Filters








384 Hits in 7.2 sec

bnstruct: an R package for Bayesian Network structure learning in the presence of missing data

Alberto Franzin, Francesco Sambo, Barbara Di Camillo
2016 Bioinformatics  
We introduce bnstruct, an open source R package to (i) learn the structure and the parameters of a Bayesian Network from data in the presence of missing values and (ii) perform reasoning and inference  ...  Motivation: A Bayesian Network is a probabilistic graphical model that encodes probabilistic dependencies between a set of random variables.  ...  Type 1 Diabetes (T1D) where screened for several anthropometric and metabolic risk factors for T1D complications.  ... 
doi:10.1093/bioinformatics/btw807 pmid:28003263 fatcat:vkycag4nx5df7mxhvuf7s3bbfq

Driving Type 2 Diabetes Risk Scores into Clinical Practice: Performance Analysis in Hospital Settings

Antonio Martinez-Millana, María Argente-Pla, Bernardo Valdivieso Martinez, Vicente Traver Salcedo, Juan Merino-Torres
2019 Journal of Clinical Medicine  
Unavailable or missing data in electronic health records was imputed using an existing validated Bayesian Network.  ...  Use of a Bayesian Network was key for completion of the risk estimation and did not affect the risk score calculation (p > 0.05).  ...  Missing data was imputed using a Bayesian Network [25] .  ... 
doi:10.3390/jcm8010107 pmid:30658456 pmcid:PMC6352264 fatcat:o5ga4lhbzrg75mbtjm4j3nprui

Probabilistic Machine Learning for Healthcare [article]

Irene Y. Chen, Shalmali Joshi, Marzyeh Ghassemi, Rajesh Ranganath
2020 arXiv   pre-print
Beyond predictive models, we also investigate the utility of probabilistic machine learning models in phenotyping, in generative models for clinical use cases, and in reinforcement learning.  ...  Machine learning can be used to make sense of healthcare data. Probabilistic machine learning models help provide a complete picture of observed data in healthcare.  ...  Krishnan, Peter Schulam, and Pete Szolovits for helpful and useful feedback. This work was supported in part by a CIFAR AI Chair at the Vector Institute (MG) and Microsoft Research (MG).  ... 
arXiv:2009.11087v1 fatcat:htosfeqvhndvfmlmud2pvl3nsy

A Review of Integrative Imputation for Multi-Omics Datasets

Meng Song, Jonathan Greenbaum, Joseph Luttrell, Weihua Zhou, Chong Wu, Hui Shen, Ping Gong, Chaoyang Zhang, Hong-Wen Deng
2020 Frontiers in Genetics  
Multi-omics studies, which explore the interactions between multiple types of biological factors, have significant advantages over single-omics analysis for their ability to provide a more holistic view  ...  In this review, we provide an overview of the currently available imputation methods for handling missing values in bioinformatics data with an emphasis on multi-omics imputation.  ...  There are a number of factors that affect the accuracy of multi-omics imputation: missing value mechanism [missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR)  ... 
doi:10.3389/fgene.2020.570255 pmid:33193667 pmcid:PMC7594632 fatcat:wmc5ksg3bbhqrpt4xvbdnlryqm

Learning to Address Health Inequality in the United States with a Bayesian Decision Network [article]

Tavpritesh Sethi, Anant Mittal, Shubham Maheshwari, Samarth Chugh
2018 arXiv   pre-print
We learn an ensemble-averaged structure, draw inferences using the joint probability distribution and extend it to a Bayesian Decision Network for identifying policy actions.  ...  We draw quantitative estimates for the impact of diversity, preventive-care quality and stable-families within the unified framework of our decision network.  ...  Rakesh Lodha, Department of Pediatrics, All India Institute of Medical Sciences, New Delhi, India.  ... 
arXiv:1809.09215v2 fatcat:y5nv57pkhncvrlqpur4vevbjcq

Machine learning to predict rapid progression of carotid atherosclerosis in patients with impaired glucose tolerance

Xia Hu, Peter D. Reaven, Aramesh Saremi, Ninghao Liu, Mohammad Ali Abbasi, Huan Liu, Raymond Q. Migrino
2016 EURASIP Journal on Bioinformatics and Systems Biology  
In particular, we first employed a Fisher Score-based feature selection method to identify the most effective variables and then proposed a probabilistic Bayes-based learning method for the prediction.  ...  Methods: In the Actos Now for Prevention of Diabetes (ACT NOW) study, 382 participants with IGT underwent carotid intima-media thickness (CIMT) ultrasound evaluation at baseline and at 15-18 months, and  ...  We would like to thank the Office of Research of the Phoenix Veterans Affairs Health Care System and the Phoenix VA Center for Healthcare Data Analytics Research for their support.  ... 
doi:10.1186/s13637-016-0049-6 pmid:27642290 pmcid:PMC5011483 fatcat:bhhpzsvsnraknjzknlrosypl2m

Integration of Distributed Services and Hybrid Models Based on Process Choreography to Predict and Detect Type 2 Diabetes

Antonio Martinez-Millana, Jose-Luis Bayo-Monton, María Argente-Pla, Carlos Fernandez-Llatas, Juan Merino-Torres, Vicente Traver-Salcedo
2017 Sensors  
Common types of models include logistic regression models, Bayesian networks, support vector machines, Cox proportional hazards models and classification trees [12] , and each type of model produces an  ...  Recent studies have demonstrated the effectiveness of new strategies to delay and even prevent the onset of type 2 diabetes by a combination of active and healthy lifestyle on cohorts of mid to high risk  ...  FP7-ICT 600914) for their commitment during concept development, which led to the development of the research reported in this manuscript.  ... 
doi:10.3390/s18010079 pmid:29286314 pmcid:PMC5795558 fatcat:wdags57mlncqdeyiflwav7asjm

Automatic Bayesian Density Analysis [article]

Antonio Vergari, Alejandro Molina, Robert Peharz, Zoubin Ghahramani, Kristian Kersting, Isabel Valera
2019 arXiv   pre-print
Making sense of a dataset in an automatic and unsupervised fashion is a challenging problem in statistics and AI.  ...  Specifically, ABDA allows for automatic and efficient missing value estimation, statistical data type and likelihood discovery, anomaly detection and dependency structure mining, on top of providing accurate  ...  This work has benefited from the DFG project CAML (KE 1686/3-1), as part of the SPP 1999, and from the BMBF project MADESI  ... 
arXiv:1807.09306v3 fatcat:vfztnsuwjvf4vitfsnl7cbzwvi

Effective Learning of Probabilistic Models for Clinical Predictions from Longitudinal Data [article]

Shuo Yang
2018 arXiv   pre-print
Those challenges include: the structured data with various storage formats and value types caused by heterogeneous data sources; the uncertainty widely existing in every aspect of medical diagnosis and  ...  learning techniques both in terms of size and complexity.  ...  of CAC level at year 25 on the risk factors of year 0, 2, 5, 7, 10, 15 and 20 respectively.  ... 
arXiv:1811.00749v1 fatcat:5tbyk62ahjh3zkosrwem7picpi

A clinical risk matrix for obstructive sleep apnea using Bayesian network approaches

Daniela Ferreira-Santos, Pedro Pereira Rodrigues
2018 International Journal of Data Science and Analytics  
This condition affects about 4% of men and 2% of women worldwide.  ...  Regarding risk matrix, female gender presented a starting rate of 8%, comparing to 20% in male gender, almost 3 times higher.  ...  Pereira and Joaquim Pereira, and Matilde Monteiro-Soares for critical review of the manuscript.  ... 
doi:10.1007/s41060-018-0118-x dblp:journals/ijdsa/SantosR19 fatcat:uvytw7g5xrd6vifljo56olhpdu

Machine Learning and Integrative Analysis of Biomedical Big Data

Bilal Mirza, Wei Wang, Jie Wang, Howard Choi, Neo Christopher Chung, Peipei Ping
2019 Genes  
In this review, we discuss state-of-the-art ML-based approaches for tackling five specific computational challenges associated with integrative analysis: curse of dimensionality, data heterogeneity, missing  ...  Integrative analysis of multi-omics and clinical data is key to new biomedical discoveries and advancements in precision medicine.  ...  Specifically, it discovers latent factors by means of multi-omics FE and uses those factors to impute missing data.  ... 
doi:10.3390/genes10020087 pmid:30696086 pmcid:PMC6410075 fatcat:vopnjgke4fculmr7t3n43ewfiy

46th European Mathematical Genetics Meeting (EMGM) 2018, Cagliari, Italy, April 18-20, 2018: Abstracts

2018 Human Heredity  
We assume a genetic background contributing to a lower CVD mortality in resettlers and a healthy migrant effect for the ancestors of the resettlers migrating to the FSU.  ...  This fact could neither be explained by commonly known life style risk factors nor the healthy migrant effect since almost all ethnic Germans in Russia resettled to Germany rather than just a selection  ...  For each individual with missing data, a single bootstrap iteration of the complete data is used to estimate a preliminary Bayesian network.  ... 
doi:10.1159/000488519 pmid:29669356 fatcat:wqy2xcswtngm3kw2oc4k7xglf4

Diagnosis of Cardiovascular Diseases using Artificial Intelligence Techniques: A Review

Tazeen Tasneem, Mir Md. Jahangir Kabir, Shuxiang Xu, Tabeen Tasneem
2021 International Journal of Computer Applications  
This article has explored the used datasets, feature selection techniques and missing value imputation methods, and finally compared their performances.  ...  In the last couple of decades, many techniques have been introduced for medical support system.  ...  Risk factors can be of two types -behavioral and physiological. Physiological factors are related to an individual's physical fitness that may include blood pressure, diabetes etc.  ... 
doi:10.5120/ijca2021921313 fatcat:h5mdead3ufciba4qs4upowoyfa

Sample-Based Extreme Learning Machine with Missing Data

Hang Gao, Xin-Wang Liu, Yu-Xing Peng, Song-Lei Jian
2015 Mathematical Problems in Engineering  
However, imputation methods are not always effective. In this paper, we propose a sample-based learning framework to address this issue.  ...  The problem of missing data is commonly handled by imputation (i.e., replacing missing values with substituted values according to available information).  ...  Sparse Bayesian ELM [6] estimates the marginal likelihood of network outputs and automatically prunes most of the redundant hidden neurons.  ... 
doi:10.1155/2015/145156 fatcat:kq5xcp6cvvcplhhrdfxmlgee5m

Using Machine Learning Techniques to Identify Key Risk Factors for Diabetes and Undiagnosed Diabetes [article]

Avraham Adler
2021 arXiv   pre-print
Blood osmolality, family history, the prevalance of various compounds, and hypertension are key indicators for all diabetes risk.  ...  A Support Vector Machine with a linear kernel performed best for predicting diabetes, returning a Brier score of 0.0654 and an AUROC of 0.9235 on the test set.  ...  There are a few types of diabetes of which the most common is type-2 diabetes [2] .  ... 
arXiv:2105.09379v1 fatcat:3ugmxnepivdvvph4hbldu2ipc4
« Previous Showing results 1 — 15 out of 384 results