Antimicrobial and anti-inflammatory effects of BenTooth: A natural product blend of burdock root, persimmon leaf extracts, and quercetin on periodontal disease.

Periodontal disease represents a condition that exhibits substantial global morbidity, and is characterized by the infection and inflammation of the periodontal tissue effectuated by bacterial pathogens. The present study aimed at evaluating the therapeutic efficacy of BenTooth, an edible natural product mixture comprising burdock root extract, persimmon leaf extract and quercetin, against periodontitis both in vitro and in vivo. BenTooth was examined for antimicrobial properties and its impact on cellular responses related to inflammation and bone resorption. Its effects were also assessed in a rat model of ligature-induced periodontitis. BenTooth demonstrated potent antimicrobial activity against P. gingivalis and S. mutans. In RAW264.7 cells, it notably diminished the expression of inducible nitric oxide synthase and cyclooxygenase-2, as well as reduced interleukin-6 and tumor necrosis factor-α levels triggered by P. gingivalis-derived lipopolysaccharide. Furthermore, BenTooth inhibited osteoclastogenesis mediated by the receptor activator of nuclear factor κB ligand. In the rat model, BenTooth consumption mitigated the ligature-induced expansion in distance between the cementoenamel junction and the alveolar bone crest and bolstered the bone volume fraction. These results present BenTooth as a potential therapeutic candidate for the prevention and remediation of periodontal diseases.

Current Health Data Standardization Project and Future Directions to Ensure Interoperability in Korea.

OBJECTIVES: The need for interoperability at the national level was highlighted in Korea, leading to a consensus on the importance of establishing national standards that align with international technological standards and reflect contemporary needs. This article aims to share insights into the background of the recent national health data standardization policy, the activities of the Health Data Standardization Taskforce, and the future direction of health data standardization in Korea. METHODS: To ensure health data interoperability, the Health Data Standardization Taskforce was jointly organized by the public and private sectors in December 2022. The taskforce operated three working groups. It reviewed international trends in interoperability standardization, assessed the current status of health data standardization, discussed its vision, mission, and strategies, engaged in short-term standardization activities, and established a governance system for standardization. RESULTS: On September 15, 2023, the notice of "Health Data Terminology and Transmission Standards" in Korea was thoroughly revised to improve the exchange of health information between information systems and ensure interoperability. This notice includes the Korea Core Data for Interoperability (KR CDI) and the Korea Core Data Transmission Standard (HL7 FHIR KR Core), which are outcomes of the taskforce's efforts. Additionally, to reinforce the standardized governance system, the Health-Data Standardization Promotion Committee was established. CONCLUSIONS: Active interest and support from medical informatics experts are needed for the development and widespread adoption of health data standards in Korea.

Lowering Barriers to Health Risk Assessments in Promoting Personalized Health Management.

This study investigates the feasibility of accurately predicting adverse health events without relying on costly data acquisition methods, such as laboratory tests, in the era of shifting healthcare paradigms towards community-based health promotion and personalized preventive healthcare through individual health risk assessments (HRAs). We assessed the incremental predictive value of four categories of predictor variables-demographic, lifestyle and family history, personal health device, and laboratory data-organized by data acquisition costs in the prediction of the risks of mortality and five chronic diseases. Machine learning methodologies were employed to develop risk prediction models, assess their predictive performance, and determine feature importance. Using data from the National Sample Cohort of the Korean National Health Insurance Service (NHIS), which includes eligibility, medical check-up, healthcare utilization, and mortality data from 2002 to 2019, our study involved 425,148 NHIS members who underwent medical check-ups between 2009 and 2012. Models using demographic, lifestyle, family history, and personal health device data, with or without laboratory data, showed comparable performance. A feature importance analysis in models excluding laboratory data highlighted modifiable lifestyle factors, which are a superior set of variables for developing health guidelines. Our findings support the practicality of precise HRAs using demographic, lifestyle, family history, and personal health device data. This approach addresses HRA barriers, particularly for healthy individuals, by eliminating the need for costly and inconvenient laboratory data collection, advancing accessible preventive health management strategies.

Survey of Medical Applications of Federated Learning.

OBJECTIVES: Medical artificial intelligence (AI) has recently attracted considerable attention. However, training medical AI models is challenging due to privacy-protection regulations. Among the proposed solutions, federated learning (FL) stands out. FL involves transmitting only model parameters without sharing the original data, making it particularly suitable for the medical field, where data privacy is paramount. This study reviews the application of FL in the medical domain. METHODS: We conducted a literature search using the keywords "federated learning" in combination with "medical," "healthcare," or "clinical" on Google Scholar and PubMed. After reviewing titles and abstracts, 58 papers were selected for analysis. These FL studies were categorized based on the types of data used, the target disease, the use of open datasets, the local model of FL, and the neural network model. We also examined issues related to heterogeneity and security. RESULTS: In the investigated FL studies, the most commonly used data type was image data, and the most studied target diseases were cancer and COVID-19. The majority of studies utilized open datasets. Furthermore, 72% of the FL articles addressed heterogeneity issues, while 50% discussed security concerns. CONCLUSIONS: FL in the medical domain appears to be in its early stages, with most research using open data and focusing on specific data types and diseases for performance verification purposes. Nonetheless, medical FL research is anticipated to be increasingly applied and to become a vital component of multi-institutional research.

Traffic Exposure and Breast Cancer Mortality by Area of Residence: Incorporating Clinical and Socioeconomic Data.

Incorporating clinical and environmental data holds promise for monitoring vulnerable populations at the community level. This spatial epidemiology study explores the link between traffic-related air pollution and breast cancer mortality in Seoul, using public socioeconomic and clinical data from Samsung Medical Center's registry (N=6,089). Traffic and socioeconomic status were collected from official sources and integrated for spatial analysis. The findings revealed a significant association between adult breast cancer mortality and districts with high road density, NO2 emissions, and family income (p<0.05). Significant spatial autocorrelation of residuals was observed (Moran's I test p<0.001).

Current Status of SNOMED CT National Extensions and Terminology Managements.

We reviewed and surveyed 15 SNOMEDCT national member countries for SNOMED CT national extensions and terminology managements. We found that national extensions were used for adding new contents, developing reference sets, translating, and mapping with other classification system; and terminology management varies in composition and content due to healthcare environment of each member country, eHealth strategy, and infrastructure of national release centers.

Evaluation of the Antiviral Activity of Tabamide A and Its Structural Derivatives against Influenza Virus.

Influenza viruses cause severe endemic respiratory infections in both humans and animals worldwide. The emergence of drug-resistant viral strains requires the development of new influenza therapeutics. Tabamide A (TA0), a phenolic compound isolated from tobacco leaves, is known to have antiviral activity. We investigated whether synthetic TA0 and its derivatives exhibit anti-influenza virus activity. Analysis of structure-activity relationship revealed that two hydroxyl groups and a double bond between C7 and C8 in TA0 are crucial for maintaining its antiviral action. Among its derivatives, TA25 showed seven-fold higher activity than TA0. Administration of TA0 or TA25 effectively increased survival rate and reduced weight loss of virus-infected mice. TA25 appears to act early in the viral infection cycle by inhibiting viral mRNA synthesis on the template-negative strand. Thus, the anti-influenza virus activity of TA0 can be expanded by application of its synthetic derivatives, which may aid in the development of novel antiviral therapeutics.

Deep learning model for distinguishing Mayo endoscopic subscore 0 and 1 in patients with ulcerative colitis.

The aim of this study was to address the issue of differentiating between Mayo endoscopic subscore (MES) 0 and MES 1 using a deep learning model. A dataset of 492 ulcerative colitis (UC) patients who demonstrated MES improvement between January 2018 and December 2019 at Samsung Medical Center was utilized. Specifically, two representative images of the colon and rectum were selected from each patient, resulting in a total of 984 images for analysis. The deep learning model utilized in this study consisted of a convolutional neural network (CNN)-based encoder, with two auxiliary classifiers for the colon and rectum, as well as a final MES classifier that combined image features from both inputs. In the internal test, the model achieved an F1-score of 0.92, surpassing the performance of seven novice classifiers by an average margin of 0.11, and outperforming their consensus by 0.02. The area under the receiver operating characteristic curve (AUROC) was calculated to be 0.97 when considering MES 1 as positive, with an area under the precision-recall curve (AUPRC) of 0.98. In the external test using the Hyperkvasir dataset, the model achieved an F1-score of 0.89, AUROC of 0.86, and AUPRC of 0.97. The results demonstrate that the proposed CNN-based model, which integrates image features from both the colon and rectum, exhibits superior performance in accurately discriminating between MES 0 and MES 1 in patients with UC.

Clinical relevance of deep learning models in predicting the onset timing of cancer pain exacerbation.

Cancer pain is a challenging clinical problem that is encountered in the management of cancer pain. We aimed to investigate the clinical relevance of deep learning models that predict the onset of cancer pain exacerbation in hospitalized patients. We defined cancer pain exacerbation (CPE) as the pain with a numerical rating scale (NRS) score of ≥ 4. We investigated the performance of the deep learning models using the Matthews correlation coefficient (MCC) with different input lengths and time binning. All the pain records were obtained from the electronic medical records of the hematology-oncology wards in a Samsung Medical Center between July 2016 and February 2020. The model was externally validated using the holdout method with 20% of the datasets. The most common type of cancer was lung cancer (n = 745, 21.7%), and the median CPE per day was 1.01. The NRS pain records showed circadian patterns that correlated with NRS pain patterns of the previous days. The correlation of the NRS scores showed a positive association with the closeness of the NRS pattern of the day with forecast date and size of time binning. The long short-term memory-based model exhibited a good performance by demonstrating 9 times the best performance and 8 times the second-best performance among 21 different settings. The best performance was achieved with 120 h input and 12 h bin lengths (MCC: 0.4927). Our study demonstrated the possibility of predicting CPE using deep learning models, thereby suggesting that preemptive cancer pain management using deep learning could potentially improve patients' daily life.

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

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.

Preliminary Attainability Assessment of Real-World Data for Answering Major Clinical Research Questions in Breast Cancer Brain Metastasis: Framework Development and Validation Study.

BACKGROUND: In recent decades, real-world evidence (RWE) in oncology has rapidly gained traction for its potential to answer clinical questions that cannot be directly addressed by randomized clinical trials. Integrating real-world data (RWD) into clinical research promises to contribute to more sustainable research designs, including extension, augmentation, enrichment, and pragmatic designs. Nevertheless, clinical research using RWD is still limited because of concerns regarding the shortage of best practices for extracting, harmonizing, and analyzing RWD. In particular, pragmatic screening methods to determine whether the content of a data source is sufficient to answer the research questions before conducting the research with RWD have not yet been established. OBJECTIVE: We examined the PAR (Preliminary Attainability Assessment of Real-World Data) framework and assessed its utility in breast cancer brain metastasis (BCBM), which has an unmet medical need for data attainability screening at the preliminary step of observational studies that use RWD. METHODS: The PAR framework was proposed to assess data attainability from a particular data source during the early research process. The PAR framework has four sequential stages, starting with clinical question clarification: (1) operational definition of variables, (2) data matching (structural/semantic), (3) data screening and extraction, and (4) data attainability diagramming. We identified 5 clinical questions to be used for PAR framework evaluation through interviews and validated them with a survey of breast cancer experts. We used the Samsung Medical Center Breast Cancer Registry, a hospital-based real-time registry implemented in March 2021, leveraging the institution's anonymized and deidentified clinical data warehouse platform. The number of breast cancer patients in the registry was 45,129; it covered the period from June 1995 to December 2021. The registry consists of 24 base data marts that represent disease-specific breast cancer characteristics and care pathways. The outcomes included screening results of the clinical questions via the PAR framework and a procedural diagram of data attainability for each research question. RESULTS: Data attainability was tested for study feasibility according to the PAR framework with 5 clinical questions for BCBM. We obtained data sets that were sufficient to conduct studies with 4 of 5 clinical questions. The research questions stratified into 3 types when we developed data fields for clearly defined research variables. In the first, only 1 question could be answered using direct data variables. In the second, the other 3 questions required surrogate definitions that combined data variables. In the third, the question turned out to be not feasible for conducting further analysis. CONCLUSIONS: The adoption of the PAR framework was associated with more efficient preliminary clinical research using RWD from BCBM. Furthermore, this framework helped accelerate RWE generation through clinical research by enhancing transparency and reproducibility and lowering the entry barrier for clinical researchers.

Deep learning approach to detection of colonoscopic information from unstructured reports.

BACKGROUND: Colorectal cancer is a leading cause of cancer deaths. Several screening tests, such as colonoscopy, can be used to find polyps or colorectal cancer. Colonoscopy reports are often written in unstructured narrative text. The information embedded in the reports can be used for various purposes, including colorectal cancer risk prediction, follow-up recommendation, and quality measurement. However, the availability and accessibility of unstructured text data are still insufficient despite the large amounts of accumulated data. We aimed to develop and apply deep learning-based natural language processing (NLP) methods to detect colonoscopic information. METHODS: This study applied several deep learning-based NLP models to colonoscopy reports. Approximately 280,668 colonoscopy reports were extracted from the clinical data warehouse of Samsung Medical Center. For 5,000 reports, procedural information and colonoscopic findings were manually annotated with 17 labels. We compared the long short-term memory (LSTM) and BioBERT model to select the one with the best performance for colonoscopy reports, which was the bidirectional LSTM with conditional random fields. Then, we applied pre-trained word embedding using large unlabeled data (280,668 reports) to the selected model. RESULTS: The NLP model with pre-trained word embedding performed better for most labels than the model with one-hot encoding. The F1 scores for colonoscopic findings were: 0.9564 for lesions, 0.9722 for locations, 0.9809 for shapes, 0.9720 for colors, 0.9862 for sizes, and 0.9717 for numbers. CONCLUSIONS: This study applied deep learning-based clinical NLP models to extract meaningful information from colonoscopy reports. The method in this study achieved promising results that demonstrate it can be applied to various practical purposes.

Changes in CT-Based Morphological Features of the Kidney with Declining Glomerular Filtration Rate in Chronic Kidney Disease.

Chronic kidney disease (CKD) progression involves morphological changes in the kidney, such as decreased length and thickness, with associated histopathological alterations. However, the relationship between morphological changes in the kidneys and glomerular filtration rate (GFR) has not been quantitatively and comprehensively evaluated. We evaluated the three-dimensional size and shape of the kidney using computed tomography (CT)-derived features in relation to kidney function. We included 257 patients aged ≥18 years who underwent non-contrast abdominal CT at the Inha University Hospital. The features were quantified using predefined algorithms in the pyRadiomics package after kidney segmentation. All features, except for flatness, significantly correlated with estimated GFR (eGFR). The surface-area-to-volume ratio (SVR) showed the strongest negative correlation (r = -0.75, p < 0.0001). Kidney size features, such as volume and diameter, showed moderate to high positive correlations; other morphological features showed low to moderate correlations. The calculated area under the receiver operating characteristic (ROC) curve (AUC) for different features ranged from 0.51 (for elongation) to 0.86 (for SVR) for different eGFR thresholds. Diabetes patients had weaker correlations between the studied features and eGFR and showed less bumpy surfaces in three-dimensional visualization. We identified alterations in the CKD kidney based on various three-dimensional shape and size features, with their potential diagnostic value.

Graphical user interface design to improve understanding of the patient-reported outcome symptom response.

BACKGROUND: Symptom monitoring application (SMA) has clinical benefits to cancer patients but patients experience difficulties in using it. Few studies have identified which types of graphical user interface (GUI) are preferred by cancer patients for using the SMA. METHODS: This is a cross-sectional study aimed to identify preferred GUI among cancer patients to use SMA. Total of 199 patients were asked to evaluate 8 types of GUIs combining text, icon, illustration, and colors using mixed-methods. Subgroup analyses were performed according to age and gender. RESULTS: The mean age of the patients was 57 and 42.5% was male. The most preferred GUI was "Text + Icon + Color" (mean = 4.43), followed by "Text + Icon" (mean = 4.39). Older patients (≥ 60 years) preferred "Text + Icon" than younger patients (p for interaction < 0.01). Simple and intuitive text and icons were the most useful GUI for cancer patients to use the SMA. CONCLUSION: Simple and intuitive text and icons were the most useful GUI for cancer patients to use the SMA. Researchers need to be careful when applying realistic face drawings to cancer symptom monitoring applications because they can recall negative images of cancer.

Deep-learning-based personalized prediction of absolute neutrophil count recovery and comparison with clinicians for validation.

Neutropenia and its complications are major adverse effects of cytotoxic chemotherapy. The time to recovery from neutropenia varies from patient to patient, and cannot be easily predicted even by experts. Therefore, we trained a deep learning model using data from 525 pediatric patients with solid tumors to predict the day when patients recover from severe neutropenia after high-dose chemotherapy. We validated the model with data from 99 patients and compared its performance to those of clinicians. The accuracy of the model at predicting the recovery day, with a 1-day error, was 76%; its performance was better than those of the specialist group (58.59%) and the resident group (32.33%). In addition, 80% of clinicians changed their initial predictions at least once after the model's prediction was conveyed to them. In total, 86 prediction changes (90.53%) improved the recovery day estimate.

Influenza Screening Using Patient-Generated Health Data in Post COVID-19 Pandemic.

It is very important to ensure reliable performance of deep learning model for future dataset for healthcare. This is more pronounced in the case of patient generated health data such as patient reported symptoms, which are not collected in a controlled environment. Since there has been a big difference in influenza incidence since the COVID-19 pandemic, we evaluated whether the deep learning model can maintain sufficiently robust performance against these changes. We have collected 226,655 episodes from 110,893 users since June 2020 and tested the influenza screening model, our model showed 87.02% sensitivity and 0.8670 of AUROC. The results of COVID-19 pandemic are comparable to that of before COVID-19 pandemic.

Symptom-Based COVID19 Screening Model Combined with Surveillance Information.

As the number of cases for COVID-19 continues to grow unprecedentedly, COVID-19 screening is becoming more important. In this study, we trained machine learning models from the Israel COVID-19 dataset and compared models that used surveillance indices of COVID-19 and those that did not. The AUC scores were 0.8478±0.0037 and 0.8062±0.005 with and without surveillance information, respectively, and there was significant improvement when the surveillance information was used.

Stakeholders' Requirements for Artificial Intelligence for Healthcare in Korea.

OBJECTIVES: The outlook of artificial intelligence for healthcare (AI4H) is promising. However, no studies have yet discussed the issues from the perspective of stakeholders in Korea. This research aimed to identify stakeholders' requirements for AI4H to accelerate the business and research of AI4H. METHODS: We identified research funding trends from the Korean National Science and Technology Knowledge Information Service (NTIS) from 2015 and 2019 using "healthcare AI" and related keywords. Furthermore, we conducted an online survey with members of the Korean Society of Artificial Intelligence in Medicine to identify experts' opinions regarding the development of AI4H. Finally, expert interviews were conducted with 13 experts in three areas (hospitals, industry, and academia). RESULTS: We found 160 related projects from the NTIS. The major data type was radiology images (59.4%). Dermatology-related diseases received the most funding, followed by pulmonary diseases. Based on the survey responses, radiology images (23.9%) were the most demanding data type. Over half of the solutions were related to diagnosis (33.3%) or prognosis prediction (31%). In the expert interviews, all experts mentioned healthcare data for AI solutions as a major issue. Experts in the industrial field mainly mentioned regulations, practical efficacy evaluation, and data accessibility. CONCLUSIONS: We identified technology, regulatory, and data issues for practical AI4H applications from the perspectives of stakeholders in hospitals, industry, and academia in Korea. We found issues and requirements, including regulations, data utilization, reimbursement, and human resource development, that should be addressed to promote further research in AI4H.

Sodium-Glucose Cotransporter-2 Inhibitor-Related Diabetic Ketoacidosis: Accuracy Verification of Operational Definition.

BACKGROUND: The most important aspect of a retrospective cohort study is the operational definition (OP) of the disease. We developed a detailed OP for the detection of sodium-glucose cotransporter-2 inhibitors (SGLT2i) related to diabetic ketoacidosis (DKA). The OP was systemically verified and analyzed. METHODS: All patients prescribed SGLT2i at four university hospitals were enrolled in this experiment. A DKA diagnostic algorithm was created and distributed to each hospital; subsequently, the number of SGLT2i-related DKAs was confirmed. Then, the algorithm functionality was verified through manual chart reviews by an endocrinologist using the same OP. RESULTS: A total of 8,958 patients were initially prescribed SGLT2i. According to the algorithm, 0.18% (16/8,958) were confirmed to have SGLT2i-related DKA. However, based on manual chart reviews of these 16 cases, there was only one case of SGLT2i-related DKA (positive predictive value = 6.3%). Even after repeatedly narrowing the diagnosis range of the algorithm, the effect of a positive predictive value was insignificant (6.3-10.0%, P > 0.999). CONCLUSION: Owing to the nature of electronic medical record data, we could not create an algorithm that clearly differentiates SGLT2i-related DKA despite repeated attempts. In all retrospective studies, a portion of the samples should be randomly selected to confirm the accuracy of the OP through chart review. In retrospective cohort studies in which chart review is not possible, it will be difficult to guarantee the reliability of the results.

Development and Validation of Digital Health Technology Literacy Assessment Questionnaire.

In clinical practice, assessing digital health literacy is important to identify patients who may encounter difficulties adapting to digital health using digital technology and service. We developed the Digital Health Technology Literacy Assessment Questionnaire (DHTL-AQ) to assess the ability to use digital health technology, services, and data. The DHTL-AQ was developed in three phases. In the first phase, the conceptual framework and domains and items were generated from a systematic literature review using relevant theory and surveys. In the second phase, a cross-sectional survey with 590 adults age ≥ 18 years was conducted at an academic hospital in Seoul, Korea in January and February 2020 to test face validity of the items. Then, psychometric validation was conducted to determine the final items and cut-off scores of the DHTL-AQ. The eHealth literacy scale, the Newest Vital Sign, and 10 mobile app task ability assessments were examined to test validity. The final DHTL-AQ includes 34 items in two domains (digital functional and digital critical literacy) and 4 categories (Information and Communications Technology terms, Information and Communications Technology icons, use of an app, evaluating reliability and relevance of health information). The DHTL-AQ had excellent internal consistency (overall Cronbach's α = 0.95; 0.87-0.94 for subtotals) and acceptable model fit (CFI = 0.821, TLI = 0.807, SRMR = 0.065, RMSEA = 0.090). The DHTL-AQ was highly correlated with task ability assessment (r = 0.7591), and moderately correlated with the eHealth literacy scale (r = 0.5265) and the Newest Vital Sign (r = 0.5929). The DHTL-AQ is a reliable and valid instrument to measure digital health technology literacy.