Hasil untuk "Medicine (General)"

Jiacheng Xie, Yang Yu, Yibo Chen et al.

Traditional Chinese Medicine (TCM), with a history spanning over two millennia, plays a role in global healthcare. However, applying large language models (LLMs) to TCM remains challenging due to its reliance on holistic reasoning, implicit logic, and multimodal diagnostic cues. Existing TCM-domain LLMs have made progress in text-based understanding but lack multimodal integration, interpretability, and clinical applicability. To address these limitations, we developed BenCao, a ChatGPT-based multimodal assistant for TCM, integrating structured knowledge bases, diagnostic data, and expert feedback refinement. BenCao was trained through natural language instruction tuning rather than parameter retraining, aligning with expert-level reasoning and ethical norms specific to TCM. The system incorporates a comprehensive knowledge base of over 1,000 classical and modern texts, a scenario-based instruction framework for diverse interactions, a chain-of-thought simulation mechanism for interpretable reasoning, and a feedback refinement process involving licensed TCM practitioners. BenCao connects to external APIs for tongue-image classification and multimodal database retrieval, enabling dynamic access to diagnostic resources. In evaluations across single-choice question benchmarks and multimodal classification tasks, BenCao achieved superior accuracy to general-domain and TCM-domain models, particularly in diagnostics, herb recognition, and constitution classification. The model was deployed as an interactive application on the OpenAI GPTs Store, accessed by nearly 1,000 users globally as of October 2025. This study demonstrates the feasibility of developing a TCM-domain LLM through natural language-based instruction tuning and multimodal integration, offering a practical framework for aligning generative AI with traditional medical reasoning and a scalable pathway for real-world deployment.

Peng Liu, Lian Cheng, Benjamin P. Omell et al.

Generation planning approaches face challenges in managing the incompatible mathematical structures between stochastic production simulations for reliability assessment and optimization models for generation planning, which hinders the integration of reliability constraints. This study proposes an approach to embedding reliability verification constraints into generation expansion planning by leveraging a weighted oblique decision tree (WODT) technique. For each planning year, a generation mix dataset, labeled with reliability assessment simulations, is generated. An WODT model is trained using this dataset. Reliability-feasible regions are extracted via depth-first search technique and formulated as disjunctive constraints. These constraints are then transformed into mixed-integer linear form using a convex hull modeling technique and embedded into a unit commitment-integrated generation expansion planning model. The proposed approach is validated through a long-term generation planning case study for the Electric Reliability Council of Texas (ERCOT) region, demonstrating its effectiveness in achieving reliable and optimal planning solutions.

Zhongxi Qiu, Zhang Zhang, Yan Hu et al.

This paper explores optimal data selection strategies for Reinforcement Learning with Verified Rewards (RLVR) training in the medical domain. While RLVR has shown exceptional potential for enhancing reasoning capabilities in large language models, most prior implementations have focused on mathematics and logical puzzles, with limited exploration of domain-specific applications like medicine. We investigate four distinct data sampling strategies from MedQA-USMLE: random sampling (baseline), and filtering using Phi-4, Gemma-3-27b-it, and Gemma-3-12b-it models. Using Gemma-3-12b-it as our base model and implementing Group Relative Policy Optimization (GRPO), we evaluate performance across multiple benchmarks including MMLU, GSM8K, MMLU-Pro, and CMMLU. Our findings demonstrate that models trained on filtered data generally outperform those trained on randomly selected samples. Notably, training on self-filtered samples (using Gemma-3-12b-it for filtering) achieved superior performance in medical domains but showed reduced robustness across different benchmarks, while filtering with larger models from the same series yielded better overall robustness. These results provide valuable insights into effective data organization strategies for RLVR in specialized domains and highlight the importance of thoughtful data selection in achieving optimal performance. You can access our repository (https://github.com/Qsingle/open-medical-r1) to get the codes.

Yishen Liu, Shengda Luo, Zishao Zhong et al.

Large language models (LLMs) primarily trained on English texts, often face biases and inaccuracies in Chinese contexts. Their limitations are pronounced in fields like Traditional Chinese Medicine (TCM), where cultural and clinical subtleties are vital, further hindered by a lack of domain-specific data, such as rheumatoid arthritis (RA). To address these issues, this paper introduces Hengqin-RA-v1, the first large language model specifically tailored for TCM with a focus on diagnosing and treating RA. We also present HQ-GCM-RA-C1, a comprehensive RA-specific dataset curated from ancient Chinese medical literature, classical texts, and modern clinical studies. This dataset empowers Hengqin-RA-v1 to deliver accurate and culturally informed responses, effectively bridging the gaps left by general-purpose models. Extensive experiments demonstrate that Hengqin-RA-v1 outperforms state-of-the-art models, even surpassing the diagnostic accuracy of TCM practitioners in certain cases.

Jiawei Wu, Jun Wen, Mingyuan Yan et al.

Medicinal synergy prediction is a powerful tool in drug discovery and development that harnesses the principles of combination therapy to enhance therapeutic outcomes by improving efficacy, reducing toxicity, and preventing drug resistance. While a myriad of computational methods has emerged for predicting synergistic drug combinations, a large portion of them may overlook the intricate, yet critical relationships between various entities in drug interaction networks, such as drugs, cell lines, and diseases. These relationships are complex and multidimensional, requiring sophisticated modeling to capture nuanced interplay that can significantly influence therapeutic efficacy. We introduce a salient deep hypergraph learning method, namely, Heterogeneous Entity Representation for MEdicinal Synergy prediction (HERMES), to predict anti-cancer drug synergy. HERMES integrates heterogeneous data sources, encompassing drug, cell line, and disease information, to provide a comprehensive understanding of the interactions involved. By leveraging advanced hypergraph neural networks with gated residual mechanisms, HERMES can effectively learn complex relationships/interactions within the data. Our results show HERMES demonstrates state-of-the-art performance, particularly in forecasting new drug combinations, significantly surpassing previous methods. This advancement underscores the potential of HERMES to facilitate more effective and precise drug combination predictions, thereby enhancing the development of novel therapeutic strategies.

Song Yu, Xiaofei Xu, Fangfei Xu et al.

Although large language models perform well in understanding and responding to user intent, their performance in specialized domains such as Traditional Chinese Medicine (TCM) remains limited due to lack of expertise. In addition, high-quality data related to TCM is scarce and difficult to obtain, making large language models ineffective in handling TCM tasks. In this work, we propose a framework to improve the performance of large language models for TCM tasks using only a small amount of data. First, we use medical case data for supervised fine-tuning of the large model, making it initially capable of performing TCM tasks. Subsequently, we further optimize the model's performance using reinforcement learning from AI feedback (RLAIF) to align it with the preference data. The ablation study also demonstrated the performance gain is attributed to both supervised fine-tuning and the direct policy optimization. The experimental results show that the model trained with a small amount of data achieves a significant performance improvement on a representative TCM task.

Bolin Zhang, Zhiwei Yi, Jiahao Wang et al.

The unique diagnosis and treatment techniques and remarkable clinical efficacy of traditional Chinese medicine (TCM) make it play an important role in the field of elderly care and healthcare, especially in the rehabilitation of some common chronic diseases of the elderly. Therefore, building a TCM chatbot for healthcare application will help users obtain consultation services in a direct and natural way. However, concepts such as acupuncture points (acupoints) and meridians involved in TCM always appear in the consultation, which cannot be displayed intuitively. To this end, we develop a \textbf{h}ealthcare chat\textbf{bot} (HBot) based on a human body model in 3D and knowledge graph, which provides conversational services such as knowledge Q\&A, prescription recommendation, moxibustion therapy recommendation, and acupoint search. When specific acupoints are involved in the conversations between user and HBot, the 3D body will jump to the corresponding acupoints and highlight them. Moreover, Hbot can also be used in training scenarios to accelerate the teaching process of TCM by intuitively displaying acupuncture points and knowledge cards. The demonstration video is available at https://www.youtube.com/watch?v=UhQhutSKkTU . Our code and dataset are publicly available at Gitee: https://gitee.com/plabrolin/interactive-3d-acup.git

Xiaoyu Wang, Haoyong Ouyang, Balu Bhasuran et al.

Accurate interpretation of lab results is crucial in clinical medicine, yet most patient portals use universal normal ranges, ignoring conditional factors like age and gender. This study introduces Lab-AI, an interactive system that offers personalized normal ranges using retrieval-augmented generation (RAG) from credible health sources. Lab-AI has two modules: factor retrieval and normal range retrieval. We tested these on 122 lab tests: 40 with conditional factors and 82 without. For tests with factors, normal ranges depend on patient-specific information. Our results show GPT-4-turbo with RAG achieved a 0.948 F1 score for factor retrieval and 0.995 accuracy for normal range retrieval. GPT-4-turbo with RAG outperformed the best non-RAG system by 33.5% in factor retrieval and showed 132% and 100% improvements in question-level and lab-level performance, respectively, for normal range retrieval. These findings highlight Lab-AI's potential to enhance patient understanding of lab results.

Greta Gasciauskaite, Clara Castellucci, Amos Malorgio et al.

BackgroundViscoelastic hemostatic assays, such as rotational thromboelastometry (ROTEM) or thromboelastography, enable prompt diagnosis and accelerate targeted treatment. However, the complex interpretation of the results remains challenging. Visual Clot—a situation awareness-based visualization technology—was developed to assist clinicians in interpreting viscoelastic tests. ObjectiveFollowing a previous high-fidelity simulation study, we analyzed users’ perceptions of the technology, to identify its strengths and limitations from clinicians’ perspectives. MethodsThis is a mixed qualitative-quantitative study consisting of interviews and a survey. After solving coagulation scenarios using Visual Clot in high-fidelity simulations, we interviewed anesthesia personnel about the perceived advantages and disadvantages of the new tool. We used a template approach to identify dominant themes in interview responses. From these themes, we defined 5 statements, which were then rated on Likert scales in a questionnaire. ResultsWe interviewed 77 participants and 23 completed the survey. We identified 9 frequently mentioned topics by analyzing the interview responses. The most common themes were “positive design features,” “intuitive and easy to learn,” and “lack of a quantitative component.” In the survey, 21 respondents agreed that Visual Clot is easy to learn and 16 respondents stated that a combination of Visual Clot and ROTEM would help them manage complex hemostatic situations. ConclusionsA group of anesthesia care providers found Visual Clot well-designed, intuitive, and easy to learn. Participants highlighted its usefulness in emergencies, especially for clinicians inexperienced in coagulation management. However, the lack of quantitative information is an area for improvement.

Zdeněk Kejík, Jan Hajduch, Nikita Abramenko et al.

Abstract Mitochondrial dysregulation plays a significant role in the carcinogenesis. On the other hand, its destabilization strongly represses the viability and metastatic potential of cancer cells. Photodynamic and photothermal therapies (PDT and PTT) target mitochondria effectively, providing innovative and non-invasive anticancer therapeutic modalities. Cyanine dyes, with strong mitochondrial selectivity, show significant potential in enhancing PDT and PTT. The potential and limitations of cyanine dyes for mitochondrial PDT and PTT are discussed, along with their applications in combination therapies, theranostic techniques, and optimal delivery systems. Additionally, novel approaches for sonodynamic therapy using photoactive cyanine dyes are presented, highlighting advances in cancer treatment.

Chenfei Dong, Yue Zhang, Jiayue Zeng et al.

Abstract Colorectal cancer (CRC) ranks as the second most lethal cancer worldwide because of its high rate of metastasis, and approximately 20% of CRC patients have metastases at initial diagnosis. Metabolic reprogramming, a hallmark of cancer cells, has been implicated in the process of metastasis. We previously demonstrated that fucosyltransferase 2 (FUT2) promotes the malignancy of CRC cells, however, the underlying mechanisms remain unclear. Here, bioinformatic analysis revealed that FUT2 is associated with the malignant phenotype and fatty acid metabolism in CRC. FUT2 knockdown decreased glucose uptake and de novo fatty acid synthesis, which in turn inhibited the proliferation and metastasis of CRC cells. Mechanistically, FUT2 promotes YAP1 nuclear translocation and stabilizes mSREBP-1 by fucosylation, thus promoting de novo fatty acid synthesis in CRC cells. In summary, this study demonstrates that FUT2 promotes the proliferation and metastasis of CRC cells by reprogramming fatty acid metabolism via YAP/TAZ signaling and SREBP-1, indicating that FUT2 might be a potential target for developing therapeutic strategies against CRC.

Fatoş Dilan Köseoğlu, Bülent Özlek

Aims: The aim of this study was to assess the prevalence of anemia and iron deficiency in patients with heart failure with preserved ejection fraction (HFpEF) and its impact on clinical outcomes. Methods: We retrospectively analyzed 212 patients with HFpEF and identified anemia as a serum hemoglobin level of less than 13 g/dL in men and less than 12 g/dL in women. Additionally, ID was defined as a serum ferritin concentration < 100 ng/mL or 100–299 ng/mL with transferrin saturation < 20%. Patients were followed up for an average of 66.2 ± 12.1 months, with the endpoint being all-cause mortality among patients with HFpEF, both with and without anemia and iron deficiency. Furthermore, we explored other predictors of all-cause mortality. Results: The average age of the entire group was 70.6 ± 10.5 years, with females comprising 55% of the patients. Anemia was present in 81 (38.2%) patients, while 108 (50.9%) had iron deficiency. At the end of the follow-up period, 60 (28.3%) of the patients had passed away. Patients with anemia displayed more heart failure (HF) symptoms, diastolic dysfunction, higher NT-pro-BNP levels, and worse baseline functional capacity than those without. Similarly, patients with iron deficiency showed more pronounced HF symptoms and worse functional capacity than those without. The results from the multivariable analyses revealed that anemia (hazard ratio [HR]: 5.401, 95% confidence interval [CI]: 4.303–6.209, log-rank <i>p</i> = 0.001), advanced age, iron deficiency (HR: 3.502, 95% CI: 2.204–6.701, log-rank <i>p</i> = 0.015), decreased left ventricular ejection fraction, chronic kidney disease, and paroxysmal nocturnal dyspnea were all independently associated with all-cause mortality. Conclusions: It is essential to consider anemia and iron deficiency as common comorbidities in managing and prognosis HFpEF, as they significantly increase mortality risk.

Haoran Zhang, Yuwei Wang, Yaping Zhang et al.

Abstract Background Housing has been associated with dementia risk and disability, but associations of housing with differential patterns of neuropsychiatric symptoms (NPS) among dementia-free older adults remain to be explored. The present study sought to explore the contribution of housing status on NPS and subsyndromes associated with cognitive dysfunction in community-dwelling dementia-free elderly in Singapore. Methods A total of 839 dementia-free elderly from the Epidemiology of Dementia in Singapore (EDIS) study aged ≥ 60 were enrolled in the current study. All participants underwent clinical, cognitive, and neuropsychiatric inventory (NPI) assessments. The housing status was divided into three categories according to housing type. Cognitive function was measured by a comprehensive neuropsychological battery. The NPS were assessed using 12-term NPI and were grouped into four clinical subsyndromes: psychosis, hyperactivity, affective, and apathy. Associations of housing with composite and domain-specific Z-scores, as well as NPI scores, were assessed using generalized linear models (GLM). Binary logistic regression models analysed the association of housing with the presence of NPS and significant NPS (NPI total scores ≥ 4). Results Better housing status (5-room executive apartments, condominium, or private housing) was associated with better NPS (OR = 0.49, 95%CI = 0.24 to 0.98, P < 0.05) and significant NPS profile (OR = 0.20, 95%CI = 0.08 to 0.46, P < 0.01), after controlling for demographics, risk factors, and cognitive performance. Compared with those living in 1–2 room apartments, older adults in better housing had lower total NPI scores (β=-0.50, 95%CI=-0.95 to -0.04, P = 0.032) and lower psychosis scores (β=-0.36, 95%CI=-0.66 to -0.05, P = 0.025), after controlling for socioeconomic status (SES) indexes. Subgroup analysis indicated a significant correlation between housing type and NPS in females, those of Malay ethnicity, the more educated, those with lower income, and those diagnosed with cognitive impairment, no dementia (CIND). Conclusions Our study showed a protective effect of better housing arrangements on NPS, especially psychosis in a multi-ethnic Asian geriatric population without dementia. The protective effect of housing on NPS was independent of SES and might have other pathogenic mechanisms. Improving housing could be an effective way to prevent neuropsychiatric disturbance among the elderly.

Afsha Fatima Qadri, Sibhghatulla Shaikh, Ye Chan Hwang et al.

Glycyrrhiza uralensis is a traditional herbal medicine with significant bioactivity. This study investigated the effect of G. uralensis crude water extract (GU-CWE) on nitric oxide synthase 2 (NOS2) expression during myogenesis. GU-CWE treatment increased myoblast differentiation by downregulating NOS2 and upregulating myogenic regulatory factors (MYOD, MYOG, and MYH). Notably, this effect was supported by an observed decrease in NOS2 expression in the gastrocnemius tissues of mice treated with GU-CWE. In addition, GU-CWE treatment and NOS2 knockdown were associated with reductions in reactive oxygen species levels. We further elucidate the role of the NOS2 gene in myoblast differentiation, demonstrating that its role was expression dependent, being beneficial at low expression but detrimental at high expression. High NOS2 gene expression induced oxidative stress, whereas its low expression impaired myotube formation. These findings highlight that the modulation of NOS2 expression by G. uralensis can potentially be use for managing muscle wasting disorders.

Weiwei Lai, Wanshan Hu, Yinming Liang et al.

Zeraoulia Rafik, Alvaro humberto Salas, Lorenzo Martinez

Recently, mathematicians have been interested in studying the theory of discrete dynamical system, specifically difference equation, such that considerable works about discussing the behavior properties of its solutions (boundedness and unboundedness) are discussed and published in many areas of mathematics which involves several interesting results and applications in applied mathematics and physics ,One of the most important discrete dynamics which is become of interest for researchers in the field is the rational dynamical system .In this paper we may discuss qualitative behavior and properties of the difference equation $x_{n+1}=ax^2_{n}+bx^2_{n-1}$ with $a$ and $b$ are two parameters and we shall show its application to medicine.

Mathieu Chevalier, Pablo Tedesco, Gael Grenouillet

Background Population dynamics are driven by a number of biotic (e.g., density-dependence) and abiotic (e.g., climate) factors whose contribution can greatly vary across study systems (i.e., populations). Yet, the extent to which the contribution of these factors varies across populations and between species and whether spatial patterns can be identified has received little attention. Methods Here, we used a long-term (1982–2011), broad scale (182 sites distributed across metropolitan France) dataset to study spatial patterns in the population’s dynamics of three freshwater fish species presenting contrasted life-histories and patterns of elevation range shifts in recent decades. We used a hierarchical Bayesian approach together with an elasticity analysis to estimate the relative contribution of a set of biotic (e.g., strength of density dependence, recruitment rate) and abiotic (mean and variability of water temperature) factors affecting the site-specific dynamic of two different size classes (0+ and >0+ individuals) for the three species. We then tested whether the local contribution of each factor presented evidence for biogeographical patterns by confronting two non-mutually exclusive hypotheses: the “range-shift” hypothesis that predicts a gradient along elevation or latitude and the “abundant-center” hypothesis that predicts a gradient from the center to the edge of the species’ distributional range. Results Despite contrasted life-histories, the three species displayed similar large-scale patterns in population dynamics with a much stronger contribution of biotic factors over abiotic ones. Yet, the contribution of the different factors strongly varied within distributional ranges and followed distinct spatial patterns. Indeed, while abiotic factors mostly varied along elevation, biotic factors—which disproportionately contributed to population dynamics—varied along both elevation and latitude. Conclusions Overall while our results provide stronger support for the range-shift hypothesis, they also highlight the dual effect of distinct factors on spatial patterns in population dynamics and can explain the overall difficulty to find general evidence for geographic gradients in natural populations. We propose that considering the separate contribution of the factors affecting population dynamics could help better understand the drivers of abundance-distribution patterns.

Adolfo Jara, Pooja Lepcha, Sankyun Kim et al.

This article presents a database containing on-orbit data samples of the Electrical Power System (EPS) from 4 different 1U CubeSats belonging to the BIRDS constellation. The EPS is responsible for providing uninterrupted power to overall satellite both during sunlight and eclipse. The satellites are based on the BIRDS open-source standardized bus designed by Kyutech for research and education. BIRDS bus was used for six satellites that were delivered to ISS on board the Cygnus re-supply spacecraft launched by Antares rocket and released from International Space Station (ISS) into ISS orbit (altitude 400 km, inclination: 51.6°, duration: 92.6 min). The dataset contains the data of voltage (mV), current (mA) and temperature (Celsius) of the battery and solar panels attached to 5 sides of the satellite. This data is collected by the on-board computer every 90 seconds in nominal operation or every 10 seconds in fast sampling mode. The data is downloaded from the satellite memory by the ground station operators. Next, space engineering experts from Kyushu Institute of Technology have analysed the dataset to classify each data sample into normal or anomaly classes. This paper provides one datafile per satellite, that includes data from solar panels and battery since their deployment into orbit until the end of its life for the UGUISU, RAAVANA, and NEPALISAT satellites, first two showing a failure in one of their panels during more than two years of operation on-orbit. The TSURU satellite dataset includes data since its deployment into orbit and will continue to be collected until the end of its life. The dataset generated will be useful for 1U CubeSat, such as BIRDS platform, users, and satellite developers by using it as a reference to compare the behaviour of their Electric Power System under different operating scenarios and align their missions according to the available power on-orbit. At the same time, the dataset can help computer science researchers to build and validate new models for fault diagnosis and outlier detection.

Yaoda Xu, Maryam Vaziri-Pashkam

Forming transformation-tolerant object representations is critical to high-level primate vision. Despite its significance, many details of tolerance in the human brain remain unknown. Likewise, despite the ability of convolutional neural networks (CNNs) to exhibit human-like object categorization performance, whether CNNs form tolerance similar to that of the human brain is unknown. Here we provide the first comprehensive documentation and comparison of three tolerance measures in the human brain and CNNs. We measured fMRI responses from human ventral visual areas to real-world objects across both Euclidean and non-Euclidean feature changes. In single fMRI voxels in higher visual areas, we observed robust object response rank-order preservation across feature changes. This is indicative of functional smoothness in tolerance at the fMRI meso-scale level that has never been reported before. At the voxel population level, we found highly consistent object representational structure across feature changes towards the end of ventral processing. Rank-order preservation, consistency, and a third tolerance measure, cross-decoding success (i.e., a linear classifier's ability to generalize performance across feature changes) showed an overall tight coupling. These tolerance measures were in general lower for Euclidean than non-Euclidean feature changes in lower visual areas, but increased over the course of ventral processing for all feature changes. These characteristics of tolerance, however, were absent in eight CNNs pretrained with ImageNet images with varying network architecture, depth, the presence/absence of recurrent processing, or whether a network was pretrained with the original or stylized ImageNet images that encouraged shape processing. CNNs do not appear to develop the same kind of tolerance as the human brain over the course of visual processing.

Katarzyna Wódka, Alicja Michalczyk, Agnieszka Jankowicz-Szymańska

Aim of the study: The aim of the study was to assess the relationship between the position of the sacrum, lumbar and thoracic spine and the mobility of the trunk in the sagittal plane in young women and men. Material and methods: 64 students (33 women and 31 men) were studied. The mean age in the study group was 22.94 ± 1.51 years. The following tests were performed on each subject once: measurement of height and weight, assessment of spinal alignment and mobility in the sagittal plane using Zebris Pointer. Results: The results obtained were analyzed using appropriate statistical tools. Statistically significant correlations were obtained: in the alignment of the sacrum in relation to the lumbar spine (strong correlation), in the alignment of the lumbar spine in relation to the thoracic spine and, in the male group only, between the alignment of the thoracic spine and mobility in the direction of flexion in the thoracic segment (moderate correlation). Conclusions: In women, horizontal sacral alignment coexisting with deepened lordosis was most frequently observed. In addition, women were more likely to have a deepened thoracic kyphosis, less range of motion in the direction of thoracic flexion and extension, and greater mobility in the direction of lumbar flexion and extension than men. In men, the vertical alignment of the sacrum was accompanied by a shallowing of the physiological lordosis. In addition, in this group, a decrease in lordosis influenced an increase in movement to flexion in the thoracic spine. When planning a physiotherapy exercise program for a person in whom abnormalities in the alignment of the lumbopelvic complex have been noted, an individual exercise program should be selected. The study should take into account not only the evaluation of the alignment of the lumbosacral spine, but also the mobility of the segments above and below the examined area taking into account intergender differences.