Objectives: The objective of this study was to introduce the Systematized Nomenclature of Medicine Clinical Terms (SNOMED CT), to describe use cases of SNOMED CT with the barriers and facilitators, and finally, to propose strategies for adopting and implementing SNOMED CT in Korea as a member of SNOMED International. Methods: We reviewed a collection of SNOMED CT documents, such as introductory materials, practical guides, technical specifications, and reference materials provided by SNOMED International and the literature on SNOMED CT published by researchers to identify use cases of SNOMED CT with barriers and facilitators. We also surveyed the attendees of SNOMED CT education and training series offered by the Korea Human Resource Development Institute for Health and Welfare to identify perceived barriers to adopting SNOMED CT in Korea. Results: We identified the barriers and facilitators to adopt SNOMED CT experienced by international terminology experts and prospective Korean users. They were related to governance and infrastructure, support services for use, education and training programs, use cases, and vendor capability to implement SNOMED CT. Based on these findings, we identified strategies for adopting and implementing SNOMED CT in Korea. They included the establishment of SNOMED CT management infrastructure, the development of SNOMED CT education and training programs for various user groups, the provision of support services for SNOMED CT use, and the development of SNOMED CT use cases. Conclusions These strategies for the adoption and implementation of SNOMED CT need to be executed step by step.

Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms—logistic regression, random forest, and artificial neural network—were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one’s health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms—logistic regression, random forest, and artificial neural network—were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one’s health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms—logistic regression, random forest, and artificial neural network—were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one’s health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

Purpose: This study aimed to develop a fall prediction model for community-dwelling older adults using machine learning. Methods: The present study was conducted with a secondary data analysis that used data from the 2020 national survey of older Koreans. Among 10,097 participants, data 177 were excluded due to incompleteness and 9,920 were included in the final analysis. Because of data imbalance, upsampling was performed to increase the number of individuals who fell. Forty-five independent variables for fall prediction were selected based on the fall risk factors from previous studies and univariate statistical analysis. The data were split into training and testing sets at an 80:20 ratio. Three machine learning algorithms—logistic regression, random forest, and artificial neural network—were used to develop a fall prediction model. Results: The random forest model outperformed the others, with an area under the curve of .91, accuracy of .94, precision of .94, recall of .74, and F1 score of .83. An analysis of feature importance revealed that satisfaction with health condition, visual difficulty, instrumental activities of daily living, performance of 400m walk, and cognitive ability were the top five features for fall prediction. Conclusion The fall prediction model developed using machine learning demonstrated high model performance, implying its suitability for use as a primary screening tool for fall risk. Subjective satisfaction with one’s health should be considered as an important factor in predicting falls in community-dwelling older adults. It is necessary for community health nurses to reinforce positive health awareness by continuous disease management and physical function improvement for older adults to prevent falls.

OBJECTIVES: We reviewed digital epidemiological studies to characterize how researchers are using digital data by topic domain, study purpose, data source, and analytic method. METHODS: We reviewed research articles published within the last decade that used digital data to answer epidemiological research questions. Data were abstracted from these articles using a data collection tool that we developed. Finally, we summarized the characteristics of the digital epidemiological studies. RESULTS: We identified six main topic domains: infectious diseases (58.7%), non-communicable diseases (29.4%), mental health and substance use (8.3%), general population behavior (4.6%), environmental, dietary, and lifestyle (4.6%), and vital status (0.9%). We identified four categories for the study purpose: description (22.9%), exploration (34.9%), explanation (27.5%), and prediction and control (14.7%). We identified eight categories for the data sources: web search query (52.3%), social media posts (31.2%), web portal posts (11.9%), webpage access logs (7.3%), images (7.3%), mobile phone network data (1.8%), global positioning system data (1.8%), and others (2.8%). Of these, 50.5% used correlation analyses, 41.3% regression analyses, 25.6% machine learning, and 19.3% descriptive analyses. CONCLUSIONS: Digital data collected for non-epidemiological purposes are being used to study health phenomena in a variety of topic domains. Digital epidemiology requires access to large datasets and advanced analytics. Ensuring open access is clearly at odds with the desire to have as little personal data as possible in these large datasets to protect privacy. Establishment of data cooperatives with restricted access may be a solution to this dilemma.
Cell Phones ; Communicable Diseases ; Data Collection ; Dataset ; Epidemiologic Studies* ; Epidemiological Monitoring ; Epidemiology* ; Geographic Information Systems ; Humans ; Information Storage and Retrieval ; Internet ; Life Style ; Machine Learning ; Mental Health ; Methods ; Privacy ; Public Health Surveillance ; Social Media

BACKGROUND: Micropapillary carcinoma (MPC) is known to have a worse prognosis than the other subtypes of breast cancer. Occasionally, MPC is observed in association with invasive ductal carcinoma not otherwise specified (IDC NOS), as well as mucinous carcinoma. METHODS: We examined the immunohistochemical expression of an estrogen receptor, progesterone receptor, and human epidermal growth factor receptor 2 (HER2) in 127 cases of surgically resected MPC or IDC NOS with MPC. Further, we classified these cases based on their immunohistochemical profile. RESULTS: Among the IDC NOS with MPC cases, 47 were luminal A (62.7%), 10 were luminal B (13.3%), and 9 were HER2 (12.0%). The MPC cases included 4 luminal A (50.0%), 2 luminal B (25.0%) and 1 HER2 (12.5%) subtypes. Of the mucinous carcinomas with MPC, 4 were grouped as luminal A (57.1%), 1 as luminal B (14.3%), and 2 as HER2 (28.6%) subtypes. However, among the mucinous carcinomas, 33 were categorized as luminal A (89.2%), 3 as luminal B (8.1%), and 1 as HER2 (2.7%) subtype, indicating a low incidence of HER2 subtype as compared to the other subtypes. CONCLUSIONS: The luminal B and HER2 subtypes were prevalent in carcinomas with MPC. This result explains the poor prognosis of breast carcinomas with an MPC pattern.
Adenocarcinoma, Mucinous ; Breast ; Breast Neoplasms ; Carcinoma, Ductal ; Estrogens ; Humans ; Immunohistochemistry ; Incidence ; Mucins ; Phenobarbital ; Prognosis ; Receptor, Epidermal Growth Factor ; Receptor, erbB-2 ; Receptors, Progesterone

OBJECTIVES: The objective of this study was to review and visualize the medical informatics field over the previous 12 months according to the frequencies of keywords and topics in papers published in the top four journals in the field and in Healthcare Informatics Research (HIR), an official journal of the Korean Society of Medical Informatics. METHODS: A six-person team conducted an extensive review of the literature on clinical and consumer informatics. The literature was searched using keywords employed in the American Medical Informatics Association year-in-review process and organized into 14 topics used in that process. Data were analyzed using word clouds, social network analysis, and association rules. RESULTS: The literature search yielded 370 references and 1,123 unique keywords. ‘Electronic Health Record’ (EHR) (78.6%) was the most frequently appearing keyword in the articles published in the five studied journals, followed by ‘telemedicine’ (2.1%). EHR (37.6%) was also the most frequently studied topic area, followed by clinical informatics (12.0%). However, ‘telemedicine’ (17.0%) was the most frequently appearing keyword in articles published in HIR, followed by ‘telecommunications’ (4.5%). Telemedicine (47.1%) was the most frequently studied topic area, followed by EHR (14.7%). CONCLUSIONS: The study findings reflect the Korean government's efforts to introduce telemedicine into the Korean healthcare system and reactions to this from the stakeholders associated with telemedicine.
Computer Graphics ; Data Mining ; Delivery of Health Care ; Informatics* ; Medical Informatics ; Telemedicine

Objectives: This study investigated the effectiveness of using standardized vocabularies to generate epilepsy patient cohorts with local medical codes, SNOMED Clinical Terms (SNOMED CT), and International Classification of Diseases tenth revision (ICD-10)/Korean Classification of Diseases-7 (KCD-7). Methods: We compared the granularity between SNOMED CT and ICD-10 for epilepsy by counting the number of SNOMED CT concepts mapped to one ICD-10 code. Next, we created epilepsy patient cohorts by selecting all patients who had at least one code included in the concept sets defined using each vocabulary. We set patient cohorts generated by local codes as the reference to evaluate the patient cohorts generated using SNOMED CT and ICD-10/KCD-7. We compared the number of patients, the prevalence of epilepsy, and the age distribution between patient cohorts by year. Results: In terms of the cohort size, the match rate with the reference cohort was approximately 99.2% for SNOMED CT and 94.0% for ICD-10/KDC7. From 2010 to 2019, the mean prevalence of epilepsy defined using the local codes, SNOMED CT, and ICD-10/KCD-7 was 0.889%, 0.891% and 0.923%, respectively. The age distribution of epilepsy patients showed no significant difference between the cohorts defined using local codes or SNOMED CT, but the ICD-9/KCD-7-generated cohort showed a substantial gap in the age distribution of patients with epilepsy compared to the cohort generated using the local codes. Conclusions The number and age distribution of patients were substantially different from the reference when we used ICD-10/KCD-7 codes, but not when we used SNOMED CT concepts. Therefore, SNOMED CT is more suitable for representing clinical ideas and conducting clinical studies than ICD-10/KCD-7.

BACKGROUND: Pleomorphic carcinoma (PC) is a rare pulmonary malignancy. Because of its rarity and histological heterogeneity, cytopathologists might suspect PC only rarely on the basis of its cytological specimen. In addition, cytological findings from fine needle aspiration (FNA) specimens have rarely been described. Hence, we investigated the cytological features of FNA in the cases of PC. METHODS: We reviewed 7 FNA specimens of PC. The patients had undergone surgical resection at the Korea Cancer Center Hospital between 2007 and 2011. The cytological features of PC were assessed and compared with the histopathological features of the corresponding surgical specimen. Immunocytochemical analysis with cytokeratin and vimentin was performed on the cell blocks. RESULTS: The tumor cells were either dispersed or arranged in loose aggregates, and generally lacked any glandular or squamous differentiation. Pleomorphic or spindle shape tumor cells were observed, and mono-, bi-, or multi-nucleated giant cells were frequently observed. The background showed necrosis and contained numerous lymphocytes and neutrophils. Immunocytochemically, the tumor cells were positive for cytokeratin and vimentin. CONCLUSIONS: PC displays characteristic cytological features. It might therefore be possible to make an accurate diagnosis of PC by assessing the degree of nuclear atypia.
Biopsy, Fine-Needle ; Giant Cells ; Humans ; Keratins ; Korea ; Lung ; Lymphocytes ; Necrosis ; Neutrophils ; Population Characteristics ; Vimentin