RESUMO
BACKGROUND: Accurate information is needed to direct healthcare systems' efforts to control methicillin-resistant Staphylococcus aureus (MRSA). Assembling complete and correct microbiology data is vital to understanding and addressing the multiple drug-resistant organisms in our hospitals. METHODS: Herein, we describe a system that securely gathers microbiology data from the Department of Veterans Affairs (VA) network of databases. Using natural language processing methods, we applied an information extraction process to extract organisms and susceptibilities from the free-text data. We then validated the extraction against independently derived electronic data and expert annotation. RESULTS: We estimate that the collected microbiology data are 98.5% complete and that methicillin-resistant Staphylococcus aureus was extracted accurately 99.7% of the time. CONCLUSIONS: Applying natural language processing methods to microbiology records appears to be a promising way to extract accurate and useful nosocomial pathogen surveillance data. Both scientific inquiry and the data's reliability will be dependent on the surveillance system's capability to compare from multiple sources and circumvent systematic error. The dataset constructed and methods used for this investigation could contribute to a comprehensive infectious disease surveillance system or other pressing needs.
Assuntos
Algoritmos , Hospitais de Veteranos/estatística & dados numéricos , Armazenamento e Recuperação da Informação/métodos , Sistemas Computadorizados de Registros Médicos/normas , Staphylococcus aureus Resistente à Meticilina , Processamento de Linguagem Natural , Viés , Humanos , Armazenamento e Recuperação da Informação/normas , Internet/estatística & dados numéricos , Staphylococcus aureus Resistente à Meticilina/isolamento & purificação , Técnicas Microbiológicas/normas , Vigilância da População/métodos , Controle de Qualidade , Padrões de Referência , Reprodutibilidade dos Testes , Infecções Estafilocócicas/epidemiologia , Infecções Estafilocócicas/microbiologia , Estados Unidos , United States Department of Veterans AffairsRESUMO
BACKGROUND: There is an increasing body of literature advocating for the collection of patient-reported outcomes (PROs) in clinical care. Unfortunately, there are many barriers to integrating PRO measures, particularly computer adaptive tests (CATs), within electronic health records (EHRs), thereby limiting access to advances in PRO measures in clinical care settings. OBJECTIVE: To address this obstacle, we created and evaluated a software integration of an Application Programming Interface (API) service for administering and scoring Patient-Reported Outcomes Measurement Information System (PROMIS) measures with the EHR system. METHODS: We created a RESTful API and evaluated the technical feasibility and impact on clinical workflow at three academic medical centers. RESULTS: Collaborative teams (i.e., clinical, information technology [IT] and administrative staff) performed these integration efforts addressing issues such as software integration as well as impact on clinical workflow. All centers considered their implementation successful based on the high rate of completed PROMIS assessments (between January 2016 and January 2021) and minimal workflow disruptions. CONCLUSION: These case studies demonstrate not only the feasibility but also the pathway for the integration of PROMIS CATs into the EHR and routine clinical care. All sites utilized diverse teams with support and commitment from institutional leadership, initial implementation in a single clinic, a process for monitoring and optimization, and use of custom software to minimize staff burden and error.
Assuntos
Registros Eletrônicos de Saúde , Medidas de Resultados Relatados pelo Paciente , Hospitais , Software , Fluxo de TrabalhoRESUMO
AIM: Patient-reported outcomes (PROs) have traditionally been implemented through a manual process of paper and pencil with little standardization throughout a Healthcare System. Each practice has asked patients specific questions to understand the patient's health as it pertains to their specialty. These data were rarely shared and there has not been a comparison of patient's health across different specialty domains. We sought to leverage interoperable electronic systems to provide a standardization of PRO assessments across sites of care. METHODS: University of Utah Health is comprised of four hospitals, 12 community clinics, over 400,000 unique annual patients, and more than 5000 providers. The enterprise wide implementation of PROs started in November of 2015. Patients can complete an assessment at home via email, or within the clinic on a tablet. Each specialty has the opportunity to add additional specialty-specific instruments. We customized the interval with which the patient answers the assessments based on specialty preference in order to minimize patient burden, while maximizing relevant data for clinicians. RESULTS: Barriers and facilitators were identified in three phases: Pre-implementation, Implementation, and Post-implementation. Each phase was further broken down into technical challenges, content inclusion and exclusion, and organizational strategy. These phases are unique and require collaboration between several groups throughout the organization with support from executive leadership. DISCUSSION: We are deploying system-wide standard and customized PRO collection with the goals of providing better patient care, improving physician-patient communication, and ultimately improving the value of the care given. Standardized assessment provides any clinician with information to quickly evaluate the overall, physical and mental health of a patient. This information is available real time to aid in patient communication for the clinician.
RESUMO
BACKGROUND: Delirium is a common syndrome in elderly hospitalized patients that is correlated with poor outcomes and higher costs yet health care teams often overlook its diagnosis and treatment. Poor data quality in EHR systems can be contributing to this as a common tool teams use to communicate and record data about their patients. METHODS: Data were gathered from 30 patients chosen randomly that spanned various data domains in the EHR. These were analyzed for concordance as an indicator of data quality. RESULTS: Concordance was high between the physician and nursing narrative documentation. The other domains of data were drastically less concordant. DISCUSSION: The low concordance between structured and narrative data domains suggests that clinicians are forgoing the features available in modern EHR systems and opting to work in narrative. For informatics, this can be troubling as narrative data are difficult to compute.