Blog

Using Natural Language Processing (NLP), Agios Pharmaceuticals discovers new therapeutic candidate

As the search for novel anti-cancer agents continues apace, the biopharma industry struggles to make sense of the myriad studies that are published describing putative small molecule inhibitors, potential genetic targets, and possibly susceptible points of attack. One area of growing interest in oncology is cancer cell metabolism: companies are striving to develop compounds that can interrupt or inhibit the metabolic process, leading to tumor cell suppression or death. The dual challenges are to identify promising lead compounds, and to detect suitable genes implicated in the metabolic process and sensitive to chemical intervention.

Rather than starting from scratch with a blank structure-activity canvas and pursuing the traditional (and potentially lengthy and risky) lead identification/lead optimization route to a pre-clinical candidate, Agios Pharmaceuticals decided to short-circuit the process and build on previously published studies. They wanted to locate and source known inhibitors for use as tool compounds in their chemical genetics screens and to identify genes with “druggable Achilles’ heels” susceptible to chemical attack, and they chose to use NLP to quickly and effectively scour the literature.


We are proud to announce that the IQVIA Linguamatics Natural Language Processing (NLP) platform was recently awarded Questex’s 2019 Fierce Innovation Award – Life Sciences Edition in the Data Analytics/Business Intelligence category. In addition, the NLP healthcare platform was recognized with a Best in Show honor for ‘Best Technology Innovation’.

Sponsored by the publisher of FierceBiotech and FiercePharma, the Fierce Innovation Awards identify and showcase outstanding innovation that is driving improvements and transforming the healthcare industry. An expert panel of judges reviews all submissions to determine which companies demonstrate innovative solutions, technologies and services that have the potential to make the greatest impact for biotech and pharma companies.

The IQVIA Linguamatics NLP platform supports life sciences organizations seeking to speed up drug development and improve patient outcomes by breaking down data silos, boosting innovation, enhancing quality and reducing risk and complexity. NLP is an artificial intelligence technology that transforms unstructured and semi-structured text into normalized, structured data suitable for analysis or to drive machine learning algorithms.

The platform uses sophisticated algorithms to identify, extract and connect key concepts, facts and relationships buried in the text rather than just retrieve documents based on keyword search. Key solution areas include:


Better diagnosis needs more than diagnosis codes

It’s well known that cardiovascular diseases are one of the major causes of death both in the US and globally. This level of disease puts great pressures on health systems to manage the patient load, both at the population level and at the individual level. As with all diseases, treatment is more effective and less costly if patients can be diagnosed earlier on their care journey. One barrier here is that diagnosis codes for conditions such as valvular heart disease can be inaccurate and vary across health systems. More information resides in the unstructured text of medical records but this is slow and tedious to extract manually.

Fast accurate diagnosis of aortic stenosis with Natural Language Processing

A recent short paper by Solomon et al from Kaiser Permanente Northern California (KPNC) used Natural Language Processing (NLP) algorithms to extract detailed clinical information from echocardiography (ECG) reports. NLP is an Artificial Intelligence (AI) technology used to transform free, unstructured text in documents and databases into normalized, structured data suitable for analysis. Their results were more accurate than using diagnosis codes to identify aortic stenosis, for a patient cohort of over 500,000 individuals.


Recently, I was fortunate to chair a panel discussion where the potentials of Artificial Intelligence (AI) and Machine Learning (ML) were fiercely discussed. AI/ML seems to be talked about everywhere at the moment, heralded as a solution for many challenges in pharma and healthcare (and indeed many other industries). But, does AI/ML really warrant this level of excitement and hype?

AI/ML leaders in advanced statistics, NLP, deep learning, neural networks come together

One thing that is often overlooked in these discussions is that AI/ML is a broad group of diverse disciplines, not a singular item. AI/ML includes advanced statistics, Natural Language Processing (NLP), deep learning, neural networks, and many other mathematical and computer science specialities. The event I attended was a Linguamatics-hosted dinner. The panel of five experts covered a broad span of expertise across different AI/ML disciplines, and ranged from academia to small and large pharma:


How to Choose the Right Natural Language Processing Solution

These days there is a lot of talk about AI in respect to Artificial intelligence, but AI has another abbreviation, Augmented Intelligence. Artificial Intelligence implies a level of machine automated processing with no human intervention whereas Augmented Intelligence is the use of technology to enhance human performance. One AI technology that has been proven to support both interpretations is Natural Language Processing, or NLP for short. This is not a new technology, in fact, Linguamatics has been successfully completing projects using NLP since 2001.

For Payers and Health plans investigating new technologies there are many areas where NLP can support improved efficiency and business insights: HEDIS medical record review for hybrid measures, Medicare risk adjustment, clinical review/medical necessity and risk stratification to name just a few. The first four areas are about using NLP to improve efficiency of often manual processes by extracting key insights from medical records and summarizing the findings; the last example is a more automated analysis of large-scale populations to identify high risk members based on Social Determinants of Health and disease severity information.

The growth of interest in NLP and AI has led to more and more businesses claiming to have AI solutions that can help healthcare organizations to make the most of their unstructured data. The question is: how do you decide which NLP offering actually works, and which NLP solution is right for you?