Machine learning classification of surgical pathology reports and chunk recognition for information extraction noise reduction

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.

BRAF mutation testing algorithm for vemurafenib treatment in melanoma: recommendations from an expert panel.

The incidence of melanoma has increased rapidly over the past 30 years, and the disease is now the sixth most common cancer among men and women in the U.K. Many patients are diagnosed with or develop metastatic disease, and survival is substantially reduced in these patients. Mutations in the BRAF gene have been identified as key drivers of melanoma cells and are found in around 50% of cutaneous melanomas. Vemurafenib (Zelboraf(®) ; Roche Molecular Systems Inc., Pleasanton, CA, U.S.A.) is the first licensed inhibitor of mutated BRAF, and offers a new first-line option for patients with unresectable or metastatic melanoma who harbour BRAF mutations. Vemurafenib was developed in conjunction with a companion diagnostic, the cobas(®) 4800 BRAF V600 Mutation Test. The purpose of this paper is to make evidence-based recommendations to facilitate the implementation of BRAF mutation testing and targeted therapy in patients with metastatic melanoma in the U.K. The recommendations are the result of a meeting of an expert panel and have been reviewed by melanoma specialists and representatives of the National Cancer Research Network Clinical Study Group on behalf of the wider melanoma community. This article is intended to be a starting point for practical advice and recommendations, which will no doubt be updated as we gain further experience in personalizing therapy for patients with melanoma.

A comparison of different pre-lysis methods and extraction kits for recovery of Stretococcus agalacticae (Lancefield group B Streptococcus) DNA from whole blood

Sub-optimal recovery of bacterial DNA from whole blood samples can limit the sensitivity of molecular assays to detect pathogenic bacteria. We compared 3 different pre-lysis protocols (none, mechanical pre-lysis and achromopeptidasepre-lysis) and 5 commercially available DNA extraction platforms for direct detection of Group B Streptococcus (GBS) in spiked whole blood samples, without enrichment culture. DNA was extracted using the QIAamp Blood Mini kit (Qiagen), UCP Pathogen Mini kit (Qiagen), QuickGene DNA Whole Blood kit S (Fuji), Speed Xtract Nucleic Acid Kit 200 (Qiagen) and MagNA Pure Compact Nucleic Acid Isolation Kit I (Roche Diagnostics Corp). Mechanical pre-lysis increased yields of bacterial genomic DNA by 51.3 fold (95% confidence interval; 31.6–85.1, p < 0.001) and pre-lysis with achromopeptidase by 6.1 fold (95% CI; 4.2–8.9, p < 0.001), compared with no pre-lysis. Differences in yield dueto pre-lysis were 2–3 fold larger than differences in yield between extraction methods. Including a pre-lysis step can improve the limits of detection of GBS using PCR or other molecular methods without need for culture.