Search PubMed⌕ Search

Biomedical subjects

H Heathfield

Publications and source records attributed to H Heathfield.

8 recordsLinked to original sources

WAX ActiveLibrary: a tool to manage information overload.

WAX Active-Library (Cambridge Centre for Clinical Informatics) is a knowledge management system that seeks to support doctors' decision making through the provision of electronic books containing a wide range of clinical knowledge and locally based information. WAX has been piloted in several regions in the United Kingdom and formally evaluated in 17 GP surgeries based in Cambridgeshire. The evaluation has provided evidence that WAX Active-Library significantly improves GPs' access to relevant information sources and by increasing appropriate patient management and referrals this might also lead to an improvement in clinical outcomes.

Artificial Intelligence↗

A clerking tool for the patient record system.

1. BACKGROUND. The goal of the PEN&PAD (Elderly Care) project is to develop a patient record system to assist the many different professionals that care for patients in a hospital setting. At the core of the project is the use of structured data which can be reused in a variety of ways--both within the system for further manipulation and display, and externally for auditing and statistical purposes. To accommodate these needs, a compositional method of data entry called Structured Data Entry (SDE) was used in this application. SDE was developed in an earlier project PEN&PAD (GP)(1). Our application utilizes a network representation of the medical semantics that can be queried to obtain what is sensible to "say" about a particular concept. This functionality is contained within a separate application known as the Terminology Server (TeS), which has been developed within the GALEN project (2). The client application (the patient record system) requests information from the TeS which can then be used to produce compositional data entry forms that require the user to choose values for given attributes (e.g., if information pertaining to chest pain were being recorded, the attribute 'location' and a choice of possible values i.e., 'left' 'right' and 'bilateral' might appear on the form). Given the importance of capturing clinical information in a highly structured format, SDE is a valuable tool. However, its long term success depends on a very comprehensive model of the medical terminology corpus. This component is currently being studied by the GALEN team. 2. CURRENT WORK. We are developing a clerking tool to be used to create records for the newly admitted patient. The clinician seeks to identify a patient's problems based on physical examination and information obtained through conversation with the patient. Patients are usually admitted with a presenting complaint and obtaining more information about this complaint is an important part of the clerking process. While the physician may be able to use the clerking data to consider possible diagnoses right away, he/she often needs to review relevant body systems before a diagnosis is made. In traditional paper based clerking systems, notes are highly formalized but still subject to variation between clinicians. A typical clerking records information such as: 1) history of the presenting complaint; 2) previous medical history; 3) review of body systems; 4) medication; 5) social history; and 6) investigations. We have attempted to retain this clerking outline as much as possible, focusing primarily on the presenting complaint and review of body systems sections. To begin the clerking process, the user chooses a presenting complaint (from the list provided) to launch the 'clerking' window. Access buttons for the different clerking sections are positioned above a data entry window. This window contains a form for collecting information on the presenting complaint. The form is divided into sections to allow the user to record the absence or presence of an associated symptoms and other details. Free text comments can be added to the window, and a data display area shows information entered so far. The user can query the body system database by choosing a system from a menu. At this point the presenting complaint window is replaced by one on the body system in question. The user is free to switch back and forth between the presenting complaint and body system screens. On returning to a previously visited window, the user may pick up where he/she left off when exiting the window. Once the clerking is completed, the information is entered as a unit into the patient record with the date and clinicians name attached. Thereafter, the file becomes read-only. We are currently putting a prototype clerking system through field trials with clinicians from of a local hospital. In our demonstration, we hope to elaborate on these trials and their outcomes.

Admitting Department, Hospital↗

A computer-based decision support system for diagnostic histopathology of the breast.

Accurate histological diagnosis of breast lesions is essential for the appropriate management of the patient. However, the technique of histological typing is problematic due to the large number of histological patterns, often of a complex and variable nature, which occur in breast disease. The introduction of the Breast Screening Programme has increased the burden on pathologists, and emphasised the need for training. Problems arise because mammographic screening detects a greater proportion of special histological types, with their attendant difficulties of identification, when compared to clinically palpable lesions. A computer-based decision support tool has been developed to assist pathologists in the histological diagnosis of breast disease. Unlike conventional expert systems, which seek to recreate the problem-solving processes of an expert, this system has been designed to act as an intelligent assistant to the pathologist. The system represents knowledge in the form of 'disease profiles', and utilises a novel inference model based upon the mathematical technique of hypergraphs. Initial trials with this system have demonstrated that a high level of diagnostic accuracy can be achieved.

Breast Diseases↗

PEN&PAD (Geriatrics): a Collaborative Patient Record System for the shared care of the elderly.

The PEN&PAD (Geriatrics) project seeks to develop a Collaborative Patient Record System for the hospital based shared care of the elderly. The goal of the project is to produce a single, integrated information system which is both useful and usable by the different practitioner groups involved in geriatric care. A User Centred Design methodology is proposed which makes users and human issues central to the design and development process. Preliminary results indicate that the specification of a Minimum Basic Data Set as the basis of a shared record system is infeasible and undesirable. An architecture is presented which illustrates how the diversity between the different disciplines may be preserved in a Collaborative Patient Record System.

Geriatrics↗

Object-oriented design and programming in medical decision support.

The concept of object-oriented design and programming has recently received a great deal of attention from the software engineering community. This paper highlights the realisable benefits of using the object-oriented approach in the design and development of clinical decision support systems. These systems seek to build a computational model of some problem domain and therefore tend to be exploratory in nature. Conventional procedural design techniques do not support either the process of model building or rapid prototyping. The central concepts of the object-oriented paradigm are introduced, namely encapsulation, inheritance and polymorphism, and their use illustrated in a case study, taken from the domain of breast histopathology. In particular, the dual roles of inheritance in object-oriented programming are examined, i.e., inheritance as a conceptual modelling tool and inheritance as a code reuse mechanism. It is argued that the use of the former is not entirely intuitive and may be difficult to incorporate into the design process. However, inheritance as a means of optimising code reuse offers substantial technical benefits.

Adult↗

Knowledge-based computer system to aid in the histopathological diagnosis of breast disease.

A knowledge-based computer system, designed to assist pathologists in the histological diagnosis of breast disease, is described. This system represents knowledge in the form of "disease profiles" and uses a novel inference model based on the mathematical technique of hypergraphs. Its design overcomes many of the limitations of existing expert system technologies when applied to breast disease. In particular, the system can quickly focus on a differential problem and thus reduce the amount of data necessary to reach a conclusion. The system was tested on two sets of samples, consisting of 14 retrospective cases and five hypothetical cases of breast disease. Its recommendations were judged "correct" by the evaluating pathologist in 15 cases. This study shows the feasibility of providing "decision support" in histopathology.

Breast↗

A cooperative approach to decision support in the differential diagnosis of breast disease.

The problem of differential diagnosis in breast histopathology is described and areas in need of decision support identified. It is argued that the conventional role played by decision support systems, i.e. that of the 'autonomous problem-solver', is unacceptable in this domain and that support must be given to the actual cognitive functions of potential system users. Decision-making processes of pathologists are examined with particular reference to Rector's category of 'broad experts'. Pathologists possess a rich set of general diagnostic concepts for their domain, but their knowledge of detailed aspects of differential diagnosis may contain gaps and errors. A cooperative model of decision support, which utilizes the strengths and complements the weaknesses of pathologists' problem-solving skills, is described and the operation of this model within a functioning system illustrated.

Artificial Intelligence↗