Supervised Machine Learning Algorithm for Detecting Consistency between Reported Findings and the Conclusions of Mammography Reports

TL;DR

This paper presents a supervised machine learning system that automatically detects discrepancies between mammography report findings and conclusions by classifying reports into BI-RADS categories and assessing semantic similarity.

Contribution

It introduces a novel approach combining term normalization, classification, and semantic similarity to identify inconsistencies in mammography reports.

Findings

97% accuracy in BI-RADS descriptor identification

76% precision and 83% recall in report classification

Effective detection of report-conclusion discrepancies

Abstract

Objective. Mammography reports document the diagnosis of patients' conditions. However, many reports contain non-standard terms (non-BI-RADS descriptors) and incomplete statements, which can lead to conclusions that are not well-supported by the reported findings. Our aim was to develop a tool to detect such discrepancies by comparing the reported conclusions to those that would be expected based on the reported radiology findings. Materials and Methods. A deidentified data set from an academic hospital containing 258 mammography reports supplemented by 120 reports found on the web was used for training and evaluation. Spell checking and term normalization was used to unambiguously determine the reported BI-RADS descriptors. The resulting data were input into seven classifiers that classify mammography reports, based on their Findings sections, into seven BI-RADS final assessment categories. Finally, the semantic similarity score of a report to each BI-RADS category is reported. Results. Our term normalization algorithm correctly identified 97% of the BI-RADS descriptors in mammography reports. Our system provided 76% precision and 83% recall in correctly classifying the reports according to BI-RADS final assessment category. Discussion. The strength of our approach relies on providing high importance to BI-RADS terms in the summarization phase, on the semantic similarity that considers the complex data representation, and on the classification into all seven BI-RADs categories. Conclusion. BI-RADS descriptors and expected final assessment categories could be automatically detected by our approach with fairly good accuracy, which could be used to make users aware that their reported findings do not match well with their conclusion.