Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
1,141
result(s) for
"Data mining History."
Sort by:
How data happened : a history from the age of reason to the age of algorithms
\"From facial recognition--capable of checking people into flights or identifying undocumented residents--to automated decision systems that inform who gets loans and who receives bail, each of us moves through a world determined by data-empowered algorithms. But these technologies didn't just appear: they are part of a history that goes back centuries, from the census enshrined in the US Constitution to the birth of eugenics in Victorian Britain to the development of Google search. Expanding on the popular course they created at Columbia University, Chris Wiggins and Matthew L. Jones illuminate the ways in which data has long been used as a tool and a weapon in arguing for what is true, as well as a means of rearranging or defending power. They explore how data was created and curated, as well as how new mathematical and computational techniques developed to contend with that data serve to shape people, ideas, society, military operations, and economies. Although technology and mathematics are at its heart, the story of data ultimately concerns an unstable game among states, corporations, and people. How were new technical and scientific capabilities developed; who supported, advanced, or funded these capabilities or transitions; and how did they change who could do what, from what, and to whom? Wiggins and Jones focus on these questions as they trace data's historical arc, and look to the future. By understanding the trajectory of data--where it has been and where it might yet go--Wiggins and Jones argue that we can understand how to bend it to ends that we collectively choose, with intentionality and purpose.\"-- Publisher marketing.
Book
Artificial intelligence in healthcare: past, present and future
Artificial intelligence (AI) aims to mimic human cognitive functions. It is bringing a paradigm shift to healthcare, powered by increasing availability of healthcare data and rapid progress of analytics techniques. We survey the current status of AI applications in healthcare and discuss its future. AI can be applied to various types of healthcare data (structured and unstructured). Popular AI techniques include machine learning methods for structured data, such as the classical support vector machine and neural network, and the modern deep learning, as well as natural language processing for unstructured data. Major disease areas that use AI tools include cancer, neurology and cardiology. We then review in more details the AI applications in stroke, in the three major areas of early detection and diagnosis, treatment, as well as outcome prediction and prognosis evaluation. We conclude with discussion about pioneer AI systems, such as IBM Watson, and hurdles for real-life deployment of AI.
Journal Article
Fragments of peer review: A quantitative analysis of the literature (1969-2015)
This paper examines research on peer review between 1969 and 2015 by looking at records indexed from the Scopus database. Although it is often argued that peer review has been poorly investigated, we found that the number of publications in this field doubled from 2005. A half of this work was indexed as research articles, a third as editorial notes and literature reviews and the rest were book chapters or letters. We identified the most prolific and influential scholars, the most cited publications and the most important journals in the field. Co-authorship network analysis showed that research on peer review is fragmented, with the largest group of co-authors including only 2.1% of the whole community. Co-citation network analysis indicated a fragmented structure also in terms of knowledge. This shows that despite its central role in research, peer review has been examined only through small-scale research projects. Our findings would suggest that there is need to encourage collaboration and knowledge sharing across different research communities.
Journal Article
Exceptionally high levels of lead pollution in the Balkans from the Early Bronze Age to the Industrial Revolution
The Balkans are considered the birthplace of mineral resource exploitation and metalworking in Europe. However, since knowledge of the timing and extent of metallurgy in southeastern Europe is largely constrained by discontinuous archaeological findings, the long-term environmental impact of past mineral resource exploitation is not fully understood. Here, we present a high-resolution and continuous geochemical record from a peat bog in western Serbia, providing a clear indication of the extent and magnitude of environmental pollution in this region, and a context in which to place archaeological findings. We observe initial evidence of anthropogenic lead (Pb) pollution during the earliest part of the Bronze Age [∼3,600 years before Common Era (BCE)], the earliest such evidence documented in European environmental records. A steady, almost linear increase in Pb concentration after 600 BCE, until ∼1,600 CE is observed, documenting the development in both sophistication and extent of southeastern European metallurgical activity throughout Antiquity and the medieval period. This provides an alternative view on the history of mineral exploitation in Europe, with metal-related pollution not ceasing at the fall of the western Roman Empire, as was the case in western Europe. Further comparison with other Pb pollution records indicates the amount of Pb deposited in the Balkans during the medieval period was, if not greater, at least similar to records located close to western European mining regions, suggestive of the key role the Balkans have played in mineral resource exploitation in Europe over the last 5,600 years.
Journal Article
Identifying risk factors for Alzheimer’s disease from multivariate longitudinal clinical data using temporal pattern mining
Background
Patient data contain a wealth of information that could aid in understanding the onset and progression of disease. However, the task of modelling clinical data, which consist of multiple heterogeneous time series of different lengths, measured at different time intervals, is a complex one. A growing body of research has applied temporal pattern mining to this problem to identify common patterns in clinical attributes over time. However, the vast majority of these algorithms use techniques that are not ideally suited to clinical data. We present an efficient and scalable framework designed specifically for temporal pattern mining of real-world clinical data. Our framework combines temporal abstraction, an extended version of the efficient pattern-growth algorithm, TPMiner, the concepts of relative risk and the odds ratio to identify interesting and high-risk patterns and multiprocessing to improve computational efficiency. A complete set of cut-off values for discretisation and interpretation of the data is provided and is applicable to studies on ageing populations in general. We name this framework Clinical Temporal Pattern Mining or C-TPM.
Results
The framework is applied to data from two real-world studies of Alzheimer’s disease (AD). The patterns discovered were predictive of AD in survival analysis models with a Concordance index of up to 0.87 and contain clinically relevant variables. A visualisation module provides a clear picture of the discovered patterns for ease of interpretability.
Conclusions
The framework provides an effective and scalable method of modelling multivariate, longitudinal clinical data and can identify patterns in uncommon diseases and those that progress slowly over time. It is generalisable to clinical data from other medical domains as well as non-clinical data.
Journal Article
Text Mining Oral Histories in Historical Archaeology
Advances in text mining and natural language processing methodologies have the potential to productively inform historical archaeology and oral history research. However, text mining methods are largely developed in the context of contemporary big data and publicly available texts, limiting the applicability of these tools in the context of historical and archaeological interpretation. Given the ability of text analysis to efficiently process and analyze large volumes of data, the potential for such tools to meaningfully inform historical archaeological research is significant, particularly for working with digitized data repositories or lengthy texts. Using oral histories recorded about a half-century ago from the anthracite coal mining region of Pennsylvania, USA, we discuss recent methodological developments in text analysis methodologies. We suggest future pathways to bridge the gap between generalized text mining methods and the particular needs of working with historical and place-based texts.
Journal Article
Risk Identification and Prediction of Coal Workers’ Pneumoconiosis in Kailuan Colliery Group in China: A Historical Cohort Study
Prior to 1970, coal mining technology and prevention measures in China were poor. Mechanized coal mining equipment and advanced protection measures were continuously installed in the mines after 1970. All these improvements may have resulted in a change in the incidence of coal workers' pneumoconiosis (CWP). Therefore, it is important to identify the characteristics of CWP today and trends for the incidence of CWP in the future.
A total of 17,023 coal workers from the Kailuan Colliery Group were studied. A life-table method was used to calculate the cumulative incidence rate of CWP and predict the number of new CWP patients in the future. The probability of developing CWP was estimated by a multilayer perceptron artificial neural network for each coal worker without CWP. The results showed that the cumulative incidence rates of CWP for tunneling, mining, combining, and helping workers were 31.8%, 27.5%, 24.2%, and 2.6%, respectively, during the same observation period of 40 years. It was estimated that there would be 844 new CWP cases among 16,185 coal workers without CWP within their life expectancy. There would be 273.1, 273.1, 227.6, and 69.9 new CWP patients in the next <10, 10-, 20-, and 30- years respectively in the study cohort within their life expectancy. It was identified that coal workers whose risk probabilities were over 0.2 were at high risk for CWP, and whose risk probabilities were under 0.1 were at low risk.
The present and future incidence trends of CWP remain high among coal workers. We suggest that coal workers at high risk of CWP undergo a physical examination for pneumoconiosis every year, and the coal workers at low risk of CWP be examined every 5 years.
Journal Article
An Entity Extraction Pipeline for Medical Text Records Using Large Language Models: Analytical Study
The study of disease progression relies on clinical data, including text data, and extracting valuable features from text data has been a research hot spot. With the rise of large language models (LLMs), semantic-based extraction pipelines are gaining acceptance in clinical research. However, the security and feature hallucination issues of LLMs require further attention.
This study aimed to introduce a novel modular LLM pipeline, which could semantically extract features from textual patient admission records.
The pipeline was designed to process a systematic succession of concept extraction, aggregation, question generation, corpus extraction, and question-and-answer scale extraction, which was tested via 2 low-parameter LLMs: Qwen-14B-Chat (QWEN) and Baichuan2-13B-Chat (BAICHUAN). A data set of 25,709 pregnancy cases from the People's Hospital of Guangxi Zhuang Autonomous Region, China, was used for evaluation with the help of a local expert's annotation. The pipeline was evaluated with the metrics of accuracy and precision, null ratio, and time consumption. Additionally, we evaluated its performance via a quantified version of Qwen-14B-Chat on a consumer-grade GPU.
The pipeline demonstrates a high level of precision in feature extraction, as evidenced by the accuracy and precision results of Qwen-14B-Chat (95.52% and 92.93%, respectively) and Baichuan2-13B-Chat (95.86% and 90.08%, respectively). Furthermore, the pipeline exhibited low null ratios and variable time consumption. The INT4-quantified version of QWEN delivered an enhanced performance with 97.28% accuracy and a 0% null ratio.
The pipeline exhibited consistent performance across different LLMs and efficiently extracted clinical features from textual data. It also showed reliable performance on consumer-grade hardware. This approach offers a viable and effective solution for mining clinical research data from textual records.
Journal Article