Decision-support systems hold a specialized body of knowledge in computerized form such that the non- specialist can obtain expert-level information. The goal of these systems in clinical sciences is usually to assist patient care by providing the clinician with improved diagnosis or treatment planning.
Decision-support systems consist of three components: the user interface through which the clinician or patient enters signs or symptoms, the set of data describing clinical knowledge in the domain of the program, and an inference engine to manipulate the data set in light of a patient’s specific signs or symptoms to arrive at a diagnosis or treatment plan. Such systems usually use one of three mechanisms of analysis alone or in combination: classification trees, Bayesian conditional probabilities, or rule-based (heuristic) systems. Numerous problems must be solved before decision-support systems will become commonplace in clinical practice.Data entry of patients’ signs and symptoms is often tedious.
The quality of the clinician’s initial observations is of great importance in determining the quality of the output. It is also often difficult to convey to a program the subtlety of clinical information observed. Knowledge required in clinical data bases is often unavailable or imprecise. As these and other challenges are addressed we can anticipate increased utility of decision support program in the future. | | Clinical Decision Support Systems: Perspectives in Dentistry Journal of Dental Education E. A. Mendonca.Clinical Decision Support Systems: Perspectives in Dentistry Clinical decision-support systems (CDSSs) are computer programs that are designed to provide expert support for health professionals making clinical decisions.
1These systems use embedded clinical knowledge to help health professionals analyze patient data and make decisions regarding diagnosis, prevention, and treatmentof health problems. Examples of such systems can be found in several disciplines in health care: dentistry, medicine, and pharmacy, among others. The following scenario is an example in which an electronic dental record and a CDSS exist.Consider a situation where a patient requires dental care. A patient calls the office assistant to schedule an appointment with the dentist for a follow-up on a treatment for an ongoing problem.
The patient complains of tooth pain. The assistant registers the patient for an appointment that same day. When the patient arrives for the appointment, he is asked to provide information on his health status as well as treatment preferences by answering a computer-based questionnaire that enters data directly into the electronic oral health record.Automated alerts generated by the system remind the dentist of health problems that may impact the patient’s oral health; for example, the patient smokes and has a previous diagnosis of subacute bacterial endocarditis (SBE), indicating that attention should be given to cancer screening and this patient may need prophylactic antibiotic. While assessing the patient’s problem, the provider completes the electronic tooth charting information, including recording the caries lesions and periodontal health. Specific caries risk questions are automatically shown to the provider.
The clinical decision-support system then classifies the patient according to the caries risk assessment, which includes sugar intake, inadequate exposure to fluoride, recent restorations for caries, last visit to the dentist, etc. A suggested treatment plan is automatically generated by the CDSS. In addition, information tailored to this specific patient is provided in a separate document, such as educational materials on the increased risk of oral cancer in a person who smokes. A Qualitative Investigation of the Content of DentalPaper-based and Computer-based Patient Record Formats.Titus Schleyer, Heiko Spallek, Pedro Hernandez JAMIA 2007;14:515-526 doi:10. 1197/jamia. M2335 Abstract Objective Approximately 25% of all general dentists practicing in the United States use a computer in the dental operatory. Only 1.
8% maintain completely electronic records. Anecdotal evidence suggests that dental computer-based patient records (CPR) do not represent clinical information with the same degree of completeness and fidelity as paper records. The objective of this study was to develop a basic content model for clinical information in paper-based records and examine its degree of coverage by CPRs.Design We compiled a baseline dental record (BDR) from a purposive sample of 10 paper record formats (two from dental schools and four each from dental practices and commercial sources). We extracted all clinical data fields, removed duplicates, and organized the resulting collection in categories/subcategories.
We then mapped the fields in four market-leading dental CPRs to the BDR. Measurements We calculated frequency counts of BDR categories and data fields for all paper-based and computer-based record formats, and cross-mapped information coverage at both the category and the data field level.Results The BDR had 20 categories and 363 data fields. On average, paper records and CPRs contained 14 categories, and 210 and 174 fields, respectively. Only 72, or 20%, of the BDR fields occurred in five or more paper records.
Categories related to diagnosis were missing from most paper-based and computer-based record formats. The CPRs rarely used the category names and groupings of data fields common in paper formats. Conclusion Existing paper records exhibit limited agreement on what information dentalrecords should contain. The CPRs only cover this information partially, and may thus impede the adoption of electronic patient records.