RESUMO
A care pathway (CP) is a standardized process that consists of multiple care stages, clinical activities and their relations, aimed at ensuring and enhancing the quality of care. However, actual care may deviate from the planned CP, and analysis of these deviations can help clinicians refine the CP and reduce medical errors. In this paper, we propose a CP variance analysis method to automatically identify the deviations between actual patient traces in electronic medical records (EMR) and a multistage CP. As the care stage information is usually unavailable in EMR, we first align every trace with the CP using a hidden Markov model. From the aligned traces, we report three types of deviations for every care stage: additional activities, absent activities and violated constraints, which are identified by using the techniques of temporal logic and binomial tests. The method has been applied to a CP for the management of congestive heart failure and real world EMR, providing meaningful evidence for the further improvement of care quality.
Assuntos
Inteligência Artificial , Procedimentos Clínicos/classificação , Procedimentos Clínicos/normas , Registros Eletrônicos de Saúde/classificação , Registros Eletrônicos de Saúde/normas , Processamento de Linguagem Natural , Garantia da Qualidade dos Cuidados de Saúde/métodos , Análise de Variância , Interpretação Estatística de Dados , Fidelidade a Diretrizes/estatística & dados numéricos , Cadeias de Markov , Reconhecimento Automatizado de Padrão/métodosRESUMO
Although, clinical guidelines are regarded as best practices for clinicians, clinician activities are not always compliant with guideline recommendations. This paper aims to improve clinician compliance with guidelines. We have developed an engine to automatically report three non-compliance situations: 1) guideline recommendations exist, and the clinician performed some activities, but not according to the guidelines; 2) guideline recommendations exist, but the clinician did nothing; 3) guideline recommendations do not exist, but the clinician performed some activities. In particular, we highlight effective time for compliance checking, as well as membership, numeric relationships, concept subsumption and contextualization. We deployed our engine to a clinical setting involving the daily care routine of diabetes patients, and generated non-compliance reports for pilot users.
