检索结果-内蒙古大学图书馆

Uncertainty abounds, what now?

学校读者我要写书评

暂无评论

science 2025年第6740期387卷 1261页

作者： Dov Greenbaum Mark Gerstein The reviewer is at the Zvi Meitar Institute for Legal Implications of Emerging Technologies The reviewer is at the Harry Radzyner Law School The reviewer is at the Dina Recanati School of Medicine Reichman University Herzliya Israel The reviewer is at the Department of Biomedical Informatics and Data Science The reviewer is at the Program in Computational Biology and Bioinformatics The reviewer is at the Department of Computer Science Yale University New Haven CT USA.

No winners: Performance of lung cancer prediction models depends on screening-detected, incidental, and biopsied pulmonary nodule use cases.

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Thomas Z. Xu, Kaiwen Krishnan, Aravind Gao, Riqiang Kammer, Michael N. Antic, Sanja Xiao, David Knight, Michael Martinez, Yency Paez, Rafael Lentz, Robert J. Deppen, Stephen Grogan, Eric L. Lasko, Thomas A. Sandler, Kim L. Maldonado, Fabien Landman, Bennett A. Medical Scientist Training Program Vanderbilt University NashvilleTN37235 United States Biomedical Engineering Vanderbilt University NashvilleTN37235 United States Computer Science Vanderbilt University NashvilleTN37235 United States Electrical and Computer Engineering Vanderbilt University NashvilleTN37235 United States Digital Technology and Innovation Siemens Healthineers PrincetonNJ08540 United States Division of Allergy Pulmonary and Critical Care Medicine Department of Medicine Vanderbilt University Medical Center NashvilleTN37232 United States Department of Thoracic Surgery Vanderbilt University Medical Center NashvilleTN37232 United States Biomedical Informatics Vanderbilt University Medical Center NashvilleTN37232 United States Radiology and Radiological Sciences Vanderbilt University Medical Center NashvilleTN37232 United States

Purpose: Statistical models for predicting lung cancer have the potential to facilitate earlier diagnosis of malignancy and avoid invasive workup of benign disease. Many models have been published, but comparative studies of their utility in different clinical settings in which patients would arguably most benefit are scarce. Materials and Methods: This study retrospectively evaluated promising predictive models for lung cancer prediction in three clinical settings: lung cancer screening with low-dose computed tomography, incidentally detected pulmonary nodules, and nodules deemed suspicious enough to warrant a biopsy. We leveraged 9 cohorts (n=898, 896, 882, 219, 364, 117, 131, 115, 373) from multiple institutions to assess the area under the receiver operating characteristic curve (AUC) of validated models including logistic regressions on clinical variables and radiologist nodule characterizations, artificial intelligence on chest CTs, longitudinal imaging AI, and multi-modal approaches. We implemented each model from their published literature, re-training the models if necessary, and curated each cohort from primary data sources. Results: We observed that model performance varied greatly across clinical use cases. No single predictive model emerged as a clear winner across all cohorts, but certain models excelled in specific clinical contexts. Single timepoint chest CT AI performed well in lung screening, but struggled to generalize to other clinical settings. Longitudinal imaging and multimodal models demonstrated comparatively promising performance on incidentally-detected nodules. However, when applied to nodules that underwent biopsy, all models underperformed. Conclusion: These results underscore the strengths and limitations of 8 validated predictive models and highlight promising directions towards personalized, noninvasive lung cancer diagnosis. © 2024, CC BY-NC-SA.

关键词： Biopsy

An Open-Source Knowledge Graph Ecosystem for the Life sciences

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Callahan, Tiffany J. Tripodi, Ignacio J. Stefanski, Adrianne L. Cappelletti, Luca Taneja, Sanya B. Wyrwa, Jordan M. Casiraghi, Elena Matentzoglu, Nicolas A. Reese, Justin Silverstein, Jonathan C. Hoyt, Charles Tapley Boyce, Richard D. Malec, Scott A. Unni, Deepak R. Joachimiak, Marcin P. Robinson, Peter N. Mungall, Christopher J. Cavalleri, Emanuele Fontana, Tommaso Valentini, Giorgio Mesiti, Marco Gillenwater, Lucas A. Santangelo, Brook Vasilevsky, Nicole A. Hoehndorf, Robert Bennett, Tellen D. Ryan, Patrick B. Hripcsak, George Kahn, Michael G. Bada, Michael Baumgartner, William A. Hunter, Lawrence E. Computational Bioscience Program University of Colorado Anschutz Medical Campus AuroraCO80045 United States Department of Biomedical Informatics Columbia University Irving Medical Center New YorkNY10032 United States Computer Science Department Interdisciplinary Quantitative Biology University of Colorado Boulder BoulderCO80301 United States AnacletoLab Computer Science Department University of Milan 20122 Italy Intelligent Systems Program University of Pittsburgh PittsburghPA15260 United States Department of Physical Medicine and Rehabilitation School of Medicine University of Colorado Anschutz Medical Campus AuroraCO80045 United States Division of Environmental Genomics and Systems Biology Lawrence Berkeley National Laboratory BerkeleyCA94720 United States Semanticly Ltd Athens Greece Department of Biomedical Informatics University of Pittsburgh School of Medicine PittsburghPA15206 United States Laboratory of Systems Pharmacology Harvard Medical School BostonMA02115 United States Division of Translational Informatics University of New Mexico School of Medicine AlbuquerqueNM87131 United States SIB Swiss Institute of Bioinformatics Basel Switzerland Berlin Institute of Health at Charité-Universitatsmedizin Berlin10117 Germany ELLIS European Laboratory for Learning and Intelligent Systems Germany Department of Biomedical Informatics University of Colorado School of Medicine AuroraCO80045 United States Data Collaboration Center Critical Path Institute 1840 E River Rd. Suite 100 TucsonAZ85718 United States Computer Electrical and Mathematical Sciences & Engineering Division Computational Bioscience Research Center King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Pediatrics University of Colorado School of Medicine AuroraCO80045 United States Janssen Research and Development RaritanNJ08869 United States Division of General Internal Medicine University of Colorado School of Medicine A

Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability of these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, and methods exist to construct them automatically. However, tackling complex biomedical integration problems requires flexibility in the way knowledge is modeled. Moreover, existing KG construction methods provide robust tooling at the cost of fixed or limited choices among knowledge representation models. PheKnowLator (Phenotype Knowledge Translator) is a semantic ecosystem for automating the FAIR (Findable, Accessible, Interoperable, and Reusable) construction of ontologically grounded KGs with fully customizable knowledge representation. The ecosystem includes KG construction resources (e.g., data preparation APIs), analysis tools (e.g., SPARQL endpoints and abstraction algorithms), and benchmarks (e.g., prebuilt KGs and embeddings). We evaluated the ecosystem by systematically comparing it to existing open-source KG construction methods and by analyzing its computational performance when used to construct 12 large-scale KGs. With flexible knowledge representation, PheKnowLator enables fully customizable KGs without compromising performance or usability. © 2023, CC BY.

关键词： Ecosystems

Contrastive Learning of Medical Visual Representations from Paired Images and Text

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Yuhao Jiang, Hang Miura, Yasuhide Manning, Christopher D. Langlotz, Curtis P. Biomedical Informatics Training Program Stanford University United States Symbolic Systems Program Stanford University United States Computer Science Department Stanford University United States Computer Science and Linguistics Departments Stanford University United States Department of Radiology Stanford University United States

Learning visual representations of medical images (e.g., X-rays) is core to medical image understanding but its progress has been held back by the scarcity of human annotations. Existing work commonly relies on fine-tuning weights transferred from ImageNet pretraining, which is suboptimal due to drastically different image characteristics, or rule-based label extraction from the textual report data paired with medical images, which is inaccurate and hard to generalize. Meanwhile, several recent studies show exciting results from unsupervised contrastive learning from natural images, but we find these methods help little on medical images because of their high inter-class similarity. We propose ConVIRT, an alternative unsupervised strategy to learn medical visual representations by exploiting naturally occurring paired descriptive text. Our new method of pretraining medical image encoders with the paired text data via a bidirectional contrastive objective between the two modalities is domain-agnostic, and requires no additional expert input. We test ConVIRT by transferring our pretrained weights to 4 medical image classification tasks and 2 zero-shot retrieval tasks, and show that it leads to image representations that considerably outperform strong baselines in most settings. Notably, in all 4 classification tasks, our method requires only 10% as much labeled training data as an ImageNet initialized counterpart to achieve better or comparable performance, demonstrating superior data efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： Zero-shot learning

Treatment Algorithm for the Resorption of Calcific Tendinitis Using Extracorporeal Shockwave Therapy: A Data Mining Study

学校读者我要写书评

暂无评论

Orthopaedic Journal of Sports Medicine 2024年第3期12卷 23259671241231609页

作者： Chou, Wen-Yi Cheng, Jai-Hong Lien, Yu-Jui Huang, Tian-Hsiang Ho, Wen-Hsien Chou, Paul Pei-Hsi Doctoral Degree Program in Biomedical Engineering College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Department of Orthopedic Surgery Kaohsiung Chang Gung Memorial Hospital Chang Gung University College of Medicine Kaohsiung Taiwan Department of Leisure and Sport Management Cheng Shiu University Kaohsiung Taiwan Center for Shockwave Medicine and Tissue Engineering Department of Medical Research Kaohsiung Chang Gung Memorial Hospital Chang Gung University College of Medicine Kaohsiung Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan College of Professional Studies National Pingtung University of Science and Technology Pingtung Taiwan Department of Sports Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Division of Sports Medicine Department of Orthopaedic Surgery Kaohsiung Medical University Hospital Kaohsiung Taiwan Department of Orthopaedics School of Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Department of Orthopaedic Surgery Kaohsiung Municipal Hsiao-Kang Hospital Kaohsiung Taiwan

Background: Although evidence indicates that extracorporeal shockwave therapy (ESWT) is effective in treating calcifying shoulder tendinitis, incomplete resorption and dissatisfactory results are still reported in many cases. Data mining techniques have been applied in health care in the past decade to predict outcomes of disease and treatment. Purpose: To identify the ideal data mining technique for the prediction of ESWT-induced shoulder calcification resorption and the most accurate algorithm for use in the clinical setting. Study Design: Case-control study. Methods: Patients with painful calcified shoulder tendinitis treated by ESWT were enrolled. Seven clinical factors related to shoulder calcification were adopted as the input attributes: sex, age, side affected, symptom duration, pretreatment Constant-Murley score, and calcification size and type. The 5 data mining techniques assessed were multilayer perceptron (neural network), naïve Bayes, sequential minimal optimization, logistic regression, and the J48 decision tree classifier. Results: A total of 248 patients with calcified shoulder tendinitis were enrolled in this study. Shorter symptom duration yielded the highest gain ratio (0.374), followed by smaller calcification size (0.336) and calcification type (0.253). With the J48 decision tree method, the accuracy of 3 input attributes was 89.5% by 10-fold cross-validation, indicating satisfactory accuracy. A treatment algorithm using the J48 decision tree indicated that a symptom duration of ≤10 months was the most positive indicator of calcification resorption, followed by a calcification size of ≤10.82 mm. Conclusion: The J48 decision tree method demonstrated the highest precision and accuracy in the prediction of shoulder calcification resorption by ESWT. A symptom duration of ≤10 months or calcification size of ≤10.82 mm represented the clinical scenarios most likely to show resorption after ESWT. © The Author(s) 2024.

关键词： calcific tendinitis data mining extracorporeal shockwave therapy J48 decision tree shoulder

Mind the Performance Gap: Examining Dataset Shift During Prospective Validation 6

学校读者我要写书评

暂无评论

Mind the Performance Gap: Examining Dataset Shift During Pro...

6th Machine Learning for Healthcare Conference, MLHC 2021

作者： Ötleş, Erkin Oh, Jeeheh Li, Benjamin Bochinski, Michelle Joo, Hyeon Ortwine, Justin Shenoy, Erica Washer, Laraine Young, Vincent B. Rao, Krishna Wiens, Jenna Department of Industrial & Operations Engineering University of Michigan United States Medical Scientist Training Program University of Michigan Medical School United States Division of Computer Science & Engineering University of Michigan United States Nursing Informatics Michigan Medicine United States Department of Anesthesiology University of Michigan Medical School United States Department of Learning Health Sciences University of Michigan Medical School United States Infection Control Unit Division of Infectious Diseases Massachusetts General Hospital Harvard Medical School United States Department of Internal Medicine Division of Infectious Diseases University of Michigan Medical School United States Department of Microbiology & Immunology University of Michigan Medical School United States

Once integrated into clinical care, patient risk stratification models may perform worse compared to their retrospective performance. To date, it is widely accepted that performance will degrade over time due to changes in care processes and patient populations. However, the extent to which this occurs is poorly understood, in part because few researchers report prospective validation performance. In this study, we compare the 2020-2021 (’20-’21) prospective performance of a patient risk stratification model for predicting healthcare-associated infections to a 2019-2020 (’19-’20) retrospective validation of the same model. We define the difference in retrospective and prospective performance as the performance gap. We estimate how i) "temporal shift", i.e., changes in clinical workflows and patient populations, and ii) "infrastructure shift", i.e., changes in access, extraction and transformation of data, both contribute to the performance gap. Applied prospectively to 26,864 hospital encounters during a twelve-month period from July 2020 to June 2021, the model achieved an area under the receiver operating characteristic curve (AUROC) of 0.767 (95% confidence interval (CI): 0.737, 0.801) and a Brier score of 0.189 (95% CI: 0.186, 0.191). Prospective performance decreased slightly compared to’19-’20 retrospective performance, in which the model achieved an AUROC of 0.778 (95% CI: 0.744, 0.815) and a Brier score of 0.163 (95% CI: 0.161, 0.165). The resulting performance gap was primarily due to infrastructure shift and not temporal shift. So long as we continue to develop and validate models using data stored in large research data warehouses, we must consider differences in how and when data are accessed, measure how these differences may negatively affect prospective performance, and work to mitigate those differences. © 2021 E. Ötleş & J. Oh et al.

关键词： Data warehouses

Negative prognostic factors and clinical improvement prediction modeling for extracorporeal shockwave therapy in calcific shoulder tendinitis using artificial intelligence techniques

学校读者我要写书评

暂无评论

Journal of Shoulder and Elbow Surgery 2025年

作者： Chou, Wen-Yi Huang, Tian-Hsiang Cheng, Jai-Hong Lien, Yu-Jui Ho, Wen-Hsien Chou, Paul Pei-Hsi Ph.D. Program in Biomedical Engineering College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Department of Orthopedic Surgery Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine Kaohsiung Taiwan Department of Leisure and Sport Management Cheng Shiu University Kaohsiung Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan Department of Medical Research Center for Shockwave Medicine and Tissue Engineering Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine Kaohsiung Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung Taiwan Department of Medical Research Kaohsiung Medical University Hospital Kaohsiung Taiwan College of Professional Studies National Pingtung University of Science and Technology Pingtung Taiwan Precision Sports Medicine and Health Promotion Center Kaohsiung Medical University Kaohsiung Taiwan Department of Sports Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Division of Sports Medicine Department of Orthopaedic Surgery Kaohsiung Medical University Hospital Kaohsiung Taiwan Department of Orthopaedics School of Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan

Background: The efficacy of extracorporeal shockwave therapy (ESWT) for treating shoulder calcific tendinitis can be influenced by various prognostic factors. This study aimed to identify prognostic factors associated with the failure of ESWT for symptom relief and to evaluate the predictive capability of the eXtreme Gradient Boosting (XGBoost) algorithm of artificial intelligence techniques in this context. Methods: This retrospective study enrolled patients with persistent shoulder pain attributed to calcific tendinitis who underwent ESWT after failed conservative treatment between January 1998 and December 2022. Age, sex, duration of symptoms, calcification classification and size, pre-ESWT visual analog scale (VAS), and pre-ESWT Constant-Murley score (CMS) served as potential input attributes. The difference in VAS and CMS were defined as the output attributes. The XGBoost model was used to predict treatment outcomes based on these factors. The dataset was balanced using the synthetic minority oversampling technique, and the model's performance was assessed using 10-fold cross-validation. Spearman's rank correlation coefficient analysis was adopted to explore the relationships between significant continuous input attributes and post-ESWT VAS and CMS scores. Results: A total of 296 patients with calcific tendinitis were enrolled and completed the 1-year follow-up. The findings revealed that a prolonged symptom duration (>10 months), severe pain (pre-ESWT VAS >5), and higher pre-ESWT CMS (>55) were significant prognostic factors for the failure of ESWT for symptom relief. Using these factors as inputs, the XGBoost model demonstrated high accuracy, precision, recall, and F1 score. By reducing the input attributes to age, calcification size, pre-ESWT CMS, and symptom duration, the model maintained a high prediction rate, suggesting that these factors are sufficient for effective prediction. Discussion: The present study identified significant prognostic factors asso

关键词： Artificial intelligence Basic science Study calcific tendinitis CMS Development of Predictive computer Modeling Using AI/Machine Learning ESWT shoulder VAS XGBoost

Scientific discovery in the age of artificial intelligence

学校读者我要写书评

暂无评论

NATURE 2023年第7978期621卷 E33-E33页

作者： Wang, Hanchen Fu, Tianfan Du, Yuanqi Gao, Wenhao Huang, Kexin Liu, Ziming Chandak, Payal Liu, Shengchao Van Katwyk, Peter Deac, Andreea Anandkumar, Anima Bergen, Karianne Gomes, Carla P. Ho, Shirley Kohli, Pushmeet Lasenby, Joan Leskovec, Jure Liu, Tie-Yan Manrai, Arjun Marks, Debora Ramsundar, Bharath Song, Le Sun, Jimeng Tang, Jian Velickovic, Petar Welling, Max Zhang, Linfeng Coley, Connor W. Bengio, Yoshua Zitnik, Marinka Department of Engineering University of Cambridge Cambridge UK Department of Computing and Mathematical Sciences California Institute of Technology Pasadena CA USA NVIDIA Santa Clara CA USA Department of Computational Science and Engineering Georgia Institute of Technology Atlanta GA USA Department of Computer Science Cornell University Ithaca NY USA Department of Chemical Engineering Massachusetts Institute of Technology Cambridge MA USA Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Department of Computer Science Stanford University Stanford CA USA Department of Physics Massachusetts Institute of Technology Cambridge MA USA Harvard-MIT Program in Health Sciences and Technology Cambridge MA USA Mila – Quebec AI Institute Montreal Quebec Canada Université de Montréal Montreal Quebec Canada HEC Montréal Montreal Quebec Canada CIFAR AI Chair Toronto Ontario Canada Department of Earth Environmental and Planetary Sciences Brown University Providence RI USA Data Science Institute Brown University Providence RI USA Center for Computational Astrophysics Flatiron Institute New York NY USA Department of Astrophysical Sciences Princeton University Princeton NJ USA Department of Physics Carnegie Mellon University Pittsburgh PA USA Department of Physics and Center for Data Science New York University New York NY USA Google DeepMind London UK Department of Computer Science and Technology University of Cambridge Cambridge UK Microsoft Research Beijing China Department of Biomedical Informatics Harvard Medical School Boston MA USA Broad Institute of MIT and Harvard Cambridge MA USA Harvard Data Science Initiative Cambridge MA USA Kempner Institute for the Study of Natural and Artificial Intelligence Harvard University Cambridge MA USA Department of Systems Biology Harvard Medical School Boston MA USA Deep Forest Sciences Palo Alto CA USA BioMap Beijing China Mo

Autoencoders as Weight Initialization of Deep Classification Networks for Cancer versus Cancer Studies

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ferreira, Mafalda Falcão Camacho, Rui Teixeira, Luís F. Doctoral Program in Informatics Engineering Faculty of Engineering University of Porto INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal Department of Informatics Engineering Faculty of Engineering University of Porto Porto - Portugal

Cancer is still one of the most devastating diseases of our time. One way of automatically classifying tumor samples is by analyzing its derived molecular information (i.e., its genes expression signatures). In this work, we aim to distinguish three different types of cancer: thyroid, skin, and stomach. For that, we compare the performance of a Denoising Autoencoder (DAE) used as weight initialization of a deep neural network. Although we address a different domain problem in this work, we have adopted the same methodology of Ferreira et al.. In our experiments, we assess two different approaches when training the classification model: (a) fixing the weights, after pre-training the DAE, and (b) allowing fine-tuning of the entire classification network. Additionally, we apply two different strategies for embedding the DAE into the classification network: (1) by only importing the encoding layers, and (2) by inserting the complete autoencoder. Our best result was the combination of unsupervised feature learning through a DAE, followed by its full import into the classification network, and subsequent fine-tuning through supervised training, achieving an F1 score of 98.04% ± 1.09 when identifying cancerous thyroid samples. Copyright © 2020, The Authors. All rights reserved.

关键词： Classification (of information)