RESUMO
OBJECTIVE: According to the American Diabetes Association, the implementation of the standards of care for diabetes has been suboptimal in most clinical settings. Diabetes is a disease that had a total estimated cost of $174 billion in 2007 for an estimated diabetes-affected population of 17.5 million in the United States. With the advent of electronic medical records (EMR), tools to analyze data residing in the EMR for healthcare surveillance can help reduce the burdens experienced today. This study was primarily designed to evaluate the efficacy of employing clinical natural language processing to analyze discharge summaries for evidence indicating a presence of diabetes, as well as to assess diabetes protocol compliance and high risk factors. METHODS: Three sets of algorithms were developed to analyze discharge summaries for: (1) identification of diabetes, (2) protocol compliance, and (3) identification of high risk factors. The algorithms utilize a common natural language processing framework that extracts relevant discourse evidence from the medical text. Evidence utilized in one or more of the algorithms include assertion of the disease and associated findings in medical text, as well as numerical clinical measurements and prescribed medications. RESULTS: The diabetes classifier was successful at classifying reports for the presence and absence of diabetes. Evaluated against 444 discharge summaries, the classifier's performance included macro and micro F-scores of 0.9698 and 0.9865, respectively. Furthermore, the protocol compliance and high risk factor classifiers showed promising results, with most F-measures exceeding 0.9. CONCLUSIONS: The presented approach accurately identified diabetes in medical discharge summaries and showed promise with regards to assessment of protocol compliance and high risk factors. Utilizing free-text analytic techniques on medical text can complement clinical-public health decision support by identifying cases and high risk factors.
Assuntos
Algoritmos , Mineração de Dados , Diabetes Mellitus/diagnóstico , Diagnóstico por Computador , Fidelidade a Diretrizes , Sistemas Computadorizados de Registros Médicos , Feminino , Humanos , Masculino , Fatores de RiscoRESUMO
Episode creation is the task of classifying medical events and related clinical data to high-level concepts, such as diseases. Challenges in episode creation result in part because of data, in the patient record, only implicitly being associated with their respective episodes. Furthermore, traditional approaches have been limited to using feature-poor claims records to generate episodes. The accurate correlation of data to their episodes is valuable in health outcomes research to discern resource utilization with respect to medical conditions. This paper describes a combinatorial optimization approach for constructing episodes, which supports the incorporation of heterogeneous data types. Aspects of this approach include an episode model for characterizing the generation of data elements as a result of a process, a methodology for identifying the relationships between implicit processes and the data elements generated by the processes, a measure for evaluating candidate episode configurations, and an energy-minimization methodology for addressing episode creation. An implementation of this work, called Episode Creation Version 2 (EC2), has been applied on patient records with various episode types, which present with knee pain. EC2 demonstrated data element classification precision and recall scores of 78% and 82%, respectively. Significant improvements in precision and recall were observed over a traditional healthcare services approach.
Assuntos
Algoritmos , Sistemas de Gerenciamento de Base de Dados , Cuidado Periódico , Armazenamento e Recuperação da Informação/métodos , Sistemas Computadorizados de Registros Médicos/organização & administração , Processamento de Linguagem Natural , Avaliação de Resultados em Cuidados de Saúde/métodos , Avaliação de Resultados em Cuidados de Saúde/organização & administração , Estados UnidosRESUMO
In the clinical environment, it is often necessary to track the progression of a condition or various pertinent findings over time. Establishing automatic mechanisms for tracking pertinent findings can aid in the management of a condition as well as provide feedback for treatment outcomes assessment. This work focuses on the challenge of correlating observation of pertinent findings, specifically lung masses, across documents from serial computed tomography examinations for lung cancer patients. A probabilistic model is presented to characterize the likeliness of two observed findings from different documents referring to the same entity. A greedy algorithm is also presented that utilizes the probabilistic model to establish coreference links between findings. Results from a preliminary evaluation of this methodology show a precision of 72% and a recall of 63% for the described inter-document coreference resolution task.
Assuntos
Algoritmos , Pulmão/diagnóstico por imagem , Modelos Estatísticos , Sistemas de Informação em Radiologia , Humanos , Processamento de Linguagem Natural , Tomografia Computadorizada por Raios XRESUMO
Episode creation, the task of classifying medical events and related clinical data to a high-level concept, such as a disease, illness or care, has been primarily an interest of healthcare payers for purposes of cost outcomes analysis. Traditional challenges in episode creation have included: inconsistencies in defining episodes; lack of sufficient information to infer episodes; and differences in methods for diagnosing and resolving episodes. However, with the advent of the electronic medical record, which contains multiple sources of patient-related information, data is now accessible to construct more accurate and refined episodes. This work presents a context-sensitive episode creation methodology that utilizes features extracted from different medical repositories (e.g., claims records, structured medical reports) to associate the data with their respective motivating episodes. The combinatorial approach used to find the optimal clustering of patient-related data into episode groups and the measure used to evaluate candidate episode sets are described.