Join our seminar in San Francisco: Connected Natural language processing

The terminology used by pathologists to describe and grade dysplasia and premalignant changes of the cervical epithelium has evolved over time. Unfortunately, coexistence of different classification systems combined with non-standardized interpretive text has created multiple layers of interpretive ambiguity.  We used natural language processing (NLP) to automate and expedite translation of interpretive text to a single most severe, and thus actionable, cervical intraepithelial neoplasia (CIN) diagnosis.  The algorithms that were developed and then applied to 35,847 unstructured cervical pathology reports assessed NLP performance in identifying the severest diagnosis, compared to expert manual review. NLP performance was determined by calculating precision (0.957), recall (0.925), and F score (0.94).  Using NLP also significantly reduced the time to evaluate each monthly biopsy file from 30 hours to 0.5 hours. The use of NLP rapidly and efficiently assigned a discrete, actionable diagnosis using CIN classification that can assist with clinical management of cervical pathology and disease. Moreover, discrete diagnostic data encoded as CIN terminology can enhance the efficiency of clinical research. 

Michael Wu from Genentech will be presenting their work with NLP. 

For true precision medicine, the importance of deep phenotyping is absolute. With increasing volumes of unstructured data vitally important to understand both the genetic basis of disease, but also the severity and progression of disease, repeatable means to create highly accurate curated features from these unstructured data is essential. In this session we will talk about how IQVIA NLP provides a repeatable and transparent means of accurate computational phenotyping that drives precision medicine. 

Around 80% of a data scientists time is spent cleaning and preparing their data before it is ready to be processed. For unstructured information, this figure could be even higher when you factor in the lack of schemas, term ambiguity, inconsistent formatting and terminologies, etc. In the session, we will show how IQVIA NLP products can be used to obtain data from free text that has been cleaned, structured and normalized, allow users to spend their time on what matters: solving high-value business problems using the available tools and data. 

Natural Language Processing is NLP is a key component of augmented intelligence in medical chart review, driving predictive analytics and risk stratification in healthcare. From government programs – such as Medicare Advantage Risk Adjustment – where chart review is necessary to ensure accurate capture and reporting of comorbid conditions, to predicting disease progression, there are many applications that are benefitted by bootstrapping chart review with AI. In this session – we will discuss how updates to the IQVIA NLP portfolio are helping healthcare organizations drive efficiencies in these areas.

From bench to bedside, researchers and clinicians need to base decisions on the best possible view of data. As 80% of data resides in unstructured sources, rapid effective access to the knowledge buried in text documents is essential.  Natural Language processing (NLP) allows organizations to transform unstructured text into actionable structured data that can be rapidly visualized and analyzed, for decision support. We will present how NLP provides a powerful solution to these challenges, with customer use cases ranging from disease understanding to medical affairs.

Powerful text-mining technologies can prove invaluable for everyone from data scientists and technology teams through to scientists and professionals across pharma functions. In this session we will take a closer look at three scalable ways we can put the power of NLP into the hands of these teams in safety, regulatory and medical affairs. The case studies and examples in this session bring to life how text mining scientific literature, drug labels & regulatory documents, social media and news sources can unlock new insights or help teams work more efficiently.  By empowering users to search, compare, extract and analyse relevant rich data that is otherwise buried within text and document sources, teams can focus on applying their expertise and less on sifting through vast data sources for the information they need to get started.