DIABNET - A QUALITATIVE MODEL-BASED ADVISORY SYSTEM FOR THERAPY PLANNING IN GESTATIONAL DIABETES

An intelligent decision support system for the analysis of home monito ring data and therapy planning in gestational diabetes is presented. T he paper describes the integration of qualitative and quantitative rea soning modules within the DIABNET advisory system. The system kernel i s a qualitative model of the physiological processes involved in the g lucose metabolism of this type of diabetic patient. A causal probabili stic network (CPN) has been used to represent the qualitative model in order to manage uncertain and missing monitoring data. The DIABNET in puts are the patient's available ambulatory monitoring data, and the o utput is a dietary and insulin therapy adjustment that includes initia tion of insulin therapy, quantitative insulin dose changes and qualita tive diet and schedule modifications. Over periods of up to seven days , monitoring data are analysed by the CPN to detect any diet or insuli n therapy items which may require modification. The qualitative insuli n needs are translated into a quantitative proposal in line with the c haracteristics of the patient and the modification strategies usually used by doctors. The first evaluation of the system has been accomplis hed, the encouraging results of which are also presented.