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.

Policy Transfer and the Sustainability of Public Private Partnership in Ireland::A conceptual analysis

There has been private sector involvement in the delivery of public services in the Irish State since its foundation. This involvement was formalised in 1998 when Public Private Partnership (PPP) was officially introduced. Ireland is a latecomer to PPP and, prior to the credit crisis, was seen as a ‘rapid follower’ relying primarily on the UK PPP model in the procurement of infrastructure in transport, education, housing/urban regeneration and water/wastewater.  PPP activity in Ireland stalled during the credit crisis, and some projects were cancelled, but it has taken off again recently with part of the Infrastructure and Capital Investment Plan 2016 – 2021 to be delivered through PPP showing continuing political commitment to PPP.  Ireland’s interest in PPP cannot be explained by economic rationale alone, as PPP was initiated during a period of prosperity. We consider three alternative explanations: voluntary adoption – where the UK model was closely followed; coercive adoption – where PPP policy was forced upon Ireland; and institutional isomorphism – where institutional creation and change was promoted to aid public sector organisations in gaining institutional legitimacy. We find evidence of all three patterns, with coercive adoption becoming more relevant in recent years. Ireland’s rapid uptake of PPP differs from other European countries, mostly because when PPP was introduced in 1998, the Irish State was in an economic position where it could have directly procured necessary infrastructure. This paper therefore asks why PPP was adopted and how this adoption pattern has affected the sustainability of PPP in Ireland.  This paper defines PPP; examines the background to the PPP approach adopted in Ireland; outlines the theoretical framework of the paper: transfer theory and institutional theory; discusses the methodology; reports on findings and gives conclusions.