ABSTRACT
Purpose@#During the COVID-19 pandemic, Korea has temporarily expanded coverage of teleconsultation to ensure access to essential health services. As a preliminary study, we investigated service utilization patterns and the characteristics of doctors and patients involved in these temporary teleconsultation services. @*Materials and Methods@#Using national health insurance claims data from February 23, 2020 to June 30, 2020 from the Health Insurance Review and Assessment Service, 228269875 cases were identified. Among them, 567390 cases that received teleconsultation services were included in our study. We performed descriptive analyses according to the types of healthcare institutions. @*Results@#In total, 6193 healthcare institutions provided teleconsultation. Of these, 5466 (88.3%) were clinics. Physicians providing teleconsultations were most likely to be doctors of internal medicine (34.0%) or pediatricians (7.0%) and based in the Seoul Metropolitan area (30.4%). In terms of patients undergoing teleconsultation, the most common major disease categories treated were circulatory system diseases (I00–I99). In a detailed analysis, hypertensive diseases (I10–I15) were the most common diagnoses, with a total of 88726 cases (15.6%), followed by diabetes mellitus at 60298 cases (10.6%). The proportion of Medical Aid recipients receiving teleconsultations was higher (9.5%) than other socioeconomic groups. Among all participants, 356622 cases (84.6%) were from a return visit, and 108838 cases (19.2%) received teleconsultation services without being prescribed drugs. @*Conclusion@#Temporarily allowed teleconsultation services were provided mostly to the following patients: 1) those scheduled for revisitation, 2) those with chronic diseases, and 3) those living in pandemic hotspots.
ABSTRACT
Purpose@#During the COVID-19 pandemic, Korea has temporarily expanded coverage of teleconsultation to ensure access to essential health services. As a preliminary study, we investigated service utilization patterns and the characteristics of doctors and patients involved in these temporary teleconsultation services. @*Materials and Methods@#Using national health insurance claims data from February 23, 2020 to June 30, 2020 from the Health Insurance Review and Assessment Service, 228269875 cases were identified. Among them, 567390 cases that received teleconsultation services were included in our study. We performed descriptive analyses according to the types of healthcare institutions. @*Results@#In total, 6193 healthcare institutions provided teleconsultation. Of these, 5466 (88.3%) were clinics. Physicians providing teleconsultations were most likely to be doctors of internal medicine (34.0%) or pediatricians (7.0%) and based in the Seoul Metropolitan area (30.4%). In terms of patients undergoing teleconsultation, the most common major disease categories treated were circulatory system diseases (I00–I99). In a detailed analysis, hypertensive diseases (I10–I15) were the most common diagnoses, with a total of 88726 cases (15.6%), followed by diabetes mellitus at 60298 cases (10.6%). The proportion of Medical Aid recipients receiving teleconsultations was higher (9.5%) than other socioeconomic groups. Among all participants, 356622 cases (84.6%) were from a return visit, and 108838 cases (19.2%) received teleconsultation services without being prescribed drugs. @*Conclusion@#Temporarily allowed teleconsultation services were provided mostly to the following patients: 1) those scheduled for revisitation, 2) those with chronic diseases, and 3) those living in pandemic hotspots.
ABSTRACT
While healthcare data sets include extensive information about patients, many researchers have limitations in analyzing them due to their intrinsic characteristics such as heterogeneity, longitudinal irregularity, and noise. In particular, since the majority of medical history information is recorded in text codes, the use of such information has been limited due to the high dimensionality of explanatory variables. To address this problem, recent studies applied word embedding techniques, originally developed for natural language processing, and derived positive results in terms of dimensional reduction and accuracy of the prediction model. This paper reviews the deep learning-based natural language processing techniques (word embedding) and summarizes research cases that have used those techniques in the health care field. Then we finally propose a research framework for applying deep learning-based natural language process in the analysis of domestic health insurance data.
ABSTRACT
The fee-for-service system is used as the main payment system for health care providers in Korea. It has been argued that it can't reflect differences in the medical practice costs across regions because the fee schedule is calculated based on the average cost. So, some researchers and providers have disputed that there is need for adopting geographic practice cost index (GPCI) used in the United States for the Medicare program for the elderly to the fee-for-service payment system. This study performed to identify whether the difference in the practice costs among regions exists or not and to examine the feasibility of applying GPCI to Korea payment system. For this purpose, we calculated modified-GPCI and examined considerations to introduce GPCI in Korea. First we identified available data to calculate GPCI. Second, we made applicable GPCI equations to Korea payment system and computed it based on four types of regions (metropolitan, urban, suburban, and rural). We also categorize the regions based on the availability of the medical resources and the capability of utilizing them. As a result, we found that there wasn't any significant difference in the GPCI by regional types in general, but the indices of rural areas (0.91–0.98) was relatively low compared to the indices of other regions (0.96–1.07). Considering the need to use GPCI floor, the pros and cons of using GPCI, and the concern of the regional imbalance of resources, the introduction of GPCI needs to be carefully considered.
Subject(s)
Aged , Humans , Fee Schedules , Fee-for-Service Plans , Health Personnel , Korea , Medicare , Relative Value Scales , United StatesABSTRACT
A novel saliency detection algorithm for video sequences based on the random walk with restart (RWR) is proposed in this paper. We adopt RWR to detect spatially and temporally salient regions. More specifically, we first find a temporal saliency distribution using the features of motion distinctiveness, temporal consistency, and abrupt change. Among them, the motion distinctiveness is derived by comparing the motion profiles of image patches. Then, we employ the temporal saliency distribution as a restarting distribution of the random walker. In addition, we design the transition probability matrix for the walker using the spatial features of intensity, color, and compactness. Finally, we estimate the spatiotemporal saliency distribution by finding the steady-state distribution of the walker. The proposed algorithm detects foreground salient objects faithfully, while suppressing cluttered backgrounds effectively, by incorporating the spatial transition matrix and the temporal restarting distribution systematically. Experimental results on various video sequences demonstrate that the proposed algorithm outperforms conventional saliency detection algorithms qualitatively and quantitatively.