OBJECTIVE: To develop a user-friendly visualization application for the automatic annotation of Human Phenotype Ontology (HPO) terms based on large language models and retrieval-augmented generation (RAG) technology, and to validate its performance in an authoritative case dataset. METHODS: By integrating the domestic open-source large language model DeepSeek-V3 with RAG technology, an interactive web application was deployed on the Streamlit cloud platform. Using only the latest official HPO dataset as the data source, the lightweight sentence-embedding model BAAI/bge-small-en-v1.5 was employed to construct a FAISS vector index. During the online phase, a four-step closed-loop process is automatically completed: multilingual translation, phenotype phrase extraction, RAG candidate retrieval, term mapping, and official database validation. 121 English case reports publicly released by BMJ Case Reports and Oxford Medical Case Reports (with a gold-standard HPO set of 1 794 terms) were selected for application validation. Precision, recall, and F1 score were calculated and compared horizontally with traditional dictionary tools, standalone large language models, and the similar application "RAG-HPO". Finally, replace the model with the more advanced ChatGPT-5 and evaluate its performance on the newly extracted dataset. RESULTS: An HPO term automatic annotation visualization application named PhenoRAG, based on large language models and RAG technology, was successfully developed. Users can access it directly via a web link. Across the 112 cases, a total of 2 150 HPO terms were generated; 2,064 (96.0%) were fully validated by the official database, with a hallucination rate of 1.3% and an HPO ID-name mismatch rate of 2.7%. After deduplication, 1,906 terms remained for testing. The overall precision was 63.65%, recall was 67.34%, and F1 was 65.44%, significantly outperforming traditional annotation tools (F1: 0.45-0.49, P < 0.001). Although PhenoRAG's F1 was lower than that of RAG-HPO (F1 = 0.78, P < 0.001), which relies on a manually constructed synonym database of 54 000 entries plus the HPO dataset, it requires no additional dictionary maintenance and can be used without any background in computer programming. Moreover, after switching to the GPT-5 model, PhenoRAG exhibited no hallucination rate on the new dataset, and its F1 score significantly increased (P = 0.038). CONCLUSION Without constructing a synonym database, the PhenoRAG achieved high-accuracy automatic mapping from clinical text to standard HPO terms. It features a low usage threshold, free access, and a Chinese-language interface, and can directly serve rare disease diagnosis, genetic counseling, and research scenarios in China and worldwide, warranting further clinical promotion and multicenter validation.
Humans ; Phenotype ; Biological Ontologies ; Language ; Software ; Large Language Models

OBJECTIVE: To explore the efficacy of a Thalassemia risk assessment software for the screening of thalassemia mutation carriers and distribution of thalassemia genotypes detected by screening. METHODS: A total of 6 040 individuals were evaluated at Leshan Maternal and Child Health Care Hospital between 2022 and 2024 using the commonly used clinical thalassemia risk assessment method and the thalassemia screening software, respectively, and the performance indicators of the two methods were compared and analyzed against the result of thalassemia gene testing. This study was approved by the Ethics Committee of our hospital (Ethics No.: LfyLL[2022]005). RESULTS: The high-risk rate by the thalassemia screening software was 11.19%, with a sensitivity of 95.12%, specificity of 93.28%, positive predictive value of 43.20%, negative predictive value of 99.72%, and the area under the ROC curve (AUC) was 0.942. The thalassemia gene detection rate of the high-risk samples screened was 4.83%. The high-risk screening rate of the conventional method was 2.50%, with a sensitivity of 51.22%, specificity of 93.28%, positive predictive value of 80.79%, negative predictive value of 97.40%, and the AUC was 0.754. The thalassemia gene detection rate of the high-risk samples was 2.02%. CONCLUSION The software can effectively detect thalassemia carriers and significantly reduce the missed detection compared with conventional method, thereby significantly improve the efficacy of screening.
Humans ; Thalassemia/diagnosis* ; Software ; Female ; Genetic Testing/methods* ; Male ; Mutation ; Adult ; Genotype ; ROC Curve ; Risk Assessment

OBJECTIVES

The increasing prevalence of Kawasaki disease in Southeast Asia (SEA) and its potential relation with Coronavirus Disease 2019 (COVID-19) infection resulted in heightened interest in KD in the region, thus, this paper aimed to determine the trend and the socioeconomic facilitators of scientific productivity of KD research within the region. Specifically, this article determined the number of publication and citations related to KD per country, institution, and journal. We also explored the networks of countries within the region to the rest of the world and the keywords mostly associated with KD research in the region. Lastly, correlation of these bibliometric indices with socioeconomic factors in the region was analyzed.

METHODS

A literature search of KD papers in SEA was performed using Scopus database. We obtained bibliographic data from the available literature and visualized network of existing collaborations and keywords using VOSviewer software.

RESULTS

A total of 196 papers were included in the study. Bibliometric analysis showed a rising trend in publication within the region, most of which were from institutions in Singapore and Thailand. The most common topics on KD studies included clinical features, complications, treatment, and comorbidities. 

Country characteristics such as gross domestic product (GDP) per capita, research and development (R&D) expenditure (% GDP), and number of physician and R&D researchers were positively correlated with bibliometric indices of KD research in SEA. Moreover, number of international linkages was significantly associated with KD research productivity in the region. 

CONCLUSION

In summary, we showed an increasing trend of KD research in SEA. Funding allocation and capacity building are necessary to strengthen research productivity within the region.

Asia ; Asia, Southeastern ; Bibliometrics ; Capacity Building ; Coronavirus ; Covid-19 ; Database ; Disease ; Efficiency ; Gross Domestic Product ; Guanosine Diphosphate ; Infection ; Infections ; Literature ; Mucocutaneous Lymph Node Syndrome ; Paper ; Physicians ; Prevalence ; Publications ; Research ; Research Personnel ; Rest ; Singapore ; Socioeconomic Factors ; Software ; Thailand ; Therapeutics

OBJECTIVES

This study aims to create a study protocol that will explore UST administrators’ perceptions of the benefits and risks of AI use in higher education learning environments.

METHODS

A qualitative descriptive design will be employed, using semi-structured interviews with at least fifteen administrators selected through purposive sampling. Audio-recorded interviews will be transcribed verbatim and subjected to thematic analysis using NVivo software

RESULTS

Administrators from different college-level fields perceive and engage with AI across various academic contexts. Exploring these perceptions will allow guidance in the development of coherent, contextually grounded institutional policies that promote responsible GenAI use and support digital leadership in Philippine higher education.

Human ; Artificial Intelligence ; Universities ; Software ; Administrative Personnel ; Intelligence ; Risk ; Policy

OBJECTIVE: To explore the accuracy of human-computer interaction software in identifying and locating type C1 distal radius fractures. METHODS: Based on relevant inclusion and exclusion criteria, 14 cases of type C1 distal radius fractures between September 2023 and March 2024 were retrospectively analyzed, comprising 3 males and 11 females(aged from 27 to 82 years). The data were assigned randomized identifiers. A senior orthopedic physician reviewed the films and measured the ulnar deviation angle, radial height, palmar inclination angle, intra-articular step, and intra-articular gap for each case on the hospital's imaging system. Based on the reduction standard for distal radius fractures, cases were divided into reduction group and non-reduction group. Then, the data were sequentially imported into a human-computer interaction intelligent software, where a junior orthopedic physician analyzed the same radiological parameters, categorized cases, and measured fracture details. The categorization results from the software were consistent with manual classifications (6 reduction cases and 8 non-reduction cases). For non-reduction cases, the software performed further analyses, including bone segmentation and fracture recognition, generating 8 diagnostic reports containing fracture recognition information. For the 6 reduction cases, the senior and junior orthopedic physicians independently analyzed the data on the hospital's imaging system and the AI software, respectively. Bone segments requiring reduction were identified, verified by two senior physicians, and measured for displacement and rotation along the X (inward and outward), Z (front and back), and Y (up and down) axes. The AI software generated comprehensive diagnostic reports for these cases, which included all measurements and fracture recognition details. RESULTS: Both the manual and AI software methods consistently categorized the 14 cases into 6 reduction and 8 non-reduction groups, with identical data distributions. A paired sample t-test revealed no statistically significant differences (P>0.05) between the manual and software-based measurements for ulnar deviation angle, radial ulnar bone height, palmar inclination angle, intra-articular step, and joint space. In fracture recognition, the AI software correctly identified 10 C-type fractures and 4 B-type fractures. For the 6 reduction cases, a total of 24 bone fragments were analyzed across both methods. After verification, it was found that the bone fragments identified by the two methods were consistent. A paired sample t-tests revealed that the identified bone fragments and measured displacement and rotation angles along the X, Y, and Z axes were consistent between the two methods. No statistically significant differences(P>0.05) were found between manual and software measurements for these parameters. CONCLUSION Human-computer interaction software employing AI technology demonstrated comparable accuracy to manual measurement in identifying and locating type C1 distal radius fractures on CT imaging.
Humans ; Male ; Female ; Radius Fractures/surgery* ; Middle Aged ; Adult ; Aged ; Aged, 80 and over ; Tomography, X-Ray Computed/methods* ; Retrospective Studies ; Software ; Wrist Fractures

OpenSim is an open source, free motion simulation and gait analysis software, which can be used to dynamically simulate and analyze the complex motion of the human body, and is widely used in human biomechanical research. Since OpenSim can analyze multi-dimensional motion data such as muscle strength, joint torque, and muscle synergistic activation during human movement, it can be used to study the biomechanical mechanism of musculoskeletal imbalance diseases and various treatment methods in TCM orthopedics, and has a broad application prospect in the field of TCM orthopedics. By the analysis of the basic characteristics, elements, analysis process, and application prospects of OpenSim, it is concluded that OpenSim musculoskeletal model has a large application space in the field of traditional Chinese medicine orthopedic, which is helpful to explain the pathogenesis and mechanism of diseases, and promote the precision diagnosis and treatment of orthopedics diseases;the application of OpenSim musculoskeletal model can solve the problem that the previous research paid attention to the bone malalignment and not enough attention to the tendon, and provide a new method for the research of orthopedic diseases. At present, there are still problems in the promotion and application of OpenSim, such as large equipment requirements and high operation threshold. Therefore, multidisciplinary cooperation, clinical research, and data sharing are the basic research strategies in this field.
Humans ; Biomechanical Phenomena ; Orthopedics ; Traumatology ; Software ; Medicine, Chinese Traditional ; Musculoskeletal System ; Models, Biological

OBJECTIVE: This study aims to address the configuration and efficiency issues in the use of digital subtraction angiography (DSA) equipment through the practical implementation of a rationalization platform based on the Internet of Things (IoT). METHODS: By employing IoT and data integration technologies, the deep integration of DSA equipment operational data with clinical data was achieved to construct a knowledge base for rational use of DSA equipment. Simultaneously, a knowledge base was developed using software engineering techniques to visually display data analysis results. RESULTS: Through thorough data analysis, an imbalance in DSA usage between the southern and northern hospital campuses was identified. Addressing this issue, optimizations were implemented based on the data analysis results, which ultimately yielded significant effects. These adjustments not only effectively alleviated the pressure on DSA equipment usage in the southern campus, but also increased equipment utilization in the northern district (the average daily working hours have increased from 4.64 h to 7.19 h), shortened patient appointment wait time (the appointment duration in the southern campus decreased by 21.86% year-on-year, while the appointment duration in the northern campus decreased by 20.51% year-on-year). CONCLUSION Through the practical implementation of a DSA rationalization platform based on IoT, this study not only successfully explored methods for rational DSA usage but also provided valuable reference for the rational management of medical equipment.
Internet of Things ; Angiography, Digital Subtraction/instrumentation* ; Humans ; Software

In order to track the running status of the accelerator in real time, discover potential problems in time, reduce the failure rate, and ensure the safety of radiotherapy patients, a linear accelerator quality management monitoring system is designed based on log files. The system adopts B/S architecture, with the server written in Python3.7 language, and is built based on Django2.2.7 framework. The system uses Python3.7 and Pylinac packages to analyze the log files of each plan, obtaining the planned beam quantity, flux gamma pass rate, and position information of multileaf collimator, etc., to realize the quality monitoring of medical linear accelerator, and customize the development of accelerator spare parts and maintenance management modules. According to statistics, after the establishment of the quality management monitoring system, the accelerator has achieved a 16% reduction in failure rate and a 30% reduction in the downtime rate, which ensures its stable operation in clinical settings.
Particle Accelerators ; Quality Control ; Software

From the perspective of performance evaluation, this paper describes briefly the concerns of study on each component module and the entire instrument, clinical items, software, and product testing on droplet digital PCR instruments, including the study methods and quality control requirements. The increase of the research and development efficiency of products and contribute to the promotion of application of digital PCR instruments in clinical laboratories are expected.
Polymerase Chain Reaction/methods* ; Quality Control ; Software ; Humans

OBJECTIVE: Evaluate the clinical application effect of low-field infant MRI. METHODS: Using literature review, expert consultation, and two rounds of Delphi to determine the evaluation index system. Then retrospectively analyze and compare the data of low-field infant MRI and high-field MRI from January 2023 to December 2024. RESULTS: There is a certain gap between low-field infant MRI and high-field MRI in terms of signal-to-noise ratio, image uniformity, software system reliability, scanning time, user interface friendliness and image result consistency. However, there was no difference in terms of spatial resolution and image quality. The noise, hardware system reliability, mean time between failure and the rate of examination completed without sedation are better than that of high-field MRI. CONCLUSION Low-field infant MRI meets needs of clinical diagnostic and has stable performance. It can be used as a routine screening tool for brain diseases near the bed.
Magnetic Resonance Imaging/methods* ; Humans ; Infant ; Retrospective Studies ; Signal-To-Noise Ratio ; Reproducibility of Results ; Brain Diseases/diagnostic imaging* ; Brain/diagnostic imaging* ; Software