Use of big data by Blue Cross and Blue Shield of North Carolina.

The health care industry is grappling with the challenges of working with and analyzing large, complex, diverse data sets. Blue Cross and Blue Shield of North Carolina provides several promising examples of how big data can be used to reduce the cost of care, to predict and manage health risks, and to improve clinical outcomes.

The Patient-Centered Outcomes Research Network: a national infrastructure for comparative effectiveness research.

The current clinical research system does not produce high-quality evidence quickly enough to support health care decision making. The Patient-Centered Outcomes Research Network (PCORnet) embodies a novel strategy for creating a national "network of networks" that is capable of significantly accelerating evidence generation to support a learning health system.

The value of all-payer claims databases to states.

All-payer claims databases are being developed in states across the nation to fill gaps in information about the health care system. The value of such databases is becoming more apparent as these databases mature and are used more frequently to help states better understand their health care utilization and costs.

Integrated data management for clinical studies: automatic transformation of data models with semantic annotations for principal investigators, data managers and statisticians.

Design, execution and analysis of clinical studies involves several stakeholders with different professional backgrounds. Typically, principle investigators are familiar with standard office tools, data managers apply electronic data capture (EDC) systems and statisticians work with statistics software. Case report forms (CRFs) specify the data model of study subjects, evolve over time and consist of hundreds to thousands of data items per study. To avoid erroneous manual transformation work, a converting tool for different representations of study data models was designed. It can convert between office format, EDC and statistics format. In addition, it supports semantic annotations, which enable precise definitions for data items. A reference implementation is available as open source package ODMconverter at http://cran.r-project.org.

How to exploit twitter for public health monitoring?

OBJECTIVES: Detecting hints to public health threats as early as possible is crucial to prevent harm from the population. However, many disease surveillance strategies rely upon data whose collection requires explicit reporting (data transmitted from hospitals, laboratories or physicians). Collecting reports takes time so that the reaction time grows. Moreover, context information on individual cases is often lost in the collection process. This paper describes a system that tries to address these limitations by processing social media for identifying information on public health threats. The primary objective is to study the usefulness of the approach for supporting the monitoring of a population's health status. METHODS: The developed system works in three main steps: Data from Twitter, blogs, and forums as well as from TV and radio channels are continuously collected and filtered by means of keyword lists. Sentences of relevant texts are classified relevant or irrelevant using a binary classifier based on support vector machines. By means of statistical methods known from biosurveillance, the relevant sentences are further analyzed and signals are generated automatically when unexpected behavior is detected. From the generated signals a subset is selected for presentation to a user by matching with user queries or profiles. In a set of evaluation experiments, public health experts assessed the generated signals with respect to correctness and relevancy. In particular, it was assessed how many relevant and irrelevant signals are generated during a specific time period. RESULTS: The experiments show that the system provides information on health events identified in social media. Signals are mainly generated from Twitter messages posted by news agencies. Personal tweets, i.e. tweets from persons observing some symptoms, only play a minor role for signal generation given a limited volume of relevant messages. Relevant signals referring to real world outbreaks were generated by the system and monitored by epidemiologists for example during the European football championship. But, the number of relevant signals among generated signals is still very small: The different experiments yielded a proportion between 5 and 20% of signals regarded as "relevant" by the users. Vaccination or education campaigns communicated via Twitter as well as use of medical terms in other contexts than for outbreak reporting led to the generation of irrelevant signals. CONCLUSIONS: The aggregation of information into signals results in a reduction of monitoring effort compared to other existing systems. Against expectations, only few messages are of personal nature, reporting on personal symptoms. Instead, media reports are distributed over social media channels. Despite the high percentage of irrelevant signals generated by the system, the users reported that the effort in monitoring aggregated information in form of signals is less demanding than monitoring huge social-media data streams manually. It remains for the future to develop strategies for reducing false alarms.

Whats the story? Information needs of trauma teams.

This paper reports on information needs of trauma teams based on an ethnographic study in an urban teaching hospital. We focus on questions posed by trauma team members during ten trauma events. We identify major categories of questions, as well as information seekers and providers. In addition to categories known from other critical care settings, we found categories unique to trauma settings. Based on these findings, we discuss implications for information technology support for trauma teams.

IT-adoption and the interaction of task, technology and individuals: a fit framework and a case study.

BACKGROUND: Factors of IT adoption have largely been discussed in the literature. However, existing frameworks (such as TAM or TTF) are failing to include one important aspect, the interaction between user and task. METHOD: Based on a literature study and a case study, we developed the FITT framework to help analyse the socio-organisational-technical factors that influence IT adoption in a health care setting. RESULTS: Our FITT framework ("Fit between Individuals, Task and Technology") is based on the idea that IT adoption in a clinical environment depends on the fit between the attributes of the individual users (e.g. computer anxiety, motivation), attributes of the technology (e.g. usability, functionality, performance), and attributes of the clinical tasks and processes (e.g. organisation, task complexity). We used this framework in the retrospective analysis of a three-year case study, describing the adoption of a nursing documentation system in various departments in a German University Hospital. We will show how the FITT framework helped analyzing the process of IT adoption during an IT implementation: we were able to describe every found IT adoption problem with regard to the three fit dimensions, and any intervention on the fit can be described with regard to the three objects of the FITT framework (individual, task, technology). We also derive facilitators and barriers to IT adoption of clinical information systems. CONCLUSION: This work should support a better understanding of the reasons for IT adoption failures and therefore enable better prepared and more successful IT introduction projects. We will discuss, however, that from a more epistemological point of view, it may be difficult or even impossible to analyse the complex and interacting factors that predict success or failure of IT projects in a socio-technical environment.

The implementation of electronic services: planned or organic growth?

The literature on innovation suggests that projects are successful when rigorous project management is mixed judiciously with 'organic' development. This paper argues that organic growth can play a substantial role in the implementation of electronic services in healthcare settings. Evidence for organic growth is presented, based on a study of email use. Methods are presented for investigating email use in health service settings in the National Health Service (NHS) in Bradford, England. Geographical information systems (GIS) outputs and social network analyses are presented. The results demonstrate a fivefold increase in the use of email over a 13-month period, which is shown to be largely independent of the growth in the number of organisations using the network. They also demonstrate a marked increase in the complexity of the patterns of email use over the period.

Limited information technology for patient care in physician offices.

Evidence of physicians' use of information technology (IT) to support patient care has been sketchy and anecdotal to date. However, new findings from the Center for Studying Health System Change (HSC) show wide variation in information technology adoption across physician practices, particularly by physician practice size. In 2001, nearly 60 percent of physicians in traditional practice settings--primarily solo or relatively small group practices where the vast majority of Americans receive care--reported that their practice used information technology in no more than one of the five following clinical functions: obtaining treatment guidelines, exchanging clinical data with other physicians, accessing patient notes, generating treatment reminders for the physician's use and writing prescriptions. Highest levels of IT support for patient care were found in staff- and group-model health maintenance organization (HMO) practices, followed by medical school faculty practices and large group practices. Overall rates of information technology adoption may have increased since 2001, but the variation in IT adoption by practice setting is unlikely to have changed

Applying data mining techniques to library design, lead generation and lead optimization.

Many data mining techniques have been applied to activity and ADMET datasets and the resulting models are being used to understand quantitative structure-activity relationships and design new libraries. This review summarizes data mining concepts and discuss their application to library design, lead generation (particularly for sequential screening) and lead optimization (specifically for generating and interpreting QSAR models). Also, this review discusses recent comparative studies between data mining techniques and draws some conclusions about the patterns emerging in the drug discovery data mining field.

How internet users find, evaluate, and use online health information: a cross-cultural review.

The Internet has become a favored source to find health information. Worldwide, about 4.5% of all Internet searches are for health-related information. However, research has found that the quality of online health information is mixed, which raises serious concerns about the impact of this information. This paper reviews relevant research to understand how health information on the Internet is retrieved, evaluated, and used. Most users of online health information are looking for information about specific health conditions because they or someone they know was diagnosed with a medical condition. They typically use general search engines to find online health information and enter short phrases, often misspelled. They seldom go beyond the first page of a search. Both their search and evaluation skills are limited although they are concerned about the quality of online health information. They avoid sites with overt commercialism, but often do not pay attention to indicators of credibility. Online health information is used to fill an information void which can enhance coping and self efficacy, affects health-related decisions and behavior of users and their friends and family, and is often discussed with health care providers. There are cross-cultural differences in the types of sites used as well as how online information is used. Based on the research reviewed in this paper, three major recommendations are suggested. Professionals should recommend sites. Professionals should promote more effective search and evaluation techniques. Professionals should be involved in developing and promoting uniform standards for health and mental health sites.

Chem-tox informatics: data mining using a medicinal chemistry building block approach.

Relating chemical structure to biological activity is not a new endeavor, however, the ability to do this on large datasets is just emerging. To cope with the enormous amounts of data being generated, an assortment of computational methods has been developed in the fields of chemoinformatics and computational toxicology. Many of the molecular descriptors used in these approaches are abstract, theoretical constructs that are difficult to understand and visualize. Having easily recognized chemical features, such as those in several new programs, will allow chemists to use toxicological information (or any biological information) when designing new libraries. These improved chem-tox informatics systems will have an impact on library design, hit and lead optimization, development candidate testing and regulatory review.

A computerized record chart for the study of chronic daily headache.

A comprehensive record chart for the study of chronic daily headache (CDH) is presented. The record chart contains 11 parts (232 items) concerning: sociodemographic data, physiological history, female reproductive life history, family history, pathological history, drug abuse, headache history, headache clinical features, prophylactic therapy, instrumental investigations, and physical and neurological examination. Furthermore, three attached special charts are illustrated which concern, respectively, the cervical spine examination, oromandibular function examination and the assessment of analgesic use.