检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Guevara, Marco Chen, Shan Thomas, Spencer Chaunzwa, Tafadzwa L. Franco, Idalid Kann, Benjamin Moningi, Shalini Qian, Jack Goldstein, Madeleine Harper, Susan Aerts, Hugo J.W.L. Savova, Guergana K. Mak, Raymond H. Bitterman, Danielle S. Program Mass General Brigham Harvard Medical School BostonMA United States Department of Radiation Oncology Brigham and Women’s Hospital Dana-Farber Cancer Institute BostonMA United States Radiology and Nuclear Medicine GROW & CARIM Maastricht University Netherlands Computational Health Informatics Program Boston Children’s Hospital Harvard Medical School BostonMA United States

Objective/Purpose: Social determinants of health (SDoH) have an important impact on patient outcomes but are incompletely collected from the electronic health records (EHR). This study researched the ability of large language models to extract SDoH from free text in EHRs, where they are most commonly documented, and explored the role of synthetic clinical text for improving the extraction of these scarcely documented, yet extremely valuable, clinical data. Materials/Methods: A corpus of 800 patient notes was manually annotated for clinically impactful SDoH categories that are not reliably documented in the EHR as structured data: employment, housing, transportation, parental status, relationship, and social support. Two additional datasets were annotated to assess generalizability: patients' notes from a different clinic in the same hospital system, and MIMIC-III notes. We defined two sentence-level multilabel classification tasks: (1) classifying any SDoH and (2) classifying adverse SDoH. Several fine-tuned transformer-based models including BERT and Flan-T5, were evaluated. We experimented with synthetic data generation to augment the training set, as well as to explore the zero- and few-shot performance of ChatGPT-family models. We assessed for algorithmic bias, and compared SDoH information captured by our models versus structured EHR data. Results: Our best-performing models were fine-tuned Flan-T5 XL (macro-F1 0.71) for any SDoH, and Flan-T5 XXL (macro-F1 0.70). The benefit of augmenting fine-tuning with synthetic data varied across model architecture and size, with smaller Flan-T5 models (base and large) showing the greatest improvements in performance (delta F1 +0.12 to +0.23). Model performance was similar on the in-hospital system dataset but worse on the MIMIC-III dataset. Our best-performing fine-tuned models outperformed zero- and few-shot performance of ChatGPT-family models for both tasks. These fine-tuned models were less likely than ChatGPT to chang

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge Distillation

Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge D...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Tin-Han Chi Kai-Chun Liu Chia-Yeh Hsieh Yu Tsao Chia-Tai Chan Department of Biomedical Engineering National Yang Ming Chiao Tung University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan

Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems" using deep learning to support wearable-based fall protection systems for preventing severe injuries. However, most works only employed simple neural network models instead of complex models considering the usability in resource-constrained mobile devices and strict latency requirements. In this work, we propose a novel pre-impact fall detection via CNN-ViT knowledge distillation, namely PreFallKD, to strike a balance between detection performance and computational complexity. The proposed PreFallKD transfers the detection knowledge from the pre-trained teacher model (vision transformer) to the student model (lightweight convolutional neural networks). Additionally, we apply data augmentation techniques to tackle issues of data imbalance. We conduct the experiment on the KFall public dataset and compare PreFallKD with other state-of-the-art models. The experiment results show that PreFallKD could boost the student model during the testing phase and achieves reliable F1-score (92.66%) and lead time (551.3 ms).

关键词： Computational modeling System performance Aging Transformers Reliability Fall detection Usability

来源：评论

学校读者我要写书评

暂无评论

PREFALLKD: PRE-IMPACT FALL DETECTION VIA CNN-VIT KNOWLEDGE DISTILLATION

arXiv

引用

arXiv 2023年

作者： Chi, Tin-Han Liu, Kai-Chun Hsieh, Chia-Yeh Tsao, Yu Chan, Chia-Tai Department of Biomedical Engineering National Yang Ming Chiao Tung University Taiwan Research Center for information Technology Innovation Academia Sinica Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Underimmunisation during the 2025 Texas measles outbreak

引用

The Lancet. Infectious diseases 2025年第6期25卷 607-609页

作者： Erin N Hulland Marie-Laure Charpignon Thomas Berkane Maimuna S Majumder Computational Health Informatics Program Boston Children's Hospital & Harvard Medical School Boston MA 02115 USA Comp Epi Dispersed Volunteer Research Network Boston MA USA. Electronic address: erin.frame@childrens.harvard.edu. Comp Epi Dispersed Volunteer Research Network Boston MA USA.

来源：评论

学校读者我要写书评

暂无评论

Early-Life Risks of Central Precocious Puberty

引用

Endocrine Practice 2025年

作者： Yin, Wei-Jou Hsu, Jhih-Wei Chen, Chun-Chang Su, Emily Chia-Yu Wang, San-Yuan Chen, Yan-Jen Chen, Yang-Ching College of Medicine Taipei Medical University Taipei Taiwan Department of Family Medicine School of Medicine College of Medicine Taipei Medical University Taipei Taiwan Graduate Institute of Biomedical Informatics Taipei Medical University Taipei Taiwan Master Program in Clinical Genomics and Proteomics Department of Pharmaceutical Sciences Taipei Medical University Taipei Taiwan Department of Family Medicine Wan Fang Hospital Taipei Medical University Taipei Taiwan Nutrition Research Center Taipei Medical University Hospital Taipei Taiwan

Objectives: To investigate the factors in early life that may contribute to central precocious puberty (CPP). Methods: The study utilized data from the Taiwan Puberty Longitudinal Study, including 2241 children under pubertal assessment and a questionnaire of risk factors. We analyzed associations using the Fitting Generalized Linear Models in R (R Core Team, 2023), with R studio (Posit, 2023) version 4.3.1. Results: Among the 2241 children examined, 745 had CPP. Overall, higher gestational weight gain (GWG) increased the risk of CPP (odds ratio [OR]: 1.03, 95% CI: 1.01-1.05);while higher GWG served as a protective factor in females (OR: 0.97, 95% CI: 0.95-0.99). Maternal gestational diabetes mellitus (GDM) also increased the CPP risk, particularly in males (OR: 2.66, 95% CI: 1.00-7.25). Longer exclusive breastfeeding was linked to lower CPP risk overall (OR: 0.96, 95% CI: 0.93-1.00) but was not significant when analyzed by gender. Conclusions: Higher maternal GWG was associated with an increased risk of CPP overall, while GWG became negatively associated with CPP, only in females. Maternal GDM was linked to a higher risk of CPP, particularly in males. The duration of exclusive breastfeeding was inversely correlated with CPP risk, but this effect was not significant when analyzed by gender. © 2025 AACE

关键词： central precocious puberty early-life risk factors pediatrics

来源：评论

学校读者我要写书评

暂无评论

Distributional bias compromises leave-one-out cross-validation

arXiv

引用

arXiv 2024年

作者： Austin, George I. Pe’er, Itsik Korem, Tal Department of Biomedical Informatics Columbia University Irving Medical Center New YorkNY United States Program for Mathematical Genomics Department of Systems Biology Columbia University Irving Medical Center New YorkNY United States Department of Computer Science Columbia University New YorkNY United States Department of Obstetrics and Gynecology Columbia University Irving Medical Center New YorkNY United States

Cross-validation is a common method for estimating the predictive performance of machine learning models. In a data-scarce regime, where one typically wishes to maximize the number of instances used for training the model, an approach called ‘leave-one-out cross-validation’ is often used. In this design, a separate model is built for predicting each data instance after training on all other instances. Since this results in a single test data point available per model trained, predictions are aggregated across the entire dataset to calculate common rank-based performance metrics such as the area under the receiver operating characteristic or precision-recall curves. In this work, we demonstrate that this approach creates a negative correlation between the average label of each training fold and the label of its corresponding test instance, a phenomenon that we term distributional bias. As machine learning models tend to regress to the mean of their training data, this distributional bias tends to negatively impact performance evaluation and hyperparameter optimization. We show that this effect generalizes to leave-P-out cross-validation and persists across a wide range of modeling and evaluation approaches, and that it can lead to a bias against stronger regularization. To address this, we propose a generalizable rebalanced cross-validation approach that corrects for distributional bias. We demonstrate that our approach improves cross-validation performance evaluation in synthetic simulations and in several published leave-one-out analyses. © 2024, CC BY-SA.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Empowering Biomedical Discovery with AI Agents

arXiv

引用

arXiv 2024年

作者： Gao, Shanghua Fang, Ada Huang, Yepeng Giunchiglia, Valentina Noori, Ayush Schwarz, Jonathan Richard Ektefaie, Yasha Kondic, Jovana Zitnik, Marinka Department of Biomedical Informatics Harvard Medical School BostonMA United States Department of Chemistry and Chemical Biology Harvard University CambridgeMA United States Program in Biological and Biomedical Sciences Harvard Medical School BostonMA United States Department of Brain Sciences Imperial College London London United Kingdom Harvard College CambridgeMA United States Program in Biomedical Informatics Harvard Medical School BostonMA United States Department of Electrical Engineering and Computer Science MIT CambridgeMA United States Kempner Institute for the Study of Natural and Artificial Intelligence Harvard University MA United States Broad Institute of MIT and Harvard CambridgeMA United States Harvard Data Science Initiative CambridgeMA United States

We envision "AI scientists" as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate AI models and biomedical tools with experimental platforms. Rather than taking humans out of the discovery process, biomedical AI agents combine human creativity and expertise with AI’s ability to analyze large datasets, navigate hypothesis spaces, and execute repetitive tasks. AI agents are poised to be proficient in various tasks, planning discovery workflows and performing self-assessment to identify and mitigate gaps in their knowledge. These agents use large language models and generative models to feature structured memory for continual learning and use machine learning tools to incorporate scientific knowledge, biological principles, and theories. AI agents can impact areas ranging from virtual cell simulation, programmable control of phenotypes, and the design of cellular circuits to developing new therapies. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for computational pathology identifies model limitations and tissue biomarkers

arXiv

引用

arXiv 2024年

作者： Kaczmarzyk, Jakub R. Saltz, Joel H. Koo, Peter K. Department of Biomedical Informatics Stony Brook University Stony BrookNY United States Simons Center for Quantitative Biology Cold Spring Harbor Laboratory Cold Spring HarborNY United States Medical Scientist Training Program Stony Brook University Stony BrookNY United States

Introduction: Deep learning models hold great promise for digital pathology, but their opaque decision-making processes undermine trust and hinder clinical adoption. Explainable AI methods are essential to enhance model transparency and reliability. Methods: We developed HIPPO, an explainable AI framework that systematically modifies tissue regions in whole slide images to generate image counterfactuals, enabling quantitative hypothesis testing, bias detection, and model evaluation beyond traditional performance metrics. HIPPO was applied to a variety of clinically important tasks, including breast metastasis detection in axillary lymph nodes, prognostication in breast cancer and melanoma, and IDH mutation classification in gliomas. In computational experiments, HIPPO was compared against traditional metrics and attention-based approaches to assess its ability to identify key tissue elements driving model predictions. Results: In metastasis detection, HIPPO uncovered critical model limitations that were undetectable by standard performance metrics or attention-based methods. For prognostic prediction, HIPPO outperformed attention by providing more nuanced insights into tissue elements influencing outcomes. In a proof-of-concept study, HIPPO facilitated hypothesis generation for identifying melanoma patients who may benefit from immunotherapy. In IDH mutation classification, HIPPO more robustly identified the pathology regions responsible for false negatives compared to attention, suggesting its potential to outperform attention in explaining model decisions. Conclusions: HIPPO expands the explainable AI toolkit for computational pathology by enabling deeper insights into model behavior. This framework supports the trustworthy development, deployment, and regulation of weakly-supervised models in clinical and research settings, promoting their broader adoption in digital pathology. © 2024, CC BY-NC-SA.

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Facilitating decision making in authentic contexts: an SVVR-based experiential flipped learning approach for professional training

引用

Interactive Learning Environments 2023年第8期31卷 5219-5235页

作者： Hsin Huang Gwo-Jen Hwang Shao-Chen Chang a Department of Nursing Tri-Service General Hospital National Defense Medical Center Taipei Taiwan b Graduate Institute of Digital Learning and Education National Taiwan University of Science and Technology Taipei Taiwan c International Bachelor Program in Informatics and the Department of Information Communication Yuan Ze University Chung-Li Taiwan

ABSTRACTFacilitating decision making in authentic contexts is an important educational objective of professional training. To enable learners to have more opportunities to practice in authentic contexts under the guidance of instructors, the flipped learning mode of shifting the lectures to be the pre-class activity with the presentation of digital media has gradually been receiving attention. However, the conventional flipped learning mostly uses videos to present teaching content. In such a learning environment with one-way information and lack of experience, it is not easy for most learners to experience the actual situation encountered in the nursing procedure, which affects their judgment and performance when dealing with actual scenarios. To solve this problem, the present study adopted spherical video-based virtual reality (SVVR) to provide an experiential learning mode in flipped learning. To verify the effects of this teaching mode, this study conducted an experiment in a blood transfusion safety training course. The experimental group used the SVVR-based experiential flipped learning (SVVR-EFL) mode, while the control group used the conventional flipped learning mode. The results showed that using the SVVR-EFL mode not only enhanced new nursing staff’s learning achievement, but also increased their decision-making performance, meta-cognition tendency, problem-solving tendency and classroom engagement.

关键词： Flipped learning virtual reality experiential learning decision making professional training

来源：评论

学校读者我要写书评

暂无评论

Trends in Undiagnosed Diabetes Mellitus Among United States Adults: Cross-Sectional Analyses from NHANES 2011-2020

引用

AMERICAN JOURNAL OF CARDIOLOGY 2022年 175卷 184-185页

作者： Gupta, Kartik Obeidat, Liyan Kakar, Tanya Singh Fadel, Raef Ali Al Rifai, Mahmoud Abushamat, Layla A. Virani, Salim S. [a]Department of Medicine Henry Ford Hospital Detroit Michigan [b]Division of Hospital Medicine Henry Ford Hospital Detroit Michigan [c]Section of Cardiology and Cardiovascular Research Department of Medicine Baylor College of Medicine Houston Texas [d]Health Policy Quality & Informatics Program Health Services Research and Development Center for Innovations in Quality Effectiveness and Safety (IQuESt) Michael E. DeBakey Veterans Affairs Medical Center Houston Texas [e]Section of Cardiology Michael E. DeBakey Veterans Affairs Medical Center Houston Texas

Early detection and management of diabetes mellitus (DM) will help achieve the World Health Organization Global Action Plan target of a 25% relative reduction in premature mortality because of non-communicable diseases.1 Currently, there are limited data on the prevalence and racial disparities in undiagnosed DM in the United States after 2016. Undiagnosed DM was defined as glycated hemoglobin (HbA1c) ≥6.5% (≥48 mmol/mol) and fasting plasma glucose (FPG) ≥126 mg/100 ml (≥7.0 mmol/L) in the same blood sample in participants without diagnosed DM. The lower prevalence in our study versus the Centers for Disease Control and Prevention data available online is because of confirmatory testing and sample weighting in our analyses.4 We feel this reflects the disease burden more accurately.5 Our study has limitations inherent to survey-based *** The authors have no conflicts of interest to *** materials Supplementary material associated with this article can be found in the online version at https://***/10.1016/*** Supplementary materials Image, application 1

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：