Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-Driven Analysis of AI in Medical Device Software in China: Deep Learning and General AI Trends Based on Regulatory Data

Yu Han, Aaron Ceross, Sarim Ather, Jeroen H. M. Bergmann

TL;DR

This paper develops a data-driven, automated approach to map AI-enabled medical devices in China using the NMPA UDI database. It identifies 43 AIMD among roughly 2,149 MDSW entries, finds that most AIMD are DL-based and concentrated in domestic SaMD, and reveals that AI devices are predominantly Class III with limited presence in SiMD. The study also highlights regulatory inconsistencies between China and the US, demonstrating the value of automated regulatory data analysis for policy insight and market surveillance. The authors provide a reproducible workflow and publicly available code, while discussing limitations related to UDI labeling and the need for standardized AI-device nomenclature across regulatory databases.

Abstract

Artificial intelligence (AI) in medical device software (MDSW) represents a transformative clinical technology, attracting increasing attention within both the medical community and the regulators. In this study, we leverage a data-driven approach to automatically extract and analyze AI-enabled medical devices (AIMD) from the National Medical Products Administration (NMPA) regulatory database. The continued increase in publicly available regulatory data requires scalable methods for analysis. Automation of regulatory information screening is essential to create reproducible insights that can be quickly updated in an ever changing medical device landscape. More than 4 million entries were assessed, identifying 2,174 MDSW registrations, including 531 standalone applications and 1,643 integrated within medical devices, of which 43 were AI-enabled. It was shown that the leading medical specialties utilizing AIMD include respiratory (20.5%), ophthalmology/endocrinology (12.8%), and orthopedics (10.3%). This approach greatly improves the speed of data extracting providing a greater ability to compare and contrast. This study provides the first extensive, data-driven exploration of AIMD in China, showcasing the potential of automated regulatory data analysis in understanding and advancing the landscape of AI in medical technology.

Data-Driven Analysis of AI in Medical Device Software in China: Deep Learning and General AI Trends Based on Regulatory Data

TL;DR

This paper develops a data-driven, automated approach to map AI-enabled medical devices in China using the NMPA UDI database. It identifies 43 AIMD among roughly 2,149 MDSW entries, finds that most AIMD are DL-based and concentrated in domestic SaMD, and reveals that AI devices are predominantly Class III with limited presence in SiMD. The study also highlights regulatory inconsistencies between China and the US, demonstrating the value of automated regulatory data analysis for policy insight and market surveillance. The authors provide a reproducible workflow and publicly available code, while discussing limitations related to UDI labeling and the need for standardized AI-device nomenclature across regulatory databases.

Abstract

Artificial intelligence (AI) in medical device software (MDSW) represents a transformative clinical technology, attracting increasing attention within both the medical community and the regulators. In this study, we leverage a data-driven approach to automatically extract and analyze AI-enabled medical devices (AIMD) from the National Medical Products Administration (NMPA) regulatory database. The continued increase in publicly available regulatory data requires scalable methods for analysis. Automation of regulatory information screening is essential to create reproducible insights that can be quickly updated in an ever changing medical device landscape. More than 4 million entries were assessed, identifying 2,174 MDSW registrations, including 531 standalone applications and 1,643 integrated within medical devices, of which 43 were AI-enabled. It was shown that the leading medical specialties utilizing AIMD include respiratory (20.5%), ophthalmology/endocrinology (12.8%), and orthopedics (10.3%). This approach greatly improves the speed of data extracting providing a greater ability to compare and contrast. This study provides the first extensive, data-driven exploration of AIMD in China, showcasing the potential of automated regulatory data analysis in understanding and advancing the landscape of AI in medical technology.

Paper Structure

This paper contains 12 sections, 9 figures, 4 tables.

Table of Contents

  1. China's New Generation Artificial Intelligence Development Plan and Effect to Medical Devices
  2. Methodology
  3. Results
  4. Devices amount and category
  5. Artificial intelligence devices and algorithms in Medical software
  6. Artificial intelligence devices and algorithms across different medical domains
  7. Deep learning and traditional AI algorithm analysis
  8. Analysis of AI algorithm in certain medical specialty
  9. Analysis of AI devices
  10. International regulatory inconsistency
  11. Discussion
  12. Conclusion and Future Work

Figures (9)

  • Figure 1: Medical device registration pathways set out by the NMPA. Imported and domestic devices relates to all class II and III devices, for Class I devices, only record-filing is required.
  • Figure 2: UDI code layout according to YY/T 1630-2018.
  • Figure 3: Pseudocode for MDSW and AIMD Identification Process
  • Figure 4: Flowchart for the selection process for the identification of software and AIMD
  • Figure 5: Domestic and Imported SaMD & SiMD Devices: AI vs. Non-AI Distribution. Different scales are applied to each subplot to better illustrate variations across categories.
  • ...and 4 more figures