RESUMEN
As the core of health information technology (HIT), electronic medical record (EMR) systems have been changing to meet health care demands. To construct a new-generation EMR system framework with the capability of self-learning and real-time feedback, thus adding intelligence to the EMR system itself, this paper proposed a novel EMR system framework by constructing a direct pathway between the EMR workflow and EMR data. A prototype of this framework was implemented based on patient similarity learning. Patient diagnoses, demographic data, vital signs and structured lab test results were considered for similarity calculations. Real hospitalization data from 12,818 patients were substituted, and Precision @ Position measurements were used to validate self-learning performance. Our EMR system changed the way in which orders are placed by establishing recommendation order menu and shortcut applications. Two learning modes (EASY MODE and COMPLEX MODE) were provided, and the precision values @ position 5 of both modes were 0.7458 and 0.8792, respectively. The precision performance of COMPLEX MODE was better than that of EASY MODE (tested using a paired Wilcoxon-Mann-Whitney test, p < 0.001). Applying the proposed framework, the EMR data value was directly demonstrated in the clinical workflow, and intelligence was added to the EMR system, which could improve system usability, reliability and the physician's work efficiency. This self-learning mechanism is based on dynamic learning models and is not limited to a specific disease or clinical scenario, thus decreasing maintenance costs in real world applications and increasing its adaptability.
Asunto(s)
Aprendizaje Automático , Sistemas de Registros Médicos Computarizados/organización & administración , Factores de Edad , China , Toma de Decisiones Asistida por Computador , Técnicas y Procedimientos Diagnósticos , Intercambio de Información en Salud , Humanos , Sistemas de Registros Médicos Computarizados/normas , Factores Sexuales , Factores Socioeconómicos , Signos VitalesRESUMEN
Secondary use of medical big data is increasingly popular in healthcare services and clinical research. Understanding the logic behind medical big data demonstrates tendencies in hospital information technology and shows great significance for hospital information systems that are designing and expanding services. Big data has four characteristics--Volume, Variety, Velocity and Value (the 4 Vs)--that make traditional systems incapable of processing these data using standalones. Apache Hadoop MapReduce is a promising software framework for developing applications that process vast amounts of data in parallel with large clusters of commodity hardware in a reliable, fault-tolerant manner. With the Hadoop framework and MapReduce application program interface (API), we can more easily develop our own MapReduce applications to run on a Hadoop framework that can scale up from a single node to thousands of machines. This paper investigates a practical case of a Hadoop-based medical big data processing system. We developed this system to intelligently process medical big data and uncover some features of hospital information system user behaviors. This paper studies user behaviors regarding various data produced by different hospital information systems for daily work. In this paper, we also built a five-node Hadoop cluster to execute distributed MapReduce algorithms. Our distributed algorithms show promise in facilitating efficient data processing with medical big data in healthcare services and clinical research compared with single nodes. Additionally, with medical big data analytics, we can design our hospital information systems to be much more intelligent and easier to use by making personalized recommendations.
Asunto(s)
Procesamiento Automatizado de Datos/instrumentación , Gestión de la Información en Salud/instrumentación , Sistemas de Información/instrumentación , Diseño de Software , Algoritmos , HumanosRESUMEN
OBJECTIVE: Clinical pathways (CPs) are widely studied methods to standardize clinical intervention and improve medical quality. However, standard care plans defined in current CPs are too general to execute in a practical healthcare environment. The purpose of this study was to create hospital-specific personalized CPs by explicitly expressing and replenishing the general knowledge of CPs by applying semantic analysis and reasoning to historical clinical data. METHODS: A semantic data model was constructed to semantically store clinical data. After querying semantic clinical data, treatment procedures were extracted. Four properties were self-defined for local ontology construction and semantic transformation, and three Jena rules were proposed to achieve error correction and pathway order recognition. Semantic reasoning was utilized to establish the relationship between data orders and pathway orders. RESULTS: A clinical pathway for deviated nasal septum was used as an example to illustrate how to combine standard care plans and practical treatment procedures. A group of 224 patients with 11,473 orders was transformed to a semantic data model, which was stored in RDF format. Long term order processing and error correction made the treatment procedures more consistent with clinical practice. The percentage of each pathway order with different probabilities was calculated to declare the commonality between the standard care plans and practical treatment procedures. Detailed treatment procedures with pathway orders, deduced pathway orders, and orders with probability greater than 80% were provided to efficiently customize the CPs. CONCLUSIONS: This study contributes to the practical application of pathway specifications recommended by the Ministry of Health of China and provides a generic framework for the hospital-specific customization of standard care plans defined by CPs or clinical guidelines.
Asunto(s)
Vías Clínicas , Sistemas de Apoyo a Decisiones Clínicas , Semántica , Sistemas de Información en Hospital , Humanos , Interfaz Usuario-ComputadorRESUMEN
AIM: To develop a novel method for the rapid and efficient extraction of exosomes secreted by tumor cells. METHODS: Unlike the traditional extraction method, the supernatants of cell cultures were concentrated, and the exosomes were isolated promptly and effectively using a novel nanomaterial called ExoQuick. Coomassie brilliant blue staining was used for protein quantification, and the morphology of the exosomes extracted by both methods was visualized by transmission electron microscopy. Exosome marker proteins were detected by Western blot analysis. Two potential hepatoma-associated proteins, tissue transglutaminase 2 (TGM2) and annexin A2, were analyzed. RESULTS: The exosomes separated by the new extraction assay based on the nanomaterial were disc-shaped, intact vesicles with lipid bilayer membranes. They were approximately 30-100 nm in diameter, which is similar to the diameter of exosomes isolated by the traditional method. The protein concentration of exosomes extracted by the new method was approximately 780 µg/10(8) cells, and therefore, it was 19 times higher than that of exosomes extracted in the traditional manner. There were differences between the total proteins of Huh-7 cells and the exosomal proteins. Typical exosome proteins, such as the transmembrane protein CD63 and heat shock protein 70, were confirmed. Two potential hepatoma-associated proteins were also identified. TGM2 was first found to exist in the exosomes of human liver cancer cells, but annexin A2 was not secreted into exosomes. CONCLUSION: The new extraction method based on the nanomaterial is quick and efficient. The cancer-associated protein TGM2 can be secreted through an exosome-mediated non-classical secretion pathway, and it may be a valuable tumor marker.
Asunto(s)
Carcinoma Hepatocelular/metabolismo , Exosomas/metabolismo , Neoplasias Hepáticas/metabolismo , Anexina A2/metabolismo , Biomarcadores de Tumor/metabolismo , Línea Celular Tumoral , Técnicas Citológicas , Proteínas de Unión al GTP/metabolismo , Humanos , Membrana Dobles de Lípidos/química , Microscopía Electrónica de Transmisión , Proteína Glutamina Gamma Glutamiltransferasa 2 , Transglutaminasas/metabolismo , Células Tumorales Cultivadas , UltracentrifugaciónRESUMEN
OBJECTIVE: The purpose of this study was to explore the effect of PERIOD3 (PER3) genotypes on circadian rhythmicity in flight cadets after militarized management. METHODS: We performed a preliminary study in 146 newly enrolled male flight cadets. Venous blood samples were collected, and genotyping of PER3 (4/5) was determined by using PCR. The morningness-eveningness questionnaire (MEQ) survey was given to flight cadets upon enrollment and after militarized management for 24 months respectively. Comparison of frequency distribution of PER3 genotypes between cases and controls (120 well-matched civilians) was performed using the X(2) test. We also compared the circadian rhythmicity upon enrollment and 24 months after enrollment in flight cadets, and analyzed the connection of changes in circadian clock with PER3 genotypes. RESULTS: The frequency distribution of PER3 genotypes in flight cadets was not significantly different from that in controls subjects. MEQ survey results showed chronotype within flight cadet group varied widely at the two time-points: the moderately morning type (50%) and the neither type (41.1%) upon enrollment; the neither type (76.7%) and the moderately morning type (21.2%) 24 months after enrollment. The circadian rhythm of individuals with the PER3 (5/5) genotype showed no significant difference before and after 24 months of militarized management, whereas notable changes were found in individuals with the PER3 (4/4) genotype (n=116, X(2) =37.26, P < 0.001). CONCLUSION: In conclusion, we provide some evidence that circadian rhythm of flight cadets with the PER3 (5) allele are less likely to be affected compared to those with the PER3 (4) allele.
Asunto(s)
Aviación , Ritmo Circadiano/genética , Personal Militar , Proteínas Circadianas Period/genética , Ciclos de Actividad/genética , Adolescente , Estudios de Casos y Controles , Distribución de Chi-Cuadrado , Frecuencia de los Genes , Heterocigoto , Homocigoto , Humanos , Masculino , Fenotipo , Reacción en Cadena de la Polimerasa , Encuestas y Cuestionarios , Factores de TiempoRESUMEN
OBJECTIVE: Neonatal hypoxic-ischemic encephalopathy (HIE) harms the lives and health of newborn infants and children severely. Given the absence of effective therapies for HIE, it is important to derive new strategies. Neural stem cells (NSCs) have great potential as a therapeutic tool for the repair of a number of central nervous system disorders that involve cell loss. This study was designed to transplant the neural stem cells derived from human fetal brain (hNSCs) into cerebral ventricle of neonatal rat following hypoxic-ischemic injury and to investigate their survival, migration and differentiation in rat brain. METHODS: Cells obtained from the forebrain of a 12-week old fetus were cultured in the presence of epidermal growth factor, basic fibroblast growth factor and leukemia inhibitory factor for 11 days. Animal models were built in 7-day-postnatal Wistar rats, 3-days after hypoxia-ischemia (HI), 5 microl suspension containing 5.0 x 10(5) hNSCs was injected into the left cerebral ventricle of each HIE rat by using stereotactic instrument. No immunosuppression therapy was given to the animals. At 1, 2, 4 weeks and 3 months after transplantation, the rats were sacrificed and brain tissues were harvested and were then examined by H-E staining and immunohistochemical analysis. RESULTS: Implanted cells expressing human nuclear protein (hNP) migrated form the subventricular zone (SVZ) along corpus callosum to the damaged areas, especially to the injured side of cortex and hippocampus. In different areas, the implanted hNSCs differentiated into different cell types which were similar to the host cells. The 85% implanted cells in cortex consisted of hNuc-NF or hNuc-Tublin double positive cells, while in the migratory way, 60% implanted cells differentiated into hNuc-GFAP double positive cells. Compared with the 1-week time point, an increased number of hNP-positive cells were observed at 2-weeks, but the number of these cells greatly decreased at 4-weeks and 3 months. CONCLUSION: The implanted hNSCs could extensively survive, migrate in the brain of neonatal rat with HIE and could differentiate into neurons and astrocytes in a regionally specific manner.
Asunto(s)
Encéfalo/patología , Diferenciación Celular , Movimiento Celular , Células Madre Fetales/trasplante , Hipoxia-Isquemia Encefálica/patología , Hipoxia-Isquemia Encefálica/terapia , Neuronas , Trasplante de Células Madre/métodos , Animales , Animales Recién Nacidos , Arteria Carótida Común/cirugía , Modelos Animales de Enfermedad , Humanos , Hipoxia/complicaciones , Hipoxia/fisiopatología , Hipoxia-Isquemia Encefálica/fisiopatología , Inmunohistoquímica , Inyecciones Intraventriculares/métodos , Ligadura/métodos , Proteínas Nucleares/metabolismo , Ratas , Ratas Sprague-Dawley , Análisis de Supervivencia , Factores de TiempoRESUMEN
OBJECTIVE: Severe newborn hypoxic-ischemic encephalopathy (HIE) has a very high rate of disability and no effective treatment is available. The present study aimed to preliminarily evaluate the effects of human neural stem cell transplantation in treatment of severe neonatal HIE. METHODS: The patient was a 75-day old male infant with sequelae of severe HIE who had highly delayed development of intelligence and movement and myotonia. MRI showed multiple cerebromalacia and encephalatrophy. Cells obtained from the forebrain of an 11-week old fetus were cultured and amplified for 15 days. And then the human fetal neural stem cells were injected into cerebral ventricle of this infant. RESULTS: Twenty eight days after transplantation, remarkable improvement occurred not only in his myotonia but also in his intelligence and movement, which became similar to those of the normal infants of the same age. Positron emission tomography (PET) showed significantly increased radioactivity at temporal and occipital lobes which suggested that the cellular metabolism had increased greatly. CONCLUSION: The short-term effect of NSCs transplantation on the infant with severe HIE sequelae was significant. PET suggested that the implanted NSCs survived. Many more studies are needed to evaluate long-term effects of NSC transplantation in treatment of HIE.