Big Data-Driven Approach for Health Inequalities in Foreign Patients with Injuries Visiting Emergency Rooms.
Ontology highlight
ABSTRACT:
SUBMITTER: Kang JY
PROVIDER: S-EPMC7010947 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectivesPredictive analytics in emergency care has mostly been limited to the use of clinical decision rules (CDRs) in the form of simple heuristics and scoring systems. In the development of CDRs, limitations in analytic methods and concerns with usability have generally constrained models to a preselected small set of variables judged to be clinically relevant and to rules that are easily calculated. Furthermore, CDRs frequently suffer from questions of generalizability, take years to develop, and lack the ability to be updated as new information becomes available. Newer analytic and machine learning techniques capable of harnessing the large number of variables that are already available through electronic health records (EHRs) may better predict patient outcomes and facilitate automation and deployment within clinical decision support systems. In this proof-of-concept study, a local, big data-driven, machine learning approach is compared to existing CDRs and traditional analytic methods using the prediction of sepsis in-hospital mortality as the use case.MethodsThis was a retrospective study of adult ED visits admitted to the hospital meeting criteria for sepsis from October 2013 to October 2014. Sepsis was defined as meeting criteria for systemic inflammatory response syndrome with an infectious admitting diagnosis in the ED. ED visits were randomly partitioned into an 80%/20% split for training and validation. A random forest model (machine learning approach) was constructed using over 500 clinical variables from data available within the EHRs of four hospitals to predict in-hospital mortality. The machine learning prediction model was then compared to a classification and regression tree (CART) model, logistic regression model, and previously developed prediction tools on the validation data set using area under the receiver operating characteristic curve (AUC) and chi-square statistics.ResultsThere were 5,278 visits among 4,676 unique patients who met criteria for sepsis. Of the 4,222 patients in the training group, 210 (5.0%) died during hospitalization, and of the 1,056 patients in the validation group, 50 (4.7%) died during hospitalization. The AUCs with 95% confidence intervals (CIs) for the different models were as follows: random forest model, 0.86 (95% CI = 0.82 to 0.90); CART model, 0.69 (95% CI = 0.62 to 0.77); logistic regression model, 0.76 (95% CI = 0.69 to 0.82); CURB-65, 0.73 (95% CI = 0.67 to 0.80); MEDS, 0.71 (95% CI = 0.63 to 0.77); and mREMS, 0.72 (95% CI = 0.65 to 0.79). The random forest model AUC was statistically different from all other models (p ≤ 0.003 for all comparisons).ConclusionsIn this proof-of-concept study, a local big data-driven, machine learning approach outperformed existing CDRs as well as traditional analytic techniques for predicting in-hospital mortality of ED patients with sepsis. Future research should prospectively evaluate the effectiveness of this approach and whether it translates into improved clinical outcomes for high-risk sepsis patients. The methods developed serve as an example of a new model for predictive analytics in emergency care that can be automated, applied to other clinical outcomes of interest, and deployed in EHRs to enable locally relevant clinical predictions.
| S-EPMC5884101 | biostudies-literature
Project description:Longitudinal nationwide surveillance data on antimicrobial non-susceptibility and prevalence of extended-spectrum ?-lactamases (ESBLs) as well as AmpC ?-lactamases producers among Escherichia coli from different sources in the community settings are limited. Such data may impact treatment practice. The present study investigated E. coli from outpatients and patients visiting emergency rooms collected by the Taiwan Surveillance of Antimicrobial Resistance (TSAR) program. A total of 3481 E. coli isolates were studied, including 2153 (61.9%) from urine and 1125 (32.3%) from blood samples. These isolates were collected biennially between 2002 and 2012 from a total of 28 hospitals located in different geographic regions of Taiwan. Minimum inhibitory concentrations (MIC) were determined using methods recommended by the Clinical Laboratory Standards Institute (CLSI). The prevalence and factors associated with the presence of ESBL and AmpC ?-lactamase-producers were determined. Significant increases in non-susceptibility to most ?-lactams and ciprofloxacin occurred during the study period. By 2012, non-susceptibility to cefotaxime and ciprofloxacin reached 21.1% and 26.9%, respectively. The prevalence of ESBL- and AmpC- producers also increased from 4.0% and 5.3%, respectively, in 2002-2004, to 10.7% for both in 2010-2012 (P < 0.001). The predominant ESBL and AmpC ?-lactamase genes were CTX-M and CMY-types, respectively. Non-susceptibility of urine isolates to nitrofurantoin remained at around 8% and to fosfomycin was low (0.7%) but to cefazolin (based on the 2014 CLSI urine criteria) increased from 11.5% in 2002-2004 to 23.9% in 2010-2012 (P <0.001). Non-susceptibility of isolates from different specimen types was generally similar, but isolates from elderly patients were significantly more resistant to most antimicrobial agents and associated with the presence of ESBL- and AmpC- ?-lactamases. An additional concern is that decreased ciprofloxacin susceptibility (MIC 0.12-1 mg/L) was as high as 25% in isolates from all age groups, including those from pediatric patients. Our data indicated that there is a need to re-evaluate appropriate treatment selection for community-acquired infections in Taiwan. Identification of community reservoirs of multidrug-resistant E. coli is also warranted.
| S-EPMC4669119 | biostudies-literature
Project description:We examine whether patient variables (geographic origin, gender, Spanish language proficiency) and subjective clinician aspects in emergency department psychiatric encounters (diagnostic certainty, clinician's comfort level with patient) are associated with diagnosis and the use of coercive measures. Using a descriptive cross-sectional design, we recorded 467 visits (400 foreign-born and 67 native-born patients) in hospital psychiatry emergency rooms (ERs) in Barcelona between 2007 and 2015. We first assessed the association of patient variables and subjective clinician aspects of psychiatric encounters with service use outcomes and with mental illness diagnosis. Fitted logistic models predicted the likelihood of service use outcomes and estimated the propensity of receiving each diagnosis. The null model evaluated the role of patient's geographical origin, while the full model evaluated the additional roles of patient's gender and language, the clinician's assessment of the influence of culture in diagnosis, and clinician comfort with two outcomes: patient's diagnosis and use of coercive measures in the ER. Women were less likely to receive coercive measures or intramuscular medications compared to men. Significant ethnic/racial and gender differences were found in receiving certain diagnoses. Additionally, a patient's lower Spanish proficiency was correlated with a higher probability of receiving a psychosis diagnosis. The clinician's level of diagnostic certainty was also positively correlated with increasing clinician-reported comfort with patient. Overall, ethnic factors and the subjective aspects of psychiatric encounters were found to influence diagnosis and the use of coercive measures. Cultural competency programs and interpreter services within psychiatric ER settings should thus be required.
| S-EPMC7554163 | biostudies-literature
Project description:Precision health relies on the ability to assess disease risk at an individual level, detect early preclinical conditions and initiate preventive strategies. Recent technological advances in omics and wearable monitoring enable deep molecular and physiological profiling and may provide important tools for precision health. We explored the ability of deep longitudinal profiling to make health-related discoveries, identify clinically relevant molecular pathways and affect behavior in a prospective longitudinal cohort (n?=?109) enriched for risk of type 2 diabetes mellitus. The cohort underwent integrative personalized omics profiling from samples collected quarterly for up to 8?years (median, 2.8?years) using clinical measures and emerging technologies including genome, immunome, transcriptome, proteome, metabolome, microbiome and wearable monitoring. We discovered more than 67 clinically actionable health discoveries and identified multiple molecular pathways associated with metabolic, cardiovascular and oncologic pathophysiology. We developed prediction models for insulin resistance by using omics measurements, illustrating their potential to replace burdensome tests. Finally, study participation led the majority of participants to implement diet and exercise changes. Altogether, we conclude that deep longitudinal profiling can lead to actionable health discoveries and provide relevant information for precision health.
| S-EPMC6713274 | biostudies-literature
Project description:BACKGROUND:To foster responsible data sharing in health research, ethical governance complementary to the EU General Data Protection Regulation is necessary. A governance framework for Big Data-driven research platforms will at least need to consider the conditions as specified a priori for individual datasets. We aim to identify and analyze these conditions for the Innovative Medicines Initiative's (IMI) BigData@Heart platform. METHODS:We performed a unique descriptive case study into the conditions for data sharing as specified for datasets participating in BigData@Heart. Principle investigators of 56 participating databases were contacted via e-mail with the request to send any kind of documentation that possibly specified the conditions for data sharing. Documents were qualitatively reviewed for conditions pertaining to data sharing and data access. RESULTS:Qualitative content analysis of 55 relevant documents revealed overlap on the conditions: (1) only to share health data for scientific research, (2) in anonymized/coded form, (3) after approval from a designated review committee, and while (4) observing all appropriate measures for data security and in compliance with the applicable laws and regulations. CONCLUSIONS:Despite considerable overlap, prespecified conditions give rise to challenges for data sharing. At the same time, these challenges inform our thinking about the design of an ethical governance framework for data sharing platforms. We urge current data sharing initiatives to concentrate on: (1) the scope of the research questions that may be addressed, (2) how to deal with varying levels of de-identification, (3) determining when and how review committees should come into play, (4) align what policies and regulations mean by "data sharing" and (5) how to deal with datasets that have no system in place for data sharing.
| S-EPMC6936121 | biostudies-literature
Project description:We investigated the incidences and characteristics of pediatric traumatic injuries requiring emergency department visits, through a complementary approach using both nationwide-sample and single-institutional data. Data for children (aged <15 years) identified with traumatic injuries during a 10-year period from the Korean National Health Insurance Sharing Service (n = 35,064 among 10,114,909 randomly sampled cases from the claim records of the National Health Insurance) and the authors' institute (n = 39,228) were retrospectively reviewed. The incidences and characteristics of the injuries were investigated using both datasets; additionally, detailed information regarding the injury environments was investigated using the single-institutional data. The findings were similar across both datasets. The incidence of injuries increased during the study period; the head was most commonly injured, whereas the trunk or proximal extremities were rarely injured; low-energy head injuries accounted for >50% of the cases in children aged <5 years, although the incidences of lower-extremity injuries and fractures increased in older children. Single-institutional data demonstrated that the proportion of indoor playground and trampoline-related injuries increased rapidly during the study period, and outdoor injuries and seasonal variation (with peak incidences in May and June) were more prominent in older children. Based on similarities between both datasets, the detailed results regarding pediatric traumatic injuries obtained from the single-institutional data could be generalized nationally with adequate external validity. To prevent traumatic injuries, it may be more effective to wear protective equipment covering the head and distal extremities rather than the trunk or proximal extremities; simple clothing, such as caps, could prevent many injuries in preschoolers. Among older children, safety guidelines for outdoor sports/leisure activities are needed. The increase in pediatric traumatic injuries may be partially explained by the increased availability of indoor playgrounds and installation of trampolines. Stricter adherence to the preventive guidelines is needed.
| S-EPMC6688833 | biostudies-literature
Project description:With the vast amount of immunological data available, immunology research is entering the big data era. These data vary in granularity, quality, and complexity and are stored in various formats, including publications, technical reports, and databases. The challenge is to make the transition from data to actionable knowledge and wisdom and bridge the knowledge gap and application gap. We report a knowledge-based approach based on a framework called KB-builder that facilitates data mining by enabling fast development and deployment of web-accessible immunological data knowledge warehouses. Immunological knowledge discovery relies heavily on both the availability of accurate, up-to-date, and well-organized data and the proper analytics tools. We propose the use of knowledge-based approaches by developing knowledgebases combining well-annotated data with specialized analytical tools and integrating them into analytical workflow. A set of well-defined workflow types with rich summarization and visualization capacity facilitates the transformation from data to critical information and knowledge. By using KB-builder, we enabled streamlining of normally time-consuming processes of database development. The knowledgebases built using KB-builder will speed up rational vaccine design by providing accurate and well-annotated data coupled with tailored computational analysis tools and workflow.
| S-EPMC4090507 | biostudies-literature
Project description:Schistosomiasis is a parasitic infection that is widespread in sub-Saharan Africa, where it represents a major health problem. We study the drivers of its geographical distribution in Senegal via a spatially explicit network model accounting for epidemiological dynamics driven by local socioeconomic and environmental conditions, and human mobility. The model is parameterized by tapping several available geodatabases and a large dataset of mobile phone traces. It reliably reproduces the observed spatial patterns of regional schistosomiasis prevalence throughout the country, provided that spatial heterogeneity and human mobility are suitably accounted for. Specifically, a fine-grained description of the socioeconomic and environmental heterogeneities involved in local disease transmission is crucial to capturing the spatial variability of disease prevalence, while the inclusion of human mobility significantly improves the explanatory power of the model. Concerning human movement, we find that moderate mobility may reduce disease prevalence, whereas either high or low mobility may result in increased prevalence of infection. The effects of control strategies based on exposure and contamination reduction via improved access to safe water or educational campaigns are also analyzed. To our knowledge, this represents the first application of an integrative schistosomiasis transmission model at a whole-country scale.
| S-EPMC5428445 | biostudies-literature
Project description:As acquiring bigger data becomes easier in experimental brain science, computational and statistical brain science must achieve similar advances to fully capitalize on these data. Tackling these problems will benefit from a more explicit and concerted effort to work together. Specifically, brain science can be further democratized by harnessing the power of community-driven tools, which both are built by and benefit from many different people with different backgrounds and expertise. This perspective can be applied across modalities and scales and enables collaborations across previously siloed communities.
| S-EPMC9119703 | biostudies-literature
Project description:During the unprecedented coronavirus disease 2019 (COVID-19) challenge, non-pharmaceutical interventions became a widely adopted strategy to limit physical movements and interactions to mitigate virus transmissions. For situational awareness and decision-support, quickly available yet accurate big-data analytics about human mobility and social distancing is invaluable to agencies and decision-makers. This paper presents a big-data-driven analytical framework that ingests terabytes of data on a daily basis and quantitatively assesses the human mobility trend during COVID-19. Using mobile device location data of over 150 million monthly active samples in the United States (U.S.), the study successfully measures human mobility with three main metrics at the county level: daily average number of trips per person; daily average person-miles traveled; and daily percentage of residents staying home. A set of generalized additive mixed models is employed to disentangle the policy effect on human mobility from other confounding effects including virus effect, socio-demographic effect, weather effect, industry effect, and spatiotemporal autocorrelation. Results reveal the policy plays a limited, time-decreasing, and region-specific effect on human movement. The stay-at-home orders only contribute to a 3.5%-7.9% decrease in human mobility, while the reopening guidelines lead to a 1.6%-5.2% mobility increase. Results also indicate a reasonable spatial heterogeneity among the U.S. counties, wherein the number of confirmed COVID-19 cases, income levels, industry structure, age and racial distribution play important roles. The data informatics generated by the framework are made available to the public for a timely understanding of mobility trends and policy effects, as well as for time-sensitive decision support to further contain the spread of the virus.
| S-EPMC7796660 | biostudies-literature