TY - JOUR
T1 - Combining tabular, rule-based, and procedural knowledge in computer- based guidelines for childhood immunization
AU - Miller, Perry L.
AU - Frawley, Sandra J.
AU - Sayward, Frederick G.
AU - Yasnoff, William A.
AU - Duncan, Lorraine
AU - Fleming, David W.
PY - 1997/6
Y1 - 1997/6
N2 - IMM/Serve is a computer program which implements the clinical guidelines for childhood immunization. IMM/Serve accepts as input a child's immunization history. It then indicates which vaccinations are due and which vaccinations should be scheduled next. The clinical guidelines for immunization are quite complex and are modified quite frequently. As a result, it is important that IMM/Serve's knowledge he represented in a format that facilitates the maintenance of that knowledge as the field evolves over time. To achieve this goal, IMM/Serve uses four representations for different parts of its knowledge base: (1) Immunization forecasting parameters that specify the minimum ages and wait-intervals for each dose are stored in tabular form. (2) The clinical logic that determines which set of forecasting parameters applies for a particular patient in each vaccine series is represented using if-then rules. (3) The temporal logic that combines dates, ages, and intervals to calculate recommended dates, is expressed procedurally. (4) The screening logic that checks each previous dose for validity is performed using a decision table that combines minimum ages and wait intervals with a small amount of clinical logic. A knowledge maintenance tool, IMM/Def, has been developed to help maintain the rule-based logic. The paper describes the design of IMM/Serve and the rationale and role of the different forms of knowledge used.
AB - IMM/Serve is a computer program which implements the clinical guidelines for childhood immunization. IMM/Serve accepts as input a child's immunization history. It then indicates which vaccinations are due and which vaccinations should be scheduled next. The clinical guidelines for immunization are quite complex and are modified quite frequently. As a result, it is important that IMM/Serve's knowledge he represented in a format that facilitates the maintenance of that knowledge as the field evolves over time. To achieve this goal, IMM/Serve uses four representations for different parts of its knowledge base: (1) Immunization forecasting parameters that specify the minimum ages and wait-intervals for each dose are stored in tabular form. (2) The clinical logic that determines which set of forecasting parameters applies for a particular patient in each vaccine series is represented using if-then rules. (3) The temporal logic that combines dates, ages, and intervals to calculate recommended dates, is expressed procedurally. (4) The screening logic that checks each previous dose for validity is performed using a decision table that combines minimum ages and wait intervals with a small amount of clinical logic. A knowledge maintenance tool, IMM/Def, has been developed to help maintain the rule-based logic. The paper describes the design of IMM/Serve and the rationale and role of the different forms of knowledge used.
UR - http://www.scopus.com/inward/record.url?scp=0031172455&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031172455&partnerID=8YFLogxK
U2 - 10.1006/cbmr.1997.1445
DO - 10.1006/cbmr.1997.1445
M3 - Article
C2 - 9281329
AN - SCOPUS:0031172455
SN - 0010-4809
VL - 30
SP - 211
EP - 231
JO - Computers and Biomedical Research
JF - Computers and Biomedical Research
IS - 3
ER -