Filters








93 Hits in 4.6 sec

Bayesian methods: a useful tool for classifying injury narratives into cause groups

M Lehto, H Marucci-Wellman, H Corns
2009 Injury Prevention  
The training set was used to develop two Bayesian classifiers that assigned BLS codes to narratives. Each model was then evaluated for the prediction set.  ...  The narratives were separated into a training set of 11 000 cases and a prediction set of 3000 cases.  ...  in administrative databases. 3 8 The potential of this approach was demonstrated in a study in which a multiple-word Fuzzy Bayes model was used to assign event codes to narrative descriptions of injury  ... 
doi:10.1136/ip.2008.021337 pmid:19652000 fatcat:gulszjagsngwphrtx3tpu2nnvq

Computerized coding of injury narrative data from the National Health Interview Survey

Helen M Wellman, Mark R Lehto, Gary S Sorock, Gordon S Smith
2004 Accident Analysis and Prevention  
Conclusions: A computer program based on Fuzzy Bayes logic is capable of accurately categorizing cause-of-injury codes from injury narratives.  ...  A Fuzzy Bayesian model was used to assign injury descriptions to 13 E-code categories.  ...  Acknowledgements The authors would like to express their gratitude to Theodore Courtney, Barbara Webster, and Dr. Margaret Warner for reviewing the manuscript.  ... 
doi:10.1016/s0001-4575(02)00146-x pmid:14642871 fatcat:yrfjfeoh6vbpfinpflp4f55udq

Near-miss narratives from the fire service: A Bayesian analysis

Jennifer A. Taylor, Alicia V. Lacovara, Gordon S. Smith, Ravi Pandian, Mark Lehto
2014 Accident Analysis and Prevention  
Methods: We manually assigned mechanism of injury codes to previously un-coded narratives from the, NFFNMRS and used this as a training set to develop two Bayesian autocoding models, Fuzzy and Naïve.  ...  Results: Overall, the Fuzzy model performed better than Naïve, with a sensitivity of 0.74 compared to 0.678., Where Fuzzy and Naïve shared the same prediction, the cross-validation showed a sensitivity  ...  Acknowledgments We would like to thank the International Association of Fire Chiefs for the opportunity to work with these data.  ... 
doi:10.1016/j.aap.2013.09.012 pmid:24144497 fatcat:vey44vkannekbnck7dzf5twtvi

A practical tool for public health surveillance: Semi-automated coding of short injury narratives from large administrative databases using Naïve Bayes algorithms

Helen R. Marucci-Wellman, Mark R. Lehto, Helen L. Corns
2015 Accident Analysis and Prevention  
We used a semi-automated approach based on two Naïve Bayesian algorithms to classify 15,000 workers compensation narratives into two-digit Bureau of Labor Statistics (BLS) event (leading to injury) codes  ...  The purpose of this study was to develop a human-machine system that could be relatively easily tailored to routinely and accurately classify injury narratives from large administrative databases such  ...  Santosh Verma and Ted Courtney for reviewing the manuscript and Ms Margaret Rothwell for editing on the final manuscript. Appendix A. See Tables A1-A3.  ... 
doi:10.1016/j.aap.2015.06.014 pmid:26412196 fatcat:fdm3fp6nffbihc7r3blbxebzji

A C-BiLSTM Approach to Classify Construction Accident Reports

Jinyue Zhang, Lijun Zi, Yuexian Hou, Da Deng, Wenting Jiang, Mingen Wang
2020 Applied Sciences  
better than some of the classic machine learning models commonly used in classification tasks, including support vector machine (SVM), naïve Bayes (NB), and logistic regression (LR).  ...  The proposed approach was applied on a dataset of construction accident narratives obtained from the Occupational Safety and Health Administration website, and the results indicate that this model performs  ...  Existing Studies on Accident Narrative Classification There are some existing studies in the field of accident classification using machine learning approaches. Bertke et al.  ... 
doi:10.3390/app10175754 fatcat:eyvwfdgy75hi3orghtodtcw4ci

Harnessing information from injury narratives in the 'big data' era: understanding and applying machine learning for injury surveillance

Kirsten Vallmuur, Helen R Marucci-Wellman, Jennifer A Taylor, Mark Lehto, Helen L Corns, Gordon S Smith
2016 Injury Prevention  
Methods: This paper reviews key aspects of machine learning using injury narratives, providing a case study to demonstrate an application to an established human-machine learning approach.  ...  Results: The range of applications and utility of narrative text has increased greatly with advancements in computing techniques over time.  ...  We consequently integrated a rule where we would only use the computer classifications when the two models agreed and then would manually code the remaining narratives.  ... 
doi:10.1136/injuryprev-2015-041813 pmid:26728004 pmcid:PMC4852152 fatcat:o26wyjrvcjfmdfzxnsswynbuaq

Injury narrative text classification using factorization model

Lin Chen, Kirsten Vallmuur, Richi Nayak
2015 BMC Medical Informatics and Decision Making  
Narrative text is a useful way of identifying injury circumstances from the routine emergency department data collections.  ...  The results are compared with the performance of various other classification approaches.  ...  A Fuzzy Bayesian model was developed for automatically assigning E-code categories to each injury narrative.  ... 
doi:10.1186/1472-6947-15-s1-s5 pmid:26043671 pmcid:PMC4460654 fatcat:4j25q6uckna5ldyptr3fzcfiv4

Comparison of methods for auto-coding causation of injury narratives

S.J. Bertke, A.R. Meyers, S.J. Wurzelbacher, A. Measure, M.P. Lampl, D. Robins
2016 Accident Analysis and Prevention  
In particular, the variations of the naïve Bayes model have been used to successfully auto-code free text narratives describing the event/exposure leading to the injury of a workers' compensation claim  ...  Further modest improvements were found through the addition of sequences of keywords in the models as opposed to consideration of only single keywords.  ...  In fact, within the field of coding injury narratives, Lehto et al. (2009) and Marucci-Wellman et al. (2011) have considered two-word (and longer) sequences in a separate model referred to as "Fuzzy  ... 
doi:10.1016/j.aap.2015.12.006 pmid:26745274 pmcid:PMC4915551 fatcat:ilv6zqdsbfdlviwkxivywwx4nu

Application of machine learning tools in classifying pedestrian crash types: A case study

Subasish Das, Minh Le, Boya Dai
2020 Transportation Safety and Environment  
The objective of this study is to develop a framework for applying machine-learning models to classify crash types from unstructured textual content.  ...  Therefore, there is a need for a supporting tool that can assist practitioners in using PBCAT more efficiently and accurately.  ...  Using human-classified data through both a fuzzy Bayes and a keyword-based model, the researchers analysed the performance and found that the connectionist and fuzzy Bayes model outperformed the keyword  ... 
doi:10.1093/tse/tdaa010 fatcat:ab4cwedj7vd7tlpzhe42gb6yge

Vehicle involvements in hydroplaning crashes: Applying interpretable machine learning

Subasish Das, Anandi Dutta, Kakan Dey, Mohammad Jalayer, Abhisek Mudgal
2020 Transportation Research Interdisciplinary Perspectives  
This approach evaluated the effectiveness of keywords in determining the classification. This study used three machine learning algorithms.  ...  This research focused on the development of a framework to apply interpretable machine learning models to unstructured textual content in order to classify the number of vehicle involvements in a crash  ...  In summary, computerized approaches and predictive models can be used to standardize crash narrative text analysis and reduce human error in crash and injury surveillance.  ... 
doi:10.1016/j.trip.2020.100176 fatcat:uuwihhacwbgovetpha575riqam

Behind the screens: Clinical decision support methodologies – A review

Paolo Fraccaro, Dympna O׳Sullivan, Panagiotis Plastiras, Hugh O׳Sullivan, Chiara Dentone, Antonio Di Biagio, Peter Weller
2015 Health Policy and Technology  
The purpose of this review is to introduce clinicians and policy makers to the most commonly computer-based methodologies employed to construct decision models to compute clinical decisions in a non-technical  ...  We hope that a better understanding of CDSSs will open up discussion about the future of CDSSs as a part of healthcare delivery as well as engage clinicians and policy makers in the development and deployment  ...  use simpler linear models to compute decisions it is easier to interpret the outputs and how a decision is computed.  ... 
doi:10.1016/j.hlpt.2014.10.001 fatcat:cju35i3kpvffnd67xtqmrngtum

Applications of artificial intelligence in dentistry: A comprehensive review

Francisco Carrillo‐Perez, Oscar E. Pecho, Juan Carlos Morales, Rade D. Paravina, Alvaro Della Bona, Razvan Ghinea, Rosa Pulgar, María del Mar Pérez, Luis Javier Herrera
2021 Journal of Esthetic and Restorative Dentistry  
To perform a comprehensive review of the use of artificial intelligence (AI) and machine learning (ML) in dentistry, providing the community with a broad insight on the different advances that these technologies  ...  The use of AI and ML has an increasing impact on the dental profession and is complementing the development of digital technologies and tools, with a wide application in treatment planning and esthetic  ...  Any kind of model can be used with GANs, but since GANs are mainly used in computer vision problems, CNNs have usually been the preferred model.  ... 
doi:10.1111/jerd.12844 pmid:34842324 fatcat:f3auyddxanhove6mqsxnzkwqy4

Semantic annotation of clinical events for generating a problem list

Danielle L Mowery, Pamela Jordan, Janyce Wiebe, Henk Harkema, John Dowling, Wendy W Chapman
2013 AMIA Annual Symposium Proceedings  
We evaluated the ability for humans to annotate clinical reports using the schema and assessed the contribution of semantic annotations in determining the status of a problem mention as active, inactive  ...  Support vector machine outperformed Naïve Bayes and Decision Tree for predicting a problem's status.  ...  a classifier (Decision Tree) that does not use them.  ... 
pmid:24551392 pmcid:PMC3900128 fatcat:66en4jjce5fidl52fzroxorqye

Natural and Artificial Intelligence in Neurosurgery: A Systematic Review

Joeky T Senders, Omar Arnaout, Aditya V Karhade, Hormuzdiyar H Dasenbrock, William B Gormley, Marike L Broekman, Timothy R Smith
2017 Neurosurgery  
Compared to clinical experts, ML models demonstrated a median absolute improvement in accuracy and area under the receiver operating curve of 13% (interquartile range 4-21%) and 0.14 (interquartile range  ...  PubMed and Embase databases as of August 2016 to review all studies comparing the performance of various ML approaches with that of clinical experts in neurosurgical literature.  ...  Acknowledgment The authors would like to thank P. Staples for his help on manually calculating P-values.  ... 
doi:10.1093/neuros/nyx384 pmid:28945910 fatcat:a33ttiskpnfglila235uc2vbym

Critical Analysis of Data Mining Techniques on Medical Data

Zahid Ullah, Muhamma Fayaz, Asif Iqbal
2016 International Journal of Modern Education and Computer Science  
The suitable use of data mining algorithm can enhance the quality of prediction, diagnosis and disease classification.  ...  The use of Data mining techniques on medical data is dramatically soar for determining helpful things which are used in decision making and identification.  ...  In the recent times Computer Aided Diagnosis system which uses CBIR to seek for experimental related and diagrammatic like images, this shows doubtful injuries and still this is a fascinating research.  ... 
doi:10.5815/ijmecs.2016.02.05 fatcat:fefglbwju5bsdal3g22ipwk4f4
« Previous Showing results 1 — 15 out of 93 results