Health Computing Professionals have long faced data challenges, from solving storage problems during the Big Data era to meeting HL7 standards to adapting infrastructure amid rapid change in telesalut. While all of these advances have improved industry-wide information exchange and, ultimately, patient experience, mountains of data have also been created. In fact, RBC Capital Reports that the healthcare industry generates 30% of the world’s data and that number is expected to grow to 36% by 2025.
This flood of data has only created new challenges for IT professionals, many of whom have been discussed here at HIT Consultant. While most of the focus is on data interoperability or rising storage costs, what few are discussing are the priceless ideas buried in the mountains of data that are being created every day. This obscure data contains critical business intelligence, but is hidden within redundant, obsolete, or trivial data, as well as being isolated within different departments. As a result, it is largely inaccessible.
Finding out this data can seem like a daunting task. And with traditional data management practices that might have been the case. But new technologies, such as data weaving and deep learning, are making this process much easier, presenting new opportunities for both the IT team and the business as a whole.
Discovering the opportunity for dark data
One of the biggest challenges associated with dark data is that the vast majority are unstructured. These PDFs, diagnostic images, clinical trial documents, case notes, etc. they contain the most valuable knowledge of a team, but are impossible to easily identify and obtain information. These data are also full of nuances. For example, different names for similar treatment side effects, disease abbreviations, sentence structures or handwritten notes, all of which may have a different value depending on the project in question.
These factors make traditional search methods ineffective. Assigning a researcher to perform this task manually will undoubtedly lead to a delay in project deadlines and human error, which will likely occur when scanning hundreds of documents to extract specific information.
The result? Lost stats and limited ROI.
Advances in deep learning algorithms are proving to be a solution to this problem. The natural language processing made possible by these algorithms allows valuable texts and knowledge to be identified at a faster rate and accuracy than traditional search methods.
Now, the researcher or healthcare professional in charge of a week-long research project can complete their task in a matter of hours or days.
Making the data work for you
Once dark data is unlocked, healthcare IT professionals can bring significant benefits to the organization, especially those in healthcare where data-driven decision making is critical to a variety of factors, from product safety to public health and patient experience. While the opportunities for leveraging dark data with the help of deep learning are ultimately endless, some short-term applications include:
– Clinical trial design: Determining the viability of a clinical trial is critical, especially as the cost of trials continues to skyrocket. Leveraging previously obscure data, companies can conduct more accurate risk assessments by analyzing key decision-making knowledge, such as disease indications, clinical trial protocols, site details, and subject demographics. .
– Detection by medical image: Images are one of the main causes of dark data given the challenges that most computer applications face when reading this type of content. However, as the number of cases around diseases such as cancer continues to increase, increased accessibility to screening images can help oncologists speed up the identification of the tissues in question and improve the accuracy of the initial diagnosis.
– Patient care: When diagnosing or determining a route of care, medical professionals often rely on the most easily accessible data for them. By unlocking dark data, these people can gain access to rich knowledge that is found within complex texts and documents to identify alternative treatments, potential side effects, and more that can greatly enhance the patient experience.
What the future holds for us
The healthcare industry is experiencing a renaissance of data. Among improvements a EHRs, new data interoperability protocols and accelerated digital transformation, the exchange of industry information is greatly improved. We have experienced this recently with the COVID-19[feminine[feminine pandemic. Real-time data exchange and access to new knowledge have helped to influence public health guidelines, identify appropriate types of treatment, and accelerate the development of various vaccines.
As IT practices in the industry become more advanced, we can ensure a future of improved response to emerging diseases, better patient care, and a healthier population. And discovering dark facts will play a key role in making this future a reality.
About Dr. Christopher Bouton
Dr. Christopher Bouton is the founder and CEO of Christopher Bouton Vyasa, a provider of deep learning AI analysis software. Prior to Vyasa, Bouton founded the big data analytics company Entagen, which was acquired by Thomson Reuters and was head of integrated data mining at Pfizer. Dr. Bouton has a PhD. in molecular neurobiology from Johns Hopkins University.