Search

Background: Synthetic data generation (SDG) based on generative adversarial networks (GANs) is used in health care, but research on preserving data with logical relationships with synthetic tabular data (STD) remains challenging. Filtering methods for SDG can lead to the loss of important information., Objective: This study proposed a divide-and-conquer (DC) method to generate STD based on the GAN algorithm, while preserving data with logical relationships., Methods: The proposed method was evaluated on data from the Korea Association for Lung Cancer Registry (KALC-R) and 2 benchmark data sets (breast cancer and diabetes). The DC-based SDG strategy comprises 3 steps: (1) We used 2 different partitioning methods (the class-specific criterion distinguished between survival and death groups, while the Cramer V criterion identified the highest correlation between columns in the original data); (2) the entire data set was divided into a number of subsets, which were then used as input for the conditional tabular generative adversarial network and the copula generative adversarial network to generate synthetic data; and (3) the generated synthetic data were consolidated into a single entity. For validation, we compared DC-based SDG and conditional sampling (CS)-based SDG through the performances of machine learning models. In addition, we generated imbalanced and balanced synthetic data for each of the 3 data sets and compared their performance using 4 classifiers: decision tree (DT), random forest (RF), Extreme Gradient Boosting (XGBoost), and light gradient-boosting machine (LGBM) models., Results: The synthetic data of the 3 diseases (non-small cell lung cancer [NSCLC], breast cancer, and diabetes) generated by our proposed model outperformed the 4 classifiers (DT, RF, XGBoost, and LGBM). The CS- versus DC-based model performances were compared using the mean area under the curve (SD) values: 74.87 (SD 0.77) versus 63.87 (SD 2.02) for NSCLC, 73.31 (SD 1.11) versus 67.96 (SD 2.15) for breast cancer, and 61.57 (SD 0.09) versus 60.08 (SD 0.17) for diabetes (DT); 85.61 (SD 0.29) versus 79.01 (SD 1.20) for NSCLC, 78.05 (SD 1.59) versus 73.48 (SD 4.73) for breast cancer, and 59.98 (SD 0.24) versus 58.55 (SD 0.17) for diabetes (RF); 85.20 (SD 0.82) versus 76.42 (SD 0.93) for NSCLC, 77.86 (SD 2.27) versus 68.32 (SD 2.37) for breast cancer, and 60.18 (SD 0.20) versus 58.98 (SD 0.29) for diabetes (XGBoost); and 85.14 (SD 0.77) versus 77.62 (SD 1.85) for NSCLC, 78.16 (SD 1.52) versus 70.02 (SD 2.17) for breast cancer, and 61.75 (SD 0.13) versus 61.12 (SD 0.23) for diabetes (LGBM). In addition, we found that balanced synthetic data performed better., Conclusions: This study is the first attempt to generate and validate STD based on a DC approach and shows improved performance using STD. The necessity for balanced SDG was also demonstrated., (©Ha Ye Jin Kang, Erdenebileg Batbaatar, Dong-Woo Choi, Kui Son Choi, Minsam Ko, Kwang Sun Ryu. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 24.11.2023.)

Competing Interests: We declare that we have no conflict of interest.

This paper determined the predefining factors of loan repayment behavior based on psychological and behavioral economics theories. The purpose of this research is to identify whether an individual's credit risk can be predicted based on psychometric tests measuring areas of psychological factors such as effective economic decision-making, self-control, conscientiousness, selflessness and a giving attitude, neuroticism, and attitude toward money. In addition, we compared the psychological indicators to the financial indicators, and different age and gender groups, to assess whether the former can predict loan default prospects. This research covered the psychometric test results, financial information, and loan default information of 1118 borrowers from loan-issuing applications on mobile phones. We validated the questionnaire using confirmatory factor analysis (CFA) and achieved an overall Cronbach's alpha reliability coefficient greater than 0.90 (α = 0.937). We applied the empirical data to construct prediction models using logistic regression. Logistic regression was employed to estimate the parameters of a logistic model. The outcome indicates that positive results from the psychometric testing of effective financial decision-making, self-control, conscientiousness, selflessness and a giving attitude, and attitude toward money enable individuals' debt access possibilities. On the other hand, one of the variables-neuroticism-was determined to be insignificant. Finally, the model only used psychological variables proven to have significant default predictability, and psychological variables and psychometric credit scoring offer the best prediction capacities.

Background: Protecting people from financial hardship and impoverishment due to health care costs is one of the fundamental purposes of the Mongolian health system. However, the inefficient, oversized hospital sector is considered one of the main shortcomings of the system. The aim of this study is to contribute to policy discussions by estimating the extent of catastrophic health expenditure and impoverishment due to inpatient care at secondary-level and tertiary-level public hospitals and private hospitals., Methods: Data were derived from a nationally representative survey, the Household Socio-Economic Survey 2012, conducted by the National Statistical Office of Mongolia. A total of 12,685 households were involved in the study. "Catastrophic health expenditure" is defined as out-of-pocket payments for inpatient care that exceed a threshold of 40% of households' non-discretionary expenditure. The "impoverishment" effect of out-of-pocket payments for inpatient care was estimated as the difference between the poverty level before health care payments and the poverty level after these payments., Results: At the threshold of 40% of capacity to pay, 0.31%, 0.07%, and 0.02% of Mongolian households suffered financially as a result of their member(s) staying in tertiary-level and secondary-level public hospitals and private hospitals respectively. About 0.13% of the total Mongolian population was impoverished owing to out-of-pocket payments for inpatient care at tertiary-level hospitals. Out-of-pocket payments for inpatient care at secondary-level hospitals and private hospitals were responsible for 0.10% and 0.09% respectively of the total population being pushed into poverty., Conclusions: Although most inpatient care at public hospitals is covered by the social health insurance benefit package, patients who utilized inpatient care at tertiary-level public hospitals were more likely to push their households into financial hardship and poverty than the inpatients at private hospitals. Improving the hospital sector's efficiency and financial protection for inpatients would be a crucial means of attaining universal health coverage in Mongolia., Competing Interests: The authors have declared that no competing interests exist.

Hematopoietic cancer is a malignant transformation in immune system cells. Hematopoietic cancer is characterized by the cells that are expressed, so it is usually difficult to distinguish its heterogeneities in the hematopoiesis process. Traditional approaches for cancer subtyping use statistical techniques. Furthermore, due to the overfitting problem of small samples, in case of a minor cancer, it does not have enough sample material for building a classification model. Therefore, we propose not only to build a classification model for five major subtypes using two kinds of losses, namely reconstruction loss and classification loss, but also to extract suitable features using a deep autoencoder. Furthermore, for considering the data imbalance problem, we apply an oversampling algorithm, the synthetic minority oversampling technique (SMOTE). For validation of our proposed autoencoder-based feature extraction approach for hematopoietic cancer subtype classification, we compared other traditional feature selection algorithms (principal component analysis, non-negative matrix factorization) and classification algorithms with the SMOTE oversampling approach. Additionally, we used the Shapley Additive exPlanations (SHAP) interpretation technique in our model to explain the important gene/protein for hematopoietic cancer subtype classification. Furthermore, we compared five widely used classification algorithms, including logistic regression, random forest, k-nearest neighbor, artificial neural network and support vector machine. The results of autoencoder-based feature extraction approaches showed good performance, and the best result was the SMOTE oversampling-applied support vector machine algorithm consider both focal loss and reconstruction loss as the loss function for autoencoder (AE) feature selection approach, which produced 97.01% accuracy, 92.60% recall, 99.52% specificity, 93.54% F1-measure, 97.87% G-mean and 95.46% index of balanced accuracy as subtype classification performance measures.

Named Entity Recognition (NER) in the healthcare domain involves identifying and categorizing disease, drugs, and symptoms for biosurveillance, extracting their related properties and activities, and identifying adverse drug events appearing in texts. These tasks are important challenges in healthcare. Analyzing user messages in social media networks such as Twitter can provide opportunities to detect and manage public health events. Twitter provides a broad range of short messages that contain interesting information for information extraction. In this paper, we present a Health-Related Named Entity Recognition (HNER) task using healthcare-domain ontology that can recognize health-related entities from large numbers of user messages from Twitter. For this task, we employ a deep learning architecture which is based on a recurrent neural network (RNN) with little feature engineering. To achieve our goal, we collected a large number of Twitter messages containing health-related information, and detected biomedical entities from the Unified Medical Language System (UMLS). A bidirectional long short-term memory (BiLSTM) model learned rich context information, and a convolutional neural network (CNN) was used to produce character-level features. The conditional random field (CRF) model predicted a sequence of labels that corresponded to a sequence of inputs, and the Viterbi algorithm was used to detect health-related entities from Twitter messages. We provide comprehensive results giving valuable insights for identifying medical entities in Twitter for various applications. The BiLSTM-CRF model achieved a precision of 93.99%, recall of 73.31%, and F1-score of 81.77% for disease or syndrome HNER; a precision of 90.83%, recall of 81.98%, and F1-score of 87.52% for sign or symptom HNER; and a precision of 94.85%, recall of 73.47%, and F1-score of 84.51% for pharmacologic substance named entities. The ontology-based manual annotation results show that it is possible to perform high-quality annotation despite the complexity of medical terminology and the lack of context in tweets.

Background: The entire population of Mongolia has free access to primary health care, which is fully funded by the government. It is provided by family health centers in urban settings. In rural areas, it is included in outpatient and inpatient services offered by rural soum (district) health centers. However, primary health care utilization differs across population groups. The aim of this study was to evaluate income-related inequality in primary health care utilization in the urban and rural areas of Mongolia., Methods: Data from the Household Socio-Economic Survey 2012 were used in this study. The Erreygers concentration index was employed to assess inequality in primary health care utilization in both urban and rural areas. The indirect standardization method was applied to measure the degree of horizontal inequity., Results: The concentration index for primary health care at family health centers in urban areas was significantly negative (-0.0069), indicating that utilization was concentrated among the poor. The concentration index for inpatient care utilization at the soum health centers was significantly positive (0.0127), indicating that, in rural areas, higher income groups were more likely to use inpatient services at the soum health centers., Conclusions: Income-related inequality in primary health care utilization exists in Mongolia and the pattern differs across geographical areas. Significant pro-poor inequality observed in urban family health centers indicates that their more effective gatekeeping role is necessary. Eliminating financial and non-financial access barriers for the poor and higher need groups in rural areas would make a key contribution to reducing pro-rich inequality in inpatient care utilization at soum health centers.

Aim: A large number of studies have addressed the detection of patient satisfaction determinants, and the results are still inconclusive. Furthermore, it is known that contradicting evidence exists across patient satisfaction studies. This article is the second part of a two-part series of research with a goal to review a current conceptual framework of patient satisfaction for further operationalisation procedures. The aim of this work was to systematically identify and review evidence regarding determinants of patient satisfaction between 1980 and 2014, and to seek the reasons for contradicting results in relationships between determinants and patient satisfaction in the literature to design a further robust measurement system for patient satisfaction., Method: This systematic review followed the guidelines of the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement. The search was conducted in PubMed, CINAHL, and Scopus in October 2014. Studies published in full in peer reviewed journals between January 1980 and August 2014 and in the English language were included. We included 109 articles for the synthesis., Results: We found several number of determinants of patient satisfaction investigated in a wide diversity of studies. However, study results were varied due to no globally accepted formulation of patient satisfaction and measurement system., Conclusions: Health care service quality indicators were the most influential determinants of patient satisfaction across the studies. Among them, health providers' interpersonal care quality was the essential determinant of patient satisfaction. Sociodemographic characteristics were the most varied in the review. The strength and directions of associations with patient satisfaction were found inconsistent. Therefore, person-related characteristics should be considered to be the potential determinants and confounders simultaneously. The selected studies were not able to show all potential characteristics which may have had effects on satisfaction. There is a need for more studies on how cultural, behavioural, and socio-demographic differences affect patient satisfaction, using a standardised questionnaire.

Background: The social health insurance coverage is relatively high in Mongolia; however, escalation of out-of-pocket payments for health care, which reached 41 % of the total health expenditure in 2011, is a policy concern. The aim of this study is to analyse the incidence of catastrophic health expenditures and to measure the rate of impoverishment from health care payments under the social health insurance scheme in Mongolia., Methods: We used the data from the Household Socio-Economic Survey 2012, conducted by the National Statistical Office of Mongolia. Catastrophic health expenditures are defined an excess of out-of-pocket payments for health care at the various thresholds for household total expenditure (capacity to pay). For an estimate of the impoverishment effect, the national and The Wold Bank poverty lines are used., Results: About 5.5 % of total households suffered from catastrophic health expenditures, when the threshold is 10 % of the total household expenditure. At the threshold of 40 % of capacity to pay, 1.1 % of the total household incurred catastrophic health expenditures. About 20,000 people were forced into poverty due to paying for health care., Conclusions: Despite the high coverage of social health insurance, a significant proportion of the population incurred catastrophic health expenditures and was forced into poverty due to out-of-pocket payments for health care.

Background: After the socioeconomic transition in 1990, Mongolia has been experiencing demographic and epidemiologic transitions; however, there is lack of evidence on socioeconomic-related inequality in health across the country. The aim of this paper is to evaluate the education-related inequalities in adult population health in urban and rural areas of Mongolia in 2007/2008., Methods: This paper used a nationwide cross-sectional data, the Household Socio-Economic Survey 2007/2008, collected by the National Statistical Office. We employed the Erreygers' concentration index to assess the degree of education-related inequality in adult health in urban and rural areas., Results: Our results suggest that a lower education level was associated with poor self-reported health. The concentration indices of physical limitation and chronic disease were significantly less than zero in both areas. On the other hand, ill-health was concentrated among the less educated groups. The decomposition results show education, economic activity status and income were the main contributors to education-related inequalities in physical limitation and chronic disease removing age-sex related contributions., Conclusions: Improving accessibility and quality of education, especially for the lower socioeconomic groups may reduce socioeconomic-related inequality in health in both rural and urban areas of Mongolia.

Aim: Patient satisfaction concept is widely measured due to its appropriateness to health service; however, evidence suggests that it is a poorly developed concept. This article is a first part of a two-part series of research with a goal to review a current conceptual framework of patient satisfaction and to bring the concept for further operationalisation procedures. The current article aimed to review a theoretical framework that helps the next article to review determinants of patient satisfaction for designing a measurement system., Method: The study used a systematic review method, meta-narrative review, based on the RAMESES guideline with the phases of screening evidence, appraisal evidence, data extraction and synthesis. Patient satisfaction theoretical articles were searched on the two databases MEDLINE and CINAHL. Inclusion criteria were articles published between 1980 and 2014, and English language papers only. There were 36 articles selected for the synthesis., Results: Results showed that most of the patient satisfaction theories and formulations are based on marketing theories and defined as how well health service fulfils patient expectations. However, review demonstrated that a relationship between expectation and satisfaction is unclear and the concept expectation itself is not distinctly theorised as well., Conclusions: Researchers brought satisfaction theories from other fields to the current healthcare literature without much adaptation. Thus, there is a need to attempt to define the patient satisfaction concept from other perspectives or to learn how patients evaluate the care rather than struggling to describe it by consumerist theories., (© Royal Society for Public Health 2015.)

Background: Although health strategies and policies have addressed equitable distribution of health care in Mongolia, few studies have been conducted on this topic. Rapid socio-economic changes have recently occurred; however, there is no evidence as to how horizontal inequity has changed. The aim of this paper is to evaluate income related-inequalities in health care utilizations and their changes between 2007/2008 and 2012 in Mongolia., Methods: The data used in this study was taken from the nationwide cross-sectional data sets, the Household Socio-Economic Survey, collected in 2007/2008 and 2012 by the National Statistical Office of Mongolia. We employed the Erreygers' concentration index to measure inequality in health service utilization. Horizontal inequity was estimated by a difference between actual and predicted use of health services using the indirect standardization method., Results: The results show that the concentration indices for tertiary level, private outpatient and inpatient services were significantly positive, the contrary for family group practice/soum hospital outpatient services, in both years. After controlling for need, pro-rich inequity (p < 0.01) was observed in the tertiary level, private outpatient, and general inpatient, services in both years. Pro-poor inequity (p < 0.01) existed in family group practice/soum hospital outpatient services in both years. Degrees of inequity in tertiary level hospital and private hospital outpatient services became more pro-rich, whereas in family group practice/soum hospital outpatient services became more pro-poor from 2007/2008 to 2012. Pro-rich inequity in inpatient services remained the same from 2007/2008 to 2012., Conclusions: Equitable distribution of health care has been well documented in health strategies and policies; however, the degree of inequity in delivery of health services has a tendency to increase in Mongolia. Therefore, there is a need to consider implementation issues of the strategies and refocus on policy prioritizations. It is necessary to strengthen primary health care services, particularly by diminishing obstacles for lower income and higher need groups.