Over the past decade, there has been a sharp increase in the number of end-stage renal disease patients requiring hemodialysis in Korea. But, national system for safety and quality control of hemodialysis has not been implemented. The Korean Society of Nephrology independently started a project of dialysis specialist and dialysis facility accreditation. In addition, the Korean Society of Nephrology is planning to legislate the management of end-stage renal disease patients and set up an public agency for evaluating hemodialysis management. In this paper, I’d like to introduce diverse efforts of Korean Society of Nephrology to ensure safety of hemodialysis patients and quality control of hemodialysis facilities.

With the recent spread of remote culture and the development of digital infrastructure technologies, it has become necessary to improve the evaluation system to respond to the upcoming changes in the medical environment. To respond to these changes, Health Insurance Review and Assessment Service (HIRA) selected 23 detailed promotion tasks for innovation and seven innovation tasks in three areas that require priority performance. First, the areas of meaningful evaluation are “a paradigm shift in introducing new evaluations,” “reorganization of evaluation indicators centered on core indicators,” and “redesign of existing evaluation items.” Second, the areas of data collection to promote innovation are “preparing the legal basis and spreading the e-form system” and “expanding the collection of present on admission.” Third, the areas of expanding the use of evaluation results are “selection to enhance public utilization of evaluation information” and “strengthening value-based compensation.” The mid- to long-term plan for innovation in the quality assessment system for healthcare benefit adequacy is first to develop and introduce new evaluations focusing on key indicators such as patient-centered and patient safety-related outcome indicators that can improve national health outcomes. Second, the reform is intended to prepare a legal basis for the smooth collection of evaluation data and switch to the collection of evaluation data using the e-form evaluation form, which is a form for submitting data at the time of claiming medical care benefit costs. Third, it is to improve and operate the current Value Incentive Program focusing on small and medium-sized hospitals and clinics that need to improve the quality of medical care and expand the evaluation items and scale of the additional reduction payment. HIRA is expected to further promote value-based medical quality improvement by doing the following: reorganizing the evaluation centering on key indicators such as outcome indicators that can measure public health performance through the seven tasks and strengthening rewards for health performance improvement.

Background: This study estimated a single index that evaluates the functional level of medical institutions in the medical delivery system by using both the functional classification result of the medical institutions and the classification result of the suitable disease group.
Methods: Inpatient and outpatient data from the 2019 Health Insurance Review and Assessment Service claim data were used for analysis. Medical institutions above the hospital level were classified into tertiary medical institutions, secondary medical institutions, and regional hospitals (general secondary and limited secondary medical institutions). Using the appropriate disease group classification system of adjacent aged diagnosis-related group (AADRG), the number of AADRG patients suitable for their function was calculated as an index in each inpatient and outpatient area. In the inpatient area, the Charlson comorbidity index was reflected.
Results: The mean of the raw scores for the hospitalization-appropriate disease group of all 525 institutions was 76.8. The raw score for the hospitalization-appropriate disease group showed the highest frequency in the range of 80–90 points (214, 40.8%). The mean of the raw scores for the outpatient-appropriate disease group was 73.9 points. A total of 198 medical institutions (37.6%) were distributed in the 70–80 point range. Regional hospitals were distributed in high scores for both inpatient and outpatient services, and tertiary and secondary medical institutions were distributed in relatively low scores.
Conclusion: It was confirmed that the proportion of medical institutions providing treatment according to their functions was low overall. Based on the results of this attempt to calculate the medical delivery system score, it will be possible to include the medical delivery system evaluation indicator in the medical quality evaluation system and use it as a policy tool to improve the medical delivery system

Background: The sampling framework of the National Patient Sample of Health Insurance Review & Assessment Service is needed to be improved due to the current demographic structure. We proposed a sampling method and additional strata for extracting the National Patient Sample data due to the current demographic structure, such as low birth rate and aged population.
Methods: A total of 36 strata were set by adding four strata compared to the existing one. The maximum rate of minimal sample number was defined among the entire strata. Based on the rate, we extracted a small-scale sample dataset consisting of about 400,000 people and a large-scale sample dataset of more than 700,000 people.
Results: The representativeness of the high-frequency disease and the low-frequency disease was confirmed. For health expenditure, the representativeness of samples was confirmed in large-scale samples. However, the representativeness of small-scale samples was not confirmed in five strata.
Conclusion: Using the maximum rate of minimal sample number can reflect the demographic structure changes and diverse medical utilization. Although lack of representativeness in the five strata of the small-scale sample, both the small-scale sample and the large-scale sample are necessary to improve data accessibility and a sustainable data provision system. It will be helpful in establishing health policies and conducting medical research.

Background: Clinical Data Warehouse (CDW) enables healthcare organizations to allow investigators to utilize their anonymous data securely. The Common Data Model (CDM) enables collaborative research between institutions. The authors describe the experience of converting CDW data into the Observational Medical Outcomes Partnership (OMOP) CDM (OMOP-CDM).
Methods: Data from electronic health records of a medical center was converted into OMOP-CDM ver. 5.3.1 (https://www.ohdsi.org/data-standardization/the-common-data-model/). Source codes of the institution were mapped to the codes in the standard vocabularies. Predefined data were extracted, transformed, and loaded into the CDM tables. Ophthalmologic data were digitalized and structured per their data configuration.
Results: The number of total patients with available data in the CDW was 8,532,392. The data from 878,141 patients were converted into CDM structure after the codes were mapped to those in the standard vocabularies. Visual acuity, intraocular pressure, automated visual field test, and optical coherence tomography were digitalized and stored.
Conclusion: Although it requires plenty of resources to convert the data set to CDM, it is worthy of keeping the activity since it provides opportunities for investigators to participate in various studies.

Background: Healthcare studies mainly use statistical methodologies, but recently, with the development of artificial intelligence (AI) technology, studies to solve the limitations of some existing methodologies are being published. This study aims to suggest a strategy for using AI technology in the future by reviewing existing research and research cases of the last 10 years using artificial intelligence technology.
Methods: We selected research papers and domestic and international journal papers by the Health Insurance Review and Assessment Service since 2010. Health insurance claim data were divided into 'cross-sectional study', 'association and comparative analysis of specific factors', and 'longitudinal cross-sectional, time series analysis study'.
Results: Four situations requiring AI technology were defined, and AI methodologies applicable to each situation were presented.
Conclusion: It is judged that it is necessary to actively discuss more specific situations and various methodologies for the use of big data in health care.

Background: The government launched a pilot project for health insurance for children’s dentists as one of the measures to expand preventive-oriented essential oral health care services for 3 years from May 2021. We will examine the pilot project targets and project contents of child dentists and analyze the general characteristics between regions subject to the pilot project and children in non-targeted areas to find out whether there are differences between regions.
Methods: This study is a prospective cohort study that lasts for 3 years in a pilot project. The subjects of the experimental group were children in the fourth grade of elementary school living in Sejong city and Gwangju metropolitan city, which participated in the pilot project, and the control group was children in the fourth grade of A elementary school located in Wonju city, which did not participate in the pilot project.
Results: The main results were that there was no regional difference in the general characteristics of the children in the experimental group and the control group. In the comparison of the oral health level, the oral health level was higher in the control group than in the experimental group, but there was no statistically significant difference.
Conclusion: This thesis is a long-term study that starts from the first year of the pilot project and continues until the end. Effect evaluation will be carried out for three years as a pilot project, and through long-term research, we believe that it will be an opportunity to confirm the actual outcomes of the children's dentistry health insurance business and to expand the children's dentistry business.

In order to improve patient safety and quality of care, the hospitalist system was implemented in Korea from January 2021. As hospitalists take on new roles in hospitals, changes are also required to efficient medical environment in the hospital information systems. By designing and implementing a hospitalist support system in hospital information systems, hospitalists set the authority to access patient information, and automated fee schedule to reduce billing errors. In addition, the calculation of the number of patients treated by hospitalists was automated, leading to a decrease in administrative work given to hospitals. All of the hospitalist’s work schedules were managed electronically, which enables monitoring of appropriate working hours. A hospitalist support system is essential for establishing an efficient medical environment and reducing administrative work, which can help hospitals introduce a hospitalist system.