Dataset Information

Analysis of Hormone Receptor Status in Primary and Recurrent Breast Cancer Via Data Mining Pathology Reports.

ABSTRACT:

Background

Hormone receptors of breast cancer, such as estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (Her-2), are important prognostic factors for breast cancer.

Objective

The current study aimed to develop a method to retrieve the statistics of hormone receptor expression status, documented in pathology reports, given their importance in research for primary and recurrent breast cancer, and quality management of pathology laboratories.

Method

A two-stage text mining approach via regular expression-based word/phrase matching, was developed to retrieve the data.

Results

The method achieved a sensitivity of 98.8%, 98.7% and 98.4% for extraction of ER, PR, and Her-2 results. The hormone expression status from 3679 primary and 44 recurrent breast cancer cases was successfully retrieved with the method. Statistical analysis of these data showed that the recurrent disease had a significantly lower positivity rate for ER (54.5% vs 76.5%, p=0.001278) than primary breast cancer and a higher positivity rate for Her-2 (48.8% vs 16.2%, p=9.79e-8). These results corroborated the previous literature.

Conclusion

Text mining on pathology reports using the developed method may benefit research of primary and recurrent breast cancer.

SUBMITTER: Chang KP

PROVIDER: S-EPMC6401490 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Analysis of Hormone Receptor Status in Primary and Recurrent Breast Cancer Via Data Mining Pathology Reports.

Chang Kai-Po KP Chu Yen-Wei YW Wang John J

Open medicine (Warsaw, Poland) 20190220

<h4>Background</h4>Hormone receptors of breast cancer, such as estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (Her-2), are important prognostic factors for breast cancer.<h4>Objective</h4>The current study aimed to develop a method to retrieve the statistics of hormone receptor expression status, documented in pathology reports, given their importance in research for primary and recurrent breast cancer, and quality management of pathology laborat ...[more]

PMID: 30847396

Similar Datasets

Project description:Background:Polycystic ovary syndrome (PCOS) is characterized by hyperandrogenemia, oligo-anovulation, and numerous ovarian cysts. Hospital electronic medical records provide an avenue for investigating polycystic ovary morphology commonly seen in PCOS at a large scale. The purpose of this study was to develop and evaluate the performance of two machine learning text algorithms, for classification of polycystic ovary morphology (PCOM) in pelvic ultrasounds. Methods:Pelvic ultrasound reports from patients at Boston Medical Center between October 1, 2003 and December 12, 2016 were included for analysis, which resulted in 39,093 ultrasound reports from 25,535 unique women. Following the 2003 Rotterdam Consensus Criteria for polycystic ovary syndrome, 2000 randomly selected ultrasounds were expert labeled for PCOM status as present, absent, or unidentifiable (not able to be determined from text alone). An ovary was marked as having PCOM if there was mention of numerous peripheral follicles or if the volume was greater than 10?ml in the absence of a dominant follicle or other confounding pathology. Half of the labeled data was used to develop and refine the algorithms, and the other half was used as a test set for evaluating its accuracy. Results:On the evaluation set of 1000 random US reports, the accuracy of the classifiers were 97.6% (95% CI: 96.5, 98.5%) and 96.1% (94.7, 97.2%). Both models were more adept at identifying PCOM-absent ultrasounds than either PCOM-unidentifiable or PCOM-present ultrasounds. The two classifiers estimated prevalence of PCOM within the whole set of 39,093 ultrasounds to be 44% PCOM-absent, 32% PCOM-unidentifiable, and 24% PCOM-present. Conclusions:Although accuracy measured on the test set and inter-rater agreement between the two classifiers (Cohen's Kappa?=?0.988) was high, a major limitation of our approach is that it uses the ultrasound report text as a proxy and does not directly count follicles from the ultrasound images themselves.

Project description:We examined whether differences in tumor DNA methylation were associated with more aggressive hormone receptor-negative breast cancer in an ethnically diverse group of patients in the Breast Cancer Care in Chicago (BCCC) study and using data from The Cancer Genome Atlas (TCGA).DNA was extracted from formalin-fixed, paraffin-embedded samples on 75 patients (21 White, 31 African-American, and 23 Hispanic) (training dataset) enrolled in the BCCC. Hormone receptor status was defined as negative if tumors were negative for both estrogen and progesterone (ER/PR) receptors (N?=?22/75). DNA methylation was analyzed at 1505 CpG sites within 807 gene promoters using the Illumina GoldenGate assay. Differential DNA methylation as a predictor of hormone receptor status was tested while controlling for false discovery rate and assigned to the gene closest to the respective CpG site. Next, those genes that predicted ER/PR status were validated using TCGA data with respect to DNA methylation (validation dataset), and correlations between CpG methylation and gene expression were examined. In the training dataset, 5.7 % of promoter mean methylation values (46/807) were associated with receptor status at P?<?0.05; for 88 % of these (38/46), hypermethylation was associated with receptor-positive disease. Hypermethylation for FZD9, MME, BCAP31, HDAC9, PAX6, SCGB3A1, PDGFRA, IGFBP3, and PTGS2 genes most strongly predicted receptor-positive disease. Twenty-one of 24 predictor genes from the training dataset were confirmed in the validation dataset. The level of DNA methylation at 19 out 22 genes, for which gene expression data were available, was associated with gene activity.Higher levels of promoter methylation strongly correlate with hormone receptor positive status of breast tumors. For most of the genes identified in our training dataset as ER/PR receptor status predictors, DNA methylation correlated with stable gene expression level. The predictors performed well when evaluated on independent set of samples, with different racioethnic distribution, thus providing evidence that this set of DNA methylation biomarkers will likely generalize to prospective patient samples.

Dataset Information

Analysis of Hormone Receptor Status in Primary and Recurrent Breast Cancer Via Data Mining Pathology Reports.

Background

Objective

Method

Results

Conclusion

Publications

Analysis of Hormone Receptor Status in Primary and Recurrent Breast Cancer Via Data Mining Pathology Reports.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets