Live sequence charts to model medical information (Theoretical Biology and Medical Modelling)

Background: Medical records accumulate data concerning patient health and the natural history of diseaseprogression. However, methods to mine information systematically in a form other than anelectronic health record are not yet available. The purpose of this study was to develop anobject modeling technique as a first step towards a formal database of medical records.MethodLive Sequence Charts (LSC) were used to formalize the narrative text obtained during apatient interview. LSCs utilize a visual scenario-based programming language to build objectmodels. LSC extends the classical language of UML message sequence charts (MSC),predominantly through addition of modalities and providing executable semantics. Interobjectscenarios were defined to specify natural history event interactions and differentscenarios in the narrative text.ResultA simulated medical record was specified into LSC formalism by translating the text into anobject model that comprised a set of entities and events. The entities described theparticipating components (i.e., doctor, patient and record) and the events described theinteractions between elements. A conceptual model is presented to illustrate the approach. Anobject model was generated from data extracted from an actual new patient interview, wherethe individual was eventually diagnosed as suffering from Chronic Fatigue Syndrome (CFS).This yielded a preliminary formal designated vocabulary for CFS development that provideda basis for future formalism of these records. Conclusions: Translation of medical records into object models created the basis for a formal database ofthe patient narrative that temporally depicts the events preceding disease, the diagnosis andtreatment approach. The LSCs object model of the medical narrative provided an intuitive,visual representation of the natural history of the patient`s disease.