How Content Intelligence Provides an Answer to Big Data Issues for Healthcare Sector
News Oct 08, 2014
More than a billion ‘information transactions’ are processed every day according to Forbes, and the healthcare sector is a major contributor, yet making sense of this volume of data remains a challenge. While the information produced by independent research labs, educational institutions, professional journals, hospitals, pharmaceutical companies, medical practices and other public healthcare providers such as the UK’s National Health Service can all be hugely beneficial to frontline healthcare professionals and their patients, accessing the right data at the necessary speed is no easy task.
Yet a recent study from MindMetre Research reveals that just a third (36%) of healthcare organisations see sheer volume as the main obstacle here. The research, based on a survey of senior information management professionals across the US and Europe, including those in healthcare and medical organisations, reveals data fragmentation to be the biggest barrier for primary care providers. In fact, 79% say the fact that much of the information they need is held in different locations and formats – making it the obstacle most identified in the study – while 46% list ineffective tagging as an obstruction to finding accurate information at speed, the second most cited challenge.
Big Data plays an enormous role in helping medical practitioners to understand specific cases and how to deal with them, researchers in finding better drugs and treatments, and patients themselves in gathering information on medical conditions or general health through healthcare portals. Being able to access the swathes of unstructured information available is becoming ever more important as professionals working in medicine and related sectors begin to understand its power and potential: 89% of those surveyed believe that being able to take better advantage of their Big Content will allow their organisations to reap benefits both in commercial terms and in helping patients.
The solution to the hurdles faced by healthcare professionals and their patients lies in Content Intelligence. Unlocking the wealth of knowledge contained in this unstructured data requires investment in systems that enhance existing information management platforms, automatically categorising or meta-tagging unstructured data accurately and managing vocabulary more precisely – of particular relevance in a sector known for its complicated terminology and jargon. Importantly, these systems also leave this data in its original locations, enabling organisations to avoid the expense of formatting and absorbing huge volumes of different types of information into a single database and allowing partner organisations to work more closely together.
The NHS has already taken the first step by implementing Content Intelligence capability in its patient information portal NHS Choices, enabling it to provide end users with a more intuitive and therefore more accurate service. By using Content Intelligence, the portal is able to read the context of a search term, even if a layman’s term is used, screening out irrelevancies and guiding the user to results that address their intended meaning. Through it, a patient searching for information on the term ‘virus’, for example will find results on viral infections rather than computer viruses.
Certainly this easy search approach is a best practice model that everyone involved in healthcare, medical research and related fields should be working towards, as well as encouraging the organisations they deal with to adopt. If healthcare providers are to take advantage of the Big Content available, not only to improve patient care but also to gain that important competitive edge, there is a very real need to invest in the implementation of Content Intelligence solutions, which can only improve the healthcare professional’s ability to filter unstructured data, giving quicker access to more relevant and accurate information, and ultimately providing a better patient experience.
Algorithm Speeds Up Medical Image Analysis 1000 TimesNews
Medical image registration is a common technique that involves overlaying two images, such as magnetic resonance imaging (MRI) scans, to compare and analyze anatomical differences in great detail. Researchers have described a machine-learning algorithm that can register brain scans and other 3-D images more than 1,000 times more quickly using novel learning techniques.
Antarctic Worm and Machine Learning Help Identify Cerebral Palsy EarlierNews
A research team has released a study in the peer-reviewed journal BMC Bioinformatics showing that DNA methylation patterns in circulating blood cells can be used to help identify spastic cerebral palsy (CP) patients. The technique which makes use of machine learning, data science and even analysis of Antarctic worms, raises hopes for earlier targeted CP therapies.
Towards Personalized Medicine: One Type of Data is Not EnoughNews
To understand the biology of diseased organs researchers use different types of molecular data. One of the biggest computational challenges at the moment is integrating these multiple data types. A new computational method jointly analyses different types of molecular data and disentangles the sources of disease variability to guide personalized treatment.READ MORE