NLP in healthcare

According to recent research, application of natural language processing (NLP) and text analytics in the healthcare and life sciences industries is forecast grow to $2.7 billion by 2021 from $1.0 billion in 2016, while the market is expanding at around 21% annually. All regions across the globe are now showing significant signs of adopting NLP and text analytics for improving the efficacy of the products as well as the quality of services offered to patients. Currently, North America and Europe are leaders in major initiatives for NLP and text analytics. Along with medical data, disruption in digital technologies across the globe has led to the increase in usage of big data which is also one of the major drivers of NLP applications across the globe.

What is NLP?

NLP is a child of artificial intelligence (AI) corresponding to unstructured data processing and mining. It is typically applied on the data generated in the form of text, voice and video contents. NLP helps AI agents to understand the language nuances and contexts expressed by humans. It provides deeper business insights by analysing clinical data, medical inquires, adverse event reports, regulatory compliances and medical data across the healthcare and life sciences industries. This helps computers to perform various other additional tasks to generate value for patients. NLP algorithms and components coupled with AI and machine learning can help businesses extract relevant and critical information from large chunks of data and analyse it carefully for enhanced processing and analytics.

Some of the examples of NLP algorithms are information extraction across articles and trials, summarisation of patient records, linking and chaining of trials with articles, trends and categories from patient inquires, mining product quality complaints, coding and extracting data from adverse event reports, etc.

As NLP on healthcare data is becoming critical with day-to-day increases in unstructured data, industries are focusing on building capabilities and big data platforms that can cater to understand, analyse, and generate languages that can be understood by businesses. NLP solutions are proving to be very effective in variety of business areas to transform the customer experience and journey. Besides, there are several other applications of NLP for enhancing the overall customer experience and improved patient value across segments of Healthcare and life science industry.

Industry challenges in adoption of NLP

Due to complex regulations and compliances, the healthcare and life sciences industries have been slow in adoption of text analytics and NLP. Industries are facing significant challenges in analysing the data due to its unstructured textual nature. Because of massive digital disruption across the globe, there is sharp rise in the generation of naturally written forms of electronic data. This explosive growth of unstructured clinical data, medical data, regulatory data and healthcare data has prioritised the use of innovative technologies of NLP and text analytics.

The key challenges in adoption of NLP are exponential growth in unstructured data in the form of texts from various business teams within the organisation. This ever-growing data remains untouched and therefore companies are unable to identify actionable insights and recommendations that can generate significant value for consumers and patients across the globe. Therefore, detecting potential actions and recommendations from unstructured data could be the key difference in serving up the right insights or deep dive into untouched behaviour and actions of physicians and patients.

Many healthcare and life sciences business organisations are progressively moving towards adopting AI-driven NLP and text analytics capabilities which would help get improved and near-real time insights from unstructured data to derive better results for improved performance across products.

Regulatory compliances and NLP

The key factor in successful adoption of NLP and text analytic technologies is successful navigation of the strict regulations put in place by bodies such as the US Food and Drug Administration and the European Medicines Agency. Compliance with the new GDPR law in Europe to protect patient data privacy has added an additional barrier to uptake of such technologies.

According to recent workshop[conducted by the FDA, NLP may aid healthcare companies in validating evidence and improve consistency and validity of efficacy, safety, and post-marketing documents. However, the FDA and other regulatory authorities foresee a potential risk in adding NLP-driven regulatory submissions as it may pose a potential threat to data integrity. To minimise the risk and ensure the data integrity, the FDA strongly recommends ensuring the NLP and AI process is transparent and provides an audit trail for each document processed.

Healthcare and life sciences companies tend to miss this guidance and thus hesitate to adopt NLP to speed the extraction, processing and validation of safety, inquires, efficacy and medical data. However, as significant developments and successes are observed in NLP, firms are starting to set up in-house teams to use NLP for complex processes.

Additionally, healthcare companies need to collaborate and partner with regulatory bodies to jointly come up with finding ways to leverage the advantages of NLP and text analytics technologies for driving value and accelerating outcomes.

Potential applications of NLP 

There are numerous areas where NLP can play a critical role in driving significant value in quality experience delivered to consumers and patients. Starting from the critical area of patient safety, NLP can assist in identifying safety data and potentially severe adverse events, flag them for immediate human review and report it to regulatory authority.

Global Medical Information teams can also use these technologies to mine inquires and product quality complaints coming from consumers, patients and physicians, to serve them with right contents or potentially identify side effects, while they area also playing a key role in helping healthcare companies follow EMA regulations on relative efficacy analysis of products.

NLP and text analytics algorithms can also transform the traditional methodologies and procedures used to evaluate and improve patient/consumer care quality. Evaluating healthcare professional performance and measuring gaps is a crucial task for insurance companies making the switch to value-based reimbursement. Here, a significant amount of R&D is being undertaken on identifying optimum solutions to use NLP for reducing the time and effort on the process of benchmarking the skills of physicians, automating the evaluation of free text.

Product development teams can perform searches within patents and publications to identify recent trends in improvements to product characteristics or off-label uses of products. They may include activities such as white spot analysis to perform a systematic search leading to potential discovery of new ideas which can speed up market-to-lab and lab-to-market strategies.

Keep your eye on NLP

While there is a slow adoption of NLP across healthcare and life science organisations, there are continuous refinements and improvements taking place in algorithms and techniques of this technology. Researchers are leveraging concepts of AI like neural nets, genetic algorithms, active learning, etc. to improve the accuracy and relevancy of insights for driving value.

Although NLP and text analytics is still in the evolution phase in the healthcare and life sciences industries, it is expected to be ready for production use anytime soon. Regulatory authorities are proactively evaluating this technology to determine how it can be adopted and deployed by healthcare and life sciences organisations to improve life expectancy and quality of life.

Prathamesh P Karmalkar is senior scientist for NLP and Text Analytics at Merck Life Sciences, India, Dr Harsha Gurulingappa is product owner for Text Analytics, Merck KGaA, Germany, and Gerard Megaro, is global head of advanced analytics, EMD Millipore Corporation, US.