Big Data Panel
|
If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL). |
Abstract
The transition from paper-based to electronic health records has generated, and continues to generate, large quantities of data. The main uses of these data are to support the direct care of individual patients and to guide the management of healthcare systems for populations. The data also have considerable potential to fuel research, but this asset has scarcely been harnessed for patient and public benefit.
Beyond the clinic, healthcare consumers worldwide are adopting mobile and web-based technologies for communicating with friends and families, searching for information and helping them to manage their day-to-day lives. So they expect healthcare to be at least as connected as other aspects of their digital lives. Patients, of their own volition, use web and mobile technologies to capture health data and seek healthcare guidance. All these interactions add to the ‘big data’ about health that could be linked and analysed.
Both clinical and consumer health data-streams, when looked from a national or international perspective are many orders of magnitude greater than the “minimum†datasets the feed conventional health science. Instead of conducting a survey or collecting a set number of data-points through phone-calls or paper forms, we now have access to the raw data of millions of daily healthcare transactions and decisions.
More data from more sources means more ways to reach specious conclusions, therefore the rigor of epidemiology and conventional clinical research methods still applies. The size, heterogeneity and speed of emergence of ‘big health data’, however, is beyond the capability of conventional research methods. New tools and techniques such as machine learning need to be explored for shaping hypotheses from the complex structure in the data, as well as expanding traditional hypothesis-driven research.
In this panel, experts from the fields of computer science, public health informatics and patient-led research will discuss some of the thornier issues associated with big data analysis in healthcare. Jim Davies, Professor of Software Engineering at the University of Oxford, will discuss the challenges of big data acquisition in healthcare and how techniques developed by companies like Google and Amazon could be applied to the healthcare domain. Iain Buchan, Professor of Public Health Informatics at the University of Manchester, will explore how big data analytics such as machine learning can be combined with hypothesis driven research for robust scientific discovery and health service development. Finally, Paul Wicks from PatientsLikeMe will talk about how the vast quantities of ‘user-generated’ data from patients’ communities such as PatientsLikeMe can be harness for clinical research.
Beyond the clinic, healthcare consumers worldwide are adopting mobile and web-based technologies for communicating with friends and families, searching for information and helping them to manage their day-to-day lives. So they expect healthcare to be at least as connected as other aspects of their digital lives. Patients, of their own volition, use web and mobile technologies to capture health data and seek healthcare guidance. All these interactions add to the ‘big data’ about health that could be linked and analysed.
Both clinical and consumer health data-streams, when looked from a national or international perspective are many orders of magnitude greater than the “minimum†datasets the feed conventional health science. Instead of conducting a survey or collecting a set number of data-points through phone-calls or paper forms, we now have access to the raw data of millions of daily healthcare transactions and decisions.
More data from more sources means more ways to reach specious conclusions, therefore the rigor of epidemiology and conventional clinical research methods still applies. The size, heterogeneity and speed of emergence of ‘big health data’, however, is beyond the capability of conventional research methods. New tools and techniques such as machine learning need to be explored for shaping hypotheses from the complex structure in the data, as well as expanding traditional hypothesis-driven research.
In this panel, experts from the fields of computer science, public health informatics and patient-led research will discuss some of the thornier issues associated with big data analysis in healthcare. Jim Davies, Professor of Software Engineering at the University of Oxford, will discuss the challenges of big data acquisition in healthcare and how techniques developed by companies like Google and Amazon could be applied to the healthcare domain. Iain Buchan, Professor of Public Health Informatics at the University of Manchester, will explore how big data analytics such as machine learning can be combined with hypothesis driven research for robust scientific discovery and health service development. Finally, Paul Wicks from PatientsLikeMe will talk about how the vast quantities of ‘user-generated’ data from patients’ communities such as PatientsLikeMe can be harness for clinical research.
Medicine 2.0® is happy to support and promote other conferences and workshops in this area. Contact us to produce, disseminate and promote your conference or workshop under this label and in this event series. In addition, we are always looking for hosts of future World Congresses. Medicine 2.0® is a registered trademark of JMIR Publications Inc., the leading academic ehealth publisher.
This work is licensed under a Creative Commons Attribution 3.0 License.