Background: Fraud, Waste, and Abuse (FWA) detection is a significant yet challenging problem in the health insurance industry. An essential step in FWA detection is to check whether the medication is clinically reasonable with respect to the diagnosis. Currently, human experts with sufficient medical knowledge are required to perform this task. To reduce the cost, insurance inspectors tend to build an intelligent system to detect suspicious claims with inappropriate diagnoses/medications automatically. Objective: The aim of this study was to develop an automated method for making use of a medical knowledge graph to identify clinically suspected claims for FWA detection. Methods: First, we identified the medical knowledge that is required to assess the clinical rationality of the claims. We then searched for data sources that contain information to build such knowledge. In this study, we focused on Chinese medical knowledge. Second, we constructed a medical knowledge graph using unstructured knowledge. We used a deep learning–based method to extract the entities and relationships from the knowledge sources and developed a multilevel similarity matching approach to conduct the entity linking. To guarantee the quality of the medical knowledge graph, we involved human experts to review the entity and relationships with lower confidence. These reviewed results could be used to further improve the machine-learning models. Finally, we developed the rules to identify the suspected claims by reasoning according to the medical knowledge graph. Results: We collected 185,796 drug labels from the China Food and Drug Administration, 3390 types of disease information from medical textbooks (eg, symptoms, diagnosis, treatment, and prognosis), and information from 5272 examinations as the knowledge sources. The final medical knowledge graph includes 1,616,549 nodes and 5,963,444 edges. We designed three knowledge graph reasoning rules to identify three kinds of inappropriate diagnosis/medications. The experimental results showed that the medical knowledge graph helps to detect 70% of the suspected claims. Conclusions: The medical knowledge graph–based method successfully identified suspected cases of FWA (such as fraud diagnosis, excess prescription, and irrational prescription) from the claim documents, which helped to improve the efficiency of claim processing.

Integrating domain-specific knowledge into large language models (LLMs) remains a critical challenge in medical education. In dental specialties such as endodontics, effective learning requires access to both textual clinical evidence and visual procedural demonstrations. However, generic LLMs often produce content that lacks clinical accuracy, contextual grounding, or pedagogical clarity, thereby limiting their applicability in specialized training environments. To develop and evaluate a Retrieval-Augmented Generation (RAG)-enhanced LLMs framework that addresses the challenge of integrating domain-specific knowledge in AI-driven endodontic education. We present Endodontics-KB, a multimodal knowledge integration platform that combines evidence-based dental literature (e.g., textbooks, clinical guidelines) with visual instructional materials (e.g., procedural videos) through a hierarchical RAG architecture. The system's core component, the EndoQ chatbot, utilizes LLMs augmented with multimodal dental datasets to enable context-aware clinical reasoning. Benchmarking was conducted against three general-purpose LLMs: GPT-4, Qwen2.5, and DeepSeek R1, using a structured question bank comprising 11 expert-validated endodontic questions. Two domain experts performed a blinded evaluation across five performance dimensions: clinical accuracy, contextual relevance, completeness, decision-making professionalism, and communication fluency. The framework integrated 2,200 multimodal knowledge units through dynamic semantic indexing. EndoQ demonstrated statistically significant improvements across all evaluation metrics compared to general purpose LLMs: accuracy (4.45 ± 0.96), clinical relevance (4.59 ± 0.8), completeness (4.27 ± 0.83), professionalism judgment (4.45 ± 1.06), and language fluency (4.86 ± 0.47), as measured on a 5-point Likert scale. This proposed framework improves educational outcomes through precise and context-aware knowledge delivery. Furthermore, it represents a scalable and transferable model for AI-enhanced clinical training across medical specialties, significantly advancing competency-based pedagogy in dental education.

Background: Pregnancy is a pivotal phase in a woman’s life, demanding special attention to ensure maternal and fetal health. Prenatal education plays a vital role in promoting healthy pregnancies and reducing adverse outcomes for pregnant women. Mobile prenatal education programs have gained traction due to their accessibility and timeliness, especially in light of finite health care resources and the constraints imposed by the COVID-19 pandemic. Objective: This study aims to develop and evaluate the effectiveness of a mobile-based prenatal education program in improving pregnancy outcomes. Methods: We developed a mobile-based prenatal education curriculum in collaboration with a multidisciplinary maternal care team from Peking Union Medical College Hospital (PUMCH) in Beijing, China. Data were retrospectively collected from 1941 pregnant women who had registered for the PUMCH mobile prenatal education program and subsequently delivered at PUMCH between May 2021 and August 2022. The study compared pregnancy outcomes between the completing group, which were pregnant women who had completed at least 1 course, and the noncompleting group. We also analyzed differences among course topics within the completing group and assessed course topic popularity among pregnant women. Results: The PUMCH mobile prenatal education curriculum consists of 436 courses across 9 topics. Out of the participants, a total of 1521 did not complete any courses, while 420 completed at least 1 course. Compared with the noncompleting group, pregnant women who completed courses exhibited a significant reduction in the risk of gestational diabetes mellitus, induced abortion, postpartum infection, fetal intrauterine distress, and neonatal malformation. Among those in the completing group, a total of 86% (361/420) started course completion during the first and second trimesters. Furthermore, completing courses related to topics of pregnancy psychology and pregnancy nutrition was associated with reduced risks of premature rupture of membranes and small for gestational age infants, respectively. Pregnancy psychology and postpartum recovery were the preferred topics among pregnant women. Conclusions: The study demonstrates the potential of mobile-based prenatal education programs in improving pregnancy outcomes and supporting health care providers in delivering effective prenatal education. The rise of mobile prenatal education presents an opportunity to improve maternal and child health outcomes. Further research and broader implementation of such programs are warranted to continually improve maternal and child health.

Background: China’s older population is facing serious health challenges, including malnutrition and multiple chronic conditions. There is a critical need for tailored food recommendation systems. Knowledge graph–based food recommendations offer considerable promise in delivering personalized nutritional support. However, the integration of disease-based nutritional principles and preference-related requirements needs to be optimized in current recommendation processes. Objective: This study aims to develop a knowledge graph–based personalized meal recommendation system for community-dwelling older adults and to conduct preliminary effectiveness testing. Methods: We developed ElCombo, a personalized meal recommendation system driven by user profiles and food knowledge graphs. User profiles were established from a survey of 96 community-dwelling older adults. Food knowledge graphs were supported by data from websites of Chinese cuisine recipes and eating history, consisting of 5 entity classes: dishes, ingredients, category of ingredients, nutrients, and diseases, along with their attributes and interrelations. A personalized meal recommendation algorithm was then developed to synthesize this information to generate packaged meals as outputs, considering disease-related nutritional constraints and personal dietary preferences. Furthermore, a validation study using a real-world data set collected from 96 community-dwelling older adults was conducted to assess ElCombo’s effectiveness in modifying their dietary habits over a 1-month intervention, using simulated data for impact analysis. Results: Our recommendation system, ElCombo, was evaluated by comparing the dietary diversity and diet quality of its recommended meals with those of the autonomous choices of 96 eligible community-dwelling older adults. Participants were grouped based on whether they had a recorded eating history, with 34 (35%) having and 62 (65%) lacking such data. Simulation experiments based on retrospective data over a 30-day evaluation revealed that ElCombo’s meal recommendations consistently had significantly higher diet quality and dietary diversity compared to the older adults’ own selections (P<.001). In addition, case studies of 2 older adults, 1 with and 1 without prior eating records, showcased ElCombo’s ability to fulfill complex nutritional requirements associated with multiple morbidities, personalized to each individual’s health profile and dietary requirements. Conclusions: ElCombo has shown enhanced potential for improving dietary quality and diversity among community-dwelling older adults in simulation tests. The evaluation metrics suggest that the food choices supported by the personalized meal recommendation system surpass autonomous selections. Future research will focus on validating and refining ElCombo’s performance in real-world settings, emphasizing the robust management of complex health data. The system’s scalability and adaptability pinpoint its potential for making a meaningful impact on the nutritional health of older adults.

Background: Drug repositioning is a pivotal strategy in pharmaceutical research, offering accelerated and cost-effective therapeutic discovery. However, biomedical information relevant to drug repositioning is often complex, dispersed, and underutilized due to limitations in traditional extraction methods, such as reliance on annotated data and poor generalizability. Large language models (LLMs) show promise but face challenges such as hallucinations and interpretability issues. Objective: This study proposed long chain-of-thought for drug repositioning knowledge extraction (LCoDR-KE), a lightweight and domain-specific framework to enhance LLMs’ accuracy and adaptability in extracting structured biomedical knowledge for drug repositioning. Methods: A domain-specific schema defined 11 entities (eg, drug, disease) and 18 relationships (eg, treats, is biomarker of). Following the established schema architecture, we constructed automatic annotation based on 10,000 PubMed abstracts via chain-of-thought prompt engineering. A total of 1000 expert-validated abstracts were curated into a drug repositioning corpus, a high-quality specialized corpus, while the remaining entries were allocated for model training purposes. Then, the proposed LCoDR-KE framework combined supervised fine-tuning of the Qwen2.5-7B-Instruct model with reinforcement learning and dual-reward mechanisms. Performance was evaluated against state-of-the-art models (eg, conditional random fields, Bidirectional Encoder Representations From Transformers, BioBERT, Qwen2.5, DeepSeek-R1, OpenBioLLM-70B, and model variants) using precision, recall, and F₁-score. In addition, the convergence of the training method was assessed by analyzing performance progression across iteration steps. Results: LCoDR-KE achieved an entity F₁ of 81.46% (eg, drug 95.83%, disease 90.52%) and triplet F₁ of 69.04%, outperforming traditional models and rivaling larger LLMs (DeepSeek-R1: entity F₁=84.64%, triplet F₁=69.02%). Ablation studies confirmed the contributions of supervised fine-tuning (8.61% and 20.70% F₁ drop if removed) and reinforcement learning (6.09% and 14.09% F₁ drop if removed). The training process demonstrated stable convergence, validated through iterative performance monitoring. Qualitative analysis of the model’s chain-of-thought outputs showed that LCoDR-KE performed structured and schema-aware reasoning by validating entity types, rejecting incompatible relations, enforcing constraints, and generating compliant JSON. Error analysis revealed 4 main types of mistakes and challenges for further improvement. Conclusions: LCoDR-KE enhances LLMs’ domain-specific adaptability for drug repositioning by offering an open-source drug repositioning corpus and a long chain-of-thought framework based on a lightweight LLM model. This framework supports drug discovery and knowledge reasoning while providing scalable, interpretable solutions applicable to broader biomedical knowledge extraction tasks.

Background: Medical postgraduates’ demand for data capabilities is growing, as biomedical research becomes more data driven, integrative, and computational. In the context of the application of big data in health and medicine, the integration of data mining skills into postgraduate medical education becomes important.Objective: This study aimed to demonstrate the design and implementation of a medical data mining course for medical postgraduates with diverse backgrounds in a medical school.Methods: We developed a medical data mining course called “Practical Techniques of Medical Data Mining” for postgraduate medical education and taught the course online at Peking Union Medical College (PUMC). To identify the background knowledge, programming skills, and expectations of targeted learners, we conducted a web-based questionnaire survey. After determining the instructional methods to be used in the course, three technical platforms—Rain Classroom, Tencent Meeting, and WeChat—were chosen for online teaching. A medical data mining platform called Medical Data Mining - R Programming Hub (MedHub) was developed for self-learning, which could support the development and comprehensive testing of data mining algorithms. Finally, we carried out a postcourse survey and a case study to demonstrate that our online course could accommodate a diverse group of medical students with a wide range of academic backgrounds and programming experience.Results: In total, 200 postgraduates from 30 disciplines participated in the precourse survey. Based on the analysis of students’ characteristics and expectations, we designed an optimized course structured into nine logical teaching units (one 4-hour unit per week for 9 weeks). The course covered basic knowledge of R programming, machine learning models, clinical data mining, and omics data mining, among other topics, as well as diversified health care analysis scenarios. Finally, this 9-week course was successfully implemented in an online format from May to July in the spring semester of 2020 at PUMC. A total of 6 faculty members and 317 students participated in the course. Postcourse survey data showed that our course was considered to be very practical (83/83, 100% indicated “very positive” or “positive”), and MedHub received the best feedback, both in function (80/83, 96% chose “satisfied”) and teaching effect (80/83, 96% chose “satisfied”). The case study showed that our course was able to fill the gap between student expectations and learning outcomes.Conclusions: We developed content for a data mining course, with online instructional methods to accommodate the diversified characteristics of students. Our optimized course could improve the data mining skills of medical students with a wide range of academic backgrounds and programming experience.