Skip to main content

Clinical Research

  1. Challenge of manual chart review
  2. The NLP solution
  3. Use cases

Accelerate clinical research using unstructured data with Linguamatics NLP

The challenge of manual chart review

Mining unstructured data to support medical research has been prevalent for many years. This requires analysis of Big Data sets and often includes manual chart review to identify patients and extract specific attributes. Chart review by qualified professionals is extremely costly and time consuming, and it is hard to achieve a good coverage of variations in language and format. Historically many clinical trials fail “50% of trials delayed due to patient recruitment issues while some trials struggle to find any patients to begin the trial at all”.

Similarly, scientific and medical research requires extensive mining of literature to track the latest publications and outcomes. There is an explosion of new publications in rapidly advancing areas of medicine such as oncology and precision medicine, making it increasingly difficult to keep up to date and understand the scientific landscape using conventional methods.

How can we reduce the manual effort in mining unstructured patient data?

The NLP solution

Linguamatics NLP allows large-scale data exploration and rapid extraction of attributes that significantly reduce manual curation.

Use cases:

  • Extract phenotype details from electronic medical records (EMRs)

Learn how University of Iowa, scientists at the Stead Family Children’s Hospital are working on a precision medicine research project for saving precious time for clinical staff. Linguamatics NLP is being utilized to extract phenotype details from electronic medical records of patients with suspected genetic disorders. Saving annual time of phenotyping of ~700 chromosomal microarray (CMA) tests from 233.33 manual hours to 1.67 hours total. To read more, click here.

  • Identify patients for clinical and observational studies based on clinical attributes in unstructured text

Learn how how Drexel was able to utilize Linguamatics NLP for only two hours of building and testing but resulted in a potential cohort of 1100 subjects compared to 700 subjects found by 5 students over 4 months working part-time. Case study: Drexel University improves cohort selection for HIV and Hepatitis C.

  • Easily construct queries that extract clinical attributes in Big Data to provide training material for machine-learning (ML) algorithms.

Learn how Kaiser Permanente (KP) utilized Linguamatics for machine learning to identifying gout flares. KP’s ML method identified more flare cases (18,869 versus 7,861 manual) and patients with ≥3 flares (1,402 versus 516 manual) when compared to the claims-based method. To learn more, click here.

  • Extract clinical attributes such as cancer stage, tumor size, histology, and biomarker values.

Learn how Huntsman Cancer Institute has used Linguamatics NLP platform to automatically abstract data for cancer research. To learn more, click here.

  • Mine scientific literature for insights into genetic mutation and disease association

Learn how Shire utilized Linguamatics NLP to uncover disease severity and genotype-phenotype associations for Hunter Syndrome.

Learn how the Medical University of South Carolina (MUSC) utilized Linguamatics NLP to determine social isolation in patients with prostate cancer.

Use cases

Case Study: Huntsman Cancer Institute optimizes research with Linguamatics NLP platform


Blog: Striving to Make a Difference in Healthcare with Augmented Intelligence


Whitepaper: 9 Ways to Improve Cancer Insights with Natural Language Processing


Download our application note below on the power of text mining for precision medicine research.

Ready to get started?

Request a Demo

Questions? Ask our experts