scholarly journals Using Taiwanese Universal Health Insurance Data to Estimate LTC Needs with Machine Learning

2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. 1028-1028
Author(s):  
Kuan-Ming Chen ◽  
Chen-Wei Hsiang ◽  
Shiau-Fang Chao ◽  
Ming-Jen Lin ◽  
Kuan-Ju Tseng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Health Insurance ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Universal Health Insurance ◽  
Term Care ◽  
Administrative Records ◽  
Icd 10 ◽  
Universal Health

Abstract One of the core issues in long-term care (LTC) policy is the growing imbalance between demand and supply of LTC services due to aging population. To estimate the imbalance and allocate LTC resources, the government regularly conducts surveys. These surveys are expensive given the sample size requirements and imprecise given their subjective nature. This study links the administrative records of the universal health insurance database with LTC program usage records in Taiwan to explore this issue. Machine learning algorithms are used in projecting LTC needs from administrative records. LTC program usage records provide detailed LTC needs information and the amount of service each individual used. In addition, health insurance claim data provides rich health information. Specific LTC needs are predicted for each individual. By further extrapolating to future demographics, long-term LTC needs could be projected. There are several findings in this study. Prediction of difficulties in activities of daily livings (ADL), measured by Barthel index, works best using the Gradient Boosting algorithm. The mean absolute error is 17.67 out of a 0 to 100 scale. In addition to dementia and stroke, diagnosis of pressure ulcer (ICD 10 code: L89) and pneumonia (ICD 10 code: J18) have high predictive power for LTC needs. Prediction of Instrumental ADL (IADL) also performs well with a mean absolute error 1.31. The prediction model suggests high LTC needs and excess demand as the demographics changing. Our study provides a reliable way of using rich information to estimate future LTC needs without conducting additional costly surveys.

The Determinants of Long-Term Care Utilization and Equity of Access to Care among Older Adults in Dong-Ku of Incheon Metropolitan City, South Korea

2005 ◽  
Vol 17 (2) ◽  
pp. 104-109 ◽  
Author(s):  
J.M. Park
Keyword(s):  
Health Insurance ◽  
Long Term Care ◽  
The Elderly ◽  
Care Utilization ◽  
Universal Health Insurance ◽  
Health Insurance System ◽  
Term Care ◽  
Insurance System ◽  
Universal Health

Under the current health care system, around three percent of the elderly remain uninsured. Based on the 2003 Dong-Ku Health Status Survey and the Aday and Andersen Access Framework, the present study examined the social and behavioral determinants of long-term care utilization and the extent to which equity in the use of long-term care services for the elderly has been achieved. The results indicate that universal health insurance system has not yielded a fully equitable distribution of services. Type of coverage and resource availability do not remain predictors of long-term care utilization. The data suggest that a universal health insurance system exists in South Korea with significant access problems for the population without insurance. Access differences also arise from obstacles in expanding the scope and level of plan benefits due to financial disparity among insurers. Health policy reforms must continue to concentrate on extending insurance coverage to the uninsured and establishing long-term insurance system for the elderly. Asia Pac J Public Health 2005; 17(2): 104-109.

Universal Health Insurance and its association with long term outcomes in Pediatric Trauma Patients

Injury ◽  
2018 ◽  
Vol 49 (1) ◽  
pp. 75-81 ◽  
Author(s):  
Meesha Sharma ◽  
Andrew J. Schoenfeld ◽  
Wei Jiang ◽  
Muhammad A. Chaudhary ◽  
Anju Ranjit ◽  
...  
Keyword(s):  
Health Insurance ◽  
Pediatric Trauma ◽  
Trauma Patients ◽  
Universal Health Insurance ◽  
Long Term Outcomes ◽  
Universal Health

scholarly journals Detection and Severity Evaluation of Combined Rail Defects Using Deep Learning

Vibration ◽  
2021 ◽  
Vol 4 (2) ◽  
pp. 341-356
Author(s):  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Machine Learning Techniques ◽  
Rolling Stock ◽  
Raw Data ◽  
Learning Techniques ◽  
Combined Defects

Various techniques have been developed to detect railway defects. One of the popular techniques is machine learning. This unprecedented study applies deep learning, which is a branch of machine learning techniques, to detect and evaluate the severity of rail combined defects. The combined defects in the study are settlement and dipped joint. Features used to detect and evaluate the severity of combined defects are axle box accelerations simulated using a verified rolling stock dynamic behavior simulation called D-Track. A total of 1650 simulations are run to generate numerical data. Deep learning techniques used in the study are deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN). Simulated data are used in two ways: simplified data and raw data. Simplified data are used to develop the DNN model, while raw data are used to develop the CNN and RNN model. For simplified data, features are extracted from raw data, which are the weight of rolling stock, the speed of rolling stock, and three peak and bottom accelerations from two wheels of rolling stock. In total, there are 14 features used as simplified data for developing the DNN model. For raw data, time-domain accelerations are used directly to develop the CNN and RNN models without processing and data extraction. Hyperparameter tuning is performed to ensure that the performance of each model is optimized. Grid search is used for performing hyperparameter tuning. To detect the combined defects, the study proposes two approaches. The first approach uses one model to detect settlement and dipped joint, and the second approach uses two models to detect settlement and dipped joint separately. The results show that the CNN models of both approaches provide the same accuracy of 99%, so one model is good enough to detect settlement and dipped joint. To evaluate the severity of the combined defects, the study applies classification and regression concepts. Classification is used to evaluate the severity by categorizing defects into light, medium, and severe classes, and regression is used to estimate the size of defects. From the study, the CNN model is suitable for evaluating dipped joint severity with an accuracy of 84% and mean absolute error (MAE) of 1.25 mm, and the RNN model is suitable for evaluating settlement severity with an accuracy of 99% and mean absolute error (MAE) of 1.58 mm.

scholarly journals Low acuity paediatric emergency visits under single-payer universal health insurance in Taiwan, 2000–2015: a population-based repeated cross-sectional design

BMJ Open ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. e042084
Author(s):  
I-Anne Huang ◽  
Yiing-Jenq Chou ◽  
I-Jun Chou ◽  
Yu-Tung Huang ◽  
Jhen-Ling Huang ◽  
...  
Keyword(s):  
Health Insurance ◽  
Paediatric Population ◽  
Population Based ◽  
Universal Health Insurance ◽  
Cross Sectional ◽  
Single Payer ◽  
Insurance Programme ◽  
Ed Visits ◽  
Cross Sectional Design ◽  
Universal Health

ObjectivesEmergency services utilisation is a critical policy concern. The paediatric population is the main user of emergency department (ED) services, and the main contributor to low acuity (LA) ED visits. We aimed to describe the trends of ED and LA ED visits under a comprehensive, universal health insurance programme in Taiwan, and to explore factors associating with potentially unnecessary ED utilisation.Design and settingWe used a population-based, repeated cross-sectional design to analyse the full year of 2000, 2005, 2010 and 2015 National Health Insurance claims data individually for individuals aged 18 years and under.ParticipantsWe identified 5 538 197, 4 818 213, 4 401 677 and 3 841 174 children in 2000, 2005, 2010 and 2015, respectively.Primary and secondary outcome measuresWe adopted a diagnosis grouping system and severity classification system to define LA paediatric ED (PED) visits. Generalised estimating equation was applied to identify factors associated with LA PED visits.ResultsThe annual LA PED visits per 100 paediatric population decreased from 10.32 in 2000 to 9.04 in 2015 (12.40%). Infectious ears, nose and throat, dental and mouth diseases persistently ranked as the top reasons for LA visits (55.31% in 2000 vs 33.94% in 2015). Physical trauma-related LA PED visits increased most rapidly between 2000 and 2015 (0.91–2.56 visits per 100 population). The dose–response patterns were observed between the likelihood of incurring LA PED visit and either child’s age (OR 1.06–1.35 as age groups increase, p<0.0001) or family socioeconomic status (OR 1.02–1.21 as family income levels decrease, p<0.05).ConclusionDespite a comprehensive coverage of emergency care and low cost-sharing obligations under a single-payer universal health insurance programme in Taiwan, no significant increase in PED utilisation for LA conditions was observed between 2000 and 2015. Taiwan’s experience may serve as an important reference for countries considering healthcare system reforms.

BPJS Kesehatan Memberikan Jaminan Kesehatan Terhadap Pasien Atau Masyarakat

2021 ◽  
Vol 7 (2) ◽  
pp. 146-154
Author(s):  
Aidha Puteri Mustikasari
Keyword(s):  
Health Care ◽  
Health Insurance ◽  
Health Services ◽  
Social Security ◽  
The State ◽  
Universal Health Care ◽  
Universal Health Insurance ◽  
Universal Health ◽  
Provide Health Insurance

Abstrak. Kepesertaan BPJS Kesehatan pada tahun 2020 tidak akan mencakup 90% penduduk Indonesia, namun rencana Universal Health Care Implementation (UHC) telah direncanakan sejak tahun sebelumnya. Di masa pandemi Covid, sejumlah besar status kepesertaan BPJS Kesehatan  dicabut karena terlambat, padahal masyarakat membutuhkan layanan kesehatan dan asuransi dengan kondisi yang ada. Kajian ini bersifat norma deskriptif , dibahas dalam konteks kepesertaan BPJS kesehatan, dan cukup  menggunakan prinsip asuransi dengan hanya memberikan jaminan kepada peserta, tetapi negara mengikuti kewajiban UUD 1945 yaitu memberikan jaminan kesehatan dan pelayanan kepada warga negara. Untuk mendukung keberadaan jaminan kesehatan universal, Indonesia perlu menerapkan formulir kepesertaan dan  sanksi untuk ketentuan wajib  peserta jaminan sosial yang efektif dan efisien. Abstract. BPJS Health membership in 2020 will not cover 90% of Indonesia's population, but the Universal Health Care Implementation (UHC) plan has been planned since the previous year. During the Covid pandemic, a large number of BPJS Health membership statuses were revoked because they were late, even though people needed health services and insurance with the existing conditions. This study is descriptive in nature, discussed in the context of BPJS health participation, and it is sufficient to use the insurance principle by only providing guarantees to participants, but the state follows the obligations of the 1945 Constitution, namely to provide health insurance and services to citizens. To support the existence of universal health insurance, Indonesia needs to implement an effective and efficient membership form and sanctions for mandatory provisions for social security participants.

Sign in / Sign up

Export Citation Format

Share Document