Development and Verification of Time-Series Deep Learning for Drug-Induced Liver Injury Detection in Patients Taking Angiotensin II Receptor Blockers: A Multicenter Distributed Research Network Approach / 대한의료정보학회지

Objectives@#The objective of this study was to develop and validate a multicenter-based, multi-model, time-series deep learning model for predicting drug-induced liver injury (DILI) in patients taking angiotensin receptor blockers (ARBs). The study leveraged a national-level multicenter approach, utilizing electronic health records (EHRs) from six hospitals in Korea. @*Methods@#A retrospective cohort analysis was conducted using EHRs from six hospitals in Korea, comprising a total of 10,852 patients whose data were converted to the Common Data Model. The study assessed the incidence rate of DILI among patients taking ARBs and compared it to a control group. Temporal patterns of important variables were analyzed using an interpretable timeseries model. @*Results@#The overall incidence rate of DILI among patients taking ARBs was found to be 1.09%. The incidence rates varied for each specific ARB drug and institution, with valsartan having the highest rate (1.24%) and olmesartan having the lowest rate (0.83%). The DILI prediction models showed varying performance, measured by the average area under the receiver operating characteristic curve, with telmisartan (0.93), losartan (0.92), and irbesartan (0.90) exhibiting higher classification performance. The aggregated attention scores from the models highlighted the importance of variables such as hematocrit, albumin, prothrombin time, and lymphocytes in predicting DILI. @*Conclusions@#Implementing a multicenter-based timeseries classification model provided evidence that could be valuable to clinicians regarding temporal patterns associated with DILI in ARB users. This information supports informed decisions regarding appropriate drug use and treatment strategies.

Feasibility Study of Federated Learning on the Distributed Research Network of OMOP Common Data Model / 대한의료정보학회지

Objectives@#Since protecting patients’ privacy is a major concern in clinical research, there has been a growing need for privacy-preserving data analysis platforms. For this purpose, a federated learning (FL) method based on the Observational Medical Outcomes Partnership (OMOP) common data model (CDM) was implemented, and its feasibility was demonstrated. @*Methods@#We implemented an FL platform on FeederNet, which is a distributed clinical data analysis platform based on the OMOP CDM in Korea. We trained it through an artificial neural network (ANN) using data from patients who received steroid prescriptions or injections, with the aim of predicting the occurrence of side effects depending on the prescribed dose. The ANN was trained using the FL platform with the OMOP CDMs of Kyung Hee University Medical Center (KHMC) and Ajou University Hospital (AUH). @*Results@#The area under the receiver operating characteristic curves (AUROCs) for predicting bone fracture, osteonecrosis, and osteoporosis using only data from each hospital were 0.8426, 0.6920, and 0.7727 for KHMC and 0.7891, 0.7049, and 0.7544 for AUH, respectively. In contrast, when using FL, the corresponding AUROCs were 0.8260, 0.7001, and 0.7928 for KHMC and 0.7912, 0.8076, and 0.7441 for AUH, respectively. In particular, FL led to a 14% improvement in performance for osteonecrosis at AUH. @*Conclusions@#FL can be performed with the OMOP CDM, and FL often shows better performance than using only a single institution's data. Therefore, research using OMOP CDM has been expanded from statistical analysis to machine learning so that researchers can conduct more diverse research.

Development and Validation of the Radiology Common Data Model (R-CDM) for the International Standardization of Medical Imaging Data

Purpose@#Digital Imaging and Communications in Medicine (DICOM), a standard file format for medical imaging data, contains metadata describing each file. However, metadata are often incomplete, and there is no standardized format for recording metadata, leading to inefficiency during the metadata-based data retrieval process. Here, we propose a novel standardization method for DICOM metadata termed the Radiology Common Data Model (R-CDM). @*Materials and Methods@#R-CDM was designed to be compatible with Health Level Seven International (HL7)/Fast Healthcare Interoperability Resources (FHIR) and linked with the Observational Medical Outcomes Partnership (OMOP)-CDM to achieve a seamless link between clinical data and medical imaging data. The terminology system was standardized using the RadLex playbook, a comprehensive lexicon of radiology. As a proof of concept, the R-CDM conversion process was conducted with 41.7 TB of data from the Ajou University Hospital. The R-CDM database visualizer was developed to visualize the main characteristics of the R-CDM database. @*Results@#Information from 2801360 cases and 87203226 DICOM files was organized into two tables constituting the R-CDM. Information on imaging device and image resolution was recorded with more than 99.9% accuracy. Furthermore, OMOP-CDM and RCDM were linked to efficiently extract specific types of images from specific patient cohorts. @*Conclusion@#R-CDM standardizes the structure and terminology for recording medical imaging data to eliminate incomplete and unstandardized information. Successful standardization was achieved by the extract, transform, and load process and image classifier. We hope that the R-CDM will contribute to deep learning research in the medical imaging field by enabling the securement of large-scale medical imaging data from multinational institutions.

Applying the OMOP Common Data Model to Facilitate Benefit-Risk Assessments of Medicinal Products Using Real-World Data from Singapore and South Korea / 대한의료정보학회지

Objectives@#The aim of this study was to characterize the benefits of converting Electronic Medical Records (EMRs) to a common data model (CDM) and to assess the potential of CDM-converted data to rapidly generate insights for benefit-risk assessments in post-market regulatory evaluation and decisions. @*Methods@#EMRs from January 2013 to December 2016 were mapped onto the Observational Medical Outcomes Partnership-CDM (OMOP-CDM) schema. Vocabulary mappings were applied to convert source data values into OMOP-CDM-endorsed terminologies. Existing analytic codes used in a prior OMOP-CDM drug utilization study were modified to conduct an illustrative analysis of oral anticoagulants used for atrial fibrillation in Singapore and South Korea, resembling a typical benefit-risk assessment. A novel visualization is proposed to represent the comparative effectiveness, safety and utilization of the drugs. @*Results@#Over 90% of records were mapped onto the OMOP-CDM. The CDM data structures and analytic code templates simplified the querying of data for the analysis. In total, 2,419 patients from Singapore and South Korea fulfilled the study criteria, the majority of whom were warfarin users. After 3 months of follow-up, differences in cumulative incidence of bleeding and thromboembolic events were observable via the proposed visualization, surfacing insights as to the agent of preference in a given clinical setting, which may meaningfully inform regulatory decision-making. @*Conclusions@#While the structure of the OMOP-CDM and its accessory tools facilitate real-world data analysis, extending them to fulfil regulatory analytic purposes in the post-market setting, such as benefit-risk assessments, may require layering on additional analytic tools and visualization techniques.

Association Between Suicide Risk and Comorbidity of Mood Disorder and Alcohol Use Disorder:Using Common Data Model in Psychiatry / 신경정신의학

Objectives@#This study determines the effects of comorbidity of mood disorder and alcohol use disorder on suicide behavior. @*Methods@#We converted data from the electronic medical records of one university hospital into a common data model and utilized it in our analysis. We selected 9551 patients with diagnosis codes of mood disorders or alcohol use disorders and divided them into three groups: mood disorder (MD) only, alcohol use disorder (AUD) only, and comorbidity of mood disorder and alcohol use disorder (MD+AUD). The mood disorder group was also subgrouped with depressive (DD) or bipolar affective disorder (BD) groups, and the comorbidity group was classified in the same way. Then, we applied logistic regression analysis to assess the risk of suicide attempts between the diagnostic groups. Subgroup analysis according to age also was conducted. @*Results@#The MD+AUD group had 2.7 (odd ratio [OR]=2.70, 95% confidence intervals [CI]=1.91– 3.81, p<0.0001) and the DD+AUD group had 2.78 (OR=2.78, 95% CI=1.95–3.98, p<0.0001) times higher risk of suicide attempts than the MD only and DD only group, respectively. Furthermore, according to the age subgroup, the risk of suicide attempts was the highest (OR=5.17, 95% CI=2.35–11.40, p<0.0001) in the DD+AUD group for those aged 40–59. There were no significant results in BD. @*Conclusion@#The results showed that the comorbidity of mood disorder and alcohol use disorder could increase suicide risk. This study suggested that alcohol use behavior needs to be assessed as well as mood symptoms for suicide prevention.

Association Between Suicide Risk and Comorbidity of Mood Disorder and Alcohol Use Disorder:Using Common Data Model in Psychiatry / 신경정신의학

Objectives@#This study determines the effects of comorbidity of mood disorder and alcohol use disorder on suicide behavior. @*Methods@#We converted data from the electronic medical records of one university hospital into a common data model and utilized it in our analysis. We selected 9551 patients with diagnosis codes of mood disorders or alcohol use disorders and divided them into three groups: mood disorder (MD) only, alcohol use disorder (AUD) only, and comorbidity of mood disorder and alcohol use disorder (MD+AUD). The mood disorder group was also subgrouped with depressive (DD) or bipolar affective disorder (BD) groups, and the comorbidity group was classified in the same way. Then, we applied logistic regression analysis to assess the risk of suicide attempts between the diagnostic groups. Subgroup analysis according to age also was conducted. @*Results@#The MD+AUD group had 2.7 (odd ratio [OR]=2.70, 95% confidence intervals [CI]=1.91– 3.81, p<0.0001) and the DD+AUD group had 2.78 (OR=2.78, 95% CI=1.95–3.98, p<0.0001) times higher risk of suicide attempts than the MD only and DD only group, respectively. Furthermore, according to the age subgroup, the risk of suicide attempts was the highest (OR=5.17, 95% CI=2.35–11.40, p<0.0001) in the DD+AUD group for those aged 40–59. There were no significant results in BD. @*Conclusion@#The results showed that the comorbidity of mood disorder and alcohol use disorder could increase suicide risk. This study suggested that alcohol use behavior needs to be assessed as well as mood symptoms for suicide prevention.

COVID-19 International Collaborative Research by the Health Insurance Review and Assessment Service Using Its Nationwide Real-world Data: Database, Outcomes, and Implications / 예방의학회지

This article aims to introduce the inception and operation of the COVID-19 International Collaborative Research Project, the world’s first coronavirus disease 2019 (COVID-19) open data project for research, along with its dataset and research method, and to discuss relevant considerations for collaborative research using nationwide real-world data (RWD). COVID-19 has spread across the world since early 2020, becoming a serious global health threat to life, safety, and social and economic activities. However, insufficient RWD from patients was available to help clinicians efficiently diagnose and treat patients with COVID-19, or to provide necessary information to the government for policy-making. Countries that saw a rapid surge of infections had to focus on leveraging medical professionals to treat patients, and the circumstances made it even more difficult to promptly use COVID-19 RWD. Against this backdrop, the Health Insurance Review and Assessment Service (HIRA) of Korea decided to open its COVID-19 RWD collected through Korea’s universal health insurance program, under the title of the COVID-19 International Collaborative Research Project. The dataset, consisting of 476 508 claim statements from 234 427 patients (7590 confirmed cases) and 18 691 318 claim statements of the same patients for the previous 3 years, was established and hosted on HIRA’s in-house server. Researchers who applied to participate in the project uploaded analysis code on the platform prepared by HIRA, and HIRA conducted the analysis and provided outcome values. As of November 2020, analyses have been completed for 129 research projects, which have been published or are in the process of being published in prestigious journals.

Incorporation of Korean Electronic Data Interchange Vocabulary into Observational Medical Outcomes Partnership Vocabulary / 대한의료정보학회지

Objectives@#We incorporated the Korean Electronic Data Interchange (EDI) vocabulary into Observational Medical Outcomes Partnership (OMOP) vocabulary using a semi-automated process. The goal of this study was to improve the Korean EDI as a standard medical ontology in Korea. @*Methods@#We incorporated the EDI vocabulary into OMOP vocabulary through four main steps. First, we improved the current classification of EDI domains and separated medical services into procedures and measurements. Second, each EDI concept was assigned a unique identifier and validity dates. Third, we built a vertical hierarchy between EDI concepts, fully describing child concepts through relationships and attributes and linking them to parent terms. Finally, we added an English definition for each EDI concept. We translated the Korean definitions of EDI concepts using Google.Cloud.Translation.V3, using a client library and manual translation. We evaluated the EDI using 11 auditing criteria for controlled vocabularies. @*Results@#We incorporated 313,431 concepts from the EDI to the OMOP Standardized Vocabularies. For 10 of the 11 auditing criteria, EDI showed a better quality index within the OMOP vocabulary than in the original EDI vocabulary. @*Conclusions@#The incorporation of the EDI vocabulary into the OMOP Standardized Vocabularies allows better standardization to facilitate network research. Our research provides a promising model for mapping Korean medical information into a global standard terminology system, although a comprehensive mapping of official vocabulary remains to be done in the future.

Association between Full Electronic Medical Record System Adoption and Drug Use: Antibiotics and Polypharmacy / 대한의료정보학회지

Comparison of First-Line Dual Combination Treatments in Hypertension: Real-World Evidence from Multinational Heterogeneous Cohorts

BACKGROUND AND OBJECTIVES: 2018 ESC/ESH Hypertension guideline recommends 2-drug combination as initial anti-hypertensive therapy. However, real-world evidence for effectiveness of recommended regimens remains limited. We aimed to compare the effectiveness of first-line anti-hypertensive treatment combining 2 out of the following classes: angiotensin-converting enzyme (ACE) inhibitors/angiotensin-receptor blocker (A), calcium channel blocker (C), and thiazide-type diuretics (D).METHODS: Treatment-naïve hypertensive adults without cardiovascular disease (CVD) who initiated dual anti-hypertensive medications were identified in 5 databases from US and Korea. The patients were matched for each comparison set by large-scale propensity score matching. Primary endpoint was all-cause mortality. Myocardial infarction, heart failure, stroke, and major adverse cardiac and cerebrovascular events as a composite outcome comprised the secondary measure.RESULTS: A total of 987,983 patients met the eligibility criteria. After matching, 222,686, 32,344, and 38,513 patients were allocated to A+C vs. A+D, C+D vs. A+C, and C+D vs. A+D comparison, respectively. There was no significant difference in the mortality during total of 1,806,077 person-years: A+C vs. A+D (hazard ratio [HR], 1.08; 95% confidence interval [CI], 0.97−1.20; p=0.127), C+D vs. A+C (HR, 0.93; 95% CI, 0.87−1.01; p=0.067), and C+D vs. A+D (HR, 1.18; 95% CI, 0.95−1.47; p=0.104). A+C was associated with a slightly higher risk of heart failure (HR, 1.09; 95% CI, 1.01−1.18; p=0.040) and stroke (HR, 1.08; 95% CI, 1.01−1.17; p=0.040) than A+D.CONCLUSIONS: There was no significant difference in mortality among A+C, A+D, and C+D combination treatment in patients without previous CVD. This finding was consistent across multi-national heterogeneous cohorts in real-world practice.

Analysis of Adverse Drug Reactions Identified in Nursing Notes Using Reinforcement Learning / 대한의료정보학회지

ObjectivesElectronic Health Records (EHRs)-based surveillance systems are being actively developed for detecting adverse drug reactions (ADRs), but this is being hindered by the difficulty of extracting data from unstructured records. This study performed the analysis of ADRs from nursing notes for drug safety surveillance using the temporal difference method in reinforcement learning (TD learning).MethodsNursing notes of 8,316 patients (4,158 ADR and 4,158 non-ADR cases) admitted to Ajou University Hospital were used for the ADR classification task. A TD(λ) model was used to estimate state values for indicating the ADR risk. For the TD learning, each nursing phrase was encoded into one of seven states, and the state values estimated during training were employed for the subsequent testing phase. We applied logistic regression to the state values from the TD(λ) model for the classification task.ResultsThe overall accuracy of TD-based logistic regression of 0.63 was comparable to that of two machine-learning methods (0.64 for a naïve Bayes classifier and 0.63 for a support vector machine), while it outperformed two deep learning-based methods (0.58 for a text convolutional neural network and 0.61 for a long short-term memory neural network). Most importantly, it was found that the TD-based method can estimate state values according to the context of nursing phrases.ConclusionsTD learning is a promising approach because it can exploit contextual, time-dependent aspects of the available data and provide an analysis of the severity of ADRs in a fully incremental manner.

Comparison of First-Line Dual Combination Treatments in Hypertension: Real-World Evidence from Multinational Heterogeneous Cohorts

BACKGROUND AND OBJECTIVES@#2018 ESC/ESH Hypertension guideline recommends 2-drug combination as initial anti-hypertensive therapy. However, real-world evidence for effectiveness of recommended regimens remains limited. We aimed to compare the effectiveness of first-line anti-hypertensive treatment combining 2 out of the following classes: angiotensin-converting enzyme (ACE) inhibitors/angiotensin-receptor blocker (A), calcium channel blocker (C), and thiazide-type diuretics (D).@*METHODS@#Treatment-naïve hypertensive adults without cardiovascular disease (CVD) who initiated dual anti-hypertensive medications were identified in 5 databases from US and Korea. The patients were matched for each comparison set by large-scale propensity score matching. Primary endpoint was all-cause mortality. Myocardial infarction, heart failure, stroke, and major adverse cardiac and cerebrovascular events as a composite outcome comprised the secondary measure.@*RESULTS@#A total of 987,983 patients met the eligibility criteria. After matching, 222,686, 32,344, and 38,513 patients were allocated to A+C vs. A+D, C+D vs. A+C, and C+D vs. A+D comparison, respectively. There was no significant difference in the mortality during total of 1,806,077 person-years: A+C vs. A+D (hazard ratio [HR], 1.08; 95% confidence interval [CI], 0.97−1.20; p=0.127), C+D vs. A+C (HR, 0.93; 95% CI, 0.87−1.01; p=0.067), and C+D vs. A+D (HR, 1.18; 95% CI, 0.95−1.47; p=0.104). A+C was associated with a slightly higher risk of heart failure (HR, 1.09; 95% CI, 1.01−1.18; p=0.040) and stroke (HR, 1.08; 95% CI, 1.01−1.17; p=0.040) than A+D.@*CONCLUSIONS@#There was no significant difference in mortality among A+C, A+D, and C+D combination treatment in patients without previous CVD. This finding was consistent across multi-national heterogeneous cohorts in real-world practice.

The Distributed Research Network, Observational Health Data Sciences and Informatics, and the South Korean Research Network / 대한내과학회지

No abstract available.

Clinical Outcomes of Antiplatelets Combined with Statins in Patients with Ischemic Heart Disease

BACKGROUND@#Patients with cardiovascular risks are recommended to use statins and antiplatelet agents to prevent major cerebrocardiovascular events (MACCE). Antiplatelet agents also possess anti-inflammatory and antioxidant effects, in addition to their inhibitory activity on platelets. The differences in clinical outcomes in ischemic heart disease (IHD) based on the type of antiplatelet therapy combined with statin treatment were investigated in this study.@*METHODS@#We conducted a retrospective cohort study using electronic medical records of IHD patients from January 2010 to December 2014 at Ajou University Hospital. Patients on combination therapy of antiplatelet drugs and statins were grouped based on antiplatelet drug types: clopidogrel, cilostazol, or sarpogrelate. Propensity score matching was applied to balance the baseline of the groups of clopidogrel vs. cilostazol and the groups of clopidogrel vs. sarpogrelate. The incidence and risk of MACCE as primary outcomes were assessed between the groups of antiplatelet drugs.@*RESULTS@#Among the approximately 128,500 patients with IHD, 1,049 patients had taken a combination therapy of statin and antiplatelet agents. The cohorts of patients administered clopidogrel, cilostazol, or sarpogrelate were 906, 79, and 64, respectively. The incidence of MACCE was not significantly different among the cohorts (p=0.58), and there were no differences between clopidogrel vs. cilostazol (p=0.72) or clopidogrel vs. sarpogrelate (p=1.00) after propensity score matching.@*CONCLUSION@#There was no difference in the incidence of MACCE based on the type of antiplatelet drug (clopidogrel, cilostazol, or sarpogrelate) in combination with a statin in patients with IHD.

Olmesartan is not associated with the risk of enteropathy: a Korean nationwide observational cohort study

BACKGROUND/AIMS: Olmesartan, a widely used angiotensin II receptor blocker (ARB), has been linked to sprue-like enteropathy. No cases of olmesartan-associated enteropathy have been reported in Northeast Asia. We investigated the associations between olmesartan and other ARBs and the incidence of enteropathy in Korea. METHODS: Our retrospective cohort study used data from the Korean National Health Insurance Service to identify 108,559 patients (58,186 females) who were initiated on angiotensin converting enzyme inhibitors (ACEis), olmesartan, or other ARBs between January 2005 and December 2012. The incidences of enteropathy were compared among drug groups. Changes in body weight were compared after propensity score matching of patients in the ACEis and olmesartan groups. RESULTS: Among 108,559 patients, 31 patients were diagnosed with enteropathy. The incidences were 0.73, 0.24, and 0.37 per 1,000 persons, in the ACEis, olmesartan, and other ARBs groups, respectively. Adjusted rate ratios for enteropathy were: olmesartan, 0.33 (95% confidential interval [CI], 0.10 to 1.09; p = 0.070) and other ARBs, 0.34 (95% CI, 0.14 to 0.83; p = 0.017) compared to the ACEis group after adjustment for age, sex, income level, and various comorbidities. The post hoc analysis with matched cohorts revealed that the proportion of patients with significant weight loss did not differ between the ACEis and olmesartan groups. CONCLUSIONS: Olmesartan was not associated with intestinal malabsorption or significant body weight loss in the general Korean population. Additional large-scale prospective studies of the relationship between olmesartan and the incidence of enteropathy in the Asian population are needed.

Construction of an Electrocardiogram Database Including 12 Lead Waveforms / 대한의료정보학회지

OBJECTIVES: Electrocardiogram (ECG) data are important for the study of cardiovascular disease and adverse drug reactions. Although the development of analytical techniques such as machine learning has improved our ability to extract useful information from ECGs, there is a lack of easily available ECG data for research purposes. We previously published an article on a database of ECG parameters and related clinical data (ECG-ViEW), which we have now updated with additional 12-lead waveform information. METHODS: All ECGs stored in portable document format (PDF) were collected from a tertiary teaching hospital in Korea over a 23-year study period. We developed software which can extract all ECG parameters and waveform information from the ECG reports in PDF format and stored it in a database (meta data) and a text file (raw waveform). RESULTS: Our database includes all parameters (ventricular rate, PR interval, QRS duration, QT/QTc interval, P-R-T axes, and interpretations) and 12-lead waveforms (for leads I, II, III, aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6) from 1,039,550 ECGs (from 447,445 patients). Demographics, drug exposure data, diagnosis history, and laboratory test results (serum calcium, magnesium, and potassium levels) were also extracted from electronic medical records and linked to the ECG information. CONCLUSIONS: Electrocardiogram information that includes 12 lead waveforms was extracted and transformed into a form that can be analyzed. The description and programming codes in this case report could be a reference for other researchers to build ECG databases using their own local ECG repository.

System for Collecting Biosignal Data from Multiple Patient Monitoring Systems / 대한의료정보학회지

OBJECTIVES: Biosignal data include important physiological information. For that reason, many devices and systems have been developed, but there has not been enough consideration of how to collect and integrate raw data from multiple systems. To overcome this limitation, we have developed a system for collecting and integrating biosignal data from two patient monitoring systems. METHODS: We developed an interface to extract biosignal data from Nihon Kohden and Philips monitoring systems. The Nihon Kohden system has a central server for the temporary storage of raw waveform data, which can be requested using the HL7 protocol. However, the Philips system used in our hospital cannot save raw waveform data. Therefore, our system was connected to monitoring devices using the RS232 protocol. After collection, the data were transformed and stored in a unified format. RESULTS: From September 2016 to August 2017, we collected approximately 117 patient-years of waveform data from 1,268 patients in 79 beds of five intensive care units. Because the two systems use the same data storage format, the application software could be run without compatibility issues. CONCLUSIONS: Our system collects biosignal data from different systems in a unified format. The data collected by the system can be used to develop algorithms or applications without the need to consider the source of the data.

Sharing Clinical Big Data While Protecting Confidentiality and Security: Observational Health Data Sciences and Informatics / 대한의료정보학회지

No abstract available.

The Best Prediction Model for Trauma Outcomes of the Current Korean Population: a Comparative Study of Three Injury Severity Scoring Systems / 대한구급학회지

BACKGROUND: Injury severity scoring systems that quantify and predict trauma outcomes have not been established in Korea. This study was designed to determine the best system for use in the Korean trauma population. METHODS: We collected and analyzed the data from trauma patients admitted to our institution from January 2010 to December 2014. Injury Severity Score (ISS), Revised Trauma Score (RTS), and Trauma and Injury Severity Score (TRISS) were calculated based on the data from the enrolled patients. Area under the receiver operating characteristic (ROC) curve (AUC) for the prediction ability of each scoring system was obtained, and a pairwise comparison of ROC curves was performed. Additionally, the cut-off values were estimated to predict mortality, and the corresponding accuracy, positive predictive value, and negative predictive value were obtained. RESULTS: A total of 7,120 trauma patients (6,668 blunt and 452 penetrating injuries) were enrolled in this study. The AUCs of ISS, RTS, and TRISS were 0.866, 0.894, and 0.942, respectively, and the prediction ability of the TRISS was significantly better than the others (p < 0.001, respectively). The cut-off value of the TRISS was 0.9082, with a sensitivity of 81.9% and specificity of 92.0%; mortality was predicted with an accuracy of 91.2%; its positive predictive value was the highest at 46.8%. CONCLUSIONS: The results of our study were based on the data from one institution and suggest that the TRISS is the best prediction model of trauma outcomes in the current Korean population. Further study is needed with more data from multiple centers in Korea.

Nomogram of Naive Bayesian Model for Recurrence Prediction of Breast Cancer / 대한의료정보학회지

OBJECTIVES: Breast cancer has a high rate of recurrence, resulting in the need for aggressive treatment and close follow-up. However, previously established classification guidelines, based on expert panels or regression models, are controversial. Prediction models based on machine learning show excellent performance, but they are not widely used because they cannot explain their decisions and cannot be presented on paper in the way that knowledge is customarily represented in the clinical world. The principal objective of this study was to develop a nomogram based on a naïve Bayesian model for the prediction of breast cancer recurrence within 5 years after breast cancer surgery. METHODS: The nomogram can provide a visual explanation of the predicted probabilities on a sheet of paper. We used a data set from a Korean tertiary teaching hospital of 679 patients who had undergone breast cancer surgery between 1994 and 2002. Seven prognostic factors were selected as independent variables for the model. RESULTS: The accuracy was 80%, and the area under the receiver operating characteristics curve (AUC) of the model was 0.81. CONCLUSIONS: The nomogram can be easily used in daily practice to aid physicians and patients in making appropriate treatment decisions after breast cancer surgery.