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

Ciyu Zhao

Xinyan Zhao, Qiongge Zhou, Yichun Guan

PurposeOur aim was to explore the clinical outcomes of a single blastocyst frozen–thawed transfer (single blastocyst frozen–thawed transfer (singleton frozen embryo transfer, sFET) derived from low-quality day 3 (D3) embryos.MethodsThis retrospective cohort study was conducted at the Reproductive Health Center of the Third Affiliated Hospital of Zhengzhou University. All data on sFET were collected between March 2016 and September 2022. Blastocysts derived from good-quality and low-quality D3 embryos were designated as the good-quality group and the low-quality group, respectively. Patients were divided into three groups according to age: <35 group, 35–39 group, and ≥40 group. Based on whether preimplantation genetic testing (PGT) was performed or not, the blastocysts derived from low-quality embryos were divided into the PGT group and the non-PGT group, respectively.ResultsAfter adjusting for female age, male age, infertility duration, and other potential confounders, the difference in the clinical pregnancy rate and the live birth rate in the good quality and low-quality groups maintained statistical significance [adjusted odds ratio adjusted odds ratio (aOR) = 0.32 and 0.35, p < 0.001]. When adjusting for embryo quality, the clinical pregnancy rate and the live birth rate in the <35 and 35–39 groups were significantly higher than those in the ≥40 group (OR = 3.02 and 3.56, p < 0.001; OR = 1.89 and 1.84, p < 0.001). Embryo quality significantly affected the clinical pregnancy rate and the live birth rate (p < 0.001). The clinical pregnancy rate and the live birth rate in the PGT group were higher than those in the non-PGT group (40.0% vs. 29.3% and 40.0% vs. 22.0%, respectively).ConclusionD3 embryos with low score/low quality can still obtain a certain live birth rate after further culturing to blastocysts with PGT.

Jiale Wei, Zheng Shen, ChunYan Zhao et al.

ObjectiveThis study aimed to evaluate the efficacy of acupuncture in improving ovulation rates in women with polycystic ovary syndrome (PCOS) and to identify optimal dosage parameters, including the number of acupoints, treatment frequency, and session duration, using integrated pairwise meta-analysis, network meta-analysis (NMA), and model-based dose-response modeling.MethodsNine databases were searched up to January 2025, yielding 43 randomized controlled trials (RCTs) involving 4,827 participants that compared acupuncture with sham acupuncture, pharmacotherapy, or conventional therapy control group. Pairwise meta-analysis, NMA, and model-based dose-response modeling were performed.ResultsAcupuncture alone significantly increased ovulation rates compared with sham acupuncture (RR = 1.15, 95% CI: 1.04-1.27) and pharmacotherapy (RR = 1.11, 95% CI: 1.04-1.20). Additionally, acupuncture combined with herbal medicine outperformed pharmacotherapy (RR = 1.27, 95% CI: 1.12-1.43). NMA ranked acupuncture combined with herbal medicine as the most effective intervention (SUCRA = 97.8%). Dose-response modeling identified the following optimal protocols: for acupuncture alone, 30 minutes per session, 29 acupoints, three sessions per week for 24 weeks; and for combined therapy, 19 minutes per session, 26 acupoints, four sessions per week for 24 weeks.ConclusionAcupuncture is an effective non-pharmacological intervention for PCOS-related ovulatory dysfunction, with its efficacy dependent on precise dosing parameters. These findings highlight the need for standardized protocols in future trials to validate dose-response thresholds and to optimize personalized treatment strategies.Systematic review registrationwww.crd.york.ac.uk, identifier PROSPERO (CRD420250651353).

Austin Polanco, M. E. J. Newman

Repurposing existing drugs to treat new diseases is a cost-effective alternative to de novo drug development, but there are millions of potential drug-disease combinations to be considered with only a small fraction being viable. In silico predictions of drug-disease associations can be invaluable for reducing the size of the search space. In this work we present a novel network of drugs and the diseases they treat, compiled using a combination of existing textual and machine-readable databases, natural-language processing tools, and hand curation, and analyze it using network-based link prediction methods to identify potential drug-disease combinations. We measure the efficacy of these methods using cross-validation tests and find that several methods, particularly those based on graph embedding and network model fitting, achieve impressive prediction performance, significantly better than previous approaches, with area under the ROC curve above 0.95 and average precision almost a thousand times better than chance.

Niranjan Kumar, Farid Seifi, Marisa Conte et al.

Clinical calculators are widely used, and large language models (LLMs) make it possible to engage them using natural language. We demonstrate a purpose-built chatbot that leverages software implementations of verifiable clinical calculators via LLM tools and metadata about these calculators via retrieval augmented generation (RAG). We compare the chatbot's response accuracy to an unassisted off-the-shelf LLM on four natural language conversation workloads. Our chatbot achieves 100% accuracy on queries interrogating calculator metadata content and shows a significant increase in clinical calculation accuracy vs. the off-the-shelf LLM when prompted with complete sentences (86.4% vs. 61.8%) or with medical shorthand (79.2% vs. 62.0%). It eliminates calculation errors when prompted with complete sentences (0% vs. 16.8%) and greatly reduces them when prompted with medical shorthand (2.4% vs. 18%). While our chatbot is not ready for clinical use, these results show progress in minimizing incorrect calculation results.

Jiacheng Hu, Bo Zhang, Ting Xu et al.

This study addresses the challenges of symptom evolution complexity and insufficient temporal dependency modeling in Parkinson's disease progression prediction. It proposes a unified prediction framework that integrates structural perception and temporal modeling. The method leverages graph neural networks to model the structural relationships among multimodal clinical symptoms and introduces graph-based representations to capture semantic dependencies between symptoms. It also incorporates a Transformer architecture to model dynamic temporal features during disease progression. To fuse structural and temporal information, a structure-aware gating mechanism is designed to dynamically adjust the fusion weights between structural encodings and temporal features, enhancing the model's ability to identify key progression stages. To improve classification accuracy and stability, the framework includes a multi-component modeling pipeline, consisting of a graph construction module, a temporal encoding module, and a prediction output layer. The model is evaluated on real-world longitudinal Parkinson's disease data. The experiments involve comparisons with mainstream models, sensitivity analysis of hyperparameters, and graph connection density control. Results show that the proposed method outperforms existing approaches in AUC, RMSE, and IPW-F1 metrics. It effectively distinguishes progression stages and improves the model's ability to capture personalized symptom trajectories. The overall framework demonstrates strong generalization and structural scalability, providing reliable support for intelligent modeling of chronic progressive diseases such as Parkinson's disease.

Tatsunori Tanaka, Fi Zheng, Kai Sato et al.

Clinical language models have achieved strong performance on downstream tasks by pretraining on domain specific corpora such as discharge summaries and medical notes. However, most approaches treat the electronic health record as a static document, neglecting the temporally-evolving and causally entwined nature of patient trajectories. In this paper, we introduce a novel temporal entailment pretraining objective for language models in the clinical domain. Our method formulates EHR segments as temporally ordered sentence pairs and trains the model to determine whether a later state is entailed by, contradictory to, or neutral with respect to an earlier state. Through this temporally structured pretraining task, models learn to perform latent clinical reasoning over time, improving their ability to generalize across forecasting and diagnosis tasks. We pretrain on a large corpus derived from MIMIC IV and demonstrate state of the art results on temporal clinical QA, early warning prediction, and disease progression modeling.

Nuria Valdés, Nuria Valdés, Ana Romero et al.

IntroductionHistorically, Multiple Endocrine Neoplasia type 1 (MEN1)-related pituitary adenomas (PAs) were considered more aggressive and treatment-resistant than sporadic PAs. However, recent studies suggest similarities in their behavior. This study aimed to evaluate the long-term outcomes of MEN1 PAs and identify predictive factors.MethodsNationwide multicenter retrospective cohort study of MEN1-related PAs with a minimum 1-year follow-up, collecting patient demographics, germline MEN1 pathogenic variants (PV), PA size, secretory profile, radiological characteristics, treatments, and outcomes.ResultsWe analyzed 84 PAs, 69%in females and 31% in males (P<0.001), diagnosed at a mean age of 35.2±14.9 years, mostly through screening (60.7%). Median follow-up was 9 years (IQR:4-16). Prolactin-secreting PAs (PRLomas) (53.5%) and microadenomas (65.5%) were most common. Dopamine agonist treatment was first line for 16 macroPRLomas and 25 microPRLomas, 60.9% of them achieved PRL normalization. There was no significant association observed with tumor size, sex, treatment duration or MEN1 PV. The risk of progression from micro-PA to invasive macro-PA was 7.2% (4/55), after 8 years (IQR:4-13), all of them were microPRLomas. Kaplan-Meier estimation curve showed significantly higher progression probability in microPRLomas than in other microadenomas subtypes (P=0.017) or microNFPAs (P=0.032). No differences were found between sex, age, or germline MEN1 PV.ConclusionMEN1-related micro-PAs have a low risk of progressing to invasive macro-PAs, regardless of sex, age at diagnosis, or MEN1 germline PV. The risk is higher for microPRLomas over the long term. Therefore, long-term surveillance with reduced frequency, rather than intensive short-term monitoring, may be appropriate for patients with MEN1-related PAs.

Kai Gao, WanChen Cao, ZiHao He et al.

IntroductionHepatocellular carcinoma (HCC) is a major cause of cancer-related mortality worldwide. Traditional Chinese Medicine (TCM) is widely utilized as an adjunct therapy, improving patient survival and quality of life. TCM categorizes HCC into five distinct syndromes, each treated with specific herbal formulae. However, the molecular mechanisms underlying these treatments remain unclear.MethodsWe employed a network medicine approach to explore the therapeutic mechanisms of TCM in HCC. By constructing a protein-protein interaction (PPI) network, we integrated genes associated with TCM syndromes and their corresponding herbal formulae. This allowed for a quantitative analysis of the topological and functional relationships between TCM syndromes, HCC, and the specific formulae used for treatment.ResultsOur findings revealed that genes related to the five TCM syndromes were closely associated with HCC-related genes within the PPI network. The gene sets corresponding to the five TCM formulae exhibited significant proximity to HCC and its related syndromes, suggesting the efficacy of TCM syndrome differentiation and treatment. Additionally, through a random walk algorithm applied to a heterogeneous network, we prioritized active herbal ingredients, with results confirmed by literature.DiscussionThe identification of these key compounds underscores the potential of network medicine to unravel the complex pharmacological actions of TCM. This study provides a molecular basis for TCM’s therapeutic strategies in HCC and highlights specific herbal ingredients as potential leads for drug development and precision medicine.

Anjanava Biswas, Wrick Talukdar

Comprehensive clinical documentation is crucial for effective healthcare delivery, yet it poses a significant burden on healthcare professionals, leading to burnout, increased medical errors, and compromised patient safety. This paper explores the potential of generative AI (Artificial Intelligence) to streamline the clinical documentation process, specifically focusing on generating SOAP (Subjective, Objective, Assessment, Plan) and BIRP (Behavior, Intervention, Response, Plan) notes. We present a case study demonstrating the application of natural language processing (NLP) and automatic speech recognition (ASR) technologies to transcribe patient-clinician interactions, coupled with advanced prompting techniques to generate draft clinical notes using large language models (LLMs). The study highlights the benefits of this approach, including time savings, improved documentation quality, and enhanced patient-centered care. Additionally, we discuss ethical considerations, such as maintaining patient confidentiality and addressing model biases, underscoring the need for responsible deployment of generative AI in healthcare settings. The findings suggest that generative AI has the potential to revolutionize clinical documentation practices, alleviating administrative burdens and enabling healthcare professionals to focus more on direct patient care.

Mercy Asiedu, Nenad Tomasev, Chintan Ghate et al.

While large language models (LLMs) have shown promise for medical question answering, there is limited work focused on tropical and infectious disease-specific exploration. We build on an opensource tropical and infectious diseases (TRINDs) dataset, expanding it to include demographic and semantic clinical and consumer augmentations yielding 11000+ prompts. We evaluate LLM performance on these, comparing generalist and medical LLMs, as well as LLM outcomes to human experts. We demonstrate through systematic experimentation, the benefit of contextual information such as demographics, location, gender, risk factors for optimal LLM response. Finally we develop a prototype of TRINDs-LM, a research tool that provides a playground to navigate how context impacts LLM outputs for health.

Tanzina Taher Ifty, Saleh Ahmed Shafin, Shoeb Mohammad Shahriar et al.

Lung diseases remain a critical global health concern, and it's crucial to have accurate and quick ways to diagnose them. This work focuses on classifying different lung diseases into five groups: viral pneumonia, bacterial pneumonia, COVID, tuberculosis, and normal lungs. Employing advanced deep learning techniques, we explore a diverse range of models including CNN, hybrid models, ensembles, transformers, and Big Transfer. The research encompasses comprehensive methodologies such as hyperparameter tuning, stratified k-fold cross-validation, and transfer learning with fine-tuning.Remarkably, our findings reveal that the Xception model, fine-tuned through 5-fold cross-validation, achieves the highest accuracy of 96.21\%. This success shows that our methods work well in accurately identifying different lung diseases. The exploration of explainable artificial intelligence (XAI) methodologies further enhances our understanding of the decision-making processes employed by these models, contributing to increased trust in their clinical applications.

Jiacheng Liu, Jaideep Srivastava

Missingness and measurement frequency are two sides of the same coin. How frequent should we measure clinical variables and conduct laboratory tests? It depends on many factors such as the stability of patient conditions, diagnostic process, treatment plan and measurement costs. The utility of measurements varies disease by disease, patient by patient. In this study we propose a novel view of clinical variable measurement frequency from a predictive modeling perspective, namely the measurements of clinical variables reduce uncertainty in model predictions. To achieve this goal, we propose variance SHAP with variational time series models, an application of Shapley Additive Expanation(SHAP) algorithm to attribute epistemic prediction uncertainty. The prediction variance is estimated by sampling the conditional hidden space in variational models and can be approximated deterministically by delta's method. This approach works with variational time series models such as variational recurrent neural networks and variational transformers. Since SHAP values are additive, the variance SHAP of binary data imputation masks can be directly interpreted as the contribution to prediction variance by measurements. We tested our ideas on a public ICU dataset with deterioration prediction task and study the relation between variance SHAP and measurement time intervals.

Astrid Soghomonian, Astrid Soghomonian, Bénédicte Gaborit et al.

Maki Gau, Ryota Suga, Atsushi Hijikata et al.

IntroductionNR5A1 and NR5A2 belong to an orphan nuclear receptor group, and approximately 60% of their amino acid sequences are conserved. Transcriptional regulation of NR5A receptors depends on interactions with co-factors or unidentified ligands.Purpose and methodsWe employed in vitro and in silico analysis for elucidating the pathophysiology of a novel variant in the ligand-binding domain of NR5A1, p.R350W which was identified from a 46,XY patient with atypical genitalia.ResultsIn the study, [1] reporter assays demonstrated that R350 is essential for NR5A1; [2] 3D model analysis predicted that R350 interacted with endogenous ligands or unknown cofactors rather than stabilizing the structure; [3] R350 is not conserved in NR5A2 but is specifically required for NR5A1; and [4] none of the 22 known missense variants of the ligand binding domain satisfied all the previous conditions [1]-[3], suggesting the unique role of R350 in NR5A1.ConclusionOur data suggest that NR5A1 has unidentified endogenous ligands or co-activators that selectively potentiate the transcriptional function of NR5A1 in vivo.

Luigia Cinque, Flavia Pugliese, Antonio Stefano Salcuni et al.

IntroductionHypophosphatasia (HPP) is a rare genetic disease caused by inactivating variants of the ALPL gene. Few data are available on the clinical presentation in Italy and/or on Italian HPP surveys.MethodsThere were 30 suspected HPP patients recruited from different Italian tertiary cares. Biological samples and related clinical, biochemical, and anamnestic data were collected and the ALPL gene sequenced. Search for large genomic deletions at the ALPL locus (1p36) was done. Phylogenetic conservation and modeling were applied to infer the effect of the variants on the protein structure.ResultsThere were 21 ALPL variants and one large genomic deletion found in 20 out of 30 patients. Unexpectedly, NGS-driven differential diagnosis allowed uncovering three hidden additional HPP cases, for a total of 33 HPP subjects. Eight out of 24 coding variants were novel and classified as “pathogenic”, “likely pathogenic”, and “variants of uncertain significance”. Bioinformatic analysis confirmed that all the variants strongly destabilize the homodimer structure. There were 10 cases with low ALP and high VitB6 that resulted negative to genetic testing, whereas two positive cases have an unexpected normal ALP value. No association was evident with other biochemical/clinical parameters.DiscussionWe present the survey of HPP Italian patients with the highest ALPL mutation rate so far reported and confirm the complexity of a prompt recognition of the syndrome, mostly for HPP in adults. Low ALP and high VitB6 values are mandatory for the genetic screening, this latter remaining the gold standard not only to confirm the clinical diagnosis but also to make differential diagnosis, to identify carriers, to avoid likely dangerous therapy in unrecognized cases.

Chun‐Heng Kuo, Hung‐Yuan Li

Yousuf Rayhan Emon, Md Golam Rabbani, Md. Taimur Ahad et al.

Sweet orange leaf diseases are significant to agricultural productivity. Leaf diseases impact fruit quality in the citrus industry. The apparition of machine learning makes the development of disease finder. Early detection and diagnosis are necessary for leaf management. Sweet orange leaf disease-predicting automated systems have already been developed using different image-processing techniques. This comprehensive literature review is systematically based on leaf disease and machine learning methodologies applied to the detection of damaged leaves via image classification. The benefits and limitations of different machine learning models, including Vision Transformer (ViT), Neural Network (CNN), CNN with SoftMax and RBF SVM, Hybrid CNN-SVM, HLB-ConvMLP, EfficientNet-b0, YOLOv5, YOLOv7, Convolutional, Deep CNN. These machine learning models tested on various datasets and detected the disease. This comprehensive review study related to leaf disease compares the performance of the models; those models' accuracy, precision, recall, etc., were used in the subsisting studies

Jafar Abdollahi

The advancement of computer-aided detection systems had a significant impact on clinical analysis and decision-making on human disease. Lung cancer requires more attention among the numerous diseases being examined because it affects both men and women, increasing the mortality rate. LeNet, a deep learning model, is used in this study to detect lung tumors. The studies were run on a publicly available dataset made up of CT image data (IQ-OTH/NCCD). Convolutional neural networks (CNNs) were employed in the experiment for feature extraction and classification. The proposed system was evaluated on Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases datasets the success percentage was calculated as 99.51%, sensitivity (93%) and specificity (95%), and better results were obtained compared to the existing methods. Development and validation of algorithms such as ours are important initial steps in the development of software suites that could be adopted in routine pathological practices and potentially help reduce the burden on pathologists.

Zhongji Zhang, Yuhang Wang, Yinghao Zhu et al.

Emerging diseases present challenges in symptom recognition and timely clinical intervention due to limited available information. An effective prognostic model could assist physicians in making accurate diagnoses and designing personalized treatment plans to prevent adverse outcomes. However, in the early stages of disease emergence, several factors hamper model development: limited data collection, insufficient clinical experience, and privacy and ethical concerns restrict data availability and complicate accurate label assignment. Furthermore, Electronic Medical Record (EMR) data from different diseases or sources often exhibit significant cross-dataset feature misalignment, severely impacting the effectiveness of deep learning models. We present a domain-invariant representation learning method that constructs a transition model between source and target datasets. By constraining the distribution shift of features generated across different domains, we capture domain-invariant features specifically relevant to downstream tasks, developing a unified domain-invariant encoder that achieves better feature representation across various task domains. Experimental results across multiple target tasks demonstrate that our proposed model surpasses competing baseline methods and achieves faster training convergence, particularly when working with limited data. Extensive experiments validate our method's effectiveness in providing more accurate predictions for emerging pandemics and other diseases. Code is publicly available at https://github.com/wang1yuhang/domain_invariant_network.