MaltSci - We reshape scientific research with AI technology