From free-text electronic health records to structured cohorts: Onconum, an innovative methodology for real-world data mining in breast cancer.

PURPOSE: A considerable amount of valuable information is present in electronic health records (EHRs) however it remains inaccessible because it is embedded into unstructured narrative documents that cannot be easily analyzed. We wanted to develop and evaluate a methodology able to extract and structure information from electronic health records in breast cancer. METHODS: We developed a software platform called Onconum (ClinicalTrials.gov Identifier: NCT02810093) which uses a hybrid method relying on machine learning approaches and rule-based lexical methods. It is based on natural language processing techniques that allows a targeted analysis of free-text medical data related to breast cancer, independently of any pre-existing dictionary, in a French context (available in N files). We then evaluated it on a validation cohort called Senometry. FINDINGS: Senometry cohort included 9,599 patients with breast cancer (both invasive and in situ), treated between 2000 and 2017 in the breast cancer unit of Strasbourg University Hospitals. Extraction rates ranged from 45 to 100%, depending on the type of each parameter. Precision of extracted information was 68%-94% compared to a structured cohort, and 89%-98% compared to manually structured databases and it retrieved more rare occurrences compared to another database search engine (+17%). INTERPRETATION: This innovative method can accurately structure relevant medical information embedded in EHRs in the context of breast cancer. Missing data handling is the main limitation of this method however multiple sources can be incorporated to reduce this limit. Nevertheless, this methodology does not need neither pre-existing dictionaries nor manually annotated corpora. It can therefore be easily implemented in non-English-speaking countries and in other diseases outside breast cancer, and it allows prospective inclusion of new patients.

Relevance of breast MRI in determining the size and focality of invasive breast cancer treated by mastectomy: a prospective study.

BACKGROUND: The aim of this study was the evaluation of breast MRI in determining the size and focality of invasive non-metastatic breast cancers. METHODS: The prospective, single-centre study conducted in 2015 compared preoperative MRI with histological analysis of mastectomy. RESULTS: One hundred one mastectomies from 98 patients were extensively analysed. The rates of false-positive and false-negative MRI were 2 and 4% respectively. The sensitivity of breast MRI was 84.7% for the detection of all invasive foci, 69% for single foci and 65.7% for multiple foci. In the evaluation of tumour size, the Spearman rank correlation coefficient r between the sizes obtained by MRI and histology was 0.62. The MRI-based prediction of a complete response to neoadjuvant chemotherapy was 75%. DISCUSSION: MRI exhibits high sensitivity in the detection of invasive breast cancers. False positives were linked to the inflammatory nature of the tumour bed. False negatives were associated with small or low-grade tumours and their retro-areolar location. The size of T1 tumours was overestimated by an average of 7%, but MRI was the most efficient procedure. The sensitivity of MRI for the diagnosis of unifocal tumours was higher than that for multifocal sites. Our study confirmed the positive contribution of preoperative MRI for invasive lobular carcinomas and complete response predictions after neoadjuvant chemotherapy.