The clinical burden of spleen-stomach disorders is substantial. While large language models (LLMs) offer new potential for medical applications, they face three major challenges in the context of integrative Chinese and Western medicine (ICWM): a lack of high-quality data, the absence of models capable of effectively integrating the reasoning logic of traditional Chinese medicine (TCM) syndrome differentiation with that of Western medical (WM) disease diagnosis, and the shortage of a standardized evaluation benchmark. To address these interrelated challenges, we propose DongYuan, an ICWM spleen-stomach diagnostic framework. Specifically, three ICWM datasets (SSDF-Syndrome, SSDF-Dialogue, and SSDF-PD) were curated to fill the gap in high-quality data for spleen-stomach disorders. We then developed SSDF-Core, a core diagnostic LLM that acquires robust ICWM reasoning capabilities through a two-stage training regimen of supervised fine-tuning. tuning (SFT) and direct preference optimization (DPO), and complemented it with SSDF-Navigator, a pluggable consultation navigation model designed to optimize clinical inquiry strategies. Additionally, we established SSDF-Bench, a comprehensive evaluation benchmark focused on ICWM diagnosis of spleen-stomach disorders. Experimental results demonstrate that SSDF-Core significantly outperforms 12 mainstream baselines on SSDF-Bench. DongYuan lays a solid methodological foundation and provides practical technical references for the future development of intelligent ICWM diagnostic systems.
Metaphorical expressions are abundant in Traditional Chinese Medicine (TCM), conveying complex disease mechanisms and holistic health concepts through culturally rich and often abstract terminology. Bridging these metaphors to anatomically driven Western medical (WM) concepts poses significant challenges for both automated language processing and real-world clinical practice. To address this gap, we propose a novel multi-agent and chain-of-thought (CoT) framework designed to interpret TCM metaphors accurately and map them to WM pathophysiology. Specifically, our approach combines domain-specialized agents (TCM Expert, WM Expert) with a Coordinator Agent, leveraging stepwise chain-of-thought prompts to ensure transparent reasoning and conflict resolution. We detail a methodology for building a metaphor-rich TCM dataset, discuss strategies for effectively integrating multi-agent collaboration and CoT reasoning, and articulate the theoretical underpinnings that guide metaphor interpretation across distinct medical paradigms. We present a comprehensive system design and highlight both the potential benefits and limitations of our approach, while leaving placeholders for future experimental validation. Our work aims to support clinical decision-making, cross-system educational initiatives, and integrated healthcare research, ultimately offering a robust scaffold for reconciling TCM's symbolic language with the mechanistic focus of Western medicine.
Natural language processing (NLP) has been traditionally applied to medicine, and generative large language models (LLMs) have become prominent recently. However, the differences between them across different medical tasks remain underexplored. We analyzed 19,123 studies, finding that generative LLMs demonstrate advantages in open-ended tasks, while traditional NLP dominates in information extraction and analysis tasks. As these technologies advance, ethical use of them is essential to ensure their potential in medical applications.
Interdisciplinary research, a process of knowledge integration, is vital for scientific advancements. It remains unclear whether prestigious journals that are highly impactful lead in disseminating interdisciplinary knowledge. In this paper, by constructing topic-level correlation networks based on publications, we evaluated the interdisciplinarity of more and less prestigious journals in medicine. We found research from prestigious medical journals tends to be less interdisciplinary than research from other medical journals. We also established that cancer-related research is the main driver of interdisciplinarity in medical science. Our results indicate a weak tendency for differences in topic correlations between more and less prestigious journals to be co-located. Accordingly, we identified that interdisciplinarity in prestigious journals mainly differs from interdisciplinarity in other journals in areas such as infections, nervous system diseases and cancer. Overall, our results suggest that interdisciplinarity in science could benefit from prestigious journals easing rigid disciplinary boundaries.
Menghua Xia, Reimund Bayerlein, Yanis Chemli
et al.
Artificial intelligence-generated content (AIGC) has shown remarkable performance in nuclear medicine imaging (NMI), offering cost-effective software solutions for tasks such as image enhancement, motion correction, and attenuation correction. However, these advancements come with the risk of hallucinations, generating realistic yet factually incorrect content. Hallucinations can misrepresent anatomical and functional information, compromising diagnostic accuracy and clinical trust. This paper presents a comprehensive perspective of hallucination-related challenges in AIGC for NMI, introducing the DREAM report, which covers recommendations for definition, representative examples, detection and evaluation metrics, underlying causes, and mitigation strategies. This position statement paper aims to initiate a common understanding for discussions and future research toward enhancing AIGC applications in NMI, thereby supporting their safe and effective deployment in clinical practice.
Tayomara Ferreira Nascimento, Silvia Cristina Mangini Bocchi, João Cesar Lyra
et al.
<b>Background/Objective</b>: The effectiveness of blue-light phototherapy (PT) is mainly dependent on the total dose of light (time under PT and amount of skin exposed) received by infants. The primary aim of this study was the development of a novel, flexible, and stretchable device to provide continuous PT treatment, avoiding temporary interruptions that are often observed in practice, such as during breastfeeding, for example. This study evaluated the biocompatibility of a novel, low-cost blanket equipped with light-emitting diode (LED) lamps designed to maintain therapeutic efficacy while facilitating uninterrupted skin-to-skin contact. <b>Methods</b>: Fourteen New Zealand White rabbits, weighing approximately 2.9 kg and aged 4 months, were randomly assigned to an experimental group (TG, n = 7) or a control group (CG, n = 7). The TG received phototherapy directly on the skin (irradiance: 19.3 [13.0–22.0] µW/cm<sup>−2</sup>/nm<sup>−1</sup>) during two 12 h sessions over consecutive days, while the CG remained under identical conditions with the device turned off. Biochemical, hematological, dermatological, and histological parameters, as well as rectal and skin temperatures, were assessed. <b>Results</b>: The results showed no differences in clinical appearance or histological analysis of skin tissue between the groups. Blood analysis indicated a reduction in absolute monocyte counts in the TG compared to the CG (<i>p =</i> 0.049), though levels remained within normal ranges. Skin temperature was consistently higher in the TG, except during the initial measurement. Rectal temperatures were similar on the first day but lower in the TG on the second day (mean 40.3 ± 0.21 °C vs. 40.7 ± 0.32 °C; <i>p =</i> 0.039). <b>Conclusions</b>: Temperature levels remained within physiological limits for both groups throughout the study. The device demonstrated biocompatibility and caused no adverse dermatological, hematological, or biochemical effects.
Manuel Fuertes-Recuero, José L. López-Hernández, Alejandra Ramírez-Lago
et al.
Chimpanzees (<i>Pan troglodytes</i>) rescued from the illegal wildlife trade often suffer from chronic, traumatic injuries that require specialized and prolonged medical treatment in wildlife rehabilitation centers. We present the case report of a two-year-old male chimpanzee admitted at the Tchimpounga Chimpanzee Rehabilitation Center in the Republic of Congo with a chronic periorbital abscess, likely caused by a machete wound sustained during the poaching of his mother. Despite receiving extended antimicrobial therapy, his condition was never fully controlled and progressed to a chronic orbital infection, causing him discomfort and producing chronic purulent discharge. Enucleation was performed under general anesthesia using ketamine and medetomidine, with surgical approach adapted to the distinctive orbital anatomy of chimpanzees. During the procedure, ligation of the optic nerve and ophthalmic vessels was required due to the confined orbital apex and extensive vascularization, ensuring adequate haemostasias and procedural safety. The chimpanzee made an uneventful postoperative recovery, resuming normal feeding and social behavior within 48 h, with complete wound healing occurring within two weeks. This case report highlights the importance of prompt surgical intervention when conservative medical management fails to resolve refractory ocular infections in chimpanzees. It also emphasizes the importance of specific anesthetic protocols, refined surgical techniques and tailored postoperative care in wildlife rehabilitation centers. Documenting and sharing detailed case reports such as this contributes to the limited veterinary literature on great ape surgery and supports evidence-based clinical decision-making to improve the welfare and treatment outcomes of rescued chimpanzees.
Aparna Mariyam Thomas, Guilherme G. Verocai, John Soghigian
et al.
The caribou (Rangifer tarandus sspp.) is a keystone wildlife species in northern ecosystems that plays a central role in the culture, spirituality and food security of Indigenous People. The Arctic is currently experiencing an unprecedented rate of climate change, including warming temperatures and altered patterns of precipitation. These environmental changes can facilitate the transmission of arthropod-borne parasites, such as filarioid nematodes.Filarioids are an important cause of morbidity and occasional mortality in Rangifer in Fennoscandia, however, much of the ecology and epidemiology of these parasites in caribou in North America, including Canada, remains unknown. We aimed to determine the parasitic diversity and geographic distribution of filarioid nematodes in three Canadian designatable units (DU) of caribou (barren-ground, boreal and Dolphin & Union) from Northwest Territories, Nunavut and Newfoundland & Labrador. Genomic DNA extracted from 768 blood samples was screened for filarioid nematodes using real-time PCR. The positive samples were Sanger sequenced to identify the parasite present. Based on the sequencing results, we identified Setaria yehi and Onchocerca cervipedis s.l. We then standardized a TaqMan probe based duplex droplet digital PCR (ddPCR) protocol for the simultaneous detection of S. yehi and O. cervipedis s.l. Based on real-time PCR results, 8/768 samples were positive. Setaria yehi and O. cervipedis s.l. were present in 4 separate samples (0.5%) each. Using ddPCR, 68/192 samples were positive (35.4%). Setaria yehi DNA was detected in 57/192 positive samples (29.7%), O. cervipedis s.l. DNA was present in 22/192 samples (11.5%) and 11/192 samples (5.7%) had co-infections. Setaria yehi was detected in all three DUs tested. Onchocerca cervipedis s.l. were found in barren-ground and boreal caribou, but not from the Dolphin and Union caribou.Through this broad-based survey and through developing and implementing advanced molecular methodologies, we have documented the apparent distribution and diversity of S. yehi and O. cervipedis s.l. in parts of three Canadian DUs of caribou. The knowledge gained from this study provides baseline data and methodology for the further elucidation of the epidemiology of these parasites in North America.
Gül Özbilen Acar, Filiz Özen, Halil İbrahim Yıldırım
et al.
Objective: The goal of this study was to investigate the expression patterns and potential relationship of the Kirsten rat sarcoma viral oncogene homolog (KRAS) and B-raf proto-oncogene (BRAF) genes in nasal polyposis (NP).
Methods: Twenty-nine patients were included in the study. Small punch biopsies were collected from nasal polyps during each operation and immediately frozen in liquid nitrogen. Punch biopsies were also taken during surgery from the inferior turbinate or the septum mucosa of the patients as a control group, and these samples were also frozen. Total ribonucleic acid (RNA) was isolated using TRIzol reagent. The gene expression analyses of the KRAS and BRAF genes were performed by the real-time polymerase chain reaction method.
Results: When compared to control subjects, KRAS nasal polyp gene expression increased in 21, but decreased in eight of the 29 patients. This statistical analysis revealed a statistically significant difference between the nasal polyp group and the controls (p=0.023). Like KRAS, a decrease was observed in BRAF gene expression in six, and an increase in 23 patients (p=0.011).
Conclusion: Our findings suggest a potential association between BRAF and KRAS genes expression and NP, but further studies are needed to confirm this relationship. This finding suggests that the genetic background of NP could be a contributing factor, with the BRAF and KRAS mutations playing a role.
Zeynep Akkutay-Yoldar, Mehmet Türkay Yoldar, Yiğit Burak Akkaş
et al.
Abstract Identifying viral replication within cells demands labor-intensive isolation methods, requiring specialized personnel and additional confirmatory tests. To facilitate this process, we developed an AI-powered automated system called AI Recognition of Viral CPE (AIRVIC), specifically designed to detect and classify label-free cytopathic effects (CPEs) induced by SARS-CoV-2, BAdV-1, BPIV3, BoAHV-1, and two strains of BoGHV-4 in Vero and MDBK cell lines. AIRVIC utilizes convolutional neural networks, with ResNet50 as the primary architecture, trained on 40,369 microscopy images at various magnifications. AIRVIC demonstrated strong CPE detection, achieving 100% accuracy for the BoGHV-4 DN-599 strain in MDBK cells, the highest among tested strains. In contrast, the BoGHV-4 MOVAR 33/63 strain in Vero cells showed a lower accuracy of 87.99%, the lowest among all models tested. For virus classification, a multi-class accuracy of 87.61% was achieved for bovine viruses in MDBK cells; however, it dropped to 63.44% when the virus was identified without specifying the cell line. To the best of our knowledge, this is the first research article published in English to utilize AI for distinguishing animal virus infections in cell culture. AIRVIC’s hierarchical structure highlights its adaptability to virological diagnostics, providing unbiased infectivity scoring and facilitating viral isolation and antiviral efficacy testing. Additionally, AIRVIC is accessible as a web-based platform, allowing global researchers to leverage its capabilities in viral diagnostics and beyond.
Chicken semen cryopreservation is crucial for utilizing high-quality cockerel genetics, but semen is highly sensitive to cryoinjury, leading to poor preservation outcomes. This study aimed to establish a theoretical foundation for selecting cockerels for semen cryopreservation through serum testing and to improve semen quality via DNA methylation editing. Semen and serum samples were collected from 102 Xiaoshan cockerels, with semen cryopreserved and thawed following standardized protocols. Post-thaw semen quality and serum testosterone (T) levels were assessed. Eight cockerels were selected based on motile sperm quality, and whole-genome bisulfite sequencing (WGBS) was used to analyze sperm DNA methylation. The results showed a significant positive correlation between serum T levels and sperm motility. There were notable differences in sperm motility and serum T levels between high-quality and low-quality semen groups but no differences in estradiol (E<sub>2</sub>), superoxide dismutase (SOD), or glutathione peroxidase (GSH-Px) levels. A total of 217 differentially methylated regions (DMRs) and 116 differentially methylated genes (DMGs) were identified. Key genes such as <i>PRKACB</i> (protein kinase, cAMP-dependent, catalytic, beta) and <i>ACSL1</i> (long-chain-fatty-acid--CoA ligase 1) were associated with sperm motility. These findings provide important insights for improving semen cryopreservation and contribute to breeding practices and the development of cryoprotectants.
Shannon L. Walston, Hiroshi Seki, Hirotaka Takita
et al.
Medicine and deep learning-based artificial intelligence (AI) engineering represent two distinct fields each with decades of published history. With such history comes a set of terminology that has a specific way in which it is applied. However, when two distinct fields with overlapping terminology start to collaborate, miscommunication and misunderstandings can occur. This narrative review aims to give historical context for these terms, accentuate the importance of clarity when these terms are used in medical AI contexts, and offer solutions to mitigate misunderstandings by readers from either field. Through an examination of historical documents, including articles, writing guidelines, and textbooks, this review traces the divergent evolution of terms for data sets and their impact. Initially, the discordant interpretations of the word 'validation' in medical and AI contexts are explored. Then the data sets used for AI evaluation are classified, namely random splitting, cross-validation, temporal, geographic, internal, and external sets. The accurate and standardized description of these data sets is crucial for demonstrating the robustness and generalizability of AI applications in medicine. This review clarifies existing literature to provide a comprehensive understanding of these classifications and their implications in AI evaluation. This review then identifies often misunderstood terms and proposes pragmatic solutions to mitigate terminological confusion. Among these solutions are the use of standardized terminology such as 'training set,' 'validation (or tuning) set,' and 'test set,' and explicit definition of data set splitting terminologies in each medical AI research publication. This review aspires to enhance the precision of communication in medical AI, thereby fostering more effective and transparent research methodologies in this interdisciplinary field.
In our original article (Sarvet & Stensrud, 2024), we examine twin definitions of "harm" in personalized medicine: one based on predictions of individuals' unmeasurable response types (counterfactual harm), and another based solely on the observations of experiments (interventionist harm). In their commentary, Mueller & Pearl (2024) (MP) read our review as an argument that "counterfactual logic should [...] be purged from consideration of harm and benefit" and "strongly object [...] that a rational decision maker may well apply the interventional perspective to the exclusion of counterfactual considerations." Here we show that this objection is misguided. We analyze MP's examples and derive a general result, showing that determinations of harm through interventionist and counterfactual analyses will always concur. Therefore, individuals who embrace counterfactual formulations and those who object to their use will make equivalent decisions in uncontroversial settings.
No previous work has studied the performance of Large Language Models (LLMs) in the context of Traditional Chinese Medicine (TCM), an essential and distinct branch of medical knowledge with a rich history. To bridge this gap, we present a TCM question dataset named TCM-QA, which comprises three question types: single choice, multiple choice, and true or false, to examine the LLM's capacity for knowledge recall and comprehensive reasoning within the TCM domain. In our study, we evaluate two settings of the LLM, zero-shot and few-shot settings, while concurrently discussing the differences between English and Chinese prompts. Our results indicate that ChatGPT performs best in true or false questions, achieving the highest precision of 0.688 while scoring the lowest precision is 0.241 in multiple-choice questions. Furthermore, we observed that Chinese prompts outperformed English prompts in our evaluations. Additionally, we assess the quality of explanations generated by ChatGPT and their potential contribution to TCM knowledge comprehension. This paper offers valuable insights into the applicability of LLMs in specialized domains and paves the way for future research in leveraging these powerful models to advance TCM.