The effects of maternal coffee consumption during pregnancy on childhood allergic diseases (ADs) remain insufficiently established. This study aimed to investigate the association between maternal coffee consumption during pregnancy and the risk of ADs in offspring up to 36 months of age. We analyzed data from 3,252 mother-child pairs enrolled in the Korean Children's Environmental health Study (Ko-CHENS). Maternal coffee and caffeine intake were assessed using a food frequency questionnaire. Childhood ADs were identified based on caregiver reports of physician diagnoses. Cox proportional hazards models were applied to estimate hazard ratios (HRs) and 95% confidence intervals (CIs), with adjustment for potential confounding factors. Overall, two-thirds (67.5%) of children were reported to have at least one AD, with cumulative incidences at 36 months of age of 47.8% for atopic dermatitis, 23.9% for food allergy, 30.2% for allergic rhinitis, and 2.4% for asthma. Compared with no coffee intake, maternal coffee consumption of <1 serving/day was associated with a reduced risk of atopic dermatitis (HR = 0.89, 95% CI 0.81-0.99, p = 0.045) and food allergy (HR = 0.86, 95% CI 0.74-1.00, p = 0.061). Higher intake (≥1 serving/day) was significantly associated with a lower risk of food allergy (HR = 0.61, 95% CI 0.42-0.88, p = 0.009). No significant associations were observed for asthma or allergic rhinitis. Mild maternal coffee intake during pregnancy may be associated with a reduced risk of specific ADs in early childhood.

The purpose of this study was to investigate practitioners' demands regarding curriculum programs and to suggest directions for future program development aimed at training healthcare data professionals. An online survey was conducted among 67 healthcare data practitioners who voluntarily participated in a training program designed to foster specialized professionals in healthcare data utilization on October 25, 2024. The collected data were analyzed using SPSS version 27.0. The most common data-related issue encountered by practitioners was concern regarding security and privacy protection, which was reported by 49.3% of participants. With respect to areas requiring improvement in job roles, 34.3% of respondents identified healthcare data analysis and utilization as the most critical domain. Practitioners emphasized the importance of governance-related competencies, and there was a strong demand for education in research ethics and data review processes. In addition, statistically significant differences were observed among groups with respect to the levels of education required. Training programs designed to encourage professionals to utilize healthcare data should be structured as practice-oriented, hands-on programs that integrate both theoretical instruction and practical training. Furthermore, advanced education related to institutional review boards and data review boards should be incorporated as a core component of the curriculum. Finally, it is necessary to develop a comprehensive and detailed interdisciplinary educational program grounded in the five core competencies.

ObjectivesThe purpose of this study was to conduct an integrative review of existing research on care robots for community-dwelling older adults and to suggest directions for future research and technology development in this area.MethodsWe focused on robots, including care robots and socially assistive robots, that help older adults living in the community maintain independence at home. Three electronic academic databases (PubMed, CINAHL, and Cochrane) were searched for eligible research articles. The keywords used included elder*, older adult*, robot* care, care robot*, assist* robot*, service robot*, companion* robot*, socia* robot*, home-based, and community-based, among others.ResultsA total of 834 research articles were identified, and 40 were ultimately reviewed and analyzed. The studies were categorized into three groups: perceptions and needs related to care robots; cognitive support; and assistance with activities of daily living.ConclusionsIt is necessary to develop and implement care robots with diverse functions that can provide practical assistance for the independent daily living of older adults. This will require collaboration among government agencies, public institutions, academia, and private health enterprises. In addition, policies must be established to support the purchase and maintenance costs of care robots to ensure continued access for community-dwelling older adults.

ObjectivesThailand recently implemented an electronic emergency referral system, known as “HIS.SANSAI,” to improve the speed, efficiency, and quality of patient care. This study evaluated the impact of HIS.SANSAI on user experiences and health outcomes.MethodsA multimethod approach was employed, combining data analysis from a cross-sectional survey that quantified users’ preferences and perceptions with an examination of de-identified emergency referral records from 2019 to 2021. Multiple regression analysis assessed whether HIS.SANSAI significantly reduced the duration of medical services, while logistic regression evaluated changes in health outcomes before and after its implementation.ResultsThe survey results revealed high proficiency in system capabilities. Referring hospitals (sending hospitals) rated the system highest, with a score of 8.00 for “Reducing coordinated time.” Referral hospitals (receiving hospitals) expressed moderate satisfaction, scoring highest (7.03) for “Reducing mistakes in patient information transfer” and lowest (4.27) for “Ease of use when recording.” The effects of HIS.SANSAI were partially supported. Positive outcomes included shorter service times and a 13.16% reduction in severity at emergency room discharge for ischemic stroke patients. However, negative consequences were observed, such as notable treatment delays for acute appendicitis patients.ConclusionsHIS.SANSAI demonstrated robust system capabilities and reduced errors in patient information transfer. Its impact on health outcomes was mixed, with both positive and negative effects. Further evaluation and enhancements are necessary to optimize the system’s overall effectiveness.

ObjectivesThis study examined the symptoms and emotions expressed by older adults with cancer and their caregivers in South Korean online cancer communities. It aimed to identify narrative patterns and provide insights to inform personalized care strategies.MethodsWe analyzed 6,908 user-generated posts collected from major online cancer communities in South Korea. Keyword frequency analysis, term frequency-inverse document frequency, 2-gram analysis, and latent Dirichlet allocation-based topic modeling were applied to explore language patterns. Sentiment analysis identified 12 emotional categories, and Pearson correlation coefficients were calculated to examine associations between symptoms and emotional expressions. All data were cleaned and standardized prior to analysis.ResultsMany users expressed anxiety (20.63%) and depression (19.59%), frequently associated with chemotherapy and sleep disturbances. Among reported symptoms, sleep problems carried the highest negative sentiment (79.81%), underscoring their profound impact on well-being. Topic modeling consistently revealed seven recurring themes, including treatment decision-making, symptom management, and concerns about family, demonstrating the layered and personalized experiences of older cancer patients and their caregivers.ConclusionsThis study explored treatment-related and symptom-related difficulties faced by older adults with cancer. Many reported significant emotional strain, especially anxiety, depression, and sleep disturbances. These findings highlight the necessity for supportive strategies addressing both psychological and physical aspects of care. Future research could investigate the utility of large language models in analyzing these narratives, provided the data is ethically managed and appropriate for such use.

The use of large language models (LLMs) has become widespread and is actively expanding across numerous fields.The medical field is no exception, as various types of LLMs have been introduced, demonstrating impressive results.Current research ranges from models capable of passing the United States Medical Licensing Examination to systems designed for summarizing complex medical documents.To keep pace with these rapid developments, the Korean Society of Medical Informatics (KOSMI) has organized a special issue titled "LLMs in Medicine" to disseminate information regarding the use of LLMs in healthcare and foster the development of innovative and impactful research ideas.For this special issue, we are honored to have the following guest editors: Namkug Kim (University of Ulsan, Korea), Edward Choi (KAIST, Korea), and Dukyong Yoon (Yonsei University, Korea).Their active engagement and dedicated efforts were instrumental in bringing this special issue to fruition.Without their valuable insights and hard work, the preparation of this issue would have been challenging.We extend our deepest gratitude to them.

ObjectivesThe high incidence of sepsis necessitates the development of practical decision-making tools for intensivists, especially during the early, critical phases of management. This study evaluates a multi-agent system intended to assist clinicians with antibiotic therapy and adherence to current sepsis management guidelines before diagnostic results become available.MethodsA multi-agent system incorporating three specialized agents was developed: a sepsis management agent, an antibiotic recommendation agent, and a sepsis guidelines compliance agent. A sepsis case from the MIMIC IV database, organized as a clinical vignette, was used to integrate and test these agents for generating management recommendations. The system leverages retrieval-augmented generation to improve decision-making through the integration of current literature and guidelines.ResultsThe application produced management recommendations for a sepsis case associated with pneumonia, including early initiation of broad-spectrum antibiotics and close monitoring for clinical deterioration. Two expert intensivists evaluated these recommendations as “acceptable” and reported moderate interrater agreement (Cohen’s kappa = 0.622, p = 0.003) across various aspects of recommendation usefulness.ConclusionsThe multi-agent system shows promise in enhancing decision-making for sepsis management by optimizing antibiotic therapy and ensuring guideline compliance. However, reliance on a single case study limits the generalizability of the findings, highlighting the need for broader validation in diverse clinical settings to improve patient outcomes.

Anemia is characterized by a reduction in red blood cells, leading to insufficient levels of hemoglobin, the molecule responsible for carrying oxygen. The current standard method for diagnosing anemia involves analyzing blood samples, a process that is time-consuming and can cause discomfort to participants. This study offers a comprehensive analysis of non-invasive anemia detection using conjunctiva images processed through various machine learning and deep learning models. The focus is on the palpebral conjunctiva, which is highly vascular and unaffected by melanin content. Conjunctiva images from both anemic and non-anemic participants were captured using a smartphone. A total of 764 conjunctiva images were augmented to 4,315 images using the deep convolutional generative adversarial network model to prevent overfitting and enhance model robustness. These processed and augmented images were then utilized to train and test multiple models, including statistical regression, machine learning algorithms, and deep learning frameworks. The stacking ensemble framework, which includes the models VGG16, ResNet-50, and InceptionV3, achieved a high area under the curve score of 0.97. This score demonstrates the framework's exceptional capability in detecting anemia through a noninvasive approach. This study introduces a noninvasive method for detecting anemia using conjunctiva images obtained with a smartphone and processed using advanced deep learning techniques.

Conventional face-to-face nutrition counseling has played a crucial role in promoting healthy habits. However, the emergence of digital health technologies has introduced mobile app-based nutrition counseling as an effective alternative. This research aims to develop and evaluate the usability and effectiveness of the FIT4PEDON mobile nutrition counseling application in promoting healthy dietary behaviors and lifestyle modifications among childhood cancer survivors (CCS). This study employed a mixed-methods approach, incorporating both survey and qualitative and quantitative analyses. A total of 33 health care professional experts participated. The reliability of the questionnaire was assessed using the Kuder-Richardson method, and its content validity was confirmed through expert evaluation. Usability testing was conducted with a validated questionnaire. The development process resulted in two applications: an Android mobile application and an admin web application. The findings indicated that a significant proportion of experts endorsed the app for dietary management. Statistical analysis showed significant differences between "yes" and "no" responses. However, no significant differences were found when comparing responses across different sex or age groups. The FIT4PEDON application shows promise in supporting CCS to adopt healthier lifestyles. Nevertheless, the study underscores the necessity for further research, particularly focusing on specific age groups of experts with relevant experience, to achieve more conclusive results. Leveraging technology through mobile apps has the potential to improve the quality of survivorship care and foster sustained engagement in long-term care for pediatric cancer survivors.

ObjectivesThis study evaluated the efficacy of integrating a retrieval-augmented generation (RAG) model and a large language model (LLM) to improve the accuracy of drug name mapping across international vocabularies.MethodsDrug ingredient names were translated into English using the Japanese Accepted Names for Pharmaceuticals. Drug concepts were extracted from the standard vocabulary of OHDSI, and the accuracy of mappings between translated terms and RxNorm was assessed by vector similarity, using the BioBERT-generated embedded vectors as the baseline. Subsequently, we developed LLMs with RAG that distinguished the final candidates from the baseline. We assessed the efficacy of the LLM with RAG in candidate selection by comparing it with conventional methods based on vector similarity.ResultsThe evaluation metrics demonstrated the superior performance of the combined LLM + RAG over traditional vector similarity methods. Notably, the hit rates of the Mixtral 8x7b and GPT-3.5 models exceeded 90%, significantly outperforming the baseline rate of 64% across stratified groups of PO drugs, injections, and all interventions. Furthermore, the r-precision metric, which measures the alignment between model judgment and human evaluation, revealed a notable improvement in LLM performance, ranging from 41% to 50% compared to the baseline of 23%.ConclusionsIntegrating an RAG and an LLM outperformed conventional string comparison and embedding vector similarity techniques, offering a more refined approach to global drug information mapping.