Preparing Clinical Text for Use in Biomedical Research

Approximately 57 different types of clinical annotations construct a patient’s medical record. These annotations include radiology reports, discharge summaries, and surgical and nursing notes. Hospitals typically produce millions of text-based medical records over the course of a year. These records are essential for the delivery of care, but many are underutilized or not utilized at all for clinical research. The textual data found in these annotations is a rich source of insights into aspects of clinical care and the clinical delivery system. Recent regulatory actions, however, require that, in many cases, data not obtained through informed consent or data not related to the delivery of care must be made anonymous (as referred to by regulators as harmless), before they can be used. This article describes a practical approach with which Cincinnati Children’s Hospital Medical Center (CCHMC), a large pediatric academic medical center with more than 761,000 annual patient encounters, developed open source software for making pediatric clinical text harmless without losing its rich meaning. Development of the software dealt with many of the issues that often arise in natural language processing, such as data collection, disambiguation, and data scrubbing.

A Prehospital Database System For Emergency Medical Services

Emergency Medical Services (EMS) are not only responsible for providing prompt and efficient medical care to many different types emergencies, but also for fully documenting each and every event. Unfortunately, the vast majority of EMS events are still documented by hand. The documents are then further processed and entered manually into various billing, research, and other databases. Hence, such a process is expensive, labor intensive, and error prone. There is a dire need for more research in this area and for faster, efficient solutions. We present a solution for this problem: Prehospital Patient Care Record (PCR) for emergency medical field usage with a system called iRevive that functions as a mobile database application. iRevive is a mobile database application that is designed to facilitate the collection and management of prehospital data. It allows point-of-care data capture in an electronic format and is equipped with individual patient sensors to automatically capture vital sign data. Patient information from the field is wirelessly transmitted to a back-end server, which uses Web service standards to promote interoperability with disparate hospital information systems, various billing agencies, and a wide variety of research applications. In this chapter, we describe the current state of EMS, the iRevive application, a mini-trial deploying iRevive in real scenarios, the results, and a future direction for our solution.

Web Portal for Genomic and Epidemiologic Medical Data

Medical data and digital imaging for medical diagnosis currently represent a very important research area in computer science. The generation of medical information is continuously increasing. More specifically, genomic (molecular and histological) data and images have become key points for diagnosis. The specific processing these data require is more and more requested. This article describes a Web portal based on the most common current standards. This platform is not only able to integrate the medical information available at several sources, but also to provide tools for the analysis of the integrated data, to use them for the study of any pathology. It will provide a common access point to share data and analysis techniques (or applications) between different groups that are currently working in several fields of health area.

Retrieving Medical Records Using Bayesian Networks

Bayesian networks (Jensen, 2001) are powerful tools for dealing with uncertainty. They have been successfully applied in a wide range of domains where this property is an important feature, as in the case of information retrieval (IR) (Turtle & Croft, 1991). This field (Baeza-Yates & Ribeiro- Neto, 1999) is concerned with the representation, storage, organization, and accessing of information items (the textual representation of any kind of object). Uncertainty is also present in this field, and, consequently, several approaches based on these probabilistic graphical models have been designed in an attempt to represent documents and their contents (expressed by means of indexed terms), and the relationships between them, so as to retrieve as many relevant documents as possible, given a query submitted by a user. Classic IR has evolved from flat documents (i.e., texts that do not have any kind of structure relating their contents) with all the indexing terms directly assigned to the document itself toward structured information retrieval (SIR) (Chiaramella, 2001), where the structure or the hierarchy of contents of a document is taken into account. For instance, a book can be divided into chapters, each chapter into sections, each section into paragraphs, and so on. Terms could be assigned to any of the parts where they occur. New standards, such as SGML or XML, have been developed to represent this type of document. Bayesian network models also have been extended to deal with this new kind of document. In this article, a structured information retrieval application in the domain of a pathological anatomy service is presented. All the medical records that this service stores are represented in XML, and our contribution involves retrieving records that are relevant for a given query that could be formulated by a Boolean expression on some fields, as well as using a text-free query on other different fields. The search engine that answers this second type of query is based on Bayesian networks.

Data Mining Medical Information

Trauma audit is intended to develop effective care for injured patients through process and outcome analysis, and dissemination of results. The system records injury details such as the patient’s sex and age, the mechanism of the injury, various measures of the severity of the injury, initial management and subsequent management interventions, and the outcome of the treatment including whether the patient lived or died. Ten years’ worth of trauma audit data from one hospital are modelled as an Artificial Neural Network (ANN) in order to compare the results with a more traditional logistic regression analysis. The output was set to be the probability that a patient will die. The ANN models and the logistic regression model achieve roughly the same predictive accuracy, although the ANNs are more difficult to interpret than the logistic regression model, and neither logistic regression nor the ANNs are particularly good at predicting death. For these reasons, ANNs are not seen as an appropriate tool to analyse trauma audit data. Results do suggest, however, the usefulness of using both traditional and non-traditional analysis techniques together and of including as many factors in the analysis as possible.

Approximate Processing for Medical Record Linking and Multidatabase Analysis

In this article we investigate how approximate query processing (AQP) can be used in medical multidatabase systems. We identify two areas where this estimation technique will be of use. First, approximate query processing can be used to preprocess medical record linking in the multidatabase. Second, approximate answers can be given for aggregate queries. In the case of multidatabase systems used to link health and health related data sources, preprocessing can be used to find records related to the same patient. This may be the first step in the linking strategy. If the aim is to gather aggregate statistics, then the approximate answers may be enough to provide the required answers. At least they may provide initial answers to encourage further investigation. This estimation may also be used for general query planning and optimization, important in multidatabase systems. In this article we propose two techniques for the estimation. These techniques enable synopses of component local databases to be precalculated and then used for obtaining approximate results for linking records and for aggregate queries. The synopses are constructed with restrictions on the storage space. We report on experiments which show that good approximate results can be obtained in a much shorter time than performing the exact query.

Privacy and Access to Electronic Health Records

The special relationship of trust that needs to exist between a patient and his or her physician has been recognized since the origins of the profession, and the need for doctors to keep confidential any information disclosed to them is codified in the Hippocratic Oath. A distinctive feature of the health records which arises from this relationship is the intimate nature of the information that they may contain; consequently, it is vitally important to maintain the confidentiality of the records and to protect the privacy of the patients. Privacy has long been recognized as a fundamental right in most western societies (Westin, 2003), and unless a patient can be sure that personal information will not be distributed against his or her wishes, the patient may be reluctant to disclose information that may in fact be crucial to his or her correct treatment (Ford, Bearman, & Moody, 1999; NZHIS, 1995), or he or she may refrain from seeking treatment (Sankar, Moran, Merz, & Jones, 2003). This is particularly true when health records contain sensitive information concerning issues like drug and alcohol problems, sexual behavior, mental health, or a genetic predisposition towards certain diseases. In such circumstances, the consequences of the inappropriate release of information could be extensive and might impact on many aspects of a person’s life, such as the ability to gain employment, to maintain a marriage, or to obtain loans or life insurance (Chadwick, 1999; Woodward, 1995).

Security in E-Health Applications

This chapter presents security solutions in integrated patient-centric Web-based health-care information systems, also known as electronic healthcare record (EHCR). Security solutions in several projects have been presented and in particular a solution for EHCR integration from scratch. Implementations of Public key infrastructure, privilege management infrastructure, role based access control and rule based access control in EHCR have been presented. Regarding EHCR integration from scratch architecture and security have been proposed and discussed. This integration is particularly suitable for developing countries with wide spread Internet while at the same time the integration of heterogeneous systems is not needed. The chapter aims at contributing to initiatives for implementation of national and transnational EHCR in security aspect.

Securing Mobile Data Computing in Healthcare

Access to mobile data and messages is essential in healthcare environment as patients and healthcare providers are mobile. This is inline with the need of ubiquitous computing in everyday life. Mobile and wireless devices can assist in ensuring patient’s safety by providing easy availability of the data at the point of care. Portability and accessibility of these devices enhances use of them in healthcare environment. However, data integrity and confidentiality of information in them need to be ensured to provide safe, effective and efficient healthcare. Mobile healthcare involves conducting healthcare related activities through using mobile devices such as a smart phone, Personal digital assistant (PDA), wireless enabled computer, iPod and so on. Mobile computing is suitable for healthcare as healthcare providers are mobile. These would be suitable for conducting patient’s healthcare activities in emergencies, ward rounds, homecare, chronic disease management, conducting clinical trials, and so on. There are various projects using mobile devices to enhance patient’s care. With the advancement of medical informatics, telemedicine and information technology, mobile data devices play an enormous role in healthcare system. In this chapter, we outline the need of mobile devices in healthcare, usage of these devices, underlying technology and applications, importance of security of these devices, securing mobile data communication in healthcare through different security models and case examples of applications that we have developed, in particular (1) iPathology tool on iPod, (2) securing healthcare information using Pocket PC 2003, and (3) securing information on handheld devices. There were several incidents in the past due to the insecurity of mobile devices that can leak information to anyone who does not have access to the information. In this chapter, we will illustrate several techniques that we have developed to protect these malicious activities and how these are applicable for securing mobile data computing in healthcare.

Information Assurance in E-Healthcare

There is growing concern that the healthcare industry has not adopted IT systems as widely and effectively as other industries. Healthcare technological advances generally emerge from the clinical and medical areas rather than clerical and administrative. The healthcare industry is perceived to be 10 to 15 years behind other industries in its use of information technology (Raghupathi & Tan, 1997). Incorporating new technology into the healthcare organization’s processes is risky because of the potential for patient information being disclosed. The purpose of this study is to investigate the information assurance factors involved with security regulations and electronic medical record initiatives—a first necessary step in making the healthcare industry more efficient. Noncompliance of a healthcare organization’s employees with security and privacy policies (i.e., information assurance) can result in legal and financial difficulties, as well as irreparable damage to an organization’s reputation. To implement electronic medical initiatives, it is vital that an organization has compliance with security and privacy policies. E-health technology is a relatively current phenomenon. There are two types of distance-related healthcare that are technology driven. Telehealth is known for involving telemedicine—medicine practiced over a distance, with the impetus of control being in the physician’s hands (Maheu, 2000). E-health involves the patient or physician actively searching for information or a service, usually via the Internet (Maheu). Electronic medical records fall into the e-health category because the physician, healthcare partners, and patient would be able to access the information through an Internet connection.