Sherrilynne S. Fuller

Knowledge Management, Data Mining, and Text Mining in Medical Informatics

In this chapter we provide a broad overview of selected knowledge management, data mining, and text mining techniques and their use in various emerging biomedical applications. It aims to set the context for subsequent chapters. We first introduce five major paradigms for machine learning and data analysis including: probabilistic and statistical models, symbolic learning and rule induction, neural networks, evolution-based algorithms, and analytic learning and fuzzy logic. We also discuss their relevance and potential for biomedical research. Example applications of relevant knowledge management, data mining, and text mining research are then reviewed in order including: ontologies; knowledge management for health care, biomedical literature, heterogeneous databases, information visualization, and multimedia databases; and data and text mining for health care, literature, and biological data. We conclude the paper with discussions of privacy and confidentiality issues of relevance to biomedical data mining.

A knowledgebase system to enhance scientific discovery: Telemakus

BackgroundWith the rapid expansion of scientific research, the ability to effectively find or integrate new domain knowledge in the sciences is proving increasingly difficult. Efforts to improve and speed up scientific discovery are being explored on a number of fronts. However, much of this work is based on traditional search and retrieval approaches and the bibliographic citation presentation format remains unchanged.MethodsCase study.ResultsThe Telemakus KnowledgeBase System provides flexible new tools for creating knowledgebases to facilitate retrieval and review of scientific research reports. In formalizing the representation of the research methods and results of scientific reports, Telemakus offers a potential strategy to enhance the scientific discovery process. While other research has demonstrated that aggregating and analyzing research findings across domains augments knowledge discovery, the Telemakus system is unique in combining document surrogates with interactive concept maps of linked relationships across groups of research reports.ConclusionBased on how scientists conduct research and read the literature, the Telemakus KnowledgeBase System brings together three innovations in analyzing, displaying and summarizing research reports across a domain: (1) research report schema, a document surrogate of extracted research methods and findings presented in a consistent and structured schema format which mimics the research process itself and provides a high-level surrogate to facilitate searching and rapid review of retrieved documents; (2) research findings, used to index the documents, allowing searchers to request, for example, research studies which have studied the relationship between neoplasms and vitamin E; and (3) visual exploration interface of linked relationships for interactive querying of research findings across the knowledgebase and graphical displays of what is known as well as, through gaps in the map, what is yet to be tested. The rationale and system architecture are described and plans for the future are discussed.

Ten years of international collaboration in biomedical informatics and beyond: the AMAUTA program in Peru

Well-trained people are urgently needed to tackle global health challenges through information and communication technologies. In this report, AMAUTA, a joint international collaborative training program between the Universidad Peruana Cayetano Heredia and the University of Washington, which has been training Peruvian health professionals in biomedical and health informatics since 1999, is described. Four short-term courses have been organized in Lima, offering training to more than 200 graduate-level students. Long-term training to masters or doctorate level has been undertaken by eight students at the University of Washington. A combination of short-term and long-term strategies was found to be effective for enhancing institutional research and training enterprise. The AMAUTA program promoted the development and institution of informatics research and training capacity in Peru, and has resulted in a group of trained people playing important roles at universities, non-government offices, and the Ministry of Health in Peru. At present, the hub is being extended into Latin American countries, promoting South-to-South collaborations.

Patient-Held Maternal and/or Child Health Records: Meeting the Information Needs of Patients and Healthcare Providers?

Though improvements in infant and maternal mortality rates have occurred over time, women and children still die every hour from preventable causes. Various regional, social and economic factors are involved in the ability of women and children to receive adequate care and prevention services. Patient-held maternal and/or child health records have been used for a number of years in many countries to help track health risks, vaccinations and other preventative health measures performed. Though these records are primarily designed to record patient histories and healthcare information and guide healthcare workers providing care, because the records are patient-held, they also allow families a greater ability to track their own health and prevention strategies. A literature search was performed to answer these questions: (1) What are maternal information needs regarding pregnancy, post-natal and infant healthcare, especially in developing countries? (2) What is known about maternal information seeking behavior in developing countries? (3) What is the history and current state of maternal and/or child patient-held healthcare records, do they provide for the information needs of the healthcare provider and what are the effects and outcomes of patient-held records in general and for maternal and/or child health in particular? Specific information needs of pregnant women and mothers are rarely studied. The small numbers of maternal information behavior results available indicate that mothers, in general, prefer to receive health information directly from their healthcare provider as opposed to from other sources (written, etc.) Overall, in developing countries, patient-held maternal and/or child healthcare records have a mostly positive effect for both patient and care provider. Mothers and children with records tend to have better outcomes in healthcare and preventative measures. Further research into the information behaviors of pregnant women and mothers to determine the extent of reliance on interpersonal information seeking is recommended before expending significant resources on enhanced patient-held maternal and/or child healthcare records including storage on mobile devices. In particular, research is needed to explore the utility of providing targeted health messages to mothers regarding their own health and that of their children; this might best be accomplished through mobile technologies.

Informatics and Medical Libraries: Changing Needs and Changing Roles.

Medical librarians play a crucial role in the evolution of institutional information policy. As information professionals, they share many similarities with their medical informatics counterparts. Both groups emphasize information delivery to the point of decision making; both groups serve as curators of institutional knowledge bases. If the term “publication” encompasses the delivery of clinical information relevant to individuals or populations, both librarians and medical informaticians have an immediate interest in the nature of biomedical publishing, particularly in areas of intellectual ownership, confidentiality, distribution, and access. Both groups also have been early leaders in applying information technology to solve pressing knowledge-management problems, and both groups have a strong commitment to educating colleagues in the effective use of information. Although the challenges faced by librarians and medical informaticians are sometimes different, the evolution of information technology and new forms of biomedical communication suggest that there is now a greater convergence between the two disciplines.

The organization of the digital library.

As digital information proliferates and the difficulties of managing it threaten to overwhelm traditional publication and information delivery processes, new visions of a digital library are forming. Exactly what a digital library is and how it is to be organized have not yet been determined, and bibliographic organization of digital information has not been sufficiently addressed. Bibliography is the systematic description or classification of writings or publications considered as material objects. In todays digital world, such material objects may no longer be relevant, but the need for systematic description remains. The important issue is not whether digital bibliography is needed but, instead, whether or not existing bibliographic techniques are appropriate for this new media. A second issue is the location of the responsibility for a new digital bibliography. Does it rest with medical informaticians, often the producers of this new digital information, or with librarians, traditionally the classifiers of information? Developments in both medical informatics and medical librarianship indicate a need for greater collaboration between these specialties in order to achieve their common purpose–the creation, classification, and dissemination of scholarly information.

An Information Extraction and Representation System for Rapid Review of the Biomedical Literature

With the rapid expansion of scientific research, the ability to effectively find or integrate new domain knowledge in the sciences is proving increasingly difficult. The development of methods and tools for assisting researchers to effectively ex-tract problem-oriented knowledge from heterogeneous and massive information sources, and for using this knowledge in problem-solving is one of the most fundamental research directions for the information and computer sciences today. There is a need for new tools to support more precise identification of relevant research articles and provide visual clues regarding relationships among the document sets. We present the Telemakus system in which aggregated citation information and extracted research findings are displayed in a schema-based document surrogate and an interactive mapping tool provides graphical displays of research inter-relationships from documents across a domain. This system is an innovative approach to creating useful and precise document surrogates and may re-conceptualize the way we currently represent, retrieve, and assimilate research findings from the published literature.

Managing Information in the Academic Medical Center: Building an Integrated Information Environment.

The strategic importance of integrated information systems and resources for academic medical centers should not be underestimated. Ten years ago, the National Library of Medicine in collaboration with the Association of Academic Medical Centers initiated the Integrated Advanced Information Management System (IAIMS) program to assist academic medical centers in defining a process for addressing deficiencies in their information environments. The authors give a brief history of the IAIMS program, and they describe both the characteristics of an integrated information environment and the technical and organizational structures necessary to create such an environment. Strategies some institutions have used to implement integrated information systems are also outlined. Finally, the authors discuss the role of librarians in integrated information system design.

Tracking the global express: new tools addressing disease threats across the world.

The term “Global Express” was coined by Ann Marie Kimball to describe the system that connects us across oceans, continents, national boundaries, cultures, languages, groups, ethnicity, and trade systems. Kimball describes the public health challenges presented by infectious diseases in an era of international trade, travel, and migration. She illustrates the challenge as presented by the SARS outbreak, which rapidly spread across continents. As global trade continues to increase in volume, in diversity of products, and in speed of movement, and as infectious disease agents (including mosquitoes) continue to expand their territories as a result of climate change, the need for rapid response information systems has never been greater. Traditional approaches to data collection are slow to pick up threats, and they tend to be retrospective in nature rather than prospective. A century and a half ago, it took a year to circumnavigate the globe; today it takes less than 36 hours. The incubation period of many infectious diseases is often longer than the time it takes to travel from one location to another. In the past, infectious disease outbreaks were detected on ships as they pulled into port, and the ships were quarantined until the danger passed. A century ago, there was extensive research to identify and track cholera epidemics based on trade routes. Although the methods used to collect and map the data were crude by today’s standards, they did not have to deal with the rapid movement of humans, animals, and other trade goods. We need much more accurate and rapid approaches to identify health challenges and prevent their spread. Prediction is at the heart of many public health systems. Despite huge investments in electronic surveillance systems and data warehouses, public health professionals continue to be the most likely “early warning system”—noticing and reporting unusual clusters of symptoms or unexpected disease virulence. The efficacy of surveillance systems is limited by lack of coherent, comprehensive data collection, with limited or no interoperability even at the local or national level, let alone regionally and internationally. Vital data are trapped in “data silos” held by different organizations, different applications, in a variety of formats, on different devices, and within different networks. Further, we lack tools to support multidisciplinary, international collaboration and research in identifying, preventing, and responding to biorisks of all types. Chretien et al provide a summary of the potential of syndromic surveillance systems in developing countries. Brownstein et al discuss a variety of digital resources that yield useful disease-tracking information that complement traditional surveillance resources.

Developing capacity in health informatics in a resource poor setting: lessons from Peru

The public sectors of developing countries require strengthened capacity in health informatics. In Peru, where formal university graduate degrees in biomedical and health informatics were lacking until recently, the AMAUTA Global Informatics Research and Training Program has provided research and training for health professionals in the region since 1999. The Fogarty International Center supports the program as a collaborative partnership between Universidad Peruana Cayetano Heredia in Peru and the University of Washington in the United States of America. The program aims to train core professionals in health informatics and to strengthen the health information resource capabilities and accessibility in Peru. The program has achieved considerable success in the development and institutionalization of informatics research and training programs in Peru. Projects supported by this program are leading to the development of sustainable training opportunities for informatics and eight of ten Peruvian fellows trained at the University of Washington are now developing informatics programs and an information infrastructure in Peru. In 2007, Universidad Peruana Cayetano Heredia started offering the first graduate diploma program in biomedical informatics in Peru.