245 Hits in 8.0 sec

Prediction of Acquired Taxane Resistance Using a Personalized Pathway-Based Machine Learning Method

Young Rae Kim, Dongha Kim, Sung Young Kim
2018 Cancer research and treatment : official journal of Korean Cancer Association  
To develop a model with enhanced generalizability, we merged multiple ATR studies then updated the learning parameter via robust cross-study validation.  ...  We successfully constructed a multi-study-derived personalized prediction model for ATR with excellent accuracy, generalizability, and transferability.  ...  Regularized machine learning such as penalized regression has been developed for high dimension data structures.  ... 
doi:10.4143/crt.2018.137 pmid:30092623 pmcid:PMC6473276 fatcat:hjxiebslvnfr7dnnkufoikpz5i

Integrating multi-omics data with deep learning for predicting cancer prognosis [article]

Hua Chai, Xiang Zhou, Zi-feng Cui, Jia-hua Rao, Zheng Hu, Yu-tong Lu, Hui-ying Zhao, Yue-dong Yang
2019 bioRxiv   pre-print
In the case study for differential gene expression analysis, we identified 161 differentially expressed genes in the cervical cancer, among which 77 genes (65.8%) have been proven to be associated with  ...  This study has provided a deep learning framework to effectively integrate multiple omics data.  ...  ′) = ( , ′) + ∑ ( ‖ ‖ 1 + ‖ 1→ ( )‖ 2 2 ) =1 (2) where k was set 5 for layers (input, output, and 3 hidden layers), and were the coefficients for L1 and L2-norm regularization penalties, here they were  ... 
doi:10.1101/807214 fatcat:ma3aq44hubbw3kt7mc7pjrrnci

Finding distributed needles in neural haystacks

Christopher R. Cox, Timothy T. Rogers
2020 Journal of Neuroscience  
and whole-brain decoding with L1 or L2 regularization-each have critical and complementary blind spots under these conditions.  ...  Thus, structured sparsity can provide an unbiased method for testing claims of functional localization.  ...  Computational efficiency It is worth noting that SOS LASSO demands considerably more computational resources than simple regularization with the L1 or L2 norm, for two reasons.  ... 
doi:10.1523/jneurosci.0904-20.2020 fatcat:jfbep6erzva65pigjdjzehnaim

DistStat.jl: Towards Unified Programming for High-Performance Statistical Computing Environments in Julia [article]

Seyoon Ko, Hua Zhou, Jin Zhou, Joong-Ho Won
2020 arXiv   pre-print
As a case in point, we analyze the on-set of type-2 diabetes from the UK Biobank with 400,000 subjects and 500,000 single nucleotide polymorphisms using the ℓ_1-regularized Cox proportional hazards model  ...  As a demonstration of the transparency and scalability of the package, we provide applications to large-scale nonnegative matrix factorization, multidimensional scaling, and ℓ_1-regularized Cox proportional  ...  B Code for memory-efficient1 -regularized Cox proportional hazards model For CPU code, the following code accelerates the computation of P (n+1) δ for ℓ1regularized Cox regression in Section 5.3 using  ... 
arXiv:2010.16114v1 fatcat:rhonnyxfn5badaznj2t7rcpzre

Brain Imaging Genomics: Integrated Analysis and Machine Learning

Li Shen, Paul M. Thompson
2019 Proceedings of the IEEE  
and machine learning methods for brain imaging genomics, as well as a practical discussion on method selection for various biomedical applications.  ...  Brain imaging genomics is an emerging data science field, where integrated analysis of brain imaging and genomics data, often combined with other biomarker, clinical and environmental data, is performed  ...  [190] performed survival analysis using the Cox proportional Hazard model to predict time to progression from MCI to AD via integrating a PHS, an imagingbased atrophy score, and the MMSE score.  ... 
doi:10.1109/jproc.2019.2947272 pmid:31902950 pmcid:PMC6941751 fatcat:rx5b44yv55d2xicdiznnwjdac4

Incremental Value of Radiomics in 5-Year Overall Survival Prediction for Stage II–III Rectal Cancer

Ke Nie, Peng Hu, Jianjun Zheng, Yang Zhang, Pengfei Yang, Salma K. Jabbour, Ning Yue, Xue Dong, Shufeng Xu, Bo Shen, Tianye Niu, Xiaotong Hu (+2 others)
2022 Frontiers in Oncology  
Although rectal cancer comprises up to one-third of colorectal cancer cases and several prognosis nomograms have been established for colon cancer, statistical tools for predicting long-term survival in  ...  for advance-staged rectal cancer patients.  ...  Multivariate analysis with a Cox regression analysis model was performed to detect independent prognostic factors for long-term survival.  ... 
doi:10.3389/fonc.2022.779030 pmid:35847948 pmcid:PMC9279662 fatcat:vursvi4wpnc3bapx4zycziznde

In-depth mining of clinical data: the construction of clinical prediction model with R

Zhi-Rui Zhou, Wei-Wei Wang, Yan Li, Kai-Rui Jin, Xuan-Yi Wang, Zi-Wei Wang, Yi-Shan Chen, Shao-Jia Wang, Jing Hu, Hui-Na Zhang, Po Huang, Guo-Zhen Zhao (+3 others)
2019 Annals of Translational Medicine  
The sixth section mainly introduces two common calculation methods for C-Index in Cox regression based on R.  ...  The tenth section is a supplement to the previous section and mainly introduces the Decision Curve Analysis of survival outcome data.  ...  Because there is a linear part of the Logistic regression function, the L1 norm and the L2 norm regularization can be used in combination.  ... 
doi:10.21037/atm.2019.08.63 pmid:32042812 pmcid:PMC6989986 fatcat:3kskwtfz65eapa726vxivmyctq

Nonparametric Conditional Local Independence Testing [article]

Alexander Mangulad Christgau, Lasse Petersen, Niels Richard Hansen
2022 arXiv   pre-print
An example based on a marginalized Cox model with time-dependent covariates is used throughout to illustrate the theory, and simulations based on this example show how double machine learning as well as  ...  It describes whether the evolution of one process is directly influenced by another process given the histories of additional processes, and it is important for the description and learning of causal relations  ...  Section V.4 in (Andersen et al. 1993) for related test statistics in the context of survival analysis.  ... 
arXiv:2203.13559v1 fatcat:w3p4quufabcbvhwra2wkvzcuci

High-Performance Statistical Computing in the Computing Environments of the 2020s [article]

Seyoon Ko, Hua Zhou, Jin J. Zhou, Joong-Ho Won
2021 arXiv   pre-print
Employing this data structure, we illustrate various statistical applications including large-scale positron emission tomography and ℓ_1-regularized Cox regression.  ...  As a case in point, we analyze the onset of type-2 diabetes from the UK Biobank with 200,000 subjects and about 500,000 single nucleotide polymorphisms using the HPC ℓ_1-regularized Cox regression.  ...  Genome-wide survival analysis of the UK Biobank dataset We demonstrate a real-world application of 1 -regularized Cox proportional hazards regression to genome-wide survival analysis for Type 2 Diabetes  ... 
arXiv:2001.01916v3 fatcat:p745jgoj3bgixpwn54npychoci

Deep Learning Models for Digital Pathology [article]

Aïcha BenTaieb, Ghassan Hamarneh
2019 arXiv   pre-print
Specifically, applications of deep learning to histopathology image analysis now offer opportunities for better quantitative modeling of disease appearance and hence possibly improved prediction of disease  ...  In this survey, we summarize the different challenges facing computational systems for digital pathology and provide a review of state-of-the-art works that developed deep learning-based solutions for  ...  The model is trained with a per-pixel regression loss that minimizes the L2 norm between the predicted proximity score map and s(l).  ... 
arXiv:1910.12329v2 fatcat:2b7h7i2zwbautewneabghm3bzi

D6.2 - Preliminary conclusions about Federated Learning applied to clinical data

Federico Álvarez, Santiago Zazo, Juan Parras, Alejandro Almodóvar, Patricia Alonso, Enrico Giampieri, Gastone Castellani, Lorenzo Sani, Cesare Rollo, Tiziana Sanavia, Anders Krogh, Íñigo Prada-Luengo (+3 others)
2021 Zenodo  
After a preliminary introductory section where the fundamental procedures and limitations are described, we detail the well-known mathematical foundation of Federated Learning for convex problems.  ...  and classification (Logistic Regression and Support Vector Machines (SVM)).  ...  It means that a representation is judged on the performance in e.g. a classification or survival analysis task. We will develop the representation learning and compare to UMAP.  ... 
doi:10.5281/zenodo.5862590 fatcat:trd6rdi7pzcq7gcta62jcitwua

Mining Electronic Health Records: A Survey [article]

Pranjul Yadav, Michael Steinbach, Vipin Kumar, Gyorgy Simon
2017 arXiv   pre-print
In this manuscript, we provide a structured and comprehensive overview of data mining techniques for modeling EHR data.  ...  Next, we describe major approaches used for EHR mining, the metrics associated with EHRs, and the various study designs.  ...  Cox regression [Cox 1992; Vinzamuri and Reddy 2013] is one of the most commonly used survival regression models.  ... 
arXiv:1702.03222v2 fatcat:aizt3bnmibcc7kv67h6qf7ts7q

Data Analysis Methods for Software Systems

Jolita Bernatavičienė
2021 Vilnius University Proceedings  
DAMSS-2021 is the 12th international conference on data analysis methods for software systems, organized in Druskininkai, Lithuania. The same place and the same time every year.  ...  This means that the topics of the conference are actual for business, too.  ...  Gathered data was proceeded using MD5 feature hashing and normalized, applying min-max scaling or L2 norm depending on the data type.  ... 
doi:10.15388/damss.12.2021 fatcat:iefv6bz3drcrfpcwxoaqmu3gra


Yan Li, Yan Li, Dissertation
2016 unpublished
In the past five years, I have learned a lot from him.  ...  From him, I also learned that as a researcher, one needs to be always positive and active, and work harder and harder. What I learned from him would be great wealth in my future study and career.  ...  Thus, the β can be learned via maximizing the partial likelihood: L(β) = K i=1 exp(X i β) j∈R i exp(X j β) (6.4) L2,1-norm regularized Cox model In this thesis, we propose a feature-based transfer learning  ... 

Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting [article]

Jun Wang, Weinan Zhang, Shuai Yuan
2017 arXiv   pre-print
Scientifically, the demand for automation, integration and optimisation in RTB also brings new research opportunities in information retrieval, data mining, machine learning and other related fields.  ...  With L2-norm regularisation, the loss function becomes: L(y,ŷ) = −y logŷ − (1 − y) log(1 −ŷ) + λ 2 w 2 2 . (4.4) Taking the derivation leads to the gradient on the efficient vector w ∂L(y,ŷ) ∂w = (ŷ −  ...  By contrast, transfer learning methods may allow for arbitrary source and target tasks.  ... 
arXiv:1610.03013v2 fatcat:f2ewm5rdhzfi3pdndao4uww6re
« Previous Showing results 1 — 15 out of 245 results