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

Sungwoo Kang

Smartphone-based tele-dermatology assumes that colorimetric calibration ensures clinical reliability, yet this remains untested for underrepresented skin phototypes. We investigated whether standard calibration translates to reliable clinical biomarkers using 43,425 images from 965 Korean subjects (Fitzpatrick III-IV) across DSLR, tablet, and smartphone devices. While Linear Color Correction Matrix (CCM) normalization reduced color error by 67-77% -- achieving near-clinical accuracy (Delta E < 2.3) -- this success did not translate to biomarker reliability. We identify a phenomenon termed "color-clinical decoupling": despite perceptual accuracy, the Individual Typology Angle (ITA) showed poor inter-device agreement (ICC = 0.40), while the Melanin Index achieved good agreement (ICC = 0.77). This decoupling is driven by the ITA formula's sensitivity to b* channel noise and is further compounded by anatomical variance. Facial region accounts for 25.2% of color variance -- 3.6x greater than device effects (7.0%) -- challenging the efficacy of single-patch calibration. Our results demonstrate that current colorimetric standards are insufficient for clinical-grade biomarker extraction, necessitating region-aware protocols for mobile dermatology.

Sara Ketabi, Dhanesh Ramachandram

Conventional machine learning models, particularly tree-based approaches, have demonstrated promising performance across various clinical prediction tasks using electronic health record (EHR) data. Despite their strengths, these models struggle with tasks that require deeper contextual understanding, such as predicting 30-day hospital readmission. This can be primarily due to the limited semantic information available in structured EHR data. To address this limitation, we propose a deep multimodal contrastive learning (CL) framework that aligns the latent representations of structured EHR data with unstructured discharge summary notes. It works by pulling together paired EHR and text embeddings while pushing apart unpaired ones. Fine-tuning the pretrained EHR encoder extracted from this framework significantly boosts downstream task performance, e.g., a 4.1% AUROC enhancement over XGBoost for 30-day readmission prediction. Such results demonstrate the effect of integrating domain knowledge from clinical notes into EHR-based pipelines, enabling more accurate and context-aware clinical decision support systems.

Zifeng Wang, Jiacheng Lin, Qiao Jin et al.

Developing artificial intelligence (AI) for clinical research requires a comprehensive data foundation that supports model training and rigorous evaluation. Here, we introduce TrialPanorama, a large-scale structured resource that aggregates 1.6M clinical trial records from fifteen global registries and links them with biomedical ontologies and associated literature. To demonstrate its utility, we build a pipeline that constructs 152K training and testing samples for eight key clinical research tasks. Three tasks support systematic review workflows, including study search, study screening, and evidence summarization. Five tasks focus on trial design and optimization, including arm design, eligibility criteria design, endpoint selection, sample size estimation, and trial completion assessment and rationalization. Benchmarking cutting-edge large language models (LLMs) reveals that generic LLMs have limited capability in clinical reasoning. In contrast, an 8B LLM we developed on TrialPanorama using supervised finetuning and reinforcement learning wins over the 70B generic counterparts in all eight tasks, with a relative improvement of 73.7%, 67.6%, 38.4%, 37.8%, 26.5%, 20.7%, 20.0%, 18.1%, and 5.2%, respectively. We envision that TrialPanorama provides a solid foundation for future scaling of AI for clinical research.

Deval Mehta, Yiwen Jiang, Catherine L Jan et al.

Recent advancements in deep learning have shown significant potential for classifying retinal diseases using color fundus images. However, existing works predominantly rely exclusively on image data, lack interpretability in their diagnostic decisions, and treat medical professionals primarily as annotators for ground truth labeling. To fill this gap, we implement two key strategies: extracting interpretable concepts of retinal diseases using the knowledge base of GPT models and incorporating these concepts as a language component in prompt-learning to train vision-language (VL) models with both fundus images and their associated concepts. Our method not only improves retinal disease classification but also enriches few-shot and zero-shot detection (novel disease detection), while offering the added benefit of concept-based model interpretability. Our extensive evaluation across two diverse retinal fundus image datasets illustrates substantial performance gains in VL-model based few-shot methodologies through our concept integration approach, demonstrating an average improvement of approximately 5.8\% and 2.7\% mean average precision for 16-shot learning and zero-shot (novel class) detection respectively. Our method marks a pivotal step towards interpretable and efficient retinal disease recognition for real-world clinical applications.

Amrita Bhowmik, Begum Rokeya, Yearul Kabir

Conclusion: This study showed that rs5219 polymorphism of the KCNJ11 gene is a significant risk factor for Type 2 diabetes mellitus in the Bangladeshi population.

Ibrahim Mohammadzadeh, Bardia Hajikarimloo, Behnaz Niroomand et al.

Abstract Background Predicting pituitary adenoma (PA) recurrence after surgical resection is critical for guiding clinical decision-making, and machine learning (ML) based models show great promise in improving the accuracy of these predictions. These models can provide valuable insights to surgeons and oncologists, helping them tailor personalized treatment plans, enhance patient prognostication, and optimize follow-up strategies. Methods We systematically searched PubMed, Scopus, Embase, Cochrane Library, and Web of Science databases until November 2024, applying PRISMA guidelines. Results Out of 1240 studies screened, six met our eligibility criteria involving ML-based approaches to predict PA recurrence. The studies employed 12 different ML algorithms. Meta-analysis showed a pooled sensitivity of 0.87 [95% CI: 0.78–0.92], specificity of 0.86 [95% CI: 0.67–0.95], positive diagnostic likelihood ratio (DLR) of 6.32 [95% CI: 2.46–16.26], and negative DLR of 0.16 [95% CI: 0.1–0.25]. The diagnostic odds ratio (DOR) was 40.52 [95% CI: 13–126.27], and the diagnostic score was 3.7 [95% CI: 2.57–4.84]. The pooled AUC was 0.89 [95% CI: 0.86–0.92], indicating a high overall diagnostic performance. For the comparison between Logistic Regression (LR) and non-LR algorithms, LR-based algorithms exhibited numerically higher AUC and sensitivity; however, these differences were not statistically significant. Additionally, LR-based algorithms showed lower specificity, positive likelihood ratio, and diagnostic odds ratios, but the statistical tests did not provide strong evidence for meaningful differences. Conclusion AI-based models show strong predictive power for recurrence in both functional and non-functional pituitary adenomas, with an average accuracy above 80%. However, the lack of external validation and the complexity of input data pose challenges, highlighting the need for rigorous validation with multi-center datasets and standardized imaging techniques to enhance clinical applicability.

Yuhan Wang, Hailing Liu, Beini Zhou et al.

Abstract Background Menopause is a significant phase in women’s health, in which the incidence of obstructive sleep apnea (OSA) is significantly increased. Body fat distribution changes with age and hormone levels in postmenopausal women, but the extent to which changes in body fat distribution affect the occurrence of OSA is unclear. Methods This research performed a cross-sectional analysis utilizing data from the 2015–2016 National Health and Nutrition Examination Survey (NHANES). Body fat distribution was quantified using dual-energy X-ray absorptiometry in kilograms. Menopausal status and OSA symptoms were determined by questionnaire. Weighted multivariable regression analysis was utilized to investigate the correlation between menopausal status and OSA symptoms and body fat composition. We did a mediation analysis to assess how much of the effect of menopausal status on OSA symptoms was mediated through in body fat composition. Results The analysis comprised 1459 individuals from NHANES, consisting of 1188 premenopausal and 271 postmenopausal women. In the weighted sample, 36.01% of premenopausal women and 53.39% of postmenopausal women had OSA symptoms. After adjusting for body mass index (BMI) and other potential confounders, menopausal status was correlated with a higher prevalence of OSA symptoms (OR = 1.57; 95% CI: 1.16,2.13), and increased visceral fat mass (β = 0.12; 95% CI: 0.07, 0.17). In addition, visceral fat mass exhibited a significant correlation with OSA symptoms (OR = 3.79; 95% CI: 1.61, 8.94). Mediation analysis showed that 29.76% of the effect of menopausal status on OSA symptoms was mediated through visceral fat. In age-matched analysis, postmenopausal women had higher visceral fat mass (0.63 kg vs. 0.52 kg, P = 0.02) and a higher prevalence of OSA symptoms (68.3% vs. 45.7%, P = 0.02) compared with premenopausal women; however, there was no significant difference in BMI (P > 0.05). Conclusion Our results suggest that menopausal status is associated with increased visceral fat accumulation and OSA symptoms prevalence. Visceral fat accumulation appears to play an important role in the development of OSA in postmenopausal women, independent of BMI; this highlights the importance of further studying this relationship.

Xueyan Men, Peipei Yue, Weiwei Hao et al.

ObjectiveDiabetic kidney disease (DKD) is one of the most serious complications of type 2 diabetes mellitus (T2DM), and bone metabolism disorders show a close linkage to DKD. Thus, this study aimed to explore the association between bone turnover markers (BTMs) and DKD.MethodsIn present cross-sectional study, serum BTMs were detected in 1433 hospitalized patients with T2DM. Logistic regression analysis was used to investigate the associations between osteocalcin (N-MID), β-cross-linked C-telopeptide (β-CTX), total type I collagen N-terminal propeptide (PINP), and the risk of DKD.ResultsThe circulation N-MID, β-CTX, and PINP levels were significantly lower in the DKD group compared with the non-DKD group (all P &lt; 0.05), especially in male and aged &lt; 60 subgroups. Serum BTM levels showed a weak correlations with certain glucose metabolism parameters–such as glycated hemoglobin, fasting blood glucose, C peptide, and fasting insulin−as well as alkaline phosphatase (ALP) levels and low-density lipoprotein (all P &lt; 0.001). A weak negative correlation was also observed with the duration of diabetes (all P &lt; 0.0001). In addition, β-CTX levels showed a minimal positive correlation with eGFR (r = 0.057, P=0.036) and a modest correlation with ALP (r = 0.31, P &lt; 0.0001). After adjusting for potential confounders, higher serum β-CTX levels were independently associated with a lower risk of DKD. However, no significant associations were found among serum N-MID, PINP, and the risk of DKD.ConclusionBTM levels were significantly decreased in patients with DKD. Lower β-CTX levels were independently associated with a larger prevalence of DKD after adjusting for potential confounders, suggesting that serum β-CTX may be an independent marker associated with the risk of DKD.

Han Trinh, Jordan Vice, Jason Charng et al.

Inherited retinal diseases (IRDs) are a diverse group of genetic disorders that lead to progressive vision loss and are a major cause of blindness in working-age adults. The complexity and heterogeneity of IRDs pose significant challenges in diagnosis, prognosis, and management. Recent advancements in artificial intelligence (AI) offer promising solutions to these challenges. However, the rapid development of AI techniques and their varied applications have led to fragmented knowledge in this field. This review consolidates existing studies, identifies gaps, and provides an overview of AI's potential in diagnosing and managing IRDs. It aims to structure pathways for advancing clinical applications by exploring AI techniques like machine learning and deep learning, particularly in disease detection, progression prediction, and personalized treatment planning. Special focus is placed on the effectiveness of convolutional neural networks in these areas. Additionally, the integration of explainable AI is discussed, emphasizing its importance in clinical settings to improve transparency and trust in AI-based systems. The review addresses the need to bridge existing gaps in focused studies on AI's role in IRDs, offering a structured analysis of current AI techniques and outlining future research directions. It concludes with an overview of the challenges and opportunities in deploying AI for IRDs, highlighting the need for interdisciplinary collaboration and the continuous development of robust, interpretable AI models to advance clinical applications.

Thomas Yu Chow Tam, Litian Liang, Ke Chen et al.

Deep learning (DL) models have shown significant potential in Alzheimer's Disease (AD) classification. However, understanding and interpreting these models remains challenging, which hinders the adoption of these models in clinical practice. Techniques such as saliency maps have been proven effective in providing visual and empirical clues about how these models work, but there still remains a gap in understanding which specific brain regions DL models focus on and whether these brain regions are pathologically associated with AD. To bridge such gap, in this study, we developed a quantitative disease-focusing strategy to first enhance the interpretability of DL models using saliency maps and brain segmentations; then we propose a disease-focus (DF) score that quantifies how much a DL model focuses on brain areas relevant to AD pathology based on clinically known MRI-based pathological regions of AD. Using this strategy, we compared several state-of-the-art DL models, including a baseline 3D ResNet model, a pretrained MedicalNet model, and a MedicalNet with data augmentation to classify patients with AD vs. cognitive normal patients using MRI data; then we evaluated these models in terms of their abilities to focus on disease-relevant regions. Our results show interesting disease-focusing patterns with different models, particularly characteristic patterns with the pretrained models and data augmentation, and also provide insight into their classification performance. These results suggest that the approach we developed for quantitatively assessing the abilities of DL models to focus on disease-relevant regions may help improve interpretability of these models for AD classification and facilitate their adoption for AD diagnosis in clinical practice. The code is publicly available at https://github.com/Liang-lt/ADNI.

Panagiota Gatoula, Dimitrios E. Diamantis, Anastasios Koulaouzidis et al.

Synthetic Data Generation (SDG) based on Artificial Intelligence (AI) can transform the way clinical medicine is delivered by overcoming privacy barriers that currently render clinical data sharing difficult. This is the key to accelerating the development of digital tools contributing to enhanced patient safety. Such tools include robust data-driven clinical decision support systems, and example-based digital training tools that will enable healthcare professionals to improve their diagnostic performance for enhanced patient safety. This study focuses on the clinical evaluation of medical SDG, with a proof-of-concept investigation on diagnosing Inflammatory Bowel Disease (IBD) using Wireless Capsule Endoscopy (WCE) images. Its scientific contributions include a) a novel protocol for the systematic Clinical Evaluation of Medical Image Synthesis (CEMIS); b) a novel variational autoencoder-based model for the generation of high-resolution synthetic WCE images; and c) a comprehensive evaluation of the synthetic images using the CEMIS protocol by 10 international WCE specialists, in terms of image quality, diversity, and realism, as well as their utility for clinical decision-making. The results show that TIDE-II generates clinically plausible, very realistic WCE images, of improved quality compared to relevant state-of-the-art generative models. Concludingly, CEMIS can serve as a reference for future research on medical image-generation techniques, while the adaptation/extension of the architecture of TIDE-II to other imaging domains can be promising.

Chufan Gao, Mandis Beigi, Afrah Shafquat et al.

Analyzing data from past clinical trials is part of the ongoing effort to optimize the design, implementation, and execution of new clinical trials and more efficiently bring life-saving interventions to market. While there have been recent advances in the generation of static context synthetic clinical trial data, due to both limited patient availability and constraints imposed by patient privacy needs, the generation of fine-grained synthetic time-sequential clinical trial data has been challenging. Given that patient trajectories over an entire clinical trial are of high importance for optimizing trial design and efforts to prevent harmful adverse events, there is a significant need for the generation of high-fidelity time-sequence clinical trial data. Here we introduce TrialSynth, a Variational Autoencoder (VAE) designed to address the specific challenges of generating synthetic time-sequence clinical trial data. Distinct from related clinical data VAE methods, the core of our method leverages Hawkes Processes (HP), which are particularly well-suited for modeling event-type and time gap prediction needed to capture the structure of sequential clinical trial data. Our experiments demonstrate that TrialSynth surpasses the performance of other comparable methods that can generate sequential clinical trial data at varying levels of fidelity / privacy tradeoff, enabling the generation of highly accurate event sequences across multiple real-world sequential event datasets with small patient source populations. Notably, our empirical findings highlight that TrialSynth not only outperforms existing clinical sequence-generating methods but also produces data with superior utility while empirically preserving patient privacy.

Indraneel Banerjee, Klaus Mohnike

Anna Fedorczak, Andrzej Lewiński, Andrzej Lewiński et al.

IntroductionSirtuin 1 (SIRT1) is known to be involved in sensing cellular energy levels and regulating energy metabolism. This study aimed to evaluate fasting serum SIRT1 levels in healthy children, and to analyse the influence of age, sex, puberty, body weight, height, and diet on its concentration.Methods47 healthy children aged 4-14 with weight and height within normal range and no chronic disease were included into the study. Fasting serum SIRT1 concentrations were estimated by Enzyme Linked Immunosorbent Assay (ELISA).ResultsResults showed that serum SIRT1 concentrations in healthy children did not differ with respect to sex, age, height, weight and puberty. Whereas, it appeared that a higher frequency of fruits, vegetables and dairy products consumption was associated with an increase in serum SIRT1 levels.DiscussionStudying SIRT1 in the context of children’s health may have implications for a broader understanding of growth processes, pubertal development, metabolic disorders and nutrition.

Xianbin Cheng, Xiangfu Ding, Sijia Wang et al.

Gasless endoscopic thyroidectomy obviates the necessity for carbon dioxide insufflation to establish a surgical workspace, thus mitigating the potential complications associated with this practice. This technique presents several benefits, such as the maintenance of neck functionality, minimal scarring, and enhanced visibility of the surgical field, which contribute to its extensive adoption in clinical settings. The objective of this study is to synthesize the current methodologies of gasless endoscopic thyroidectomy and to evaluate the advantages and disadvantages inherent to each technique. It aims to offer theoretical insights to assist surgeons in determining the most suitable approach for gasless endoscopic thyroidectomy in their clinical practice.

Zifeng Wang, Cao Xiao, Jimeng Sun

Clinical trials are critical for drug development. Constructing the appropriate eligibility criteria (i.e., the inclusion/exclusion criteria for patient recruitment) is essential for the trial's success. Proper design of clinical trial protocols should consider similar precedent trials and their eligibility criteria to ensure sufficient patient coverage. In this paper, we present a method named AutoTrial to aid the design of clinical eligibility criteria using language models. It allows (1) controllable generation under instructions via a hybrid of discrete and neural prompting, (2) scalable knowledge incorporation via in-context learning, and (3) explicit reasoning chains to provide rationales for understanding the outputs. Experiments on over 70K clinical trials verify that AutoTrial generates high-quality criteria texts that are fluent and coherent and with high accuracy in capturing the relevant clinical concepts to the target trial. It is noteworthy that our method, with a much smaller parameter size, gains around 60% winning rate against the GPT-3.5 baselines via human evaluations.

Zolzaya Dashdorj, Stanislav Grigorev, Munguntsatsral Dovdondash

In the field of health-care and bio-medical research, understanding the relationship between the symptoms of diseases is crucial for early diagnosis and determining hidden relationships between diseases. The study aimed to understand the extent of symptom types in disease prediction tasks. In this research, we analyze a pre-generated symptom-based human disease dataset and demonstrate the degree of predictability for each disease based on the Convolutional Neural Network and the Support Vector Machine. Ambiguity of disease is studied using the K-Means and the Principal Component Analysis. Our results indicate that machine learning can potentially diagnose diseases with the 98-100% accuracy in the early stage, taking the characteristics of symptoms into account. Our result highlights that types of unusual symptoms are a good proxy for disease early identification accurately. We also highlight that unusual symptoms increase the accuracy of the disease prediction task.

Eric Lehman, Evan Hernandez, Diwakar Mahajan et al.

Although recent advances in scaling large language models (LLMs) have resulted in improvements on many NLP tasks, it remains unclear whether these models trained primarily with general web text are the right tool in highly specialized, safety critical domains such as clinical text. Recent results have suggested that LLMs encode a surprising amount of medical knowledge. This raises an important question regarding the utility of smaller domain-specific language models. With the success of general-domain LLMs, is there still a need for specialized clinical models? To investigate this question, we conduct an extensive empirical analysis of 12 language models, ranging from 220M to 175B parameters, measuring their performance on 3 different clinical tasks that test their ability to parse and reason over electronic health records. As part of our experiments, we train T5-Base and T5-Large models from scratch on clinical notes from MIMIC III and IV to directly investigate the efficiency of clinical tokens. We show that relatively small specialized clinical models substantially outperform all in-context learning approaches, even when finetuned on limited annotated data. Further, we find that pretraining on clinical tokens allows for smaller, more parameter-efficient models that either match or outperform much larger language models trained on general text. We release the code and the models used under the PhysioNet Credentialed Health Data license and data use agreement.

Viktor Schlegel, Abhinav Ramesh Kashyap, Thanh-Tung Nguyen et al.

Computerised clinical coding approaches aim to automate the process of assigning a set of codes to medical records. While there is active research pushing the state of the art on clinical coding for hospitalized patients, the outpatient setting -- where doctors tend to non-hospitalised patients -- is overlooked. Although both settings can be formalised as a multi-label classification task, they present unique and distinct challenges, which raises the question of whether the success of inpatient clinical coding approaches translates to the outpatient setting. This paper is the first to investigate how well state-of-the-art deep learning-based clinical coding approaches work in the outpatient setting at hospital scale. To this end, we collect a large outpatient dataset comprising over 7 million notes documenting over half a million patients. We adapt four state-of-the-art clinical coding approaches to this setting and evaluate their potential to assist coders. We find evidence that clinical coding in outpatient settings can benefit from more innovations in popular inpatient coding benchmarks. A deeper analysis of the factors contributing to the success -- amount and form of data and choice of document representation -- reveals the presence of easy-to-solve examples, the coding of which can be completely automated with a low error rate.

Yurong Hu, Manuel Burger, Gunnar Rätsch et al.

In research areas with scarce data, representation learning plays a significant role. This work aims to enhance representation learning for clinical time series by deriving universal embeddings for clinical features, such as heart rate and blood pressure. We use self-supervised training paradigms for language models to learn high-quality clinical feature embeddings, achieving a finer granularity than existing time-step and patient-level representation learning. We visualize the learnt embeddings via unsupervised dimension reduction techniques and observe a high degree of consistency with prior clinical knowledge. We also evaluate the model performance on the MIMIC-III benchmark and demonstrate the effectiveness of using clinical feature embeddings. We publish our code online for replication.