Modeling patient-specific therapeutic strategy in the guideline-based management of a chronic disease.
Like any chronic disease, hypertension is complex to manage. Despite the availability of evidence-based clinical practice guidelines in most countries, a lot of hypertensive patients remain inadequately managed. One difficulty lies in the synchronization of a patient's own therapeutic history with the guideline strategy. We propose a formal model to represent guideline-based therapeutic strategies as bi-dimensional matrices. We built the knowledge base as a two-level decision tree to be read during an hypertextual navigation. The first level is used to identify a patient-specific clinical situation on the basis of key elements of clinical examination (complication of hypertension, associated diseases). The second level aims at dynamically refining the theoretical strategy, a priori established in the guideline for the corresponding clinical situation, by the specific therapeutic history of the patient. Finally, depending on the patient's response to the ongoing treatment, the system provides a recommendation consistent with the guideline strategy, whatever the patient's past treatments. A first evaluation of the system on simulated cases has been well accepted by general practitioners.