Use case:
Diagnosis support

A support tool for early breast cancer detection, based on the following criteria..

Need

  • Women, more than 45 years old.

  • Other specific risk factors: first or second-degree relatives with breat cancer diagnosis, overweight, sedentary lifestyle, smokers, non-healthy eating habits.

  • Presence of unfrequent symptoms: itch, reddening of breast, back pain, pain and sensitivity in underarms.

Opportunity

Plenty of information, lack of data

Most clinical information in millions of health records is in unstructured format, ie text.

Mentioned risk factors and symptoms are in visit notes. This means that they are “buried” under 75%-85% unstructured information, being ignored and leading to late diagnosis.

Solution

Natural Language Processing

SVG
1

Electronic Health Records. Including text

SVG
2

Natural Language Processing identifies all clinical concepts.

SVG
3

Structured Database through NLP Coded

Result
SVG

  • Recurring queries are run upon structured database.

  • Patients that comply with criteria are selected.

  • Doctors receive an alarm and decide if selected patients require additional examination.

Benefits

In a year, 500 patients with probability of breast cancer diagnosis were found.

Earlier diagnosis and treatment.

Data security guaranteed.

Detailed infographic

Download