Text mining approach to predict hospital admissions using early medical records from the emergency department
International Journal of Medical InformaticsPublished 6 January 2017
Filipe R. Lucini, Flávio S. Fogliatto, Giovani J.C. da Silveira, Jeruza Lavanholi Neyeloff, Michel J. Anzanello, Ricardo Kuchenbecker
Citations141
SJR quartileQ1
SJR score1.19
SNIP1.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Text mining could provide valuable information and facilitate decision-making by inward bed management teams and could be used to manage daily routines in EDs such as capacity planning and resource allocation.
Abstract
The method could be used to manage daily routines in EDs such as capacity planning and resource allocation. Text mining could provide valuable information and facilitate decision-making by inward bed management teams.
Keywords
Computer ScienceMedicineHealth Professions
Machine LearningRandom Forests
126,192 Citations2001Leo Breiman
Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
The Elements of Statistical Learning: Data Mining, Inference, and Prediction
19,345 Citations2013Trevor Hastie, Robert Tibshirani +1 more
Machine LearningExtremely randomized trees
8,669 Citations2006Pierre Geurts, Damien Ernst +1 more
A new tree-based ensemble method for supervised classification and regression problems that consists of randomizing strongly both attribute and cut-point choice while splitting a tree node and builds totally randomized trees whose structures are independent of the output values of the learning sample.
CERN Document Server (European Organization for Nuclear Research)Natural Language Processing with Python
3,449 Citations2009Steven Bird, Ewan Klein +1 more
Annals of Emergency MedicineSystematic Review of Emergency Department Crowding: Causes, Effects, and Solutions
1,669 Citations2008Nathan R. Hoot, Dominik Aronsky
A structured overview of the literature may help to identify future directions for the crowding research agenda and provide valuable contributions toward better understanding and alleviating the daily crisis.
Choice Reviews OnlineThe text mining handbook: advanced approaches in analyzing unstructured data
1,626 Citations2007
The LancetChronic non-communicable diseases in Brazil: burden and current challenges
1,616 Citations2011María Inês Schmidt, Bruce Bartholow Duncan +6 more
Brazil has implemented major policies for the prevention of NCDs, and its age-adjusted NCD mortality is falling by 1·8% per year, however, the unfavourable trends for most major risk factors pose an enormous challenge and call for additional and timely action and policies.
Studies in fuzziness and soft computingCombining SVMs with Various Feature Selection Strategies
991 Citations2008Yiwei Chen, Chih‐Jen Lin
This article investigates the performance of combining support vector machines (SVM) and various feature selection strategies, some are filter-type approaches: general feature selection methods independent of SVM, and some are wrapper-type methods: modifications of S VM which can be used to select features.
The Medical Journal of AustraliaThe association between hospital overcrowding and mortality among patients admitted via Western Australian emergency departments
767 Citations2006Peter Sprivulis, Julie‐Ann Da Silva +3 more
The Medical Journal of AustraliaThe association between hospital overcrowding and mortality among patients admitted via Western Australian emergency departments
753 Citations2006Peter Sprivulis, Julie‐Ann Da Silva +3 more
The relationship between hospital and emergency department occupancy, as indicators of hospital overcrowding, and mortality after emergency admission, is examined to examine the relationship between hospitals overcrowding and ED occupancy.
Journal of the American Medical Informatics AssociationReducing Workload in Systematic Review Preparation Using Automated Citation Classification
408 Citations2005Aaron Cohen, William Hersh +2 more
Whether automated classification of document citations can be useful in reducing the time spent by experts reviewing journal articles for inclusion in updating systematic reviews of drug class efficacy for treatment of disease is investigated.
Knowledge-Based SystemsA novel probabilistic feature selection method for text classification
303 Citations2012Alper Kürşat Uysal, Serkan Günal
This study proposes a novel filter based probabilistic feature selection method, namely distinguishing feature selector (DFS), for text classification that is compared with well-known filter approaches including chi square, information gain, Gini index and deviation from Poisson distribution.
Journal of the American Medical Informatics AssociationActive Computerized Pharmacovigilance Using Natural Language Processing, Statistics, and Electronic Health Records: A Feasibility Study
286 Citations2009Xiaofang Wang, George Hripcsak +2 more
This study provides a framework for the development of active, high-throughput and prospective systems which could potentially unveil drug safety profiles throughout their entire market life, and is the first study using comprehensive unstructured data from the EHR for pharmacovigilance.
NeurocomputingBrain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests
252 Citations2015Deepak Ranjan Nayak, Ratnakar Dash +1 more
An automated and accurate computer-aided diagnosis (CAD) system for brain magnetic resonance (MR) image classification that uses an AdaBoost algorithm with random forests as its base classifier and outperforms others in all the three datasets.
Mastering Machine Learning With scikit-learn
239 Citations2014Gavin Hackeling
This book examines machine learning models including logistic regression, decision trees, and support vector machines, and applies them to common problems such as categorizing documents and classifying images and uses an unsupervised Hidden Markov Model to predict stock prices.
Expert Systems with ApplicationsKnowledge discovery in medicine: Current issue and future trend
237 Citations2014Nura Esfandiari, Mohammad Reza Babavalian +2 more
The main idea in this paper is to describe key papers and provide some guidelines to help medical practitioners to explore previous works and identify interesting areas for future research.
Journal of the American Medical Informatics AssociationAutomated Acquisition of Disease-Drug Knowledge from Biomedical and Clinical Documents: An Initial Study
211 Citations2007Elizabeth Chen, George Hripcsak +3 more
A method for acquiring disease-specific knowledge based on applying a combination of NLP and statistical techniques to both biomedical and clinical documents is presented and a feasibility study of the method is conducted.
International Journal of Medical InformaticsText mining of cancer-related information: Review of current status and future directions
210 Citations2014Irena Spasić, Jacqueline E. Livsey +2 more
A critical overview of the current state of the art for TM related to cancer is provided and a strong bias towards symbolic methods is highlighted, e.g. named entity recognition based on dictionary lookup and information extraction relying on pattern matching.
Journal of Biomedical InformaticsFiltering big data from social media – Building an early warning system for adverse drug reactions
150 Citations2015Ming Yang, Melody Y. Kiang +1 more
The overall design of the system provides satisfactory performance in identifying ADR related posts for post-marketing drug surveillance and points out a potentially fruitful direction for building other early warning systems that need to filter big data from social media networks.
Journal of the American Medical Informatics AssociationRapidly Retargetable Approaches to De-identification in Medical Records
127 Citations2007Ben Wellner, M. Huyck +7 more
This paper describes a successful approach to de-identification that was developed to participate in a recent AMIA-sponsored challenge evaluation, and developed a method for tuning the balance of recall vs. precision in the Carafe system.
Journal of Biomedical InformaticsToward a complete dataset of drug–drug interaction information from publicly available sources
124 Citations2015Serkan Ayvaz, John R. Horn +10 more
It is thought that systems that provide access to the comprehensive lists, such as APIs into RxNorm, should be careful to inform users that the lists may be incomplete with respect to PDDIs that drug experts suggest clinicians be aware of.
Computers and Electronics in AgricultureBiometric cattle identification approach based on Weber’s Local Descriptor and AdaBoost classifier
122 Citations2016Tarek Gaber, Alaa Tharwat +2 more
A new and robust biometric-based approach to identify head of cattle based on biometric features based on Weber's Local Descriptor along with AdaBoost algorithm gave very promising results compared to both of the k-NN and Fk-NN algorithms.
Journal of Counseling & DevelopmentLearning to Write Case Notes Using the SOAP Format
114 Citations2002Susan Cameron, Imani Turtle‐Song
This article discusses how to use the SOAP (subjective, objective, assessment, and plan) note format to provide clear and concise documentation of the client's continuum of care.
Academic Emergency MedicineEmergency Department Patient Flow: The Influence of Hospital Census Variables on Emergency Department Length of Stay
104 Citations2009Ray Lucas, Heather Farley +5 more
In multiple hospital settings, emergency department (ED) length of stay (LOS) is correlated with the number of admissions and census of the higher acuity nursing units, more so than thenumber of ED patients each day, particularly in larger hospitals with busier EDs.
Journal of the American Medical Informatics AssociationA Text Mining Approach to the Prediction of Disease Status from Clinical Discharge Summaries
95 Citations2009Hui Yang, Irena Spasić +2 more
A system developed for the i2b2 obesity challenge, whose aim was to automatically identify the status of obesity and 15 related co-morbidities in patients using their clinical discharge summaries, achieved performance in line with the agreement between human annotators, indicating the potential of text mining for accurate and efficient prediction of disease statuses.
Journal of the American Medical Informatics AssociationCross-Topic Learning for Work Prioritization in Systematic Review Creation and Update
88 Citations2009Aaron Cohen, Kyle Ambert +1 more
This work investigates whether a topic-specific automated document ranking system for SRs can be improved using a hybrid approach, combining topic- Specific training data with data from other SR topics, and finds that the hybrid system performed significantly better than the baseline system at all levels of topic- specific training data.
Australian Health ReviewIntegrated care facilitation for older patients with complex health care needs reduces hospital demand
83 Citations2007Stephen R. Bird, William Kurowski +2 more
A model of care that facilitates access to community health services and provides coordination between existing services reduces hospital demand.
Journal of the American Medical Informatics AssociationImproved Identification of Noun Phrases in Clinical Radiology Reports Using a High-Performance Statistical Natural Language Parser Augmented with the UMLS Specialist Lexicon
82 Citations2005Yang Huang
After the adaptation using the UMLS Specialist Lexicon, the statistical parser's NPI performance on radiology reports increased to levels comparable to the parser's native performance in its newswire training domain and to that reported by other researchers in the general nonmedical domain.
NeurocomputingFacial expression recognition from image sequences using twofold random forest classifier
81 Citations2015Xiaorong Pu, Ke Fan +3 more
A novel framework for facial expressions analysis by recognizing AUs from image sequences using twofold random forest classifier using Extended Cohn-Kanade(CK+) database demonstrates that the proposed method can achieve higher performance than several other approaches on both AUs and facial expression recognition.
Journal of Computational ScienceHMV: A medical decision support framework using multi-layer classifiers for disease prediction
81 Citations2016Saba Bashir, Usman Qamar +2 more
A multi-layer classifier ensemble framework is proposed based on the optimal combination of heterogeneous classifiers that overcomes the limitations of conventional performance bottlenecks by utilizing an ensemble of seven heterogeneousclassifiers.
Journal of the American Medical Informatics AssociationA Document Clustering and Ranking System for Exploring MEDLINE Citations
76 Citations2007Yen-Yin Lin, Wei Li +2 more
Journal of Epidemiology & Community HealthModels for forecasting hospital bed requirements in the acute sector.
73 Citations1990Rohit Farmer, J Emami
The simple trend fitting approach is inferior to the time series approach in modelling hospital bed requirements, and the Box-Jenkins method was shown to be a more appropriate way of modelling the data.
Health Care Management ScienceChoice of Models for the Analysis and Forecasting of Hospital Beds
65 Citations2005M. F. Mackay, Michael Lee
Analysis of model fit against the test data showed that increasing model complexity did result in over-fitting, and better prediction was achieved with a relatively simple model, while in terms of generalisation, the seasonal models performed best.
Decision Support SystemsAn analytic approach to better understanding and management of coronary surgeries
64 Citations2011Dursun Delen, Asil Oztekin +1 more
Using a large, feature-rich, nationwide inpatient databases along with four popular machine learning techniques, predictive models were developed; and using an information fusion based sensitivity analysis on these models, the surgical outcome of a patient undergoing a coronary artery bypass grafting was explained.
Accident Analysis & PreventionMachine learning approaches to analysing textual injury surveillance data: A systematic review
62 Citations2015Kirsten Vallmuur
Machine learning was found to provide high precision and accuracy when predicting a small number of categories, was valuable for visualisation of injury patterns and prediction of future outcomes, however, difficulties related to generalizability, source data quality, complexity of models and integration of content and technical knowledge were discussed.
Medical Engineering & PhysicsIntracranial hypertension prediction using extremely randomized decision trees
61 Citations2012Fabien Scalzo, Robert Hamilton +3 more
A computational framework is proposed to predict prolonged intracranial hypertension based on morphological waveform features computed from the ICP to exploit an ensemble classifier method based on extremely randomized decision trees (Extra-Trees).
Journal of the American Medical Informatics AssociationSemantic Classification of Diseases in Discharge Summaries Using a Context-aware Rule-based Classifier
61 Citations2009Ido Solt, Domonkos Tikk +2 more
The authors show in the paper that a simple rule-based classifier can tackle the semantic classification task more successfully than machine learning techniques, if the training data are limited and some semantic labels are very sparse.
Journal of the American Medical Informatics AssociationEnhancing Text Categorization with Semantic-enriched Representation and Training Data Augmentation
60 Citations2006Xinghua Lu, Bin Zheng +2 more
Semantic-enriched data transformation and the pseudo-positive-cases augmented training data enhance the efficiency and performance of text categorization by SVM.
The American Journal of Emergency MedicinePredictors of patient length of stay in 9 emergency departments
57 Citations2012Jennifer L. Wiler, Daniel A. Handel +11 more
Length of stay was increased onDays with higher percentage daily admissions, higher elopements, higher periods of ambulance diversion, and during weekdays, whereas LOS was decreased on days with higher numbers of discharges and weekends.
Electric Power Systems ResearchA rule-based S-Transform and AdaBoost based approach for power quality assessment
53 Citations2016Motakatla Venkateswara Reddy, Ranjana Sodhi
The results reveal that the proposed rule-based ST and AdaBoost based method performs better than the other methods viz., SVM and Decision Tree (DT), under varied noise conditions as well as under varied amount of data used for training.
Journal of Biomedical SemanticsNeuroanatomical domain of the foundational model of anatomy ontology
45 Citations2014B. Nolan Nichols, José L. V. Mejino +6 more
Recent enhancements to the neuroanatomical content of the Foundational Model of Anatomy that models cytoarchitectural and morphological regions of the cerebral cortex, as well as white matter structure and connectivity are described.
Journal of Biomedical InformaticsClassification of clinically useful sentences in clinical evidence resources
44 Citations2016Mohammad Amin Morid, Marcelo Fiszman +3 more
A Kernel-based Bayesian Network classification model based on different domain-specific feature types extracted from sentences in a gold standard composed of 18 UpToDate documents significantly outperforms general baseline methods and significantly outperformed classifiers based on a single type of feature.
Journal of Biomedical InformaticsBuilding an automated SOAP classifier for emergency department reports
42 Citations2011Danielle L. Mowery, Janyce Wiebe +3 more
This quantitative study applied the SOAP framework to sentences from emergency department reports, and trained and evaluated SOAP classifiers built with various linguistic features, and found theSOAP framework can be applied manually toEmergency department reports with high agreement.
Journal of the American Medical Informatics AssociationA System for Classifying Disease Comorbidity Status from Medical Discharge Summaries Using Automated Hotspot and Negated Concept Detection
34 Citations2009Kyle Ambert, A. M. Cohen
The system demonstrates that effective comorbidity status classification by an automated system is possible and incorporates a variety of automated techniques, including hot-spot filtering, negated concept identification, zero-vector filtering, weighting by inverse class-frequency, and error-correcting of output codes with linear support vector machines.
Procedia TechnologyICD9-based Text Mining Approach to Children Epilepsy Classification
30 Citations2013Luís A. M. Pereira, Rui Rijo +2 more
A text mining approach is put forward, using processed electronic medical records and a K-Nearest Neighbor is applied as a white-box multi classifier approach to classify each instance mapping into the corresponding standard code.
A hybrid prediction model with F-score feature selection for type II Diabetes databases
28 Citations2010Ilango Paramasivam, N. Ramaraj
This study proposes a Hybrid Prediction Model with F-score feature selection approach to identify the optimal feature subset of the Pima Indians Diabetes dataset, and achieves the highest predictive accuracy for diabetes dataset compared to other models in literature for this problem.
Journal of Biomedical SemanticsMining characteristics of epidemiological studies from Medline: a case study in obesity
25 Citations2014George Karystianis, Iain Buchan +1 more
An information extraction approach that enables users to identify key characteristics of epidemiological studies from MEDLINE abstracts and suggests that the proposed approach could identify key epidemiological characteristics associated with a complex clinical problem from related abstracts.
Journal of Evaluation in Clinical PracticeClassification of patients by severity grades during triage in the emergency department using data mining methods
23 Citations2010Dror Zmiri, Yuval Shaḥar +1 more
It is possible to produce a computerized classification model for the severity grade of triage patients, using data mining methods, and learning from patient records regarding which there is a consensus of several physicians is preferable to learning from each physician's patients.
American Journal of Infection ControlAssessing surgical site infection risk factors using electronic medical records and text mining
23 Citations2014James D. Michelson, Jenna S. Pariseau +1 more
Text mining techniques to detect surgical site infections (SSI) in unstructured clinical notes were used to improve SSI detection and all of the 22 SSIs detected by traditional hospital-based surveillance were found using text mining, along with an additional 37 SSIs not detected byTraditional surveillance.
The Open Medical Informatics JournalValidating Emergency Department Vital Signs Using a Data Quality Engine for Data Warehouse
21 Citations2013Nicholas Genes, D Chandra +2 more
In developing a method for importing free-text vital sign data from the emergency department information system, a data warehouse with a broad array of quality-checked vital signs is created, permitting analysis and correlation with demographics and outcomes.
Journal of the American Medical Informatics AssociationMachineProse: An Ontological Framework for Scientific Assertions
18 Citations2005Deendayal Dinakarpandian, Y. Lee +2 more
MachineProse is a novel semantic framework that may be used to summarize research findings, annotate biomedical publications, and support sophisticated searches.
Pattern RecognitionProbability estimation for multi-class classification using AdaBoost
16 Citations2014Qingfeng Nie, Lizuo Jin +1 more
A theoretical analysis of probability estimation model for multi-class classification by pairwise coupling is put forward and some verification experiments indicate that AdaBoost can be used for probability estimation.
BMJInstrument for objective assessment of appropriateness of surgical bed occupancy: validation study
14 Citations2003A. Alijani, George B Hanna +5 more
A valid instrument for the objective assessment of appropriateness of occupancy of surgical beds is developed and a validation study on 100 bed days in a general surgical unit with an interest in colorectal surgery is conducted.
AJN American Journal of NursingTechniques in Clinical Nursing
13 Citations1987VICKI K. GREENFIELD
Searching for this popular book now is the techniques in clinical nursing a nursing process approach will give you benefit and you will not run out of this book.
BMJForecasting hospital bed needs.
11 Citations1981Terry Sweeney, J S Ashley
The method in this study is founded on the belief that hospital services should be planned to relate directly to the pattern of morbidity in the population served and is, therefore, based on projections of disease trends modified in the light of clinical and epidemiological information.
Using the Electronic Health Record in the Health Care Provider Practice
9 Citations2007Shirley Eichenwald Maki, Bonnie J. Petterson
Using the electronic health record in the health care provider practice, Using the electronic Health Record in the Health Care provider practice , and more.
The OTA's Guide to Writing Soap Notes
5 Citations2002Sherry Borcherding, Carol Kappel
The OTA's Guide to Writing SOAP Notes is an instruction manual for teaching a specific skill: documentation as required for reimbursement in occupational therapy.
Journal of Emergency MedicineWorkforce projections for Emergency Medicine in Puerto Rico: A five-year follow-up of an evident demand
4 Citations2005Carlos García-Gubern, Lissandra Colón-Rolón +1 more
There is an actual significant shortage in the Puerto Rico EP workforce and it will take a long time to make leaders understand the positive impact of having residency-trained EPs in every ED, on quality patient care and the whole health care system.