There are plenty of advocates touting the potential that Big Data has in healthcare, whether its helping us to fight flu epidemics, manage asthma and diabetes, or prevent disease epidemics at mass gatherings. Few doubt that Big Data will eventually be able to prolong our lives, but there are quite a few hurdles to overcome before we reach that point – with one of the biggest being the age-old problem of how to harness all of that data in the first place.
Healthcare leaders appreciate that Big Data can make a big difference, but it’s no secret that many are struggling to implement it, which is why the Institute for Health Technology Transformation (iHT2) recently commissioned a new report offering guidance on how to do just that.
The report makes for an interesting read, and highlights numerous success stories that reinforce the view that Big Data and healthcare are made for each other. In one example, the report highlights a recent partnership between IBM and the University of Ontario to develop monitoring software for newborn babies that allows medical staff to predict the likelihood of nosocomial infections 24 hours before any symptoms appear.
In another example case, the report points to research from the John Hopkins School of Medicine that correctly predicted a surge in flu-related hospital visits weeks before the aforementioned flu epidemic that struck the US this winter.
Despite these successes, the authors warn that there is still some way to go before we can feel the real impact of Big Data in healthcare:
“It must be emphasized that the healthcare industry remains well within its infancy of leveraging big data for business and clinical use. Although there have been some successes, many are unproven at the outcome level and much work remains”
So what can healthcare leaders do to get beyond the infancy stage and implement Big Data solutions for their patients?
The first part of the answer is knowing where to look, and to that end the report identifies five kinds of data where medical professionals can garner insights from – data from the web and social media; machine-to-machine data, such as from meters, sensors and so on; biometric data like genetics, retinal scans, X-rays, blood pressure readings and fingerprints; transaction data from medical billing records; and human-generated data from medical records, emails, phsyicians notes and so on.
The above mentioned data can be mined to provide insights into improving the efficiency and quality of services, methods of detecting disease earlier, and also the detection of fraud. However, the authors iterate that technology is not the only solution, and that this must be integrated seamlessly into healthcare organization’s work flow.
“The potential for benefits is predicated on the assumption that the organization/providers are committed to evidence-supported decisions using analytic tools with available information. If that commitment has not been made, analytic tools provide little value… Key to achieving [these goals] is knowing specifically what metrics are necessary to measure progress.”
Several strategies are suggested by the report’s authors for leveraging Big Data, including the implementation of a carefully structured framework for enterprise-wide data governance, and the fostering of transparency and comepetition among healthcare organizations. In addition, organizations should also find ways to bake analytics into training, because few nurses or physicians understand how to use Big Data tools, nor do they appreciate the value they can add to healthcare. Finally, there is a need to create simple, understandable tools like dashboards that allow phsyicians to visualize incoming data, in order to provide real-time clinical decision support.
Read the report in full to learn more about what the healtcare sector can do to implement Big Data.