Predicting the learning and consultation time in a computerized primary healthcare clinic.

Managers would like to know how long it takes healthcare service providers to achieve the same throughput of patients per day that they were used to with a pen-and-paper system. This study has been undertaken to derive a model for predicting the time it takes a service provider from a previously disadvantaged community to enter a patient's record in terms of his or her experience and the number of data units that have to be captured. A model was also derived to predict the average consultation time in terms of the number of data units that are captured by an experienced service provider. It can be inferred that healthcare service providers should be allowed at least 6 months of computerized system experience before any decisions about the success of the technology introduction can be made.

System requirements for a computerised patient record information system at a busy primary health care clinic.

A prototyping approach was used to determine the essential system requirements of a computerised patient record information system for a typical township primary health care clinic. A pilot clinic was identified and the existing manual system and business processes in this clinic was studied intensively before the first prototype was implemented. Interviews with users, incidental observations and analysis of actual data entered were used as primary techniques to refine the prototype system iteratively until a system with an acceptable data set and adequate functionalities were in place. Several non-functional and user-related requirements were also discovered during the prototyping period.

The use of knowledge-based systems in medicine in developing countries: a luxury or a necessity?

Knowledge-based systems (KBSs) in medicine have received much attention over the past two decades, mainly because of the potential benefits that can be gained from using them. They may facilitate in increasing productivity in a medical environment, support the making of diagnoses and other types of medical decisions, assist in the training of medical professionals, and can even handle some routine tasks in a medical environment. However, some critical problems in this field have also been identified. For example, research indicated that some problems can be solved partially, but not completely, with existing artificial intelligence techniques. Another problem is that many of the existing medical information systems do not support the integration of KBSs in a natural way. Furthermore, the routine use of a medical KBS is complicated by legal issues. These and other problems contribute to what we experience today: a large proportion of the medical KB applications that are developed is never actually used in practice. This justifies questions such as: Should developing countries, having limited infrastructure and research resources, invest in medical KBSs research and development, or should this field be regarded as a luxury that only belongs to developed countries?, and: Can developing countries really benefit from the use of these systems? These questions are discussed in this paper. We highlight the main problems surrounding the development and use of medical KBSs. With the focus on developing countries we discuss potential benefits that could be obtained by investing in these systems and we offer guidelines for focusing research and development of medical KBSs.