Machine learning can help detect presence of cancer, improve public health reporting

To support public health reporting, the use of computers and machine learning can better help with access to unstructured clinical data--including in cancer case detection, according to a recent study. 

Often, the unstructured free text data made available by electronic health records is obtained by means that are "resource intensive, inherently complex and rely on structured clinical data and dictionary-based approaches," according to the authors of the study, published in the Journal of Biomedical Informatics.

The researchers, from the Regenstrief Institute and Indiana University-Purdue University in Indianapolis, used about 7,000 pathology reports from the Indiana health information exchange to attempt to detect cancer cases using already available algorithms and open source machine learning tools.

"We think that its no longer necessary for humans to spend time reviewing text reports to determine if cancer is present or not," Shaun Grannis, M.D., interim director of the Regenstrief Center of Biomedical Informatics, said in an announcement. "We have come to the point in time that technology can handle this. A human's time is better spent helping other humans by providing them with better clinical care."

The researchers concluded that machine learning-based methods are "feasible and practical" ways to extract value from medical data, and can "represent potentially significant value to the public health field" because they are much easier to use than previously relied upon methods. 

Stanford University researchers also found success in using analysis of free-text notes in electronic health records for surveillance of drug interactions in near real time, adding that the evolution of better tools in natural language processing will help speed up the process.

To learn more:
- here's the study
- read the announcement