In this special guest feature, Simon Beaulah, Senior Director of Healthcare at Linguamatics, discusses how natural language processing (NLP) has become a crucial tool in healthcare and the life sciences as these sectors struggle to catch up to other industries and transform their big data into actionable data. Beaulah is responsible for the company’s healthcare products and solutions, including applications for clinical risk models, population health and medical research.
Healthcare has lagged behind other industries in the successful transformation of big data into actionable data that can be easily leveraged for business insights to improve efficiencies and lower costs. The ecosystem of drug company, payer and health system all need to make more effective use of Big Data to ultimately improve patient care, outcomes and wellness.
A key reason: much of the clinical insight into the health of patient populations isn’t in a structured format. This large realm of unstructured data includes qualitative information that contributes indispensable context in many different reports in the EHR, such as outside lab results, radiology images, pathology reports, patient feedback and other clinical reports. When combined with claims data this mix of data provides the raw material for healthcare payers and health systems to perform analytics. Outside the clinical setting, patient-reported outcomes can be hugely valuable, especially for life science companies seeking to understand the long-term efficacy and safety of therapeutic products across a wide population.
Until now it has been very difficult to mesh quantitative and qualitative clinical data to produce a comprehensive, 360-degree picture of the patient. However, these 360-degree patient views are urgently needed to help payers and health systems execute on population health strategies and other value-based care initiatives designed to improve care outcomes and lower costs.
A key Big Data challenge is to find effective ways to extract critical information from unstructured data in a format that supports actionable insights. That’s where natural language processing (NLP) comes in. NLP uses linguistic algorithms to identify key elements in everyday language and extract meaning from unstructured patient information.
NLP is a key component to development of machine learning applications, transforming unstructured data into quality input to train machine learning algorithms. With so much potential for machine learning to identify new understanding of healthcare issues, the use of unstructured data can cause a significant delay in implementing and training new algorithms because of the manual effort required to extract concepts from text upon which the algorithms are trained. The use of NLP to search large data sets and categorize concepts for extraction is critical to accelerate the utilization of unstructured data for analytics and machine learning. By integrating NLP into enterprise analytics infrastructure, organizations are better able to discover critical insights from their Big Data. Within healthcare and the life sciences, NLP is proving to be an essential tool for improving clinical and financial outcomes.
NLP for healthcare: improving wellness and long-term health
In order to assign risk under evolving value-based reimbursement models, payers and providers must analyze patient populations and stratify patients based on known health and life style conditions. Often, critical patient information, including congestive health failure (CHF) status and risk factors, is hidden in unstructured formats held in data “lakes.” NLP technology gives payers the ability to extract key insights from unstructured data and integrate it with conventional data warehousing and analytical solutions for further analysis.
One large payer, for example, has improved its risk assessment process with the implementation of NLP. Unstructured data from exported EHR data in continuity of care document (CCD) format, including nurse notes from member calls and emails, and PDF documents are all stored in a Hadoop data lake. The payer uses NLP to identify CHF risk factors such as family history and smoking status from the unstructured data. The NLP results are then integrated with the structured data in a Netezza data warehouse. This allows both structured and unstructured data to be used in risk stratification models. As a result, the payer is able to glean vital insights to more precisely assess population risk.
NLP for pharma: finding customer signals to drive commercial decisions
NLP also has significant value in the life sciences sphere. For example, so-called “voice of the customer” (VoC) call transcripts can provide pharmaceutical companies with a rich array of data, including patient-reported outcomes, side effects and drug interactions. Pharmacovigilance, medical affairs and product team professionals can then use NLP to annotate and categorize these call feeds to assess customer insights and make better commercial business decisions.
At one top-10 pharmaceutical company, researchers built a workflow to process the unstructured feed from call transcripts using advanced text analytics. Their goal was to create a visual output to assess trends and to build predictive models based on different products and the real-world data collected from patients, consumers, medical assistants, pharmacists and sales representatives.
Researchers categorized and tagged the calls for key metadata, including caller demographics and the call reasons, such as registering a complaint; requesting formulation information; or, reporting a side effect or drug-drug interaction. The extracted features are also used as the substrate for machine learning algorithms to assist in the categorization of call feeds and the manual review of key cases.
An indispensable tool for healthcare insights
NLP has become a crucial tool in healthcare and the life sciences as these sectors struggle to catch up to other industries and transform their big data into actionable data. NLP is helping healthcare and biopharma organizations to translate qualitative patient and customer data into usable information. With the combination of unstructured data with structured data, healthcare can realize the promise of Big Data, machine learning, natural language analytics and drive better care and efficiencies.
Sign up for the free insideBIGDATA newsletter.
Good blog; you just prove it that, how NLP helps to improve our health. but how this effect for a long time improvement in my health. Some other blogs in which some writers say how can NLP help in our health you just look. http://www.transhumanconsulting.com/blog.php