Filters








7,726 Hits in 6.9 sec

Unsupervised Extraction of Phenotypes from Cancer Clinical Notes for Association Studies [article]

Stefan G. Stark, Stephanie L. Hyland, Melanie F. Pradier, Kjong Lehmann, Andreas Wicki, Fernando Perez Cruz, Julia E. Vogt, Gunnar Rätsch
2019 arXiv   pre-print
To demonstrate the utility of our approach, we perform an association study of clinical features with somatic mutation profiles from 4,007 cancer patients and their tumors.  ...  In this work, we develop the methodology to automatically extract clinical features from clinical narratives from large EHR corpora without the need for prior knowledge.  ...  Acknowledgements: This study was supported by the MSK Cancer Center Support Grant (P30 CA008748).  ... 
arXiv:1904.12973v2 fatcat:t4v6liyfyzbodg7bba4lc6tqmi

Natural Language Processing for EHR-Based Computational Phenotyping

Zexian Zeng, Yu Deng, Xiaoyu Li, Tristan Naumann, Yuan Luo
2018 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
adverse drug event (ADE) detection, as well as genome-wide and phenome-wide association studies.  ...  Recently, deep learning and unsupervised learning have received growing attention, with the former favored for its performance and the latter for its ability to find novel phenotypes.  ...  Acknowledgment This work was supported in part by NIH Grant 1R21LM012618-01, NLM Biomedical Informatics Training Grant 2T15 LM007092-22, and the Intel Science and Technology Center for Big Data.  ... 
doi:10.1109/tcbb.2018.2849968 pmid:29994486 pmcid:PMC6388621 fatcat:wsksxvr7lfbgjowrsymghld64u

Natural Language Processing for EHR-Based Computational Phenotyping [article]

Zexian Zeng, Yu Deng, Xiaoyu Li, Tristan Naumann, Yuan Luo
2018 arXiv   pre-print
adverse drug event (ADE) detection, as well as genome-wide and phenome-wide association studies.  ...  Recently, deep learning and unsupervised learning have received growing attention, with the former favored for its performance and the latter for its ability to find novel phenotypes.  ...  [187] proposed using unsupervised methods for both entity and relation extraction from clinical notes. Clustering was applied to all the entity pairs for possible relations discovery.  ... 
arXiv:1806.04820v2 fatcat:fo5ck7rpgzhb7dgmqfjc3bdw7y

Imaging phenotypes of breast cancer heterogeneity in pre-operative breast Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) scans predict 10-year recurrence

Rhea Chitalia, Jennifer Rowland, Elizabeth S. McDonald, Lauren Pantalone, Eric A Cohen, Aimilia Gastounioti, Michael Feldman, Mitchell Schnall, Emily Conant, Despina Kontos
2019 Clinical Cancer Research  
Intrinsic phenotypes of tumor heterogeneity were identified via unsupervised hierarchical clustering of the extracted features.  ...  For each woman, a signal enhancement ratio (SER) map was generated for the entire segmented primary lesion volume from which 60 radiomic features of texture and morphology were extracted.  ...  Acknowledgments This study was supported by the NCI at the NIH: 5R01CA197000-03 (to R.D.  ... 
doi:10.1158/1078-0432.ccr-18-4067 pmid:31732521 pmcid:PMC7024654 fatcat:uwjv4b3zmjbrlnf2uxnpyclmgy

DNA Methylation Status of Epithelial-Mesenchymal Transition (EMT) - Related Genes Is Associated with Severe Clinical Phenotypes in Ulcerative Colitis (UC)

Tomomitsu Tahara, Tomoyuki Shibata, Masaaki Okubo, Takamitsu Ishizuka, Masakatsu Nakamura, Mitsuo Nagasaka, Yoshihito Nakagawa, Naoki Ohmiya, Tomiyasu Arisawa, Ichiro Hirata, Regine Schneider-Stock
2014 PLoS ONE  
Conclusions: Our data suggest that variability in the methylation status of EMT-related genes is associated with more severe clinical phenotypes in UC.  ...  Results: Using an unsupervised hierarchical clustering analysis, inflamed rectal mucosa was well separated from mucosa that appeared normal.  ...  same specimens used for DNA extraction.  ... 
doi:10.1371/journal.pone.0107947 pmid:25303049 pmcid:PMC4193736 fatcat:rk2x3fzajnb35a7vu2clttncpm

Artificial Intelligence toward Personalized Medicine

2021 Pharmaceutical Sciences and Research  
of multi-modalities data, (3) disease specialist to guide the development of AI model, (4) investigation of AI-finding by clinical community, and (5) follow-up of AI-finding by the large clinical trial  ...  From the analysis, we concluded that AI for personalized medicine could benefit by five factors: (1) standardization and pooling of genetics and health data, nationally and internationally, (2) the use  ...  Both human and ML model can "learn" from each other. As last note, we saw that most AI finding are retrospective, meaning the data was extracted from previous clinical trials in other studies.  ... 
doi:10.7454/psr.v8i2.1199 fatcat:gt33f5iucrdltppu5wxawmhg4e

Chronic Lymphocytic Leukemia Progression Diagnosis with Intrinsic Cellular Patterns via Unsupervised Clustering

Pingjun Chen, Siba El Hussein, Fuyong Xing, Muhammad Aminu, Aparajith Kannapiran, John D. Hazle, L. Jeffrey Medeiros, Ignacio I. Wistuba, David Jaffray, Joseph D. Khoury, Jia Wu
2022 Cancers  
The outcome of this study serves as proof of principle using an unsupervised machine learning scheme to enhance the diagnostic accuracy of the heterogeneous histology patterns that pathologists might not  ...  We further validate the reproducibility and robustness of unsupervised feature extraction via stability and repeated splitting analysis, supporting its utility as a diagnostic aid in identifying CLL patients  ...  Conflicts of Interest: The authors declare no conflict of interest. Cancers 2022, 14, 2398  ... 
doi:10.3390/cancers14102398 fatcat:hiwc4ltnsrafvativi5h6ap2ge

A Novel Prostate Cell Type-Specific Gene Signature to Interrogate Prostate Tumor Differentiation Status and Monitor Therapeutic Response (Running Title: Phenotypic Classification of Prostate Tumors)

Sarah N. Mapelli, Domenico Albino, Maurizia Mello-Grand, Dheeraj Shinde, Manuel Scimeca, Rita Bonfiglio, Elena Bonanno, Giovanna Chiorino, Ramon Garcia-Escudero, Carlo V. Catapano, Giuseppina M. Carbone
2020 Cancers  
We found also an association of LumE score with tumor phenotype in genetically engineered mouse models (GEMMs) of prostate cancer.  ...  Immunohistochemistry for COL4A1, a low-luminal marker, sustained the association of attenuated luminal phenotype with metastatic disease.  ...  Clinical evolution of prostate cancer is highly heterogeneous ranging from indolent phenotype might predispose to castration resistance.  ... 
doi:10.3390/cancers12010176 pmid:31936761 fatcat:tjx6nzmcwjhqbbpojaeaf7qnfq

An Unsupervised Approach to Identify Molecular Phenotypic Components Influencing Breast Cancer Features

Florin M. Selaru, Jing Yin, Andreea Olaru, Yuriko Mori, Yan Xu, Steven H. Epstein, Fumiaki Sato, Elena Deacu, Suna Wang, Anca Sterian, Amy Fulton, John M. Abraham (+4 others)
2004 Cancer Research  
These results provide a molecular phenotypic basis for the existence of a biologically unique subgroup comprising ER (؉) breast cancers from African-American patients.  ...  To discover a biological basis for clinical subgroupings within breast cancers, we applied principal components (PCs) analysis to cDNA microarray data from 36 breast cancers.  ...  Therefore, in the current study, we analyzed global gene expression data from breast cancers using an unsupervised bioinformatics approach, principal components analysis (PCA).  ... 
doi:10.1158/0008-5472.can-03-3208 pmid:14996713 fatcat:lstyfrawefeljaoquk4fvfrn2a

Deep Phenotyping: Embracing Complexity and Temporality—Towards Scalability, Portability, and Interoperability

Chunhua Weng, Nigam Shah, George Hripcsak
2020 Journal of Biomedical Informatics  
unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source.  ...  These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.  ...  Acknowledgments The editors acknowledge funding support from the United States National Institutes of Health grants R01LM009886-10, R01LM006910-19, U01HG008680-05 and R01LM011369-07.  ... 
doi:10.1016/j.jbi.2020.103433 pmid:32335224 pmcid:PMC7179504 fatcat:53xsdcycxvgq5h6wkfivz4azei

Combining radiomic phenotypes of non-small cell lung cancer with liquid biopsy data may improve prediction of response to EGFR inhibitors

Bardia Yousefi, Michael J. LaRiviere, Eric A. Cohen, Thomas H. Buckingham, Stephanie S. Yee, Taylor A. Black, Austin L. Chien, Peter Noël, Wei-Ting Hwang, Sharyn I. Katz, Charu Aggarwal, Jeffrey C. Thompson (+2 others)
2021 Scientific Reports  
Clinical data included age, smoking status, and ECOG performance status. Baseline chest CT scans were analyzed to extract 429 radiomic features from each primary tumor.  ...  For OS, adding radiomic phenotypes resulted in c-statistic of 0.83 versus 0.80 when using clinical and ctDNA variables (LRT p = 0.08).  ...  of care, and radiomic features extracted from clinically acquired chest CT scans.  ... 
doi:10.1038/s41598-021-88239-y pmid:33976268 pmcid:PMC8113313 fatcat:nq4q7wbcxnhsxpzsn24ch7mway

A Review of Automatic Phenotyping Approaches using Electronic Health Records

Hadeel Alzoubi, Raid Alzubi, Naeem Ramzan, Daune West, Tawfik Al-Hadhrami, Mamoun Alazab
2019 Electronics  
This review summarizes and offers a critical evaluation of the literature relating to studies conducted into the development of EHR phenotyping systems.  ...  In order to utilize EHRs for medical observational research a range of algorithms for automatically identifying individuals with a specific phenotype have been developed.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics8111235 fatcat:6wygemixhvgoxkhjqrmmjs3ynq

Radiomic Phenotypes of Mammographic Parenchymal Complexity: Toward Augmenting Breast Density in Breast Cancer Risk Assessment

Despina Kontos, Stacey J. Winham, Andrew Oustimov, Lauren Pantalone, Meng-Kang Hsieh, Aimilia Gastounioti, Dana H. Whaley, Carrie B. Hruska, Karla Kerlikowske, Kathleen Brandt, Emily F. Conant, Celine M. Vachon
2019 Radiology  
(from 140 of 291 [48.1%] in the high-complexity phenotype to 275 of 511 [53.8%] in the low-complexity phenotype).  ...  Purpose To identify phenotypes of mammographic parenchymal complexity by using radiomic features and to evaluate their associations with breast density and other breast cancer risk factors.  ...  Activities not related to the present article: is inventor of patents licensed to Gamma Medica (acquired by CMR Naviscan); received royalties for technologies licensed to Gamma Medica.  ... 
doi:10.1148/radiol.2018180179 pmid:30375931 pmcid:PMC6314515 fatcat:uu7oh7tf6reldhhlvjb7eoeype

Radiomic Phenotypes for Improving Early Prediction of Survival in Stage III Non-Small Cell Lung Cancer Adenocarcinoma after Chemoradiation

José Marcio Luna, Andrew R. Barsky, Russell T. Shinohara, Leonid Roshkovan, Michelle Hershman, Alexandra D. Dreyfuss, Hannah Horng, Carolyn Lou, Peter B. Noël, Keith A. Cengel, Sharyn Katz, Eric S. Diffenderfer (+1 others)
2022 Cancers  
A binary radiomic phenotype to predict OS was derived through the unsupervised hierarchical clustering of the first principal components explaining 85% of the variance of the radiomic features.  ...  We evaluate radiomic phenotypes derived from CT scans as early predictors of overall survival (OS) after chemoradiation in stage III primary lung adenocarcinoma.  ...  In this study, we investigate the association between OS and radiomic features extracted from chest CT scans of a relatively homogeneous cohort of stage III NSCLC adenocarcinoma patients at our institution  ... 
doi:10.3390/cancers14030700 pmid:35158971 pmcid:PMC8833400 fatcat:rvngwzsvibfhnflodw7wcok7hm

Graph-based signal integration for high-throughput phenotyping

Jorge R Herskovic, Devika Subramanian, Trevor Cohen, Pamela A Bozzo-Silva, Charles F Bearden, Elmer V Bernstam
2012 BMC Bioinformatics  
Conclusions: We conclude that our approach is a promising alternative for unsupervised high-throughput phenotyping.  ...  Our unsupervised graph-based high-throughput phenotyping had accuracy of 84.1%; recall=46.3%, precision=61.2%, and F 1 =52.8%.  ...  This article has been published as part of BMC Bioinformatics Volume 13 Supplement 13, 2012: Selected articles from The 8th Annual Biotechnology and Bioinformatics Symposium (BIOT-2011).  ... 
doi:10.1186/1471-2105-13-s13-s2 pmid:23320851 pmcid:PMC3426800 fatcat:sbh2odhx2vaqnn3s4oscyoobha
« Previous Showing results 1 — 15 out of 7,726 results