Paola Baiardi

A computerised guideline for pressure ulcer prevention

Abstract This paper illustrates the implementation of a computerised guideline for pressure ulcer prevention. In particular, it describes the aspects related to the site-specification of a guideline delivered by the Agency for Health Care Policy Research (AHCPR), to its integration with the electronic patient record, and to its implementation within the clinical routine. The primary goal of the system is both to facilitate nurses assessing the risk of ulcer development, and to manage patients at risk by producing daily prevention work-plans. Concerning this functionality, particular attention has been paid to manage nurses non-compliance with the guideline suggestions and to collect data for evaluating the guideline impact. Moreover, since it is well known that nurses are often over-loaded, the human computer interaction has been studied in such a way to optimise the time spent for data input. An additional functionality of the system is the novice nurses’ education — they can browse a graphical representation of the guideline, asking details about the different tasks, and they can simulate patients to obtain real-time advice. The educational tool is written in Java and it is based on a representation of the guideline as a relational database. A preliminary evaluation of the system has been performed and the results are presented on the management of about 40 patients.

Spreading the clinical information system: which users are satisfied?

The present study deals with the assessment of the perceived usefulness and perceived ease of use of the clinical core of the HIS we are building, and progressively spreading into the medical centre, through the use of two questionnaires. The differences in subjective perception among clinical units and professional roles have been analyzed. Results show that the system, in use on a mandatory basis, has been accepted. Most of the users are satisfied, and probable removable causes of dissatisfaction have been identified.

Use of statistical classifiers as support tools for the diagnosis of iron-deficiency anemia in patients on chronic hemodialysis

Discriminant analysis, logistic regression and neural network models were applied to the diagnosis of iron-deficiency anemia in hemodialyzed patients. The ability of the three quantitative approaches to distinguish between subjects suffering or not from iron-deficiency anemia was compared by re-substitution and cross-validation testing. Methods performance was evaluated by means of sensitivity, specificity and accuracy. All the methods performed globally well (sensitivity and specificity > 0.85), revealing that the problem is classifiable. Neural networks showed the highest accuracy, both in the re-substitution (models developed and tested on the complete data set) and 3-way cross-validation (data set randomly splitted into 3 developmental and validation data sets) testing. These preliminary results suggest that the correct classification of iron status in the hemodialytic population can be treated as a pattern classification problem, for which neural networks and traditional statistical modelling can be a valuable aid to the clinical diagnosis of iron-deficiency anemia. A better performance of the neural network model must be confirmed through prospective testing on a larger data set.

Diagnosis of Iron-Deficiency Anemia in Hemodialyzed Patients through Support Vector Machines Technique

Support Vector Machines (SVMs) technique is a recent method for empirical data modelling applied to pattern recognition problems. The aim of the present study is to test SVMs performance when applied to a specific medical classification problem - diagnosis of iron-deficiency anemia in uremic patients - and to compare the results with those obtained by traditional techniques such as logistic regression and discriminant analysis. Models have been compared both in learning and validation phases. All methods performed well (accuracy > 80%). Sensibility of SVMs is always higher than the ones of the other models; specificity and accuracy are lower in one repetition over three. Within the limits of the present study, we can say that the SVMs can constitute an innovative method to approach clinical classification problem on which to further invest.

A computerised guideline for pressure ulcer prevention.

This work illustrates the implementation of a computerised guideline for the pressure ulcers prevention. In particular, we describe the site-specification of a guideline delivered by the Agency for Health Care Policy Research, its integration with the electronic patient record, and its introduction within the clinical routine. The system facilitates trained nurses in the patient management by producing daily workplans, and novice nurses by running as an educational tool.

Lesson learnt from a halt of the hospital information system.

The present paper deals with an experience of blackout of the hospital information system at our Medical Centre, trying to evaluate the impact on internal users (physicians, nurses, clerks) and patients population. Limited inconveniences have occurred to out-patients in terms of delay in collecting medical reports after diagnostic test execution. As regards direct users, impact was evaluated through a structured interview. Administrative personnel, that have been using computer-based system for at least ten years, have not declared particular inconveniences, accepting the overtime or the extra-work as simply unavoidable. On the contrary, health-care personnel reported a heavy negative impact of the system failure on their activity. After a great effort to achieve the system acceptance and direct physicians usage, the blackout of the system has pointed out that the situation has changed since a few years ago: now the HIS, and particularly its clinical core, is considered mission critical.