Hasil untuk "Diseases of the endocrine glands. Clinical endocrinology"

Chaeeun Lee, T. Michael Yates, Pasquale Minervini et al.

Clinical decision-making requires nuanced reasoning over heterogeneous evidence and traceable justifications. While recent LLM multi-agent systems (MAS) show promise, they largely optimise for outcome accuracy while overlooking process-grounded reasoning aligned with clinical standards. One critical real-world case of this is gene-disease validity curation, where experts must determine whether a gene is causally implicated in a disease by synthesising diverse biomedical evidence. We introduce an agent-as-tool reinforcement learning framework for this task with two objectives: (i) process-level supervision to ensure reasoning follows valid clinical pathways, and (ii) efficient coordination via a hierarchical multi-agent system. Our evaluation on the ClinGen dataset shows that with outcome-only rewards, MAS with a GRPO-trained Qwen3-4B supervisor agent substantially improves final outcome accuracy from 0.195 with a base model supervisor to 0.732, but results in poor process alignment (0.392 F1). Conversely, with process + outcome rewards, MAS with GRPO-trained supervisor achieves higher outcome accuracy (0.750) while significantly improving process fidelity to 0.520 F1. Our code is available at https://github.com/chaeeunlee-io/GeneDiseaseCurationAgents.

Ishaan Mahapatra, Nihar R. Mahapatra

Voice biomarkers--human-generated acoustic signals such as speech, coughing, and breathing--are promising tools for scalable, non-invasive detection and monitoring of mental health and neurodegenerative diseases. Yet, their clinical adoption remains constrained by inconsistent quality and limited usability of publicly available datasets. To address this gap, we present the first systematic FAIR (Findable, Accessible, Interoperable, Reusable) evaluation of 27 publicly available voice biomarker datasets focused on these disease areas. Using the FAIR Data Maturity Model and a structured, priority-weighted scoring method, we assessed FAIRness at subprinciple, principle, and composite levels. Our analysis revealed consistently high Findability but substantial variability and weaknesses in Accessibility, Interoperability, and Reusability. Mental health datasets exhibited greater variability in FAIR scores, while neurodegenerative datasets were slightly more consistent. Repository choice also significantly influenced FAIRness scores. To enhance dataset quality and clinical utility, we recommend adopting structured, domain-specific metadata standards, prioritizing FAIR-compliant repositories, and routinely applying structured FAIR evaluation frameworks. These findings provide actionable guidance to improve dataset interoperability and reuse, thereby accelerating the clinical translation of voice biomarker technologies.

Pascal Helson, Arvind Kumar

Despite the diversity and volume of brain data acquired and advanced AI-based algorithms to analyze them, brain features are rarely used in clinics for diagnosis and prognosis. Here we argue that the field continues to rely on cohort comparisons to seek biomarkers, despite the well-established degeneracy of brain features. Using a thought experiment (Brain Swap), we show that more data and more powerful algorithms will not be sufficient to identify biomarkers of brain diseases. We argue that instead of comparing patient versus healthy controls using single data type, we should use multimodal (e.g. brain activity, neurotransmitters, neuromodulators, brain imaging) and longitudinal brain data to guide the grouping before defining multidimensional biomarkers for brain diseases.

Loan Dao, Ngoc Quoc Ly

Medical artificial intelligence (AI) systems frequently lack systematic domain expertise integration, potentially compromising diagnostic reliability. This study presents an ontology-based framework for bone disease diagnosis, developed in collaboration with Ho Chi Minh City Hospital for Traumatology and Orthopedics. The framework introduces three theoretical contributions: (1) a hierarchical neural network architecture guided by bone disease ontology for segmentation-classification tasks, incorporating Visual Language Models (VLMs) through prompts, (2) an ontology-enhanced Visual Question Answering (VQA) system for clinical reasoning, and (3) a multimodal deep learning model that integrates imaging, clinical, and laboratory data through ontological relationships. The methodology maintains clinical interpretability through systematic knowledge digitization, standardized medical terminology mapping, and modular architecture design. The framework demonstrates potential for extension beyond bone diseases through its standardized structure and reusable components. While theoretical foundations are established, experimental validation remains pending due to current dataset and computational resource limitations. Future work will focus on expanding the clinical dataset and conducting comprehensive system validation.

Maya Kruse, Shiyue Hu, Nicholas Derby et al.

Recent advances in large language models (LLMs) have shown potential in clinical text summarization, but their ability to handle long patient trajectories with multi-modal data spread across time remains underexplored. This study systematically evaluates several state-of-the-art open-source LLMs, their Retrieval Augmented Generation (RAG) variants and chain-of-thought (CoT) prompting on long-context clinical summarization and prediction. We examine their ability to synthesize structured and unstructured Electronic Health Records (EHR) data while reasoning over temporal coherence, by re-engineering existing tasks, including discharge summarization and diagnosis prediction from two publicly available EHR datasets. Our results indicate that long context windows improve input integration but do not consistently enhance clinical reasoning, and LLMs are still struggling with temporal progression and rare disease prediction. While RAG shows improvements in hallucination in some cases, it does not fully address these limitations. Our work fills the gap in long clinical text summarization, establishing a foundation for evaluating LLMs with multi-modal data and temporal reasoning.

Lizbeth T. Arias-Pacheco, Tatiana M. Villacrés-Landeta, Edgar V. Mora-Brito

Antecedentes: La diabetes mellitus 2 (DM2) afecta la salud pública y la economía, especialmente de los países con ingresos medios y bajos, como Ecuador. Su alta prevalencia, complicaciones frecuentes y crecientes costos sanitarios, generan una carga social y económica significativa para el paciente, sus familias y los sistemas que la financian. La prevención y atención primaria son clave para reducir el impacto. Objetivo: Estimar el costo integral de la diabetes mellitus tipo 2 (DM2) y sus complicaciones en Ecuador. Método: Se realizó un microcosteo de la atención integral de la DM2 por fases utilizando el Tarifario de Prestaciones del Sistema Nacional de Salud, según la Guía de Práctica Clínica del Ministerio de Salud Pública, con valoración del médico experto y estandarización con estadígrafos. Las complicaciones fueron costeadas bajo la misma metodología, con énfasis en la práctica clínica habitual. Resultados: El costo de la DM2 en la región guarda relación con Ecuador, con un costo estándar por paciente de $9619.41, $31,751.76 por pie diabético y $5879.26 por retinopatía diabética, y un costo integral de $11,704.38 (incluye complicaciones) en dólares internacionales. Incorporando una tasa de prevalencia del 5.5%, el costo del tratamiento de la DM2 más sus complicaciones fue de $11,565.81 millones de dólares internacionales, demostrando que el esquema preventivo es más costo-efectivo, con una estimación de $295.67 millones de dólares internacionales para la prevención de la población con factores de riesgo. Conclusiones: La estrategia frente al alto costo es el planteamiento de una política pública que modifique los lineamientos del Manual de Atención Integral de Salud orientándose hacia un enfoque preventivo para la reducción de factores de riesgo.

Leila Yazdanpanah, Hajieh Shahbazian, Saeed Hesam et al.

Abstract Aim/Introduction This study was designed as the second phase of a prospective cohort study to evaluate the incidence and risk factors of diabetic foot ulcers (DFU). Materials and methods The study was conducted in a university hospital in Iran. Each participant was checked and followed up for two years in terms of developing newfound DFU as ultimate outcome. We investigated the variables using univariate analysis and then by backward elimination multiple logistic regression. Results We followed up 901 eligible patients with diabetes for two years. The mean age of the participants was 53.24 ± 11.46 years, and 58.53% of them were female. The two-year cumulative incidence of diabetic foot ulcer was 8% (95% CI 0.071, 0.089) [Incidence rate: 49.9 /1000 person-years]. However, the second-year incidence which was coincident with the COVID-19 pandemic was higher than the first-year incidence (4.18% and 1.8%, respectively). Based on our analysis, the following variables were the main risk factors for DFU incidence: former history of DFU or amputation [OR = 76.5, 95% CI(33.45,174.97), P value < 0.001], ill-fitting foot-wear [OR = 10.38, 95% CI(4.47,24.12), P value < 0.001], smoking [OR = 3.87,95%CI(1.28, 11.71),P value = 0.016], lack of preventive foot care [OR = 2.91%CI(1.02,8.29),P value = 0.045], and insufficient physical activity[OR = 2.25,95% CI(0.95,5.35),P value = 0.066]. Conclusion Overall, the two-year cumulative incidence of diabetic foot ulcer was 8% [Incidence rate: 49.9 /1000 person-years]; however, the second-year incidence was higher than the first-year incidence which was coincident with the COVID-19 pandemic (4.18% and 1.8%, respectively). Independent risk factors of DFU occurrence were prior history of DFU or amputation, ill-fitting footwear, smoking, lack of preventive foot care, and insufficient physical activity.

Allen Yang, Edward Yang

According to PBS, nearly one-third of Americans lack access to primary care services, and another forty percent delay going to avoid medical costs. As a result, many diseases are left undiagnosed and untreated, even if the disease shows many physical symptoms on the skin. With the rise of AI, self-diagnosis and improved disease recognition have become more promising than ever; in spite of that, existing methods suffer from a lack of large-scale patient databases and outdated methods of study, resulting in studies being limited to only a few diseases or modalities. This study incorporates readily available and easily accessible patient information via image and text for skin disease classification on a new dataset of 26 skin disease types that includes both skin disease images (37K) and associated patient narratives. Using this dataset, baselines for various image models were established that outperform existing methods. Initially, the Resnet-50 model was only able to achieve an accuracy of 70% but, after various optimization techniques, the accuracy was improved to 80%. In addition, this study proposes a novel fine-tuning strategy for sequence classification Large Language Models (LLMs), Chain of Options, which breaks down a complex reasoning task into intermediate steps at training time instead of inference. With Chain of Options and preliminary disease recommendations from the image model, this method achieves state of the art accuracy 91% in diagnosing patient skin disease given just an image of the afflicted area as well as a patient description of the symptoms (such as itchiness or dizziness). Through this research, an earlier diagnosis of skin diseases can occur, and clinicians can work with deep learning models to give a more accurate diagnosis, improving quality of life and saving lives.

Maxime Wack, Adrien Coulet, Anita Burgun et al.

Background. Clinical data warehouses (CDWs) are essential in the reuse of hospital data in observational studies or predictive modeling. However, state of-the-art CDW systems present two drawbacks. First, they do not support the management of large data files, what is critical in medical genomics, radiology, digital pathology, and other domains where such files are generated. Second, they do not provide provenance management or means to represent longitudinal relationships between patient events. Indeed, a disease diagnosis and its follow-up rely on multiple analyses. In these cases no relationship between the data (e.g., a large file) and its associated analysis and decision can be documented.Method. We introduce gitOmmix, an approach that overcomes these limitations, and illustrate its usefulness in the management of medical omics data. gitOmmix relies on (i) a file versioning system: git, (ii) an extension that handles large files: git-annex, (iii) a provenance knowledge graph: PROV-O, and (iv) an alignment between the git versioning information and the provenance knowledge graph.Results. Capabilities inherited from git and git-annex enable retracing the history of a clinical interpretation back to the patient sample, through supporting data and analyses. In addition, the provenance knowledge graph, aligned with the git versioning information, enables querying and browsing provenance relationships between these elements.Conclusion. gitOmmix adds a provenance layer to CDWs, while scaling to large files and being agnostic of the CDW system. For these reasons, we think that it is a viable and generalizable solution for omics clinical studies.

Karthik Gopinath, Douglas N. Greve, Sudeshna Das et al.

Surface analysis of the cortex is ubiquitous in human neuroimaging with MRI, e.g., for cortical registration, parcellation, or thickness estimation. The convoluted cortical geometry requires isotropic scans (e.g., 1mm MPRAGEs) and good gray-white matter contrast for 3D reconstruction. This precludes the analysis of most brain MRI scans acquired for clinical purposes. Analyzing such scans would enable neuroimaging studies with sample sizes that cannot be achieved with current research datasets, particularly for underrepresented populations and rare diseases. Here we present the first method for cortical reconstruction, registration, parcellation, and thickness estimation for clinical brain MRI scans of any resolution and pulse sequence. The methods has a learning component and a classical optimization module. The former uses domain randomization to train a CNN that predicts an implicit representation of the white matter and pial surfaces (a signed distance function) at 1mm isotropic resolution, independently of the pulse sequence and resolution of the input. The latter uses geometry processing to place the surfaces while accurately satisfying topological and geometric constraints, thus enabling subsequent parcellation and thickness estimation with existing methods. We present results on 5mm axial FLAIR scans from ADNI and on a highly heterogeneous clinical dataset with 5,000 scans. Code and data are publicly available at https://surfer.nmr.mgh.harvard.edu/fswiki/recon-all-clinical

Jihen Amara, Birgitta König-Ries, Sheeba Samuel

Plant diseases remain a considerable threat to food security and agricultural sustainability. Rapid and early identification of these diseases has become a significant concern motivating several studies to rely on the increasing global digitalization and the recent advances in computer vision based on deep learning. In fact, plant disease classification based on deep convolutional neural networks has shown impressive performance. However, these methods have yet to be adopted globally due to concerns regarding their robustness, transparency, and the lack of explainability compared with their human experts counterparts. Methods such as saliency-based approaches associating the network output to perturbations of the input pixels have been proposed to give insights into these algorithms. Still, they are not easily comprehensible and not intuitive for human users and are threatened by bias. In this work, we deploy a method called Testing with Concept Activation Vectors (TCAV) that shifts the focus from pixels to user-defined concepts. To the best of our knowledge, our paper is the first to employ this method in the field of plant disease classification. Important concepts such as color, texture and disease related concepts were analyzed. The results suggest that concept-based explanation methods can significantly benefit automated plant disease identification.

Ilker Uçkay, Madlaina Schöni, Martin C. Berli et al.

Abstract We investigated if a chronic, enhanced immunosuppressed condition, beyond the immunodeficiency related to diabetes, is associated with clinical failures after combined surgical and medical treatment for diabetic foot infection (DFI). This is a case‐control cohort study in a tertiary centre for diabetic foot problems, using case‐mix adjustments with multivariate Cox regression models. Among 1013 DFI episodes in 586 patients (median age 67 years; 882 with osteomyelitis), we identified a chronic, enhanced immune‐suppression condition in 388 (38%) cases: dialysis (85), solid organ transplantation (25), immune‐suppressive medication (70), cirrhosis (9), cancer chemotherapy (15) and alcohol abuse (243). Overall, 255 treatment episodes failed (25%). By multivariate analysis, the presence (as compared with absence) of chronic, enhanced immune‐suppression was associated with a higher rate of clinical failures in DFI cases (hazard ratio 1.5, 95% confidence interval 1.1–2.0). We conclude that a chronic, enhanced immune‐suppressed state might be an independent risk factor for treatment failure in DFI. Validation of this hypothesis could be useful information for both affected patients and their treating clinicians.

Jose Augusto Sgarbi, Celia Regina Nogueira, Gabriela Brenta et al.

Benjamin Udoka Nwosu

Despite advances in the characterization of partial clinical remission (PR) of type 1 diabetes, an accurate definition of PR remains problematic. Two recent studies in children with new-onset T1D demonstrated serious limitations of the present gold standard definition of PR, a stimulated C-peptide (SCP) concentration of &gt;300 pmol/L. The first study employed the concept of insulin sensitivity score (ISS) to show that 55% of subjects with new-onset T1D and a detectable SCP level of &gt;300 pmol/L had low insulin sensitivity (IS) and thus might not be in remission when assessed by insulin-dose adjusted A1c (IDAA1c), an acceptable clinical marker of PR. The second study, a randomized controlled trial of vitamin D (ergocalciferol) administration in children and adolescents with new-onset T1D, demonstrated no significant difference in SCP between the ergocalciferol and placebo groups, but showed a significant blunting of the temporal trend in both A1c and IDAA1c in the ergocalciferol group. These two recent studies indicate the poor specificity and sensitivity of SCP to adequately characterize PR and thus call for a re-examination of current approaches to the definition of PR. They demonstrate the limited sensitivity of SCP, a static biochemical test, to detect the complex physiological changes that occur during PR such as changes in insulin sensitivity, insulin requirements, body weight, and physical activity. These shortcomings call for a broader definition of PR using a combination of functional markers such as IDAA1c and ISS to provide a valid assessment of PR that reaches beyond the static changes in SCP alone.

Yingdi Yuan, Ying Li, Lingmin Hu et al.

IntroductionExosomes are cell-derived vesicles that are present in many biological fluids. Exosomal RNAs in cord blood may allow intercellular communication between mother and fetus. We aimed to establish exosomal RNA expression profiles in cord blood from patients with gestational diabetes mellitus and macrosomia (GDM-M) and evaluate their prediction performance.MethodsWe used microarray technology to establish the differential messenger RNA (mRNA), long non-coding RNA (lncRNA), and circular RNA (circRNA) expression profiles in cord blood exosomes from 3 patients with GDM-M compared with 3 patients with GDM and normal neonatal weight, followed by qPCR validation in an additional 40 patients with GDM. Logistic regression, receiver operating characteristic (ROC) curves, and graphical nomogram were applied to evaluate the performance of exosomal RNA (in peripheral blood) in macrosomia prediction.ResultsA total of 98 mRNAs, 372 lncRNAs, and 452 circRNAs were differentially expressed in cord blood exosomes from patients with GDM-M. Pathway analysis based on screening data showed that the differential genes were associated with Phosphatidylinositol 3'-kinase (PI3acK)-Akt signaling pathway, Janus kinase/signal transducers and activators of transcription (JAK/STAT) signaling pathway, Transforming growth factor (TGF)-beta signaling pathway, insulin resistance, glycerolipid metabolism, fatty acid degradation, and mammalian target of rapamycin (mTOR) signaling pathway. After validation by qPCR, the expressions of GDF3, PROM1, AC006064.4, lnc-HPS6-1:1, and circ_0014635 were significantly increased and the expression of lnc-ZFHX3-7:1 was significantly decreased in cord blood exosomes of an additional 20 patients with GDM-M. The risk prediction performance of the expression of these validated genes (in peripheral blood exosomes) for GDM-related macrosomia was also evaluated. Only GDF3 expression and AC006064.4 expression showed well prediction performance [area under the curve (AUC) = 0.78 and 0.74, respectively]. Excitingly, the model including maternal age, fasting plasma glucose, 2-h plasma glucose, GDF3 expression, and AC006064.4 expression in peripheral blood exosomes had better prediction performance with an AUC of 0.86 (95% CI = 0.75–0.97).ConclusionThese results showed that exosomal RNAs are aberrantly expressed in the cord blood of patients with GDM-M and highlighted the importance of exosomal RNAs in peripheral blood for GDM-M prediction.

Leonardo Rossi, Marco Valenti, Sara Elisabetta Legler et al.

The Instance Segmentation task, an extension of the well-known Object Detection task, is of great help in many areas, such as precision agriculture: being able to automatically identify plant organs and the possible diseases associated with them, allows to effectively scale and automate crop monitoring and its diseases control. To address the problem related to early disease detection and diagnosis on vines plants, a new dataset has been created with the goal of advancing the state-of-the-art of diseases recognition via instance segmentation approaches. This was achieved by gathering images of leaves and clusters of grapes affected by diseases in their natural context. The dataset contains photos of 10 object types which include leaves and grapes with and without symptoms of the eight more common grape diseases, with a total of 17,706 labeled instances in 1,092 images. Multiple statistical measures are proposed in order to offer a complete view on the characteristics of the dataset. Preliminary results for the object detection and instance segmentation tasks reached by the models Mask R-CNN and R^3-CNN are provided as baseline, demonstrating that the procedure is able to reach promising results about the objective of automatic diseases' symptoms recognition.

Petchiammal A, Briskline Kiruba S, D. Murugan

Agriculture is the mainstay of human society because it is an essential need for every organism. Paddy cultivation is very significant so far as humans are concerned, largely in the Asian continent, and it is one of the staple foods. However, plant diseases in agriculture lead to depletion in productivity. Plant diseases are generally caused by pests, insects, and pathogens that decrease productivity to a large scale if not controlled within a particular time. Eventually, one cannot see an increase in paddy yield. Accurate and timely identification of plant diseases can help farmers mitigate losses due to pests and diseases. Recently, deep learning techniques have been used to identify paddy diseases and overcome these problems. This paper implements a convolutional neural network (CNN) based on a model and tests a public dataset consisting of 636 infrared image samples with five paddy disease classes and one healthy class. The proposed model proficiently identified and classified paddy diseases of five different types and achieved an accuracy of 88.28%

Jingqing Zhang, Atri Sharma, Luis Bolanos et al.

Clinicians may rely on medical coding systems such as International Classification of Diseases (ICD) to identify patients with diseases from Electronic Health Records (EHRs). However, due to the lack of detail and specificity as well as a probability of miscoding, recent studies suggest the ICD codes often cannot characterise patients accurately for specific diseases in real clinical practice, and as a result, using them to find patients for studies or trials can result in high failure rates and missing out on uncoded patients. Manual inspection of all patients at scale is not feasible as it is highly costly and slow. This paper proposes a scalable workflow which leverages both structured data and unstructured textual notes from EHRs with techniques including NLP, AutoML and Clinician-in-the-Loop mechanism to build machine learning classifiers to identify patients at scale with given diseases, especially those who might currently be miscoded or missed by ICD codes. Case studies in the MIMIC-III dataset were conducted where the proposed workflow demonstrates a higher classification performance in terms of F1 scores compared to simply using ICD codes on gold testing subset to identify patients with Ovarian Cancer (0.901 vs 0.814), Lung Cancer (0.859 vs 0.828), Cancer Cachexia (0.862 vs 0.650), and Lupus Nephritis (0.959 vs 0.855). Also, the proposed workflow that leverages unstructured notes consistently outperforms the baseline that uses structured data only with an increase of F1 (Ovarian Cancer 0.901 vs 0.719, Lung Cancer 0.859 vs 0.787, Cancer Cachexia 0.862 vs 0.838 and Lupus Nephritis 0.959 vs 0.785). Experiments on the large testing set also demonstrate the proposed workflow can find more patients who are miscoded or missed by ICD codes. Moreover, interpretability studies are also conducted to clinically validate the top impact features of the classifiers.

Irfan Al-Hussaini, Davi Nakajima An, Albert J. Lee et al.

Clinical Cohort Studies (CCS), such as randomized clinical trials, are a great source of documented clinical research. Ideally, a clinical expert inspects these articles for exploratory analysis ranging from drug discovery for evaluating the efficacy of existing drugs in tackling emerging diseases to the first test of newly developed drugs. However, more than 100 articles are published daily on a single prevalent disease like COVID-19 in PubMed. As a result, it can take days for a physician to find articles and extract relevant information. Can we develop a system to sift through the long list of these articles faster and document the crucial takeaways from each of these articles? In this work, we propose CCS Explorer, an end-to-end system for relevance prediction of sentences, extractive summarization, and patient, outcome, and intervention entity detection from CCS. CCS Explorer is packaged in a web-based graphical user interface where the user can provide any disease name. CCS Explorer then extracts and aggregates all relevant information from articles on PubMed based on the results of an automatically generated query produced on the back-end. For each task, CCS Explorer fine-tunes pre-trained language representation models based on transformers with additional layers. The models are evaluated using two publicly available datasets. CCS Explorer obtains a recall of 80.2%, AUC-ROC of 0.843, and an accuracy of 88.3% on sentence relevance prediction using BioBERT and achieves an average Micro F1-Score of 77.8% on Patient, Intervention, Outcome detection (PIO) using PubMedBERT. Thus, CCS Explorer can reliably extract relevant information to summarize articles, saving time by $\sim \text{660}\times$.

Osamu Wada-Hiraike

Endometriosis, characterized by macroscopic lesions in the ovaries, is a serious problem for women who desire conception. Damage to the ovarian cortex is inevitable when lesions are removed via surgery, which finally decreases the ovarian reserve, thereby accelerating the transition to the menopausal state. Soon after cessation of ovarian function, in addition to climacteric symptoms, dyslipidemia and osteopenia are known to occur in women aged >50 years. Epidemiologically, there are sex-related differences in the frequencies of dyslipidemia, hypertension, and osteoporosis. Females are more susceptible to these diseases, prevention of which is important for healthy life expectancy. Dyslipidemia and hypertension are associated with the progression of arteriosclerosis, and arteriosclerotic changes in the large and middle blood vessels are one of the main causes of myocardial and cerebral infarctions. Osteoporosis is associated with aberrant fractures in the spine and hip, which may confine the patients to the bed for long durations. Bone resorption is accelerated by activated osteoclasts, and rapid bone remodeling reduces bone mineral density. Resveratrol, a plant-derived molecule that promotes the function and expression of the sirtuin, SIRT1, has been attracting attention, and many reports have shown that resveratrol might exert cardiovascular protective effects. Preclinical reports also indicate that it can prevent bone loss and endometriosis. In this review, I have described the possible protective effects of resveratrol against arteriosclerosis, osteoporosis, and endometriosis because of its wide-ranging functions, including anti-inflammatory and antioxidative stress functions. As ovarian function inevitably declines after 40 years, intake of resveratrol can be beneficial for women with endometriosis aged <40 years.