Literature DB >> 27742349

Text mining electronic hospital records to automatically classify admissions against disease: Measuring the impact of linking data sources.

Simon Kocbek1, Lawrence Cavedon2, David Martinez3, Christopher Bain4, Chris Mac Manus5, Gholamreza Haffari6, Ingrid Zukerman6, Karin Verspoor3.   

Abstract

OBJECTIVE: Text and data mining play an important role in obtaining insights from Health and Hospital Information Systems. This paper presents a text mining system for detecting admissions marked as positive for several diseases: Lung Cancer, Breast Cancer, Colon Cancer, Secondary Malignant Neoplasm of Respiratory and Digestive Organs, Multiple Myeloma and Malignant Plasma Cell Neoplasms, Pneumonia, and Pulmonary Embolism. We specifically examine the effect of linking multiple data sources on text classification performance.
METHODS: Support Vector Machine classifiers are built for eight data source combinations, and evaluated using the metrics of Precision, Recall and F-Score. Sub-sampling techniques are used to address unbalanced datasets of medical records. We use radiology reports as an initial data source and add other sources, such as pathology reports and patient and hospital admission data, in order to assess the research question regarding the impact of the value of multiple data sources. Statistical significance is measured using the Wilcoxon signed-rank test. A second set of experiments explores aspects of the system in greater depth, focusing on Lung Cancer. We explore the impact of feature selection; analyse the learning curve; examine the effect of restricting admissions to only those containing reports from all data sources; and examine the impact of reducing the sub-sampling. These experiments provide better understanding of how to best apply text classification in the context of imbalanced data of variable completeness.
RESULTS: Radiology questions plus patient and hospital admission data contribute valuable information for detecting most of the diseases, significantly improving performance when added to radiology reports alone or to the combination of radiology and pathology reports.
CONCLUSION: Overall, linking data sources significantly improved classification performance for all the diseases examined. However, there is no single approach that suits all scenarios; the choice of the most effective combination of data sources depends on the specific disease to be classified. Copyright Â
© 2016 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Cancer record retrieval; Electronic Health Records; Natural Language Processing; Pathology; Radiology; Text mining

Mesh:

Year:  2016        PMID: 27742349     DOI: 10.1016/j.jbi.2016.10.008

Source DB:  PubMed          Journal:  J Biomed Inform        ISSN: 1532-0464            Impact factor:   6.317


  10 in total

1.  Evaluation of Clinical Text Segmentation to Facilitate Cohort Retrieval.

Authors:  Tracy Edinger; Dina Demner-Fushman; Aaron M Cohen; Steven Bedrick; William Hersh
Journal:  AMIA Annu Symp Proc       Date:  2018-04-16

2.  Cross-registry neural domain adaptation to extract mutational test results from pathology reports.

Authors:  Anthony Rios; Eric B Durbin; Isaac Hands; Susanne M Arnold; Darshil Shah; Stephen M Schwartz; Bernardo H L Goulart; Ramakanth Kavuluru
Journal:  J Biomed Inform       Date:  2019-08-08       Impact factor: 6.317

3.  Medical knowledge infused convolutional neural networks for cohort selection in clinical trials.

Authors:  Chi-Jen Chen; Neha Warikoo; Yung-Chun Chang; Jin-Hua Chen; Wen-Lian Hsu
Journal:  J Am Med Inform Assoc       Date:  2019-11-01       Impact factor: 4.497

4.  Integrating Natural Language Processing and Machine Learning Algorithms to Categorize Oncologic Response in Radiology Reports.

Authors:  Po-Hao Chen; Hanna Zafar; Maya Galperin-Aizenberg; Tessa Cook
Journal:  J Digit Imaging       Date:  2018-04       Impact factor: 4.056

5.  Medical subdomain classification of clinical notes using a machine learning-based natural language processing approach.

Authors:  Wei-Hung Weng; Kavishwar B Wagholikar; Alexa T McCray; Peter Szolovits; Henry C Chueh
Journal:  BMC Med Inform Decis Mak       Date:  2017-12-01       Impact factor: 2.796

6.  Bioinformatic analysis of the molecular mechanism underlying bronchial pulmonary dysplasia using a text mining approach.

Authors:  Weitao Zhou; Fei Shao; Jing Li
Journal:  Medicine (Baltimore)       Date:  2019-12       Impact factor: 1.817

Review 7.  Research and Application of Artificial Intelligence Based on Electronic Health Records of Patients With Cancer: Systematic Review.

Authors:  Xinyu Yang; Dongmei Mu; Hao Peng; Hua Li; Ying Wang; Ping Wang; Yue Wang; Siqi Han
Journal:  JMIR Med Inform       Date:  2022-04-20

8.  Building interpretable models for polypharmacy prediction in older chronic patients based on drug prescription records.

Authors:  Simon Kocbek; Primoz Kocbek; Andraz Stozer; Tina Zupanic; Tudor Groza; Gregor Stiglic
Journal:  PeerJ       Date:  2018-10-12       Impact factor: 2.984

9.  Supervised and unsupervised language modelling in Chest X-Ray radiological reports.

Authors:  Ignat Drozdov; Daniel Forbes; Benjamin Szubert; Mark Hall; Chris Carlin; David J Lowe
Journal:  PLoS One       Date:  2020-03-10       Impact factor: 3.240

10.  LASSO Regression Modeling on Prediction of Medical Terms among Seafarers' Health Documents Using Tidy Text Mining.

Authors:  Nalini Chintalapudi; Ulrico Angeloni; Gopi Battineni; Marzio di Canio; Claudia Marotta; Giovanni Rezza; Getu Gamo Sagaro; Andrea Silenzi; Francesco Amenta
Journal:  Bioengineering (Basel)       Date:  2022-03-17
  10 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.