Real-world evidence of constipation and laxative use in the Korean population with chronic kidney disease from a common data model.

Constipation is a highly prevalent gastrointestinal disorder in patients with chronic kidney disease (CKD). However, our understanding of its epidemiology and management in CKD is limited. We aimed to explore real-world data on constipation and laxative use in patients with CKD in a nationwide population-based cohort from the Korean Health Insurance Review and Assessment-National Patient Sample database. This study analyzed retrospective health claims data in Korea from 2012 to 2017 that were transformed into the Observational Medical Outcomes Partnership Common Data Model. The pooled proportion of constipation diagnoses was 30.5% in all patients with CKD and 15.9%, 16.5%, 17.4%, 29.9%, and 43.3% in patients with CKD stages 1-5, respectively, suggesting a higher prevalence in advanced CKD. Patients receiving peritoneal dialysis or hemodialysis had the highest prevalence of constipation, while transplant recipients showed a prevalence comparable to that of patients with early CKD. Patients with CKD had a significantly higher risk of constipation than age- and sex-matched non-CKD individuals (range of odds ratio [OR]:1.66-1.90). Laxative prescribing patterns differed by CKD severity. Osmotic agents were prescribed in more than half of patients with advanced CKD, while magnesium salts and bulking agents were prescribed less frequently. The CKD patients with constipation were more likely to be prescribed constipation-inducing medications, including antipsychotic and neurological medications. Our findings provide real-world constipation and laxative prescription status in the Korean CKD population, revealing a significantly higher risk of constipation and different laxative prescribing patterns in patients with CKD.

Machine learning approaches that use clinical, laboratory, and electrocardiogram data enhance the prediction of obstructive coronary artery disease.

Pretest probability (PTP) for assessing obstructive coronary artery disease (ObCAD) was updated to reduce overestimation. However, standard laboratory findings and electrocardiogram (ECG) raw data as first-line tests have not been evaluated for integration into the PTP estimation. Therefore, this study developed an ensemble model by adopting machine learning (ML) and deep learning (DL) algorithms with clinical, laboratory, and ECG data for the assessment of ObCAD. Data were extracted from the electronic medical records of patients with suspected ObCAD who underwent coronary angiography. With the ML algorithm, 27 clinical and laboratory data were included to identify ObCAD, whereas ECG waveform data were utilized with the DL algorithm. The ensemble method combined the clinical-laboratory and ECG models. We included 7907 patients between 2008 and 2020. The clinical and laboratory model showed an area under the curve (AUC) of 0.747; the ECG model had an AUC of 0.685. The ensemble model demonstrated the highest AUC of 0.767. The sensitivity, specificity, and F1 score of the ensemble model ObCAD were 0.761, 0.625, and 0.696, respectively. It demonstrated good performance and superior prediction over traditional PTP models. This may facilitate personalized decisions for ObCAD assessment and reduce PTP overestimation.

Machine learning model for predicting ciprofloxacin resistance and presence of ESBL in patients with UTI in the ED.

Increasing antimicrobial resistance in uropathogens is a clinical challenge to emergency physicians as antibiotics should be selected before an infecting pathogen or its antibiotic resistance profile is confirmed. We created a predictive model for antibiotic resistance of uropathogens, using machine learning (ML) algorithms. This single-center retrospective study evaluated patients diagnosed with urinary tract infection (UTI) in the emergency department (ED) between January 2020 and June 2021. Thirty-nine variables were used to train the model to predict resistance to ciprofloxacin and the presence of urinary pathogens' extended-spectrum beta-lactamases. The model was built with Gradient-Boosted Decision Tree (GBDT) with performance evaluation. Also, we visualized feature importance using SHapely Additive exPlanations. After two-step customization of threshold adjustment and feature selection, the final model was compared with that of the original prescribers in the emergency department (ED) according to the ineffectiveness of the antibiotic selected. The probability of using ineffective antibiotics in the ED was significantly lowered by 20% in our GBDT model through customization of the decision threshold. Moreover, we could narrow the number of predictors down to twenty and five variables with high importance while maintaining similar model performance. An ML model is potentially useful for predicting antibiotic resistance improving the effectiveness of empirical antimicrobial treatment in patients with UTI in the ED. The model could be a point-of-care decision support tool to guide clinicians toward individualized antibiotic prescriptions.

Public Reporting on the Quality of Care in Patients with Acute Myocardial Infarction: The Korean Experience.

Public reporting is a way to promote quality of healthcare. However, evidence supporting improved quality of care using public reporting in patients with acute myocardial infarction (AMI) is disputed. This study aims to describe the impact of public reporting of AMI care on hospital quality improvement in Korea. Patients with AMI admitted to the emergency room with ICD-10 codes of I21.0 to I21.9 as the primary or secondary diagnosis were identified from the national health insurance claims data (2007-2012). Between 2007 and 2012, 43,240/83,378 (51.9%) patients manifested ST segment elevation myocardial infarction (STEMI). Timely reperfusion rate increased (ß = 2.78, p = 0.001). The mortality rate of STEMI patients was not changed (ß = -0.0098, p = 0.384) but that of NSTEMI patients decreased (ß = -0.465, p = 0.001). Public reporting has a substantial impact on the process indicators of AMI in Korea because of the increased reperfusion rate. However, the outcome indicators such as mortality did not significantly change, suggesting that public reporting did not necessarily improve the quality of care.

Estimated Prevalence and Incidence of Uterine Leiomyoma, and Its Treatment Trend in South Korean Women for 12 years: A National Population-Based Study.

Background: Although uterine leiomyoma causes many problems, including infertility, there are few studies that have investigated the epidemiologic characteristics of uterine leiomyoma in South Korea. The aim of this study is to estimate the prevalence and incidence of uterine leiomyoma in South Korea and analyze the treatment trends. Materials and Methods: Women of reproductive age (15-54 years) were selected from the Korean National Health Insurance Service (NHIS) sample cohort dataset, which was collected from 2002 to 2013. Patients with uterine leiomyoma were identified by ICD-10 (International Codes of Disease, 10th Edition) and intervention codes. Prevalence and incidence were calculated from the NHIS cohort dataset and the treatment trends were analyzed for diagnosed patients. Results: The prevalence in overall age groups increased from 0.96% in 2002 to 2.43% in 2013, and the 1-year incidences of all age groups increased. The 26-30 age group showed the highest rate of 1-year incidence increase (2.14-folds, 0.33% in 2003 to 0.70% in 2013). The proportion of myomectomy increased from 22% in 2002 to 49% in 2013, whereas the proportion of hysterectomy decreased from 78% to 45%. Conclusions: The prevalence and incidence of uterine leiomyoma are increasing in South Korea as time progresses, and the rate of incidence increase is higher in younger reproductive women. Overall trends in uterine leiomyoma treatment are shifting to the methods of the saving uterus.

The Estimated Prevalence and Incidence of Endometriosis With the Korean National Health Insurance Service-National Sample Cohort (NHIS-NSC): A National Population-Based Study.

BACKGROUND: The incidence and prevalence of endometriosis remain unclear due to diagnostic difficulties. Especially, there has been little information regarding the population-based epidemiology of endometriosis. The purpose of this study is to estimate the prevalence and incidence of endometriosis in Korea based on the health insurance claims data. METHODS: This study is a retrospective cohort study using the Korean National Health Insurance Service-National Sample Cohort, which correspond to approximately 1 million Korean populations from 2002 to 2013. Patients aged 15-54 years were selected, and the prevalence and incidence of endometriosis were estimated by time and age groups. RESULTS: The age-adjusted prevalence rate of endometriosis also increased from 2.12 per 1,000 persons (95% confidence interval [CI], 2.01-2.24) in 2002 to 3.56 per 1,000 persons (95% CI, 3.40-3.71) in 2013. The average adjusted incidence showed no statistically significant increase. However, the age-specific incidence of the 15-19 and 20-24 years age groups increased significantly from 0.24 and 1.29 per 1,000 persons in 2003 to 2.73 and 2.71 per 1,000 persons in 2013 (R2 = 0.93 and 0.77, P < 0.001), while the incidence rate of the age group 40-44 and 45-49 years decreased from 2.36 and 1.72 per 1,000 persons in 2003 to 0.81 and 0.27 per 1,000 persons in 2013 (R2 = 0.83 and 0.89, P < 0.001). CONCLUSION: The prevalence and incidence of endometriosis in Korean women were lower than that of previous reports in high-risk population studies. Furthermore, we found a significant increase in the diagnosis of endometriosis in younger age groups.

The effect of the look-back period for estimating incidence using administrative data.

BACKGROUND: The look-back period is needed to define baseline population for estimating incidence. However, short look-back period is known to overestimate incidence of diseases misclassifying prevalent cases to incident cases. The purpose of this study is to evaluate the impact of the various length of look-back period on the observed incidences of uterine leiomyoma, endometriosis and adenomyosis, and to estimate true incidences considering the misclassification errors in the longitudinal administrative data in Korea. METHODS: A total of 319,608 women between 15 to 54 years of age in 2002 were selected from Korea National Health Insurance Services (KNHIS) cohort database. In order to minimize misclassification bias incurred when applying various length of look-back period, we used 11 years of claim data to estimate the incidence by equally setting the look-back period to 11 years for each year using prediction model. The association between the year of diagnosis and the number of prevalent cases with the misclassification rates by each look-back period was investigated. Based on the findings, prediction models on the proportion of misclassified incident cases were developed using multiple linear regression. RESULTS: The proportion of misclassified incident cases of uterine leiomyoma, endometriosis and adenomyosis were 32.8, 10.4 and 13.6% respectively for the one-year look-back period in 2003. These numbers decreased to 6.3% in uterine leiomyoma and - 0.8% in both endometriosis and adenomyosis using all available look-back periods (11 years) in 2013. CONCLUSION: This study demonstrates approaches for estimating incidences considering the different proportion of misclassified cases for various length of look-back period. Although the prediction model used for estimation showed strong R-squared values, follow-up studies are required for validation of the study results.

Transformation of Arden Syntax's medical logic modules into ArdenML for a business rules management system.

INTRODUCTION: Arden Syntax is a Health Level Seven International (HL7) standard language that is used for representing medical knowledge as logic statements. Arden Syntax Markup Language (ArdenML) is a new representation of Arden Syntax based on XML. Compilers are required to execute medical logic modules (MLMs) in the hospital environment. However, ArdenML may also replace the compiler. The purpose of this study is to demonstrate that MLMs, encoded in ArdenML, can be transformed into a commercial rule engine format through an XSLT stylesheet and made executable in a target system. METHODS: The target rule engine selected was Blaze Advisor. We developed an XSLT stylesheet to transform MLMs in ArdenML into Structured Rules Language (SRL) in Blaze Advisor, through a comparison of syntax between the two languages. The stylesheet was then refined recursively, by building and applying rules collected from the billing and coding guidelines of the Korean health insurance service. Two nurse coders collected and verified the rules and two information technology (IT) specialists encoded the MLMs and built the XSLT stylesheet. Finally, the stylesheet was validated by importing the MLMs into Blaze Advisor and applying them to claims data. RESULTS: The language comparison revealed that Blaze Advisor requires the declaration of variables with explicit types. We used both integer and real numbers for numeric types in ArdenML. "IF∼THEN" statements and assignment statements in ArdenML become rules in Blaze Advisor. We designed an XSLT stylesheet to solve this issue. In addition, we maintained the order of rule execution in the transformed rules, and added two small programs to support variable declarations and action statements. A total of 1489 rules were reviewed during this study, of which 324 rules were collected. We removed duplicate rules and encoded 241 unique MLMs in ArdenML, which were successfully transformed into SRL and imported to Blaze Advisor via the XSLT stylesheet. When applied to 73,841 outpatients' insurance claims data, the review result was the same as that of the legacy system. CONCLUSION: We have demonstrated that ArdenML can replace a compiler for transforming MLMs into commercial rule engine format. While the proposed XSLT stylesheet requires refinement for general use, we anticipate that the development of further XSLT stylesheets will support various rule engines.

The effect of the introduction of a nationwide DUR system where local DUR systems are operating--The Korean experience.

OBJECTIVE: Outpatient clinics in Korea usually have local DUR (drug utilisation review) systems, which are integrated with EMRs or health insurance claims submission systems. Whenever, the government announces a list of drug contraindications, each local DUR system loads the list and applies it in practice. In December 2010, a nationwide DUR system was introduced. This study is to investigate the impact of the nationwide DUR system on prescribing practices where local DUR systems are already operating. METHODS: Between January 2009 and December 2012 the monthly number of drugs per prescription was retrieved from the health insurance claims data warehouse at the Health Insurance Review and Assessment (HIRA). The monthly proportions of 3 DDI (drug-drug interaction) pairs, 6 drug-age contraindications, and 3 drug-pregnancy contraindications from January 2007 to December 2012, at the outpatient clinic level, were also retrieved. An interrupted time series analysis was used for controlling government announcements of drug contraindications. RESULTS: There was no difference in the number of drugs per prescription before and after the introduction of the nationwide DUR system. Most proportions of the 3 DDI pairs, 6 drug-age contraindications, and 3 drug-pregnancy contraindications, were significantly reduced following the government announcement of drug contraindications in the short term and/or long term. CONCLUSION: The number of drugs per prescription was not related to the nationwide DUR introduction in places where local DUR systems are operating. The introduction of duplicate guidelines, in locations where the guidelines were already well followed, is considered to be the main reason for this. Furthermore, the Doctor's ignorance of alerts, and their continued substitution of regulated drugs, for non-regulated drugs, likely played a role in nullifying the effectiveness of the nationwide DUR system.

Stakeholder analysis for adopting a personal health record standard in Korea.

BACKGROUND: Interest in health information exchanges (HIEs) is increasing. Several countries have adopted core health data standards with appropriate strategies. OBJECTIVE: This study was conducted to determine the feasibility of a continuity of care record (CCR) as the standard for an electronic version of the official transfer note and the HIE in Korean healthcare. METHOD: A technical review of the CCR standard and analysis of stakeholders' views were undertaken. Transfer notes were reviewed and matched with CCR standard categories. The standard for the Korean coding system was selected. Stakeholder analysis included an online survey of members of the Korean Society of Medical Informatics, a public hearing to derive opinions of consumers, doctors, vendors, academic societies and policy makers about the policy process, and a focus group meeting with EMR vendors to determine which HIE objects were technically applicable. RESULTS: Data objects in the official transfer note form matched CCR standards. Korean Classification of Diseases, Korean Standard Terminology of Medicine, Electronic Data Interchange code (EDI code), Logical Observation Identifiers Names and Codes, and Korean drug codes (KD code) were recommended as the Korean coding standard.'Social history', 'payers', and 'encounters' were mostly marked as optional or unnecessary sections, and 'allergies', 'alerts', 'medication list', 'problems/diagnoses', 'results',and 'procedures' as mandatory. Unlike the US, 'social history' was considered optional and 'advance directives' mandatory.At the public hearing there was some objection from the Korean Medical Association to the HIE on legal grounds in termsof intellectual property and patients' personal information. Other groups showed positive or neutral responses. Focus group members divided CCR data objects into three phases based onpredicted adoption time in CCR: (i) immediate adoption; (ii) short-term adoption ('alerts', 'family history'); and (iii) long-term adoption ('results', 'advanced directives', 'functional status', 'medical equipment', 'vital signs', 'plan of care', 'social history'). CONCLUSION: There were no technical problems in generating the CCR standard document from EMRs. Matters of concern that arose from study results should be resolved with time and consultation.

Appropriateness of ICNP in Korean home care nursing.

OBJECTIVES: There are several hospitals in Korea that introduced the ICNP (International Classification for Nursing Practice) as the standard terminology for clinical and home care nursing. This research attempted to determine the appropriateness of ICNP in Korean, hospital based, home care nursing. METHODS: The data was collected from a home care nursing center from January 1, 2009 to September 21, 2012. The center is operated by a Korean teaching hospital equipped with an ICNP based electronic nursing record (ENR) system. Via a refining process, 40,082 simplified sentences of nursing intervention were acquired from 41,158 nursing records. Among them, 545 preferred nursing statements were extracted, then mapped, to ICNP 2011 at both axis and sentence levels. RESULTS: The mapping results were classified into three categories based on the axis of concept origin and the level of hierarchy. These categories were titled: complete, incomplete and no mapping. Out of 45 unique concepts in the action axis, 42 (93.33%) concepts were completely mapped. However, only 38 (15.08%), out of 252 unique concepts, were completely mapped in the focus axis. At the statement level, only 19.63% of statements were completely mapped. CONCLUSIONS: The ICNP is not useful as a tool for home care nursing in its present form. The granularity of ICNP has to be improved and more concepts, specific to home care nursing, need to be added in the focus and action axes. Also, a new measure needs to be introduced to prevent information loss during mapping.

Executing medical logic modules expressed in ArdenML using Drools.

The Arden Syntax is an HL7 standard language for representing medical knowledge as logic statements. Despite nearly 2 decades of availability, Arden Syntax has not been widely used. This has been attributed to the lack of a generally available compiler to implement the logic, to Arden's complex syntax, to the challenges of mapping local data to data references in the Medical Logic Modules (MLMs), or, more globally, to the general absence of decision support in healthcare computing. An XML representation (ArdenML) may partially address the technical challenges. MLMs created in ArdenML can be converted into executable files using standard transforms written in the Extensible Stylesheet Language Transformation (XSLT) language. As an example, we have demonstrated an approach to executing MLMs written in ArdenML using the Drools business rule management system. Extensions to ArdenML make it possible to generate a user interface through which an MLM developer can test for logical errors.

Common data model for natural language processing based on two existing standard information models: CDA+GrAF.

An increasing need for collaboration and resources sharing in the Natural Language Processing (NLP) research and development community motivates efforts to create and share a common data model and a common terminology for all information annotated and extracted from clinical text. We have combined two existing standards: the HL7 Clinical Document Architecture (CDA), and the ISO Graph Annotation Format (GrAF; in development), to develop such a data model entitled "CDA+GrAF". We experimented with several methods to combine these existing standards, and eventually selected a method wrapping separate CDA and GrAF parts in a common standoff annotation (i.e., separate from the annotated text) XML document. Two use cases, clinical document sections, and the 2010 i2b2/VA NLP Challenge (i.e., problems, tests, and treatments, with their assertions and relations), were used to create examples of such standoff annotation documents, and were successfully validated with the XML schemata provided with both standards. We developed a tool to automatically translate annotation documents from the 2010 i2b2/VA NLP Challenge format to GrAF, and automatically generated 50 annotation documents using this tool, all successfully validated. Finally, we adapted the XSL stylesheet provided with HL7 CDA to allow viewing annotation XML documents in a web browser, and plan to adapt existing tools for translating annotation documents between CDA+GrAF and the UIMA and GATE frameworks. This common data model may ease directly comparing NLP tools and applications, combining their output, transforming and "translating" annotations between different NLP applications, and eventually "plug-and-play" of different modules in NLP applications.