Key Takeaways:
- Seoul partners with MOHW to connect startups with hospital data for AI-driven R&D.
- Hong Kong’s eHealth app now allows users to view pathology reports.
- South Korea’s National Cancer Center uses NLP to structure breast cancer pathology data.
Seoul Supports Digital Health Startups with Hospital Data Access
The city government of Seoul has announced a collaboration with South Korea’s Ministry of Health and Welfare (MOHW) to support health and medical startups in leveraging hospital data for research and development. According to a report published on Healthcare IT News, the initiative aims to facilitate access to de-identified and anonymised medical data from 43 hospitals.
Under this program, seven startups will be selected to benefit from this data-sharing framework. These startups will also receive up to 50 million won (approximately $35,000) in business funding, alongside expert consultation services focused on medical data analysis and research methodologies.
This effort underscores the growing emphasis on fostering innovation in digital health technologies, particularly those driven by artificial intelligence. By providing startups with access to hospital datasets, Seoul and the MOHW aim to encourage the development of solutions that could enhance healthcare delivery and patient outcomes.
Hong Kong Enhances eHealth App with Pathology Report Viewing
Hong Kong’s eHealth mobile application has been updated to include a new feature allowing users to view pathology reports. As reported by Healthcare IT News, the Health Bureau confirmed that these reports are accessible under the Investigations function 14 days after their release by the Hospital Authority, Department of Health, and private healthcare providers.
The expansion reflects ongoing efforts to integrate more electronic health record (EHR) types into the platform. Launched in 2021, the eHealth app currently provides access to nine EHR categories, with plans to include radiology images, Chinese medicine prescriptions, and dental records in the near future.
As of February, nearly 100 sites across public health settings and 40 private providers have been uploading pathology reports to citizens’ eHealth accounts. This update aligns with the broader goals of Hong Kong’s five-year eHealth+ plan, which began in 2023. The initiative seeks to streamline healthcare data sharing, service delivery, and care journey management through the mobile app.
South Korea’s National Cancer Center Adopts NLP for Pathology Data Structuring
In another development highlighted by Healthcare IT News, South Korea’s National Cancer Center has demonstrated the potential of natural language processing (NLP) models to extract and formalise information from semi-structured breast pathology reports.
The center’s research team fine-tuned existing NLP models, including Google’s BERT-basic, BioBERT, and ClinicalBERT, using a dataset of 1,215 breast cancer pathology reports. These models achieved an accuracy rate of 96% or higher in converting unstructured data into a structured format.
The researchers noted that hospitals previously faced significant challenges in manually transforming large volumes of free-entry pathology reports into usable formats for cancer research. This process was hindered by earlier government restrictions on medical data format conversion. However, recent regulatory changes now permit the use of NLP technologies to automate this task, offering a more efficient solution.
According to the center, this advancement addresses a critical bottleneck in cancer research while enabling more comprehensive analyses of pathology data.
This article highlights collaborative efforts in South Korea and Hong Kong to advance digital health initiatives, as originally reported by Adam Ang on Healthcare IT News.
The information and viewpoints presented in the above news piece or article do not necessarily reflect the official stance or policy of Dental Resource Asia or the DRA Journal. While we strive to ensure the accuracy of our content, Dental Resource Asia (DRA) or DRA Journal cannot guarantee the constant correctness, comprehensiveness, or timeliness of all the information contained within this website or journal.
Please be aware that all product details, product specifications, and data on this website or journal may be modified without prior notice in order to enhance reliability, functionality, design, or for other reasons.
The content contributed by our bloggers or authors represents their personal opinions and is not intended to defame or discredit any religion, ethnic group, club, organisation, company, individual, or any entity or individual.