Medical decision-support systems have three main components: knowledge, rules, and software. Knowledge stored electronically includes published clinical practice guidelines, commercial databases, and custom-designed knowledge bases, based on expert opinion. Knowledge is translated into active rules used within the system. The software applies the knowledge, rules, and local patient and clinical data, and presents the computerized diagnosis functionality on the clinician’s desktop.
These systems vary in complexity. The more complex systems match characteristics of individual patients with a computerized knowledge base and generate patient-specific and situation-specific recommendations. Systems that generate conclusions from patient data typically utilize knowledge-based technologies. There is generally the following four-type classification for medical decision-support systems:
Type One: Provides categorized information that requires further processing and analysis by users before a decision can be made.
Type Two: Presents the clinician with trends of patients’ changing clinical status and alerts clinicians to out of range assessment results and intervention strategies. Clinicians are prompted to review information related to the alerts before arriving at a clinical decision.
Type Three: Uses deductive inference engines to operate on a specific knowledge base and automatically generates diagnostic or intervention recommendations based on changing patient clinical condition, with the knowledge and inference engines stored in the knowledge base.
Type Four: Uses more complex knowledge management and inference models such as case management reasoning, neural networks, or statistical discrimination analysis to perform outcome or prognostic predictions. Such systems possess self-learning capabilities and use Fuzzy Set Theory and similarity measures or confidence level computation as mechanisms to deal intelligently and accurately with uncertainty.
Ideally, the patient information used in medical decision-support systems would come from existing electronic sources such as electronic medical records; therefore, medical decision-support systems are usually embedded in other computer applications such as those used for prescribing and dispensing medicines, electronic medical records, and other information systems used in health settings. However, medical decision-support embedding in medical instruments such as electrocardiographs and lung function recorders, are not popularly known as medical decision-support systems.