Giulio Napolitano1, Adele Marshall2, Peter Hamilton3, Anna T Gavin4. 1. Institut für Medizinische Biometrie, Informatik und Epidemiologie (IMBIE), Universität Bonn, Haus 325/11/1.OG/Raum 620, Sigmund-Freud-Straße 25, 53105 Bonn, Germany. Electronic address: g.napolitano@imbie.uni-bonn.de. 2. Queen's University Belfast, School of Mathematics and Physics, University Road, Belfast BT7 1NN, United Kingdom. 3. Queen's University Belfast, School of Medicine, Dentistry and Biomedical Sciences, 97 Lisburn Road, Belfast BT9 7BL, United Kingdom. 4. NICR-Centre for Public Health, The Queen's University of Belfast, Mulhouse Building, Grosvenor Road, Belfast BT12 6DP, United Kingdom.
Abstract
BACKGROUND AND AIMS: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging. MATERIALS AND METHODS: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: 'semi-structured' and 'unstructured'. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry. RESULTS: The best result of 99.4% accuracy - which included only one semi-structured report predicted as unstructured - was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured. CONCLUSIONS: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.
BACKGROUND AND AIMS: Machine learning techniques for the text mining of cancer-related clinical documents have not been sufficiently explored. Here some techniques are presented for the pre-processing of free-text breast cancer pathology reports, with the aim of facilitating the extraction of information relevant to cancer staging. MATERIALS AND METHODS: The first technique was implemented using the freely available software RapidMiner to classify the reports according to their general layout: 'semi-structured' and 'unstructured'. The second technique was developed using the open source language engineering framework GATE and aimed at the prediction of chunks of the report text containing information pertaining to the cancer morphology, the tumour size, its hormone receptor status and the number of positive nodes. The classifiers were trained and tested respectively on sets of 635 and 163 manually classified or annotated reports, from the Northern Ireland Cancer Registry. RESULTS: The best result of 99.4% accuracy - which included only one semi-structured report predicted as unstructured - was produced by the layout classifier with the k nearest algorithm, using the binary term occurrence word vector type with stopword filter and pruning. For chunk recognition, the best results were found using the PAUM algorithm with the same parameters for all cases, except for the prediction of chunks containing cancer morphology. For semi-structured reports the performance ranged from 0.97 to 0.94 and from 0.92 to 0.83 in precision and recall, while for unstructured reports performance ranged from 0.91 to 0.64 and from 0.68 to 0.41 in precision and recall. Poor results were found when the classifier was trained on semi-structured reports but tested on unstructured. CONCLUSIONS: These results show that it is possible and beneficial to predict the layout of reports and that the accuracy of prediction of which segments of a report may contain certain information is sensitive to the report layout and the type of information sought.
Authors: Tomasz Oliwa; Steven B Maron; Leah M Chase; Samantha Lomnicki; Daniel V T Catenacci; Brian Furner; Samuel L Volchenboum Journal: JCO Clin Cancer Inform Date: 2019-08
Authors: Seyedmostafa Sheikhalishahi; Riccardo Miotto; Joel T Dudley; Alberto Lavelli; Fabio Rinaldi; Venet Osmani Journal: JMIR Med Inform Date: 2019-04-27