Abstract

ABSTRACT The purpose of this expert system is to assess a predisposition to bleeding in a patient undergoing a tonsillectomy and/or adenoidectomy as may occur with patients who have certain blood conditions such as hemophilia and von Willebrand's disease. This goal is achieved by establishing a correlation between the patients' responses to a medical questionnaire and the relative quantities of blood lost during the operation.There are three major components to the system. First, there is the automated questionnaire to be completed by the patient (or the patient's guardian). It is divided into fourteen sections which involves patient queries on topics such as the frequency of nosebleeds and the occurrence of bruises and positive familial histories. Secondly, there is the expert system proper which takes the responses to the questionnaire and determines risk categories for patients undergoing the operations. The expert system also uses any coagulation lab data that may have been recorded for the patients (this data is sometimes present when a patient definitely has [or is suspected to have] some blood disorder and is subsequently referred to the hematology section). Finally, there is a patient database which contains the patients' questionnaire responses, personal data, medical data (if any were recorded), and the final and intermediate risk assessments generated by the expert system. Standard statistical analysis techniques are applied to the patient records in the database to determine the sensitivity and specificity of the expert system's risk assessments as compared against the patient's blood loss during the operation and, if warranted, an off-line update of the system's knowledge base may then be performed.This paper discusses the knowledge architecture of the hematology system, identifies some problems encountered during the knowledge engineering process and presents some statistical data pertaining to the accuracy of it's risk assessments.1. INTRODUCTIONThe development of the Hematology Expert System for Tonsillectomy/Adenoidectomy Patients (HES) is a project being undertaken by the Robotics and Automation Section of the National Research Council of Canada, the Pediatrics and Child Health Department of the Health Sciences Centre and Knowledge Systems International. HES determines any propensities that a patient may have towards suffering greater than normal blood losses during a tonsillectomy and/or adenoidectomy (T/A) as well as any predispositions towards certain blood abnormalities such as hemophilia and von Willebrand's disease. The intention is to use this system as a preoperative filter to identify these high risk patients so that they may have subsequent coagulation tests performed. In this clinical regard, HES could serve as an effective cost containment tool. As a research instrument, HES could be used as a central hub of a longer-term investigation into the efficacy of preoperatively administered coagulants upon patients with hemostatic (bleeding) defects who are to undergo surgery.2. HISTORYThe complexity of many modern surgical techniques, although desirable for most patients, can be associated with severe complications in those patients with certain types of hemostatic defects. Hemophilia, involving a deficiency of the blood component FVniC (antihemophilic factor), and von Willebrand's disease, which consists of a deficiency of vWRC and vWAg (restocetin and antigen cofactors), are bleeding disorders which can place a patient in serious risk when undergoing an operation especially if that operation involves an extremely vascular area such as the tonsils or adenoids. When such defects as above are suspected by the specialist, he/she has a huge array of accurate but costly coagulation tests which may be performed

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.