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

Large language models (LLMs) such as ChatGPT, Claude, Llama, and Qwen are emerging as transformative technologies for the diagnosis and treatment of various diseases. With their exceptional long-context reasoning capabilities, LLMs are proficient in clinically relevant tasks, particularly in medical text analysis and interactive dialogue. They can enhance diagnostic accuracy by processing vast amounts of patient data and medical literature and have demonstrated their utility in diagnosing common diseases and facilitating the identification of rare diseases by recognizing subtle patterns in symptoms and test results. Building on their image-recognition abilities, multimodal LLMs (MLLMs) show promising potential for diagnosis based on radiography, chest computed tomography (CT), electrocardiography (ECG), and common pathological images. These models can also assist in treatment planning by suggesting evidence-based interventions and improving clinical decision support systems through integrated analysis of patient records. Despite these promising developments, significant challenges persist regarding the use of LLMs in medicine, including concerns regarding algorithmic bias, the potential for hallucinations, and the need for rigorous clinical validation. Ethical considerations also underscore the importance of maintaining the function of supervision in clinical practice. This paper highlights the rapid advancements in research on the diagnostic and therapeutic applications of LLMs across different medical disciplines and emphasizes the importance of policymaking, ethical supervision, and multidisciplinary collaboration in promoting more effective and safer clinical applications of LLMs. Future directions include the integration of proprietary clinical knowledge, the investigation of open-source and customized models, and the evaluation of real-time effects in clinical diagnosis and treatment practices.
Humans ; Large Language Models ; Tomography, X-Ray Computed

OBJECTIVES

This study aimed to describe the demographic profile, intervention sessions, goal attainment scaling (GAS), and health-related quality of life (HRQOL) of autistic children receiving speech and language therapy (SLT) in a higher educational institution in the Philippines.

Deidentified data from 18 autistic children aged 4–16 years (mean=8.2; SD=2.9) who received SLT for two months were analyzed. Their demographic profile, intervention sessions, GAS scores, and generic HRQOL scores were documented.

Most participants were school-age children (n=12; 66%) and were boys (n=14; 78%). After two months, the GAS scores of 11 participants (61%) increased by 1–2 points, whereas the scores of the remaining participants decreased (n=6; 33%) or did not change (n=1; 6%). Their mean generic HRQOL scores before and after SLT were 65.6 (SD=15.2) and 61.2 (SD=17.4), respectively.

While the GAS scores increased for most participants, their generic HRQOL scores did not show clinically significant changes after two months of SLT. This can be attributed to the few therapy sessions and short follow-up period. The findings highlight the need to provide long-term support to SLT services of autistic children in the Philippines to document more desirable quality of life outcomes.

Language ; Pathology ; Speech ; Speech-language Pathology ; Weights And Measures

This paper focuses on the necessity and feasibility of the multidimensional integration of clinic, culture and language in the international education of acupuncture-moxibustion within a cross-cultural context. In view of the current gap between theory and practice, and the barrier of culture and language in the international education of acupuncture-moxibustion, it proposes the specific integration approaches, such as the "trinity teaching method" and "modularization of acupuncture courses", which develops the framework of international education of acupuncture-moxibustion, guided by "cultural exploration" in macroscopic view and implemented through "cultural experience", aiming to achieve a seamless integration of clinic, culture, and language. This initiative not only inherits and promotes Chinese acupuncture-moxibustion, maintains its unique position in global healthcare, but also fosters dialogue and exchange between Eastern and Western medicine. Ultimately, it enhances the international recognition of Chinese acupuncture-moxibustion. By offering fresh perspectives and methodologies, this paper paves the way for a more comprehensive and systematic approaches to international education of acupuncture-moxibustion, presenting the theoretical and practical significance in advancing the globalization of traditional Chinese medicine.
Humans ; Moxibustion ; Language ; Acupuncture/education* ; Acupuncture Therapy ; Culture ; China

The acupoint name is a core term in traditional Chinese medicine and has its own mysterious and abstruse feature. Designated by the international organizations such as World Federation of Chinese Medicine Societies, World Health Organization, the phonetic translation method has been adopted for the standardization of acupuncture nomenclature. But this method neglects the cultural attributes of acupoint names. The liberal translation should be considered appropriately. English translation of acupoint name should be composed of two steps, intralingual translation (exegesis) and interlingual translation. During exegesis, the methods for discriminating phonetic loan character, selecting meanings and identifying character patterns should be sufficiently used. The interlingual translation is launched only after the fully understanding of acupoint names (based on intralingual translation).
Acupuncture Points ; Terminology as Topic ; Humans ; Translations ; Language ; Translating ; Medicine, Chinese Traditional

Humans ; Language Development Disorders/diagnosis* ; Early Diagnosis ; Child

Automatic classification of medical questions is of great significance in improving the quality and efficiency of online medical services, and belongs to the task of intent recognition. Joint entity recognition and intent recognition perform better than single task models. Currently, most publicly available medical text intent recognition datasets lack entity annotation, and manual annotation of these entities requires a lot of time and manpower. To solve this problem, this paper proposes a medical text classification model, bidirectional encoder representation based on transformer-recurrent convolutional neural network-entity-label-semantics (BRELS), which integrates medical entity label semantics. This model firstly utilizes an adaptive fusion mechanism to absorb prior knowledge of medical entity labels, achieving local feature enhancement. Then in global feature extraction, a lightweight recurrent convolutional neural network (LRCNN) is used to suppress parameter growth while preserving the original semantics of the text. The ablation and comparison experiments are conducted on three public medical text intent recognition datasets to validate the performance of the model. The results show that F1 score reaches 87.34%, 81.71%, and 77.74% on each dataset, respectively. The results show that the BRELS model can effectively identify and understand medical terminology, thereby effectively identifying users' intentions, which can improve the quality and efficiency of online medical services.
Semantics ; Neural Networks, Computer ; Humans ; Natural Language Processing

OBJECTIVES: To summarize the clinical manifestations and genetic characteristics of creatine deficiency syndrome (CDS) caused by GAMT gene mutations. METHODS: A retrospective analysis was conducted on the clinical and genetic data of two children diagnosed with GAMT deficiency-type CDS at the Children's Medical Center of Xiangya Hospital, Central South University, from December 2020 to December 2024. RESULTS: The two patients presented with symptoms in infancy, and both had compound heterozygous mutations in the GAMT gene. Case 1 exhibited seizures and intellectual disability, while Case 2 had intellectual disability and attention-deficit hyperactivity disorder. Magnetic resonance spectroscopy of cranial MRI in both patients indicated reduced creatine peaks. After creatine treatment, seizures in Case 1 were controlled, but both patients continued to experience intellectual disabilities and behavioral issues. As of December 2024, a total of 21 cases have been reported in China (including this study), and 115 cases have been reported abroad. All patients exhibited developmental delay or intellectual disabilities, with 66.9% (91/136) experiencing seizures, 33.8% (46/136) presenting with motor disorders, and 36.8% (50/136) having behavioral problems. Seventy-five percent (102/136) of patients received creatine treatment, leading to significant improvements in seizures and motor disorders, although cognitive improvement was not substantial. CONCLUSIONS GAMT deficiency-type CDS is rare and presents with nonspecific clinical features. Timely diagnosis facilitates targeted treatment, which can partially improve prognosis.
Child ; Female ; Humans ; Male ; Creatine/deficiency* ; Guanidinoacetate N-Methyltransferase/deficiency* ; Intellectual Disability/genetics* ; Mutation ; Retrospective Studies ; Rhabdomyolysis/genetics* ; Language Development Disorders ; Movement Disorders/congenital*

OBJECTIVES: Accurate identification of risk factors for precocious puberty is essential for clinical diagnosis and management, yet the performance of natural language processing methods applied to unstructured electronic medical record (EMR) data remains to be fully evaluated. This study aims to assess the performance of a prompt engineering method for extracting individual risk factors of precocious puberty from EMRs. METHODS: Based on the capacity and role-insight-statement-personality-experiment (CRISPE) prompt framework, both simple and optimized prompts were designed to guide the large language model GLM-4-9B in extracting 10 types of risk factors for precocious puberty from 653 EMRs. Accuracy, precision, recall, and F1-score were used as evaluation metrics for the information extraction task. RESULTS: Under simple and optimized prompt conditions, the overall accuracy, precision, recall, and F1-score of the model were 84.18%, 98.09%, 81.99%, and 89.32% versus 97.15%, 98.31%, 98.16%, and 98.23%, respectively. The optimized prompts achieved more stable performance across age (<9 years vs ≥9 years) and visit-time (<2023 vs ≥2023) subgroups compared with simple prompts. The accuracy range for extracting each risk factor was 60.03%-97.24%, while with optimized prompts, the range improved to 92.19%-99.85%. The largest performance improvement occurred for "beverage intake" (60.03% vs 92.19%), and the smallest for "maternal age of menarche" (97.24% vs 99.23%). In comparing distributions among simple prompts, optimized prompts, and ground truth, statistically significant differences were observed for snack intake, beverage intake, soy milk intake, honey intake, supplement use, tonic use, sleep quality, and sleeping with the light on (all P<0.001), while exercise (P=0.966) and maternal menarche age (P=0.952) showed no significant differences. CONCLUSIONS Compared with simple prompts, optimized prompts substantially improved the extraction performance of individual risk factors for precocious puberty from EMRs, underscoring the critical role of prompt engineering in enhancing large language model performance.
Humans ; Puberty, Precocious/epidemiology* ; Risk Factors ; Electronic Health Records ; Female ; Child ; Natural Language Processing