Exploiting Rules to Enhance Machine Learning in Extracting Information From Multi-Institutional Prostate Pathology Reports.

Enrico Santus¹, Tal Schuster¹, Amir M Tahmasebi^2,3, Clara Li¹, Adam Yala¹, Conor R Lanahan⁴, Peter Prinsen⁵, Scott F Thompson³, Samuel Coons³, Lance Mynderse⁶, Regina Barzilay¹, Kevin Hughes⁴

¹Department of Electrical Engineering and Computer Science, CSAIL, MIT, Cambridge, MA.

²CodaMetrix, Boston, MA.

³Philips Healthcare, Cambridge, MA.

⁴Department of Oncology, Massachusetts General Hospital, Boston, MA.

⁵Philips Research, Eindhoven, the Netherlands.

⁶Mayo Clinics, Rochester, MN.

PubMed DOI

Abstract

PURPOSE: Literature on clinical note mining has highlighted the superiority of machine learning (ML) over hand-crafted rules. Nevertheless, most studies assume the availability of large training sets, which is rarely the case. For this reason, in the clinical setting, rules are still common. We suggest 2 methods to leverage the knowledge encoded in pre-existing rules to inform ML decisions and obt…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.