Supervised machine learning and active learning in classification of radiology reports.
Objective: This paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology re...
| Publicado en: | Journal of the American Medical Informatics Association Vol. 21; no. 5; pp. 893 - 902 |
|---|---|
| Autores principales: | , |
| Formato: | research Journal Article |
| Publicado: |
Oxford University Press / USA
Sep2014
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=103985578&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 103985578 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 10675027 FZ9 jtl: Journal of the American Medical Informatics Association issn: 10675027 maglogo: N pubinfo: dt: Sep2014 vid: 21 iid: 5 pid: 622 pub: Oxford University Press / USA artinfo: ui: 103985578 NLM24853067 2012683776 10.1136/amiajnl-2013-002516 NLM24853067 PMC4147614 103985578 ppf: 893 ppct: 9 formats: tig: atl: Supervised machine learning and active learning in classification of radiology reports. aug: au: Nguyen, Dung H M Patrick, Jon D affil: School of Information Technologies, University of Sydney, Sydney, New South Wales, Australia. sug: subj: Algorithms Artificial Intelligence Diagnostic Imaging Classification Neoplasms Diagnosis Human Magnetic Resonance Imaging Classification Tomography, Emission-Computed Classification Radiology Information Systems Sensitivity and Specificity Tomography, X-Ray Computed Classification Vocabulary, Controlled ab: Objective: This paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology reports for use in the Victorian Cancer Registry.Materials and Methods: In addition to traditional supervised learning methods such as conditional random fields and support vector machines, active learning (AL) approaches were investigated to optimize training production and further improve classification performance. The project involved two pilot sites in Victoria, Australia (Lake Imaging (Ballarat) and Peter MacCallum Cancer Centre (Melbourne)) and, in collaboration with the NSW Central Registry, one pilot site at Westmead Hospital (Sydney).Results: The reportability classifier performance achieved 98.25% sensitivity and 96.14% specificity on the cancer registry's held-out test set. Up to 92% of training data needed for supervised machine learning can be saved by AL.Discussion: AL is a promising method for optimizing the supervised training production used in classification of radiology reports. When an AL strategy is applied during the data selection process, the cost of manual classification can be reduced significantly.Conclusions: The most important practical application of the reportability classifier is that it can dramatically reduce human effort in identifying relevant reports from the large imaging pool for further investigation of cancer. The classifier is built on a large real-world dataset and can achieve high performance in filtering relevant reports to support cancer registries. pubtype: Academic Journal doctype: research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|