Producing computer-generated tailored written information for stroke patients and their carers: System development and preliminary evaluation

Purpose: The aim of this project was to design and evaluate a system that would produce tailored information for stroke patients and their carers, customised according to their informational needs, and facilitate communication between the patient and, health professional. Method: A human factors development approach was used to develop a computer system, which dynamically compiles stroke education booklets for patients and carers. Patients and carers are able to select the topics about which they wish to receive information, the amount of information they want, and the font size of the printed booklet. The system is designed so that the health professional interacts with it, thereby providing opportunities for communication between the health professional and patient/carer at a number of points in time. Results: Preliminary evaluation of the system by health professionals, patients and carers was positive. A randomised controlled trial that examines the effect of the system on patient and carer outcomes is underway. (C) 2004 Elsevier Ireland Ltd. All rights reserved.

Analysis of stroke patients' and carers' reading ability and the content and design of written materials: Recommendations for improving written stroke information

Objective: This study (a) evaluated the reading ability of patients following stroke and their carers and the reading level and content and design characteristics of the written information provided to them, (b) explored the influence of sociodemographic and clinical characteristics on patients' reading ability, and (c) described an education package that provides well-designed information tailored to patients' and carers' informational needs. Methods: Fifty-seven patients and 12 carers were interviewed about their informational needs in an acute stroke unit. Their reading ability was assessed using the Rapid Estimate of Adult Literacy in Medicine (REALM). The written information provided to them in the acute stroke unit was analysed using the SMOG readability formula and the Suitability Assessment of Materials (SAM). Results: Thirteen (22.8%) patients and 5 (41.7%) carers had received written stroke information. The mean reading level of materials analysed was 11th grade while patients read at a mean of 7-8th grade. Most materials (89%) scored as only adequate in content and design. Patients with combined aphasia read significantly lower (4-6th grade) than other patients (p = 0.001). Conclusion: Only a small proportion of patients and carers received written materials about stroke and the readability level and content and design characteristics of most materials required improvement. Practice implications: When developing and distributing written materials about stroke, health professionals should consider the reading ability and informational needs of the recipients, and the reading level and content and design characteristics of the written materials. A computer system can be used to generate written materials tailored to the informational needs and literacy skills of patients and carers. (c) 2005 Elsevier Ireland Ltd. All rights reserved.

Fitness assessment of document model

Document classification is a supervised machine learning process, where predefined category labels are assigned to documents based on the hypothesis derived from training set of labelled documents. Documents cannot be directly interpreted by a computer system unless they have been modelled as a collection of computable features. Rogati and Yang [M. Rogati and Y. Yang, Resource selection for domain-specific cross-lingual IR, in SIGIR 2004: Proceedings of the 27th annual international conference on Research and Development in Information Retrieval, ACM Press, Sheffied: United Kingdom, pp. 154-161.] pointed out that the effectiveness of document classification system may vary in different domains. This implies that the quality of document model contributes to the effectiveness of document classification. Conventionally, model evaluation is accomplished by comparing the effectiveness scores of classifiers on model candidates. However, this kind of evaluation methods may encounter either under-fitting or over-fitting problems, because the effectiveness scores are restricted by the learning capacities of classifiers. We propose a model fitness evaluation method to determine whether a model is sufficient to distinguish positive and negative instances while still competent to provide satisfactory effectiveness with a small feature subset. Our experiments demonstrated how the fitness of models are assessed. The results of our work contribute to the researches of feature selection, dimensionality reduction and document classification.