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.

Building a 'Repository of Science': the importance of integrating Biobanks within molecular pathology programmes

Repositories containing high quality human biospecimens linked with robust and relevant clinical and pathological information are required for the discovery and validation of biomarkers for disease diagnosis, progression and response to treatment. Current molecular based discovery projects using either low or high throughput technologies rely heavily on ready access to such sample collections. It is imperative that modern biobanks align with molecular diagnostic pathology practices not only to provide the type of samples needed for discovery projects but also to ensure requirements for ongoing sample collections and the future needs of researchers are adequately addressed. Biobanks within comprehensive molecular pathology programmes are perfectly positioned to offer more than just tumour derived biospecimens; for example, they have the ability to facilitate researchers gaining access to sample metadata such as digitised scans of tissue samples annotated prior to macrodissection for molecular diagnostics or pseudoanonymised clinical outcome data or research results retrieved from other users utilising the same or overlapping cohorts of samples. Furthermore, biobanks can work with molecular diagnostic laboratories to develop standardized methodologies for the acquisition and storage of samples required for new approaches to research such as ‘liquid biopsies’ which will ultimately feed into the test validations required in large prospective clinical studies in order to implement liquid biopsy approaches for routine clinical practice. We draw on our experience in Northern Ireland to discuss how this harmonised approach of biobanks working synergistically with molecular pathology programmes is key for the future success of precision medicine.

Measuring the geographic distribution of maternal education in Africa

Thesis (Master's)--University of Washington, 2016-08

The Cardiovascular Pathology of Stimulant Overdose Decedents in King County, Washington

Thesis (Master's)--University of Washington, 2016-09

The pathology of command and control: a formal synthesis

One of the most important theories in the study of environmental governance and policy is the pathology of command and control, which describes the negative consequences of top-down, technocratic governance of social and ecological systems. However, to date, this theory has been expressed somewhat inconsistently and informally in the literature, even by the seminal works that have established its importance and popularized it. This presents a problem for the sustainability science community if it cannot be sure of the precise details of one of its most important theories. Without such precision, applications and tests of various elements of the theory cannot be conducted reliably to advance the knowledge of environmental governance. I address this problem by synthesizing several seminal works to formalize this theory. The formalization involves the identification of the individual elements of the theory and a diagrammatic description of their relationships with each other that unfold in a series of semi-independent causal paths. Ideally, with such a formalization, scholars can use this theory more reliably and more meaningfully in their future work. I conclude by discussing the implications this theory has for the governance of natural resources.

Predicting bee community responses to land-use changes: Effects of geographic and taxonomic biases

Land-use change and intensification threaten bee populations worldwide, imperilling pollination services. Global models are needed to better characterise, project, and mitigate bees' responses to these human impacts. The available data are, however, geographically and taxonomically unrepresentative; most data are from North America and Western Europe, overrepresenting bumblebees and raising concerns that model results may not be generalizable to other regions and taxa. To assess whether the geographic and taxonomic biases of data could undermine effectiveness of models for conservation policy, we have collated from the published literature a global dataset of bee diversity at sites facing land-use change and intensification, and assess whether bee responses to these pressures vary across 11 regions (Western, Northern, Eastern and Southern Europe; North, Central and South America; Australia and New Zealand; South East Asia; Middle and Southern Africa) and between bumblebees and other bees. Our analyses highlight strong regionally-based responses of total abundance, species richness and Simpson's diversity to land use, caused by variation in the sensitivity of species and potentially in the nature of threats. These results suggest that global extrapolation of models based on geographically and taxonomically restricted data may underestimate the true uncertainty, increasing the risk of ecological surprises.

Investigating the Diabetic Brain: The Effects of Pioglitazone and Insulin on the Cellular Processes and Pathology of Alzheimer's Disease

Alzheimer’s disease (AD) is the sixth leading cause of death in the US. Some researchers refer to AD as “Type III Diabetes” because of reported glucose metabolism dysfunction. Preclinical studies suggest increasing insulin decreases AD pathology, although the mechanism remains unclear. To sensitize insulin signaling, this study activated Peroxisome Proliferator-Activated Receptor Gamma using intranasal co-administration of pioglitazone (PGZ) and insulin. This method targeted the site of action to reduce peripheral effects and to maximize impact in transgenic mice expressing AD pathology. Data from GC-MS fluxomics analysis suggested that PGZ+Insulin increased glucose metabolism in the brain. Immunohistochemistry with relevant antibodies was used to identify AD pathological markers in the subiculum, indicating that PGZ+Insulin decreased pathology compared to Insulin and Saline. This suggests that increasing glucose uptake in the brain alleviated AD pathology, further clarifying the role of insulin signaling in AD pathology.Gemstone

Revealing Cultural Ecosystem Services through Instagram Images : The Potential of Social Media Volunteered Geographic Information for Urban Green Infrastructure Planning and Governance

With the prevalence of smartphones, new ways of engaging citizens and stakeholders in urban planning and govern-ance are emerging. The technologies in smartphones allow citizens to act as sensors of their environment, producing and sharing rich spatial data useful for new types of collaborative governance set-ups. Data derived from Volunteered Geographic Information (VGI) can support accessible, transparent, democratic, inclusive, and locally-based governance situations of interest to planners, citizens, politicians, and scientists. However, there are still uncertainties about how to actually conduct this in practice. This study explores how social media VGI can be used to document spatial tendencies regarding citizens’ uses and perceptions of urban nature with relevance for urban green space governance. Via the hashtag #sharingcph, created by the City of Copenhagen in 2014, VGI data consisting of geo-referenced images were collected from Instagram, categorised according to their content and analysed according to their spatial distribution patterns. The results show specific spatial distributions of the images and main hotspots. Many possibilities and much potential of using VGI for generating, sharing, visualising and communicating knowledge about citizens’ spatial uses and preferences exist, but as a tool to support scientific and democratic interaction, VGI data is challenged by practical, technical and ethical concerns. More research is needed in order to better understand the usefulness and application of this rich data source to governance.

eLearning in the context of a one-year postgraduate course in macroscopy in pathology: benefits of a multifaceted and pluripotent concept

Performing Macroscopy in Pathology implies to plan and implement methods of selection, description and collection of biological material from human organs and tissues, actively contributing to the clinical pathology analysis by preparing macroscopic report and the collection and identification of fragments, according to the standardized protocols and recognizing the criteria internationally established for determining the prognosis. The Macroscopy in Pathology course is a full year program with theoretical and pratical components taught by Pathologists. It is divided by organ/system surgical pathology into weekly modules and includes a practical "hands-on" component in Pathology Departments. The students are 50 biomedical scientists aged from 22 to 50 years old from all across the country that want to acquire competences in macroscopy. A blended learning strategy was used in order to: give students the opportunity to attend from distance; support the contents, lessons and the interaction with colleagues and teachers; facilitate the formative/summative assessment.

Real-Time PCR Assays for the Detection of Puccinia psidii

Puccinia psidii (Myrtle rust) is an emerging pathogen that has a wide host range in the Myrtaceae family; it continues to show an increase in geographic range and is considered to be a significant threat to Myrtaceae plants worldwide. In this study, we describe the development and validation of three novel real-time polymerase reaction (qPCR) assays using ribosomal DNA and β-tubulin gene sequences to detect P. psidii. All qPCR assays were able to detect P. psidii DNA extracted from urediniospores and from infected plants, including asymptomatic leaf tissues. Depending on the gene target, qPCR was able to detect down to 0.011 pg of P. psidii DNA. The most optimum qPCR assay was shown to be highly specific, repeatable, and reproducible following testing using different qPCR reagents and real-time PCR platforms in different laboratories. In addition, a duplex qPCR assay was developed to allow coamplification of the cytochrome oxidase gene from host plants for use as an internal PCR control. The most optimum qPCR assay proved to be faster and more sensitive than the previously published nested PCR assay and will be particularly useful for high-throughput testing and to detect P. psidii at the early stages of infection, before the development of sporulating rust pustules.

Mass mortality in bivalves and the intricate case of the Pacific oyster, Crassostrea gigas

Massive mortality outbreaks in cultured bivalves have been reported worldwide and they have been associated with infection by a range of viral and bacterial pathogens. Due to their economic and social impact, these episodes constitute a particularly sensitive issue in Pacific oyster (Crassostrea gigas) production. Since 2008, mortality outbreaks affecting C. gigas have increased in terms of intensity and geographic distribution. Epidemiologic surveys have lead to the incrimination of pathogens, specifically OsHV-1 and bacteria of the Vibrio genus, in particular Vibrio aestuarianus. Pathogen diversity may partially account for the variability in the outcome of infections. Host factors (age, reproductive status…) including their genetic background that has an impact on host susceptibility towards infection, also play a role herein. Finally, environmental factors have significant effects on the pathogens themselves, on the host and on the host-pathogen interaction. Further knowledge on pathogen diversity, classification, and spread, may contribute towards a better understanding of this issue and potential ways to mitigate the impact of these outbreaks.

Survey on parasites of Rutilus frisii Kutum in South west of Caspian Sea with the emphasis of pathology of Dactylogyrus frisii and morphological identification of Paradiplozoon sp and Anisakis sp

Rutilus frisii Kutum is one of the most precious fish in the Caspian Sea. Investigation of the various aspects of its biocharactristics. Including its parasite fauna and ecological aspects are of prime importance. In this study the farmed kutum fry were on the focus of investigation in various seasons of the year and prior to their being released in the sea. This included also the study on the kutum spawners caught both from liver and the sea. The results were that 17 external and internal parasite species were distinct within different organs which were further identified down to genus and species. The single celled parasites identified included Ichthyophthirius multifilils, Chilodonella hexastica, Chilodonella pisicola, Trichodina sp Along with the monogene parasites that included Paradiplozoon chazaricum, D. rarissimus, D. turaliensis, D. nybelini, Dactylogyrus frisii. Meanwhile Diplostomum spathaceum constituted the single eyed parasites and the intestinal termatode were Aspidogaster limacoides, Asymphyoldora kubanicum as well as Bothriocephalus gowkongeniss as the sestads. The nematodes defrentiated were Raphidascaris acus, Dioctophyma renale, and Eustrongylides excisus followed by Lernaea cyprinacea as a crustacean. In this study, infestations by single celled parasites, crustaceans and sestod were found to be present only among the farmed kutum fry which varied in terms of percentage and intensity of infection as well as the parasite species and season of the year. The highest percentage of infection among kutum fry and spawners in both fresh water and in the sea during all seasons belonged to monogene parasites (33%). This was up to 100% among spawners. Infection caused by nematodes was exclusively detected among riverine spawners (7.5-5%) and the infection by Asymphyoldora kubanicum and Aspidogaster limacoides among Spawners caught at Sea and rivers varied within different seasons of the year. The infestation of Metacercer diplostomum spathaceum among kutum fry was 12% which compared to spawners was in slightly higher level. The study could identify Dioctophyma renale for the first time in the country and Eustrongylidis excisu was also detected among Rutilus frisii kutum.