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

Ruixue Sun, Shuang Liu, Hong Han et al.

Iatrogenic Cushing syndrome caused by topical corticosteroid preparations is only reported in infants. We describe a case in a patient with obsessive-compulsive disorder: the patient had tic disorder and obsessive-compulsive disorder, and the condition was under stable control. After the appearance of oral ulcers, the patient uncontrollably used a large amount of chlorhexidine dexamethasone membranes, resulting in iatrogenic Cushing syndrome. The fatty liver and abnormal liver function associated with Cushing syndrome led to the discontinuation of fluvoxamine and aripiprazole for obsessive-compulsive disorder. The patient’s tic and compulsive symptoms worsened, and he repeatedly bit his tongue. Under multidisciplinary diagnosis and treatment in emergency department, endocrinology department, psychological department, and dentistry department, both the mental and physical symptoms were controlled and the patient’s prognosis was satisfactory. Genetic testing revealed no clear abnormalities that could explain the patient’s phenotype. Therefore, medication use on obsessive-compulsive disorder patients with somatic diseases should be monitored. Multidisciplinary cooperation, especially consultation liaison psychiatry in general hospitals, is essential for the diagnosis and treatment of patients with both physical and mental symptoms in general hospitals.

Shaheer Ahmad Khan, Muhammad Usamah Shahid, Muddassar Farooq

Chronic diseases are long-lasting conditions that require lifelong medical attention. Using big EMR data, we have developed early disease risk prediction models for five common chronic diseases: diabetes, hypertension, CKD, COPD, and chronic ischemic heart disease. In this study, we present a novel approach for disease risk models by integrating survival analysis with classification techniques. Traditional models for predicting the risk of chronic diseases predominantly focus on either survival analysis or classification independently. In this paper, we show survival analysis methods can be re-engineered to enable them to do classification efficiently and effectively, thereby making them a comprehensive tool for developing disease risk surveillance models. The results of our experiments on real-world big EMR data show that the performance of survival models in terms of accuracy, F1 score, and AUROC is comparable to or better than that of prior state-of-the-art models like LightGBM and XGBoost. Lastly, the proposed survival models use a novel methodology to generate explanations, which have been clinically validated by a panel of three expert physicians.

Shao Ching Tu, Marium Khan, Katie Wolfe et al.

Abstract Maple syrup urine disease (MSUD) is an inborn error of metabolism characterized by the accumulation of branched‐chain amino acids (leucine, isoleucine, and valine) caused by a defect in the branched‐chain alpha‐keto acid dehydrogenase complex. Liver transplant is an effective therapy for MSUD, and patients can usually tolerate a regular diet after transplant without symptomatic metabolic decompensation. Most post‐transplant patients do not follow a sick‐day diet. We report a case of a 7‐year‐old male with MSUD Type IA, status post‐liver transplant at 2 years of age, who presented with profound encephalopathy following poor oral intake and vomiting for 3 days. Broad laboratory workup was significant for hyperleucinosis and an unrevealing infectious workup. We conducted a review of eight post‐liver transplant MSUD patients followed at Washington University in St. Louis. The review revealed that plasma amino acids were generally not checked during intercurrent illnesses in this patient cohort. While most of our patients have not had documented encephalopathy, one of the patients with epilepsy had a seizure during a gastrointestinal illness. Based on the review of the literature and from our center's experience, acute metabolic decompensation with intercurrent illnesses in MSUD patients after liver transplant appears to be rare. This case report raises awareness that patients with MSUD are still at risk of developing metabolic crisis post‐liver transplant and provides additional insight into the risk factors associated with metabolic decompensation in this patient cohort.

Merve Çatak, Şerife Gülhan Konuk, Sema Hepsen

ABSTRACT Objective To investigate the relationship between four metabolic indices—visceral adiposity index (VAI), lipid accumulation product (LAP), triglyceride glucose (TyG) index, and cholesterol‐HDL‐glucose (CHG) index—and the presence of diabetic nephropathy (DN) and diabetic retinopathy (DR) in patients with long‐standing type 2 diabetes mellitus (T2DM). Materials and Methods This prospective cross‐sectional study included 175 T2DM patients with disease duration >10 years who attended an endocrinology outpatient clinic between July 2021 and January 2022. DR was assessed via fundus photography, and DN was defined using the urinary albumin‐to‐creatinine ratio and eGFR. VAI, LAP, TyG, and CHG indices were calculated using anthropometric and biochemical parameters. Logistic regression was used to identify independent predictors. Results The mean age was 60 ± 10.1 years; 63.4% were female. DR and DN were observed in 50.3% and 38.9% of patients, respectively. VAI, LAP, and TyG were significantly higher in patients with DN but not with DR. CHG was elevated in both DN and DR (P < 0.05), and was the only independent predictor of DN (P = 0.005). Notably, CHG was significantly higher in proliferative vs non‐proliferative DR (P = 0.009), unlike the other indices. Conclusions While VAI, LAP, and TyG were associated only with nephropathy, CHG was linked to both DN and DR. Its integration of glycemic and lipid parameters may offer greater sensitivity for microvascular risk stratification in T2DM.

Jialu Tang, Hung Manh Pham, Ignace De Lathauwer et al.

Electrocardiogram (ECG) interpretation is essential for cardiovascular disease diagnosis, but current automated systems often struggle with transparency and generalization to unseen conditions. To address this, we introduce ZETA, a zero-shot multimodal framework designed for interpretable ECG diagnosis aligned with clinical workflows. ZETA uniquely compares ECG signals against structured positive and negative clinical observations, which are curated through an LLM-assisted, expert-validated process, thereby mimicking differential diagnosis. Our approach leverages a pre-trained multimodal model to align ECG and text embeddings without disease-specific fine-tuning. Empirical evaluations demonstrate ZETA's competitive zero-shot classification performance and, importantly, provide qualitative and quantitative evidence of enhanced interpretability, grounding predictions in specific, clinically relevant positive and negative diagnostic features. ZETA underscores the potential of aligning ECG analysis with structured clinical knowledge for building more transparent, generalizable, and trustworthy AI diagnostic systems. We will release the curated observation dataset and code to facilitate future research.

Weijieying Ren, Tianxiang Zhao, Lei Wang et al.

Recent advances in Large Language Models (LLMs) have led to remarkable progresses in medical consultation. However, existing medical LLMs overlook the essential role of Electronic Health Records (EHR) and focus primarily on diagnosis recommendation, limiting their clinical applicability. We propose DiaLLM, the first medical LLM that integrates heterogeneous EHR data into clinically grounded dialogues, enabling clinical test recommendation, result interpretation, and diagnosis prediction to better align with real-world medical practice. To construct clinically grounded dialogues from EHR, we design a Clinical Test Reference (CTR) strategy that maps each clinical code to its corresponding description and classifies test results as "normal" or "abnormal". Additionally, DiaLLM employs a reinforcement learning framework for evidence acquisition and automated diagnosis. To handle the large action space, we introduce a reject sampling strategy to reduce redundancy and improve exploration efficiency. Furthermore, a confirmation reward and a class-sensitive diagnosis reward are designed to guide accurate diagnosis prediction. Extensive experimental results demonstrate that DiaLLM outperforms baselines in clinical test recommendation and diagnosis prediction.

Vivekanandhan Aravindhan, Srinivasan Yuvaraj

Tuberculosis patients with diabetes, have higher sputum bacillary load, delayed sputum conversion, higher rates of drug resistance, higher lung cavitary involvement and extra-pulmonary TB infection, which is called as “Diabetes-Tuberculosis Nexus”. However, recently we have shown a reciprocal relationship between latent tuberculosis infection and insulin resistance, which has not been reported before. In this review, we would first discuss about the immune-endocrine network, which operates during pre-diabetes and incipient diabetes and how it confers protection against LTBI. The ability of IR to augment anti-TB immunity and the immunomodulatory effect of LTBI to quench IR were discussed, under IR-LTB antagonism. The ability of diabetes to impair anti-TB immunity and ability of active TB to worsen glycemic control, were discussed under “Diabetes-Tuberculosis Synergy”. The concept of “Fighter Genes” and how they confer protection against TB but susceptibility to IR was elaborated. Finally, we conclude with an evolutionary perspective about how IR and LTBI co-evolved in endemic zones, and have explained the molecular basis of “IR-LTB” Antagonism” and “DM-TB Synergy”, from an evolutionary perspective.

Elizaveta Lavrova, Henry C. Woodruff, Hamza Khan et al.

Medical imaging technologies have undergone extensive development, enabling non-invasive visualization of clinical information. The traditional review of medical images by clinicians remains subjective, time-consuming, and prone to human error. With the recent availability of medical imaging data, quantification have become important goals in the field. Radiomics, a methodology aimed at extracting quantitative information from imaging data, has emerged as a promising approach to uncover hidden biological information and support decision-making in clinical practice. This paper presents a review of the radiomic pipeline from the clinical neuroimaging perspective, providing a detailed overview of each step with practical advice. It discusses the application of handcrafted and deep radiomics in neuroimaging, stratified by neurological diagnosis. Although radiomics shows great potential for increasing diagnostic precision and improving treatment quality in neurology, several limitations hinder its clinical implementation. Addressing these challenges requires collaborative efforts, advancements in image harmonization methods, and the establishment of reproducible and standardized pipelines with transparent reporting. By overcoming these obstacles, radiomics can significantly impact clinical neurology and enhance patient care.

Juliette Ortholand, Nicolas Gensollen, Stanley Durrleman et al.

Introduction: Heterogeneity of the progression of neurodegenerative diseases is one of the main challenges faced in developing effective therapies. With the increasing number of large clinical databases, disease progression models have led to a better understanding of this heterogeneity. Nevertheless, these diseases may have no clear onset and biological underlying processes may start before the first symptoms. Such an ill-defined disease reference time is an issue for current joint models, which have proven their effectiveness by combining longitudinal and survival data. Objective In this work, we propose a joint non-linear mixed effect model with a latent disease age, to overcome this need for a precise reference time. Method: To do so, we utilized an existing longitudinal model with a latent disease age as a longitudinal sub-model and associated it with a survival sub-model that estimates a Weibull distribution from the latent disease age. We then validated our model on different simulated scenarios. Finally, we benchmarked our model with a state-of-the-art joint model and reference survival and longitudinal models on simulated and real data in the context of Amyotrophic Lateral Sclerosis (ALS). Results: On real data, our model got significantly better results than the state-of-the-art joint model for absolute bias (4.21(4.41) versus 4.24(4.14)(p-value=1.4e-17)), and mean cumulative AUC for right censored events (0.67(0.07) versus 0.61(0.09)(p-value=1.7e-03)). Conclusion: We showed that our approach is better suited than the state-of-the-art in the context where the reference time is not reliable. This work opens up the perspective to design predictive and personalized therapeutic strategies.

Karthik Soman, Andrew Langdon, Catalina Villouta et al.

Rare diseases present unique challenges in healthcare, often suffering from delayed diagnosis and fragmented information landscapes. The scarcity of reliable knowledge in these conditions poses a distinct challenge for Large Language Models (LLMs) in supporting clinical management and delivering precise patient information underscoring the need for focused training on these 'zebra' cases. We present Zebra-Llama, a specialized context-aware language model with high precision Retrieval Augmented Generation (RAG) capability, focusing on Ehlers-Danlos Syndrome (EDS) as our case study. EDS, affecting 1 in 5,000 individuals, exemplifies the complexities of rare diseases with its diverse symptoms, multiple subtypes, and evolving diagnostic criteria. By implementing a novel context-aware fine-tuning methodology trained on questions derived from medical literature, patient experiences, and clinical resources, along with expertly curated responses, Zebra-Llama demonstrates unprecedented capabilities in handling EDS-related queries. On a test set of real-world questions collected from EDS patients and clinicians, medical experts evaluated the responses generated by both models, revealing Zebra-Llama's substantial improvements over base model (Llama 3.1-8B-Instruct) in thoroughness (77.5% vs. 70.1%), accuracy (83.0% vs. 78.8%), clarity (74.7% vs. 72.0%) and citation reliability (70.6% vs. 52.3%). Released as an open-source resource, Zebra-Llama not only provides more accessible and reliable EDS information but also establishes a framework for developing specialized AI solutions for other rare conditions. This work represents a crucial step towards democratizing expert-level knowledge in rare disease management, potentially transforming how healthcare providers and patients navigate the complex landscape of rare diseases.

Josué Pagán, José L. Risco-Martín, José M. Moya et al.

Prediction of symptomatic crises in chronic diseases allows to take decisions before the symptoms occur, such as the intake of drugs to avoid the symptoms or the activation of medical alarms. The prediction horizon is in this case an important parameter in order to fulfill the pharmacokinetics of medications, or the time response of medical services. This paper presents a study about the prediction limits of a chronic disease with symptomatic crises: the migraine. For that purpose, this work develops a methodology to build predictive migraine models and to improve these predictions beyond the limits of the initial models. The maximum prediction horizon is analyzed, and its dependency on the selected features is studied. A strategy for model selection is proposed to tackle the trade off between conservative but robust predictive models, with respect to less accurate predictions with higher horizons. The obtained results show a prediction horizon close to 40 minutes, which is in the time range of the drug pharmacokinetics. Experiments have been performed in a realistic scenario where input data have been acquired in an ambulatory clinical study by the deployment of a non-intrusive Wireless Body Sensor Network. Our results provide an effective methodology for the selection of the future horizon in the development of prediction algorithms for diseases experiencing symptomatic crises.

Yu-gen Li, Xiao-bin Chen, Chun-mei Wang et al.

BackgroundThe comparative advantages of robotic posterior retroperitoneal adrenalectomy (RPRA) over laparoscopic posterior retroperitoneal adrenalectomy (LPRA) remain a topic of ongoing debate within the medical community. This systematic literature review and meta-analysis aim to assess the safety and efficacy of RPRA compared to LPRA, with the ultimate goal of determining which procedure yields superior clinical outcomes.MethodsA systematic search was conducted on databases including PubMed, Embase, Web of Science, and the Cochrane Library database to identify relevant studies, encompassing both randomized controlled trials (RCTs) and non-RCTs, that compare the outcomes of RPRA and LPRA. The primary focus of this study was to evaluate perioperative surgical outcomes and complications. Review Manager 5.4 was used for this analysis. The study was registered with PROSPERO (ID: CRD42023453816).ResultsA total of seven non-RCTs were identified and included in this study, encompassing a cohort of 675 patients. The findings indicate that RPRA exhibited superior performance compared to LPRA in terms of hospital stay (weighted mean difference [WMD] -0.78 days, 95% confidence interval [CI] -1.46 to -0.10; p = 0.02). However, there were no statistically significant differences observed between the two techniques in terms of operative time, blood loss, transfusion rates, conversion rates, major complications, and overall complications.ConclusionRPRA is associated with a significantly shorter hospital stay compared to LPRA, while demonstrating comparable operative time, blood loss, conversion rate, and complication rate. However, it is important to note that further research of a more comprehensive and rigorous nature is necessary to validate these findings.Systematic review registrationhttps://www.crd.york.ac.uk/prospero/display_record.php?RecordID=453816, identifier CRD42023453816.

Isabella Bonilha, Beatriz Luchiari, Wilson Nadruz et al.

ABSTRACT In individuals with very low high-density lipoprotein (HDL-C) cholesterol, such as Tangier disease, LCAT deficiency, and familial hypoalphalipoproteinemia, there is an increased risk of premature atherosclerosis. However, analyzes based on comparisons of populations with small variations in HDL-C mediated by polygenic alterations do not confirm these findings, suggesting that there is an indirect association or heterogeneity in the pathophysiological mechanisms related to the reduction of HDL-C. Trials that evaluated some of the HDL functions demonstrate a more robust degree of association between the HDL system and atherosclerotic risk, but as they were not designed to modify lipoprotein functionality, there is insufficient data to establish a causal relationship. We currently have randomized clinical trials of therapies that increase HDL-C concentration by various mechanisms, and this HDL-C elevation has not independently demonstrated a reduction in the risk of cardiovascular events. Therefore, this evidence shows that (a) measuring HDL-C as a way of estimating HDL-related atheroprotective system function is insufficient and (b) we still do not know how to increase cardiovascular protection with therapies aimed at modifying HDL metabolism. This leads us to a greater effort to understand the mechanisms of molecular action and cellular interaction of HDL, completely abandoning the traditional view focused on the plasma concentration of HDL-C. In this review, we will detail this new understanding and the new horizon for using the HDL system to mitigate residual atherosclerotic risk.

Yongqi Gao, Zhongji Wu, Simin Liu et al.

BackgroundPreeclampsia (PE) is the primary cause of perinatal maternal-fetal mortality and morbidity. The exact molecular mechanisms of PE pathogenesis are largely unknown. This study aims to identify the hub genes in PE and explore their potential molecular regulatory network.MethodsWe downloaded the GSE148241, GSE190971, GSE74341, and GSE114691 datasets for the placenta and performed a differential expression analysis to identify hub genes. We performed Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), Disease Ontology (DO), Gene Set Enrichment Analysis (GSEA), and Protein–Protein Interaction (PPI) Analysis to determine functional roles and regulatory networks of differentially expressed genes (DEGs). We then verified the DEGs at transcriptional and translational levels by analyzing the GSE44711 and GSE177049 datasets and our clinical samples, respectively.ResultsWe identified 60 DEGs in the discovery phase, consisting of 7 downregulated genes and 53 upregulated genes. We then identified seven hub genes using Cytoscape software. In the verification phase, 4 and 3 of the seven genes exhibited the same variation patterns at the transcriptional level in the GSE44711 and GSE177049 datasets, respectively. Validation of our clinical samples showed that CADM3 has the best discriminative performance for predicting PEConclusionThese findings may enhance the understanding of PE and provide new insight into identifying potential therapeutic targets for PE.

Wentao Zhang, Yujun Huang, Tong Zhang et al.

Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed, under the condition of preserving old disease knowledge. In particular, updating an intelligent diagnosis system with training data of new diseases would cause catastrophic forgetting of old disease knowledge. To address the catastrophic forgetting issue, an Adapter-based Continual Learning framework called ACL is proposed to help effectively learn a set of new diseases at each round (or task) of continual learning, without changing the shared feature extractor. The learnable lightweight task-specific adapter(s) can be flexibly designed (e.g., two convolutional layers) and then added to the pretrained and fixed feature extractor. Together with a specially designed task-specific head which absorbs all previously learned old diseases as a single "out-of-distribution" category, task-specific adapter(s) can help the pretrained feature extractor more effectively extract discriminative features between diseases. In addition, a simple yet effective fine-tuning is applied to collaboratively fine-tune multiple task-specific heads such that outputs from different heads are comparable and consequently the appropriate classifier head can be more accurately selected during model inference. Extensive empirical evaluations on three image datasets demonstrate the superior performance of ACL in continual learning of new diseases. The source code is available at https://github.com/GiantJun/CL_Pytorch.

Katharina Waury

Discovery of novel protein biomarkers for clinical applications is an active research field across a manifold of diseases. Despite some successes and progress, the biomarker development pipeline still frequently ends in failure as biomarker candidates cannot be validated or translated to immunoassays. Selection of strong disease biomarker candidates that further constitute suitable targets for antibody binding in immunoassays is thus important. This essential selection step can be supported and rationalized using bioinformatics tools such as protein databases. Here, I present a workflow in the form of decision trees to computationally investigate biomarker candidates and their available affinity reagents in depth. This analysis can identify the most promising biomarker candidates for assay development while minimal time and effort is required.

Achyut Tiwari, Aryan Chugh, Aman Sharma

Heart disease is the major cause of non-communicable and silent death worldwide. Heart diseases or cardiovascular diseases are classified into four types: coronary heart disease, heart failure, congenital heart disease, and cardiomyopathy. It is vital to diagnose heart disease early and accurately in order to avoid further injury and save patients' lives. As a result, we need a system that can predict cardiovascular disease before it becomes a critical situation. Machine learning has piqued the interest of researchers in the field of medical sciences. For heart disease prediction, researchers implement a variety of machine learning methods and approaches. In this work, to the best of our knowledge, we have used the dataset from IEEE Data Port which is one of the online available largest datasets for cardiovascular diseases individuals. The dataset isa combination of Hungarian, Cleveland, Long Beach VA, Switzerland & Statlog datasets with important features such as Maximum Heart Rate Achieved, Serum Cholesterol, Chest Pain Type, Fasting blood sugar, and so on. To assess the efficacy and strength of the developed model, several performance measures are used, such as ROC, AUC curve, specificity, F1-score, sensitivity, MCC, and accuracy. In this study, we have proposed a framework with a stacked ensemble classifier using several machine learning algorithms including ExtraTrees Classifier, Random Forest, XGBoost, and so on. Our proposed framework attained an accuracy of 92.34% which is higher than the existing literature.

Ayush Garg, Julia Lu, Anika Maji

Oral diseases such as periodontal (gum) diseases and dental caries (cavities) affect billions of people across the world today. However, previous state-of-the-art models have relied on X-ray images to detect oral diseases, making them inaccessible to remote monitoring, developing countries, and telemedicine. To combat this overuse of X-ray imagery, we propose a lightweight machine learning model capable of detecting calculus (also known as hardened plaque or tartar) in RGB images while running efficiently on low-end devices. The model, a modified MobileNetV3-Small neural network transfer learned from ImageNet, achieved an accuracy of 72.73% (which is comparable to state-of-the-art solutions) while still being able to run on mobile devices due to its reduced memory requirements and processing times. A ResNet34-based model was also constructed and achieved an accuracy of 81.82%. Both of these models were tested on a mobile app, demonstrating their potential to limit the number of serious oral disease cases as their predictions can help patients schedule appointments earlier without the need to go to the clinic.

Susana Salzberg

Until a few years ago, the classification of the Food and Drug Administration (FDA) to indicate the level of risk of drugs on the fetus established five categories (A, B, C, D, X). Category X included contraindicated drugs, among which were statins. That is to say, there was a formal contraindication for statins to be used during pregnancy, or in women who could become pregnant, due to their possible teratogenic effects. Studies published after this categorization provided new data on the subject. In particular, they question the positive association between the use of statins in the embryogenic period and congenital malformations. Some studies have even shown that intrauterine exposure to statins favors prematurity and/or low birth weight.

Marta Bassi, Marta Bassi, Marina Francesca Strati et al.

ObjectiveTandem Control-IQ is an advanced hybrid closed loop (AHCL) system with a Sleep Activity Mode to intensify glycemic control overnight. The aim of the study is to evaluate the effectiveness of using Sleep Mode or not among Tandem Control-IQ users.Research design and methodsWe performed a retrospective Tandem Control-IQ data download for patients followed at IRCCS G. Gaslini Pediatric Diabetes Centre. We divided the patients into group 1 (Sleep Mode users) and group 2 (non-users) and compared their overall glycemic data, particularly during nighttime.ResultsGroup 1 (n = 49) does not show better nocturnal glycemic control as expected when compared with group 2 (n = 34). Group 2 shows a nighttime TIR% of 69.50 versus 66.25 (p = 0.20). Only the patients who do not use Sleep Mode and with sensor and automatic mode use ≥90% reached TIR &gt;70% during nighttime, as well as lower nocturnal TAR% (18.80 versus 21.78, p = 0.05).ConclusionsThis is the first study that evaluates the real-life effectiveness of the use of Sleep Mode in young patients with T1D. Control-IQ Sleep Activity Mode may not be as effective in Italian patients as in American patients due to the different habits.