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

Tongze Zhang, Jun-En Ding, Melik Ozolcer et al.

Alzheimer's disease (AD) has become a prevalent neurodegenerative disease worldwide. Traditional diagnosis still relies heavily on medical imaging and clinical assessment by physicians, which is often time-consuming and resource-intensive in terms of both human expertise and healthcare resources. In recent years, large language models (LLMs) have been increasingly applied to the medical field using electronic health records (EHRs), yet their application in Alzheimer's disease assessment remains limited, particularly given that AD involves complex multifactorial etiologies that are difficult to observe directly through imaging modalities. In this work, we propose leveraging LLMs to perform Chain-of-Thought (CoT) reasoning on patients' clinical EHRs. Unlike direct fine-tuning of LLMs on EHR data for AD classification, our approach utilizes LLM-generated CoT reasoning paths to provide the model with explicit diagnostic rationale for AD assessment, followed by structured CoT-based predictions. This pipeline not only enhances the model's ability to diagnose intrinsically complex factors but also improves the interpretability of the prediction process across different stages of AD progression. Experimental results demonstrate that the proposed CoT-based diagnostic framework significantly enhances stability and diagnostic performance across multiple CDR grading tasks, achieving up to a 15% improvement in F1 score compared to the zero-shot baseline method.

Nishan Mitra

Early and accurate detection of Alzheimer's disease (AD) remains a major challenge in medical diagnosis due to its subtle onset and progressive nature. This research introduces an explainable ensemble learning Framework designed to classify individuals as Alzheimer's or Non-Alzheimer's using structured clinical, lifestyle, metabolic, and lifestyle features. The workflow incorporates rigorous preprocessing, advanced feature engineering, SMOTE-Tomek hybrid class balancing, and optimized modeling using five ensemble algorithms-Random Forest, XGBoost, LightGBM, CatBoost, and Extra Trees-alongside a deep artificial neural network. Model selection was performed using stratified validation to prevent leakage, and the best-performing model was evaluated on a fully unseen test set. Ensemble methods achieved superior performance over deep learning, with XGBoost, Random Forest, and Soft Voting showing the strongest accuracy, sensitivity, and F1-score profiles. Explainability techniques, including SHAP and feature importance analysis, highlighted MMSE, Functional Assessment Age, and several engineered interaction features as the most influential determinants. The results demonstrate that the proposed framework provides a reliable and transparent approach to Alzheimer's disease prediction, offering strong potential for clinical decision support applications.

Michael Keeman, Anastasia Keeman

When OpenAI deprecated GPT-4o in early 2026, thousands of users protested under #keep4o, claiming newer models had "lost their empathy." No published study has tested this claim. We conducted the first clinical measurement, evaluating three OpenAI model generations (GPT-4o, o4-mini, GPT-5-mini) across 14 emotionally challenging conversational scenarios in mental health and AI companion domains, producing 2,100 scored AI responses assessed on six psychological safety dimensions using clinically-grounded rubrics. Empathy scores are statistically indistinguishable across all three models (Kruskal-Wallis H=4.33, p=0.115). What changed is the safety posture: crisis detection improved monotonically from GPT-4o to GPT-5-mini (H=13.88, p=0.001), while advice safety declined (H=16.63, p<0.001). Per-turn trajectory analysis -- a novel methodological contribution -- reveals these shifts are sharpest during mid-conversation crisis moments invisible to aggregate scoring. In a self-harm scenario involving a minor, GPT-4o scored 3.6/10 on crisis detection during early disclosure turns; GPT-5-mini never dropped below 7.8. What users perceived as "lost empathy" was a shift from a cautious model that missed crises to an alert model that sometimes says too much -- a trade-off with real consequences for vulnerable users, currently invisible to both the people who feel it and the developers who create it.

Megan A. Witherow, Michael L. Evans, Ahmed Temtam et al.

Alzheimer's disease (AD), defined as an abnormal buildup of amyloid plaques and tau tangles in the brain can be diagnosed with high accuracy based on protein biomarkers via PET or CSF analysis. However, due to the invasive nature of biomarker collection, most AD diagnoses are made in memory clinics using cognitive tests and evaluation of hippocampal atrophy based on MRI. While clinical assessment and hippocampal volume show high diagnostic accuracy for amnestic or typical AD (tAD), a substantial subgroup of AD patients with atypical presentation (atAD) are routinely misdiagnosed. To improve diagnosis of atAD patients, we propose a machine learning approach to distinguish between atAD and non-AD cognitive impairment using clinical testing battery and MRI data collected as standard-of-care. We develop and evaluate our approach using 1410 subjects across four groups (273 tAD, 184 atAD, 235 non-AD, and 685 cognitively normal) collected from one private data set and two public data sets from the National Alzheimer's Coordinating Center (NACC) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). We perform multiple atAD vs. non-AD classification experiments using clinical features and hippocampal volume as well as a comprehensive set of MRI features from across the brain. The best performance is achieved by incorporating additional important MRI features, which outperforms using hippocampal volume alone. Furthermore, we use the Boruta statistical approach to identify and visualize significant brain regions distinguishing between diagnostic groups. Our ML approach improves the percentage of correctly diagnosed atAD cases (the recall) from 52% to 69% for NACC and from 34% to 77% for ADNI, while achieving high precision. The proposed approach has important implications for improving diagnostic accuracy for non-amnestic atAD in clinical settings using only clinical testing battery and MRI.

Laurent Irakoze, Linqiang Ma, Yuanfeng Gu et al.

ABSTRACT Background There is still a lack of enough evidence about Nogo‐B levels and vascular complications in patients with type 2 diabetes. Our first aim was to assess the levels of Nogo‐B in type 2 diabetes mellitus (T2DM) patients with or without vascular complications (VC). Our second aim was to determine the mechanism by which Nogo‐B may protect vasculature using a hyperglycemic HUVEC model. Methods Sera or samples of patients with T2DM and subjects without diabetes were collected from the First or Second Affiliated Hospital of Chongqing Medical University. Human umbilical endothelial cells (HUVECs) were purchased and treated with high glucose (HG) and/or cholesterol (C) before and after Nogo‐B knockdown or overexpression. Graphpad and SPSS version 27 software were used for statistical analyses. Results T2DM patients with vascular complications (DM + VC) displayed significantly lower levels of Nogo‐B when compared with T2DM patients without VC (DM) or subjects without diabetes (NC) (p < 0.001). In addition, lower levels of Nogo‐B were independently associated with diabetes and/or VC in T2DM patients. Nogo‐B overexpression reduced the expression of mesenchymal markers (α‐SMA and Collagen‐1), TGF‐β1 and P‐smad2/3, while increasing the expression of endothelial markers (CD31, eNOS and VWF) in HUVECs treated with HG and/or C. Conclusion Our study has proved that lower levels of Nogo‐B are independently associated with VC in T2DM patients. In an in vitro model, Nogo‐B alleviates endothelial cell injury by affecting TGF‐β signalling. Further studies are still needed to support or verify our findings.

Aobo Gong, Ying Cao, Zexi Li et al.

IntroductionAtrial fibrillation (AF) is closely associated with metabolic dysfunction. The uric acid–to–albumin ratio (UAR), integrating oxidative stress, inflammation, and nutritional status, reflect cardiometabolic burden, but evidence linking UAR to AF prognosis remains limited.MethodsWe analyzed clinical data from 1,908 AF patients at West China Hospital, with external validation from the MIMIC database (n=1,366). Associations were assessed using Kaplan–Meier analyses, restricted cubic splines, and multivariable Cox proportional hazards models. Incremental prognostic value beyond the CHA2DS2-VASc score was evaluated in both cohorts. Exploratory machine learning and SHAP analyses were employed to assess the variable importance of UAR. Subgroup and sensitivity analyses were performed in primary cohort, including additional cardiometabolic adjustment, analyses with cardiac mortality, competing risk models, and longer follow-up.ResultsBaseline characteristics differed across UAR quartiles, with high UARs associated with substantial burdens of metabolic comorbidities, heart failure, renal dysfunction, and elevated inflammatory and cardiac biomarkers. Mortality was higher in the highest UAR quartile (log-rank P&lt;0.001). In the primary cohort, restricted cubic splines showed a J-shaped association between UAR and 1-year mortality (P for nonlinearity &lt;0.001). In fully adjusted Cox models, UAR (per SD) predicted 1-year all-cause mortality in the primary cohort (HR 1.162, 95% CI 1.036–1.304) and in the MIMIC cohort (HR 1.137, 95% CI 1.092–1.185). Adding UAR to the CHA2DS2-VASc score improved discrimination (C-index 0.654 to 0.692; P = 0.001), reclassification (continuous NRI 0.178), calibration, and clinical net benefit, with consistent incremental performance in the MIMIC cohort. In both cohorts, SHAP analysis consistently identified UAR as one of the major contributors to mortality prediction. Findings were consistent across subgroups and sensitivity analyses.ConclusionUAR is an independent predictor of mortality in AF and captures cardiometabolic remodeling beyond conventional risk assessment. As a readily available biomarker, UAR may facilitate metabolically guided risk stratification and individualized management in AF populations.

Bolin Liu, Alexander Fulton, Hector Zenil

Understanding disease relationships through blood biomarkers offers a pathway toward data driven taxonomy and precision medicine. We constructed a digital blood twin from 103 disease signatures comprising longitudinal hematological and biochemical analytes. Profiles were standardized into a unified disease analyte matrix, and pairwise Pearson correlations were computed to assess similarity. Hierarchical clustering revealed robust grouping of hematopoietic disorders, while metabolic, endocrine, and respiratory diseases were more heterogeneous, reflecting weaker cohesion. To evaluate structure, the tree was cut at a stringent threshold, yielding 16 groups. Enrichment of the largest heterogeneous cluster (Cluster 9) showed convergence on cytokine-signaling pathways, indicating shared immunological and inflammatory mechanisms across clinical boundaries. Dimensionality reduction with PCA and UMAP corroborated these results, consistently separating hematological diseases. Random Forest feature selection identified neutrophils, mean corpuscular volume, red blood cell count, and platelets as the most discriminative analytes, reinforcing hematopoietic markers as key drivers. Collectively, these findings show that blood-derived digital signatures can recover clinically meaningful clusters while revealing mechanistic overlaps across categories. The coherence of hematological diseases contrasts with the dispersion of systemic and metabolic disorders, underscoring both the promise and limits of blood-based classification. This framework highlights the potential of integrating routine laboratory data with computational methods to refine disease ontology, map comorbidities, and advance precision diagnostics.

Ting Xu, Xiaoxiao Deng, Xiandong Meng et al.

This paper addresses the challenges posed by the unstructured nature and high-dimensional semantic complexity of electronic health record texts. A deep learning method based on attention mechanisms is proposed to achieve unified modeling for information extraction and multi-label disease prediction. The study is conducted on the MIMIC-IV dataset. A Transformer-based architecture is used to perform representation learning over clinical text. Multi-layer self-attention mechanisms are employed to capture key medical entities and their contextual relationships. A Sigmoid-based multi-label classifier is then applied to predict multiple disease labels. The model incorporates a context-aware semantic alignment mechanism, enhancing its representational capacity in typical medical scenarios such as label co-occurrence and sparse information. To comprehensively evaluate model performance, a series of experiments were conducted, including baseline comparisons, hyperparameter sensitivity analysis, data perturbation studies, and noise injection tests. Results demonstrate that the proposed method consistently outperforms representative existing approaches across multiple performance metrics. The model maintains strong generalization under varying data scales, interference levels, and model depth configurations. The framework developed in this study offers an efficient algorithmic foundation for processing real-world clinical texts and presents practical significance for multi-label medical text modeling tasks.

Mingcheng Zhu, Yu Liu, Zhiyao Luo et al.

Artificial Intelligence has revolutionised critical care for common conditions. Yet, rare conditions in the intensive care unit (ICU), including recognised rare diseases and low-prevalence conditions in the ICU, remain underserved due to data scarcity and intra-condition heterogeneity. To bridge such gaps, we developed KnowRare, a domain adaptation-based deep learning framework for predicting clinical outcomes for rare conditions in the ICU. KnowRare mitigates data scarcity by initially learning condition-agnostic representations from diverse electronic health records through self-supervised pre-training. It addresses intra-condition heterogeneity by selectively adapting knowledge from clinically similar conditions with a developed condition knowledge graph. Evaluated on two ICU datasets across five clinical prediction tasks (90-day mortality, 30-day readmission, ICU mortality, remaining length of stay, and phenotyping), KnowRare consistently outperformed existing state-of-the-art models. Additionally, KnowRare demonstrated superior predictive performance compared to established ICU scoring systems, including APACHE IV and IV-a. Case studies further demonstrated KnowRare's flexibility in adapting its parameters to accommodate dataset-specific and task-specific characteristics, its generalisation to common conditions under limited data scenarios, and its rationality in selecting source conditions. These findings highlight KnowRare's potential as a robust and practical solution for supporting clinical decision-making and improving care for rare conditions in the ICU.

Hui-Chen Wang, Hui-Chen Wang, Wen-Sen Lee et al.

IntroductionWe previously demonstrated that progesterone (P4) can promote breast cancer cell proliferation and migration through activating the P4 receptor (PR)/cSrc-mediated signaling pathway. It has been suggested that high level of Src homology region 2 domain-containing phosphatase-2 (SHP2) might be involved in breast oncogenesis. This study aimed to investigate whether SHP2 is involved in the P4-mediated cSrc activation in breast cancer cells.MethodsT47D, MCF-7 and BT-483 breast cancer cell lines were used in this study. Cell proliferation and migration were examined using MTT technique and wound healing assay, respectively. Immunoprecipitation assay and Western blot analysis were performed to evaluate protein-protein interaction and protein expression, respectively. Small interfering RNA (siRNA) technique was used to knock down protein expression.ResultsKnockdown of SHP2 expression abolished the P4-promoted cell proliferation and migration in T47D, MCF and BT-483 cell lines, suggesting that presence of SHP2 is essential for the P4-increased proliferation and migration of breast cancer cell lines. P4 (50 nM) treatment increased the complex formations of PR-cSrc-SHP2-caveolin-1, SHP2-p140Cap, and SHP2-Csk, and the level of p-cSrcY416 (activated form of cSrc). However, knockdown of SHP2 expression increased the complex formations of PR-cSrc-caveolin-1-Csk-p140Cap and the levels of p-caveolin-1, p-Csk and p-cSrcY527 (inactivated form of cSrc).DiscussionOur data suggest that SHP2 can bind to cSrc-negative regulatory proteins (p140Cap and Csk), hence preventing the interaction between cSrc and cSrc-negative regulatory proteins, leading to decreased phosphorylation of cSrc Y527 and prolonged cSrc activation. These findings highlight the role of SHP2 in the P4-promoted breast cancer cell proliferation and migration.

John Charlton, Ibrahim Alsanie, Syed Ali Khurram

This work shows promising results using multiple instance learning on salivary gland tumours in classifying cancers on whole slide images. Utilising CTransPath as a patch-level feature extractor and CLAM as a feature aggregator, an F1 score of over 0.88 and AUROC of 0.92 are obtained for detecting cancer in whole slide images.

Qian Shao, Bang Du, Yixuan Wu et al.

Deep learning models for pulmonary disease screening from Computed Tomography (CT) scans promise to alleviate the immense workload on radiologists. Still, their high computational cost, stemming from processing entire 3D volumes, remains a major barrier to widespread clinical adoption. Current sub-sampling techniques often compromise diagnostic integrity by introducing artifacts or discarding critical information. To overcome these limitations, we propose an Efficient and Reliable Framework (ERF) that fundamentally improves the practicality of automated CT analysis. Our framework introduces two core innovations: (1) A Cluster-based Sub-Sampling (CSS) method that efficiently selects a compact yet comprehensive subset of CT slices by optimizing for both representativeness and diversity. By integrating an efficient k-nearest neighbor search with an iterative refinement process, CSS bypasses the computational bottlenecks of previous methods while preserving vital diagnostic features. (2) An Ambiguity-aware Uncertainty Quantification (AUQ) mechanism, which enhances reliability by specifically targeting data ambiguity arising from subtle lesions and artifacts. Unlike standard uncertainty measures, AUQ leverages the predictive discrepancy between auxiliary classifiers to construct a specialized ambiguity score. By maximizing this discrepancy during training, the system effectively flags ambiguous samples where the model lacks confidence due to visual noise or intricate pathologies. Validated on two public datasets with 2,654 CT volumes across diagnostic tasks for 3 pulmonary diseases, ERF achieves diagnostic performance comparable to the full-volume analysis (over 90% accuracy and recall) while reducing processing time by more than 60%. This work represents a significant step towards deploying fast, accurate, and trustworthy AI-powered screening tools in time-sensitive clinical settings.

K. V. Pocheniuk, I. A. Holovanova

Diabetes mellitus has become one of the most prevalent chronic diseases in childhood today. International forecasts suggest that the incidence of diabetes will continue to rise in the coming decades, leading to a lifelong burden for millions of children worldwide. Therefore, prediction, prevention, and optimal treatment of diabetes, as well as early prevention of serious long-term complications, remain essential. Providing highly qualified medical care to diabetic patients is a crucial step in preventing the development of complications. The purpose of this article is to review existing research on diabetes prevention strategies for children, considering the different levels of medical care support available. Materials and Methods. This study investigates the organization of preventive care for children with diabetes in Ukraine. Researchers employed three key methods: bibliosemantic analysis, content analysis focused on analyzing Ukraine relevant regulations and legal frameworks, and the method of systemic approach and analysis to gain a comprehensive understanding of how preventive care is currently organized for children with diabetes in Ukraine. Results. In Ukraine, preventive measures and the provision of medical care to pediatric patients with diabetes in the past years and today are regulated by a number of documents and orders of the Ministry of Health. As part of the Comprehensive Program “Diabetes Mellitus” (1999) and in accordance with the Order of the Ministry of Health of Ukraine “On Improving the Organization of Providing Endocrinological Care to the Population of Ukraine” (2006), the State Register of Patients with Diabetes Mellitus (SYNADIAB) was created. The next step was the approval of the State Target Program “Diabetes Mellitus”. Subsequently, the Project of the national program “Health 2020: Ukrainian Dimension” became an effective tool, which outlined the main principles of the program implementation in the “Endocrinology” section for 2013-2020. It defined measures at all stages of diabetes prevention, such as primary prevention, which consists of maintaining and strengthening the general state of health and preventing or delaying the development of diabetes; secondary prevention should improve early detection of diabetes mellitus; tertiary prevention, which ensures the effectiveness and safety of treatment of children with diabetes to prevent the development of long-term complications. Today, the guidelines for the management of children with diabetes mellitus have been continued in such documents as “Diabetes Mellitus in Children”, Evidence-Based Clinical Guidelines (2023) and Standards of Care (2023). Conclusion. Diabetes mellitus is a chronic disease that ranks third in prevalence after cardiovascular and cancerous diseases and second in the structure of endocrine diseases after thyroid gland pathology. Today, the prevalence of diabetes mellitus among children is constantly increasing and, therefore, solving the issues associated with this disease is one of the priority tasks for the national health care system. This is because diabetes mellitus is associated with a high risk of complications leading to loss of work capacity, disability, and mortality across various population groups. Organizing high-quality medical care and establishing an effective prevention system based on the latest medical technologies is crucial. Diabetes demands attention. Understanding the risks and prevention of the disease can significantly increase the chances of protection and a long, healthy life through timely treatment.

A. Jain, E. Naous, S. Sedrakyan et al.

Abstract Disclosure: A. Jain: None. E. Naous: None. S. Sedrakyan: None. A.T. Sweeney: None. Background: Thyrotoxicosis may cause many cardiovascular manifestations including tachycardia, hypertension, atrial fibrillation and heart failure. Iatrogenic exposure to iodinated contrast media (ICM) precipitating iodine induced thyrotoxicosis (or the Jod-Basedow phenomenon) is often overlooked. Here, we describe a case of iodine induced thyrotoxicosis leading to takotsubu cardiomyopathy, following multiple exposures to ICM. Case Presentation: An 88-year-old male with a history of hypertension, dyslipidemia, chronic obstructive pulmonary disease, and an ED visit one month ago for hemoptysis for which a CT Angiography (CTA) of the chest was obtained (which excluded Pulmonary Embolism(PE)), presented with fever and shortness of breath. On physical examination his temperature was 100.3F, heart rate was 104bpm, blood pressure 130/62mmHg, respiratory rate was 20/min and saturation was 88% (room air). He was frail but his examination was otherwise unremarkable. Electrocardiogram (EKG) revealed sinus tachycardia. Chest CTA excluded PE. Transthoracic echocardiogram (TTE) showed an ejection fraction (EF) of 73% and no wall motion abnormalities. He was admitted to the hospital for a viral upper respiratory infection and was treated conservatively with bronchodilators. Odynophagia prompted a CT with contrast of the neck soft tissue, which was unrevealing. He was planned to be discharged the next day, but overnight developed severe abdominal pain, and atrial fibrillation with a rapid ventricular response (Troponin t was 191 ng/L (normal {nl}: <9 ng/L)). EKG showed new T-wave inversions in the anterolateral leads, raising a suspicion of myocardial ischemia. A repeated TTE revealed a new drop in EF from 73 to 41%, with new apical akinesis, suspicious for takotsubo cardiomyopathy. CT of the abdomen with contrast was unrevealing. Lab results showed a suppressed TSH of <0.01uIU/mL (nl: 0.34-5.60 uIU/mL), elevated FT4 of 13ng/dL (nl: 0.93-1.70 ng/dL), and TSI 4.97 IU/ L (nl: 0-0.55 IU/ L). Endocrinology was consulted. His thyroid examination was normal, and he had no eye findings. Neck ultrasound revealed a homogeneous thyroid gland without any nodules. His clinical course was consistent with the diagnosis of acute thyrotoxicosis precipitating takotsubu cardiomyopathy. He likely developed iodine induced thyrotoxicosis from multiple exposures to ICM, in a background of previously undiagnosed Graves’ disease. Discussion: Screening for thyroid disease is critical in patients with new onset tachyarrhythmias and stress cardiomyopathy. Iodine induced thyrotoxicosis typically presents after patients with underlying thyroid disease are exposed to iodinated contrast. Prior to ordering studies requiring ICM, it is important to thoroughly evaluate patients for possible pre-existing thyroid disease. Presentation: 6/2/2024

Kathrin Schilling, Kathrin Schilling, Heng Chen et al.

BackgroundMore than 700 million people worldwide suffer from diseases of the pancreas, such as diabetes, pancreatitis and pancreatic cancer. Often dysregulation of potassium (K+) channels, co-transporters and pumps can promote development and progression of many types of these diseases. The role of K+ transport system in pancreatic cell homeostasis and disease development remains largely unexplored. Potassium isotope analysis (δ41K), however, might have the potential to detect minute changes in metabolic processes relevant for pancreatic diseases.MethodsWe assessed urinary K isotope composition in a case-control study by measuring K concentrations and δ41K in spot urines collected from patients diagnosed with pancreatic cancer (n=18), other pancreas-related diseases (n=14) and compared those data to healthy controls (n=16). ResultsOur results show that urinary K+ levels for patients with diseased pancreas (benign and pancreatic cancer) are significantly lower than the healthy controls. For δ41K, the values tend to be higher for individuals with pancreatic cancer (mean δ41K = -0.58 ± 0.33‰) than for healthy individuals (mean δ41K = -0.78 ± 0.19‰) but the difference is not significant (p=0.08). For diabetics, urinary K+ levels are significantly lower (p=0.03) and δ41K is significantly higher (p=0.009) than for the healthy controls. These results suggest that urinary K+ levels and K isotopes can help identify K disturbances related to diabetes, an associated factors of all-cause mortality for diabetics.ConclusionAlthough the K isotope results should be considered exploratory and hypothesis-generating and future studies should focus on larger sample size and δ41K analysis of other K-disrupting diseases (e.g., chronic kidney disease), our data hold great promise for K isotopes as disease marker.

Long Chen, Liben Chen, Binfeng Xu et al.

The aging population of the U.S. drives the prevalence of Alzheimer's disease. Brookmeyer et al. forecasts approximately 15 million Americans will have either clinical AD or mild cognitive impairment by 2060. In response to this urgent call, methods for early detection of Alzheimer's disease have been developed for prevention and pre-treatment. Notably, literature on the application of deep learning in the automatic detection of the disease has been proliferating. This study builds upon previous literature and maintains a focus on leveraging multi-modal information to enhance automatic detection. We aim to predict the stage of the disease - Cognitively Normal (CN), Mildly Cognitive Impairment (MCI), and Alzheimer's Disease (AD), based on two different types of brain MRI scans. We design an AlexNet-based deep learning model that learns the synergy of complementary information from both T1 and FLAIR MRI scans.

Yunyou Huang, Xiaoshuang Liang, Xiangjiang Lu et al.

Although Alzheimer's disease (AD) cannot be reversed or cured, timely diagnosis can significantly reduce the burden of treatment and care. Current research on AD diagnosis models usually regards the diagnosis task as a typical classification task with two primary assumptions: 1) All target categories are known a priori; 2) The diagnostic strategy for each patient is consistent, that is, the number and type of model input data for each patient are the same. However, real-world clinical settings are open, with complexity and uncertainty in terms of both subjects and the resources of the medical institutions. This means that diagnostic models may encounter unseen disease categories and need to dynamically develop diagnostic strategies based on the subject's specific circumstances and available medical resources. Thus, the AD diagnosis task is tangled and coupled with the diagnosis strategy formulation. To promote the application of diagnostic systems in real-world clinical settings, we propose OpenClinicalAI for direct AD diagnosis in complex and uncertain clinical settings. This is the first powerful end-to-end model to dynamically formulate diagnostic strategies and provide diagnostic results based on the subject's conditions and available medical resources. OpenClinicalAI combines reciprocally coupled deep multiaction reinforcement learning (DMARL) for diagnostic strategy formulation and multicenter meta-learning (MCML) for open-set recognition. The experimental results show that OpenClinicalAI achieves better performance and fewer clinical examinations than the state-of-the-art model. Our method provides an opportunity to embed the AD diagnostic system into the current health care system to cooperate with clinicians to improve current health care.

James Huynh, Alladdin Makawi, Ghada Elshimy

Abstract Disclosure: J. Huynh: None. A. Makawi: None. G. Elshimy: None. Introduction: Modern healthcare relies on laboratory and imaging results for accurate diagnosis and medical decision-making. However, the collection and distillation of laboratory results is a multi-step process with the potential for error at each stage. This may result in diagnostic errors. A review of salient cases is one avenue to improving awareness of the risk for failure in the laboratory assessment process. We present one such case of a patient initially referred to neurosurgery for management of a thyroid stimulating hormone (TSH) secreting microadenoma, which is a rare disease and accounts for less than 1% of all pituitary adenomas, with incongruent laboratory presentation including elevation in TSH and free T4. Endocrinology consultation prompted further investigations which led to the diagnosis of Graves’ disease with a concomitant nonfunctional pituitary microadenoma. Case Presentation: This is a case of a 61-year-old white male who presented with 30-lb weight loss, insomnia, palpitations, and diaphoresis. Initial thyroid stimulating hormone (TSH) from outside facility was > 90 mcIU/mL with elevated free T4 of 23.4 pg/mL. MRI of the brain shows a 3x3 mm pituitary microadenoma raising concern for an atypical case of TSH-secreting adenoma. The patient referred to Neurosurgery for evaluation by primary care. Endocrinology was consulted for evaluation prior to any surgical intervention. A large goiter was noted on exam. Clinical presentation was highly concern for Graves’ disease. Repeated labs included undetectable TSH with FT4 of 4.4 pg/mL and free T3 12.9 pg/ml. TPO-ab was elevated at 17.1 IU/mL. TSIg index was low. Ultrasound of the thyroid gland revealed a normal thyroid without nodules. He was diagnosed with Graves’ disease and was initiated on methimazole and propranolol with symptomatic improvement. His pituitary panels continued to show suppressed TSH pre and post treatment with no other significant pituitary abnormalities hence the diagnosis of a concomitant nonfunctional pituitary microadenoma was made. Discussion: Ultimately, the initial TSH-secreting microadenoma has deemed a misdiagnosis and he was subsequently treated appropriately for Graves’ disease with normalization of thyroid functions. Standard of care for any laboratory abnormalities is to assess for reproducibility of the result. In our patient, subsequent in-house and outside assays were unable to demonstrate elevation of both TSH and FT4. Instead, the patient had suppressed TSH with elevated FT4, without evidence of nodules consistent with Graves’ disease. Treatment of Graves’ disease differs greatly from the treatment of TSH-secreting pituitary adenoma, which includes surgical resection, radiotherapy, and/or, a somatostatin analog based on the clinical picture. Correct diagnosis prevented our patients from unnecessary surgical complications and lifelong morbidity. Presentation: Friday, June 16, 2023

Jing Ling Ruan, Jing Ling Ruan, Shan Shan Liang et al.

Research questionDoes artificial oocyte activation (AOA) by a calcium ionophore (ionomycin) improve the previous fertilization failure or poor embryo development of intracytoplasmic sperm injection (ICSI) account for male factor infertility or other infertility causes?DesignThis retrospective study involved 114 patients receiving ICSI-AOA in Shanghai First Maternity and Infant Hospital with previous ICSI fertilization failure or poor embryo development. The previous ICSI cycles of the same patients without AOA served as the control group. The fertilization rates, cleavage rates, transferable embryo rates and blastocyst formation rates of the two groups were compared. Additionally, the clinical pregnancy, implantation rate and live birth rates were also compared to assess the efficiency and safety of AOA. Furthermore, two subgroup analyses were performed in this study based on the cause of infertility and the reason for AOA. The fertilization rate, embryonic development potential and clinical outcome were compared among groups.ResultsAmong 114 ICSI-AOA cycles, the fertilization rate, top-quality embryo rate, implantation rate, clinical pregnancy per patient and live birth rate per patient were improved significantly compared with previous ICSI cycles (p&lt;0.05 to P&lt; 0.001), and the miscarriage rate in the AOA group was significantly lower than that of the control group (p&lt;0.001). In the AOA subgroups based on the cause of infertility, the fertilization rates of each subgroup were significantly improved compared with previous control cycles except for the mixed factor infertility subgroup (p&lt;0.05 to p&lt;0.001). In the AOA subgroups based on the reason for AOA, the fertilization rates of each subgroup were significantly increased compared with those in their previous ICSI cycle without AOA (p&lt;0.001); however, there was no significant difference in the top-quality embryo rate. No significant improvement was found in the implantation rates and the clinical pregnancy rate in each subgroup except for the poor embryo development subgroup. In the 114 AOA cycles, 35 healthy infants (21 singletons and 7 twins) were delivered without major congenital birth defects or malformations.ConclusionThis study showed that AOA with the calcium ionophore ionomycin can improve the reproductive outcomes of patients with previous fertilization failure and poor embryo development after ICSI.

Yingjie Ma, Jingyan Song, Jingyan Song et al.

ObjectiveTo study the effect of Guilu Erxian ointment on the outcome of IVF-ET in older patients with poor ovarian response infertility of kidney-qi deficiency type, and to verify and analyze the mechanism of action of traditional Chinese medicine on improving older patients with poor ovarian response infertility of kidney-qi deficiency type from the perspective of metabolomics using targeted metabolomics technology, identify the related metabolic pathways, and provide metabolic biomarker basis and clinical treatment ideas for improving older patients with poor ovarian response infertility.MethodsThis study was a double-blind, randomized, placebo-controlled trial, and a total of 119 infertile patients who underwent IVF-ET at Shandong Center for Reproduction and Genetics of Integrated Traditional Chinese and Western Medicine were selected. Eighty older patients with infertility undergoing IVF were randomly divided into older treatment group and older placebo group, and another 39 young healthy women who underwent IVF-ET or ICSI due to male factors were selected as the normal control group. Flexible GnRH antagonist protocol was used for ovulation induction in all three groups, and Guilu Erxian ointment and placebo groups started taking Guilu Erxian ointment and placebo from the third day of menstruation until IVF surgery. And ultra-high performance liquid chromatography-triple quadrupole mass spectrometer (UHPLC-QTRAP MS) was used to detect metabolites in the three groups of samples.ResultsCompared with the placebo group, the number of oocytes retrieved, 2PN fertilization, high-quality embryos, total number of available embryos and estrogen on HCG day were increased in the treatment group, and the differences were statistically significant (P &gt; 0.05), but the clinical pregnancy rate of fresh embryos and frozen embryos were not statistically significant (P &gt; 0.05). The results of targeted metabolomics analysis showed that follicular fluid in the treatment group clustered with the normal young group and deviated from the placebo group. A total of 55 significant differential metabolites were found in the follicular fluid of older patients with poor ovarian response of kidney-qi deficiency type and patients in the normal young group, after Guilu Erxian ointment intervention, Metabolites such as L-Aspartic acid, Glycine, L-Serine, Palmitoleic Acid, Palmitelaidic acid, L-Alanine, Gamma-Linolenic acid, Alpha-Linolenic Acid, and N-acetyltryptophan were down-regulated, mainly involving amino acid metabolism and fatty acid metabolism.ConclusionGuilu Erxian ointment can effectively improve the clinical symptoms and IVF outcomes of older patients with poor ovarian response of kidney-qi deficiency type. There were differences in follicular fluid metabolites between older patients with poor ovarian response of kidney-qi deficiency type and normal women. L-Aspartic acid, L-Alanine, Aminoadipic acid, L-Asparagine, L-Arginine, L-Serine, Gamma- Linolenic acid, Pentadecanoic acid and Alpha-Linolenic Acid are closely related to older patients with poor ovarian response due to deficiency of kidney-qi and may be inferred as biomarkers. The mechanism of Guilu Erxian ointment intervention may be mainly through amino acid metabolism and fatty acid metabolism regulation.