5 Key Factors to Consider When Evaluating NLP APIs - MedCity News

In today’s world, connectivity and interoperability reign supreme as everything from banking to shopping transitions to a seamless and intelligence-based experience. One industry where interoperability is very much in the spotlight today is healthcare, with federal legislation mandating the easy transfer of electronic data.

Interoperability has been part of healthcare strategy for some time, but the Covid-19 crisis has highlighted the challenges of siled healthcare systems. At a time when we needed to rapidly collect data regarding the epidemiology, clinical characteristics, and potential treatments for Covid-19, our efforts were hampered by systems that could not easily standardize and transmit data to each other, and by the fact that that much of the required information was captured in unstructured data.

Legislation such as the 21st Century Cures Act has facilitated the rise of application programming interfaces (APIs) in healthcare. Coupled with the recent realization that data needs to be more easily discoverable and analyzable, it seems like everyone is talking about Natural Language Processing (NLP) APIs. From a relatively niche and specialized ability just five years ago, NLP is now mainstream and offers fast results.

Access data with the right NLP APIs

In simple terms, APIs act as a software intermediary that allows two applications to communicate with each other, offering a critical link to connect. The NLP API allows users to send text to an endpoint – and receive back structured data representing the content of that free text. With these APIs, data scientists, developers, and analysts can free themselves from the frustrating, tedious, and manual efforts of coding and cleaning unstructured data. This is especially valuable in healthcare, where up to 80% of data is locked in unstructured text.

However, health and animal care organizations looking to add NLP to their workflows via APIs should keep in mind that not all NLP APIs are created equal. When looking for tools to effectively and efficiently surface healthcare concepts, it’s important to find technologies that capture the nuances of medical and scientific language and are designed to answer data scientists’ most common questions.

When evaluating NLP API alternatives, here are five key factors to consider:

  • Is the API configured to recognize healthcare concepts? Improve usability and minimize coding time with tools designed to recognize key health concepts, context and patterns in data such as drugs, doses, diseases and demographics.
  • Is the application programming interface (API) designed to surface common healthcare and life science questions? Common use cases may include inferring SDoH from unstructured information, identifying and coding adverse events into MedDRA concepts, and retrieving gene/protein biomarkers listed in FDA drug labels or used in ClinicalTrials.gov by drug and indication.
  • Does the solution offer the flexibility to apply NLP to your own documents as well as offer a library of cloud-based scholarly documents? Users often need flexibility to find the meaningful metadata and concepts they need. Access to a vast library of biomedical data sources such as PubMed, ClinicalTrials.gov, and FDA Drug Labels provides a richer source of data for decision making.
  • Is there an option for instant, free access with no prior commitment? For users who have limited needs or want to pilot a use case, having a readily available free option that does not require commitment and expertise in NLP is an important advantage.
  • Does the API return an easy-to-use result? Choosing an API that will output results in a consistent format that is easy to parse in downstream tools is a key consideration that is often overlooked.

Along with these five factors, there is a sixth that is just as important – “what comes next”. Often the output of healthcare NLP APIs is more than sufficient for user requirements. However, just as often, once users begin to realize the value of their unstructured data, more questions will follow. Therefore, an organization’s best approach to successfully master its unstructured data is to look for NLP vendors that allow users to create custom APIs as well as implement NLP directly into their infrastructure.

The pandemic has highlighted the critical value to public health and research of rapid data availability and analytical capacity. With the right NLP API solutions, data scientists now have the ability to quickly access a wide variety of data for a wide range of use cases, including adverse event detection from case reports or literature; identifying relevant biomarker data in clinical trial records and drug labels; predictive analyzes and population health analyzes of social determinants of health, etc.

Photo: bsd555, Getty Images

Source link

Leave a Reply

Your email address will not be published. Required fields are marked *