Automatic Extraction of Breast Cancer Information from Clinical Reports

Clinical Data Extraction and Normalization of Cyrillic Electronic Health Records Via Deep-Learning Natural Language Processing

“…2 One study achieved only 69% accuracy for extracting hormonal status. 3 Alternatively, machine learning or natural language processing (NLP)–based data extraction 4-6 has been applied with varying degrees of accuracy. Most use classical machine learning classifiers (eg, support vector machines [SVMs], decision trees) as individual models or as part of ensemble models.…”

A frame semantic overview of NLP-based information extraction for cancer-related EHR notes

“…Frame Elements References CANCER DIAGNOSIS NAME: cancer type [44], [45], [42], [46], [47], [48], [49], [50], [51] ANATOMICAL SITE: the location description of the finding (including primary and metastatic sites) [45], [52], [42], [53], [54], [55], [25], [27], [56], [57] HISTOLOGY: histological description (e.g. carcinoma) [44], [52], [58], [55], [53], [54], [4], [27], [59], [43], [57] GRADE: appearance of the cancerous cells, can be frame with further information (GRADING VALUE) [44], [52], [54], [4], [48], [27], [59], [60], [43], [61], [62] INVASION TYPE: the stage or level of invasion [52] TUMOR BLOCK: tissue cores removed from regions of interest in paraffinembedded tissues (e.g. 0.6 mm in diameter) [52] TISSUE BANK: identifiers about location of tissue samples within an institution [52...…”

“…0.6 mm in diameter) [52] TISSUE BANK: identifiers about location of tissue samples within an institution [52] STATUS: whether confirmed, suspected and there is no evidence of finding (e.g. probable, definite, without) [42], [57] RECURRENT STATUS: the value of recurrent status [42], [63], [57] TEMPORAL INFORMATION: refers to information about time (e.g., year, month, and date, 2007-08-04) [42], [57] SPECIMEN TYPE: the type of specimen involved in diagnosis [53] LATERALITY: describes the side of a paired organ associated with origin of the primary cancer [53], [54], [25], [48], [64], [27], [51] TUMOR SIZE: how large across the tumor is at its widest point (part of cancer staging) [52], [53], [54], [25], [48], [65], [59], [60], [62], [57] TNM STAGE: cancer staging system, can be a separate frame with further information (TNM CLASSIFICATION) [55], [53], [2], [3], [25], [66], [67], [60], [50], [40], [61] EXTENSION: direct extension of tumor [53] UNCERTAINTY: used to differentiate clinical suspicions from conclusive findings (e.g., possible, likely) [68],…”

“…VALUE: the distance between the upper layer of the epidermis and the deepest point of tumor penetration [5] GLEASON SCORE SCORE: grading system used to determine the aggressiveness of prostate cancer [5], [68], [76] ASSESSMENT FOR PROSTATE CANCER SURGERY CANCER PROCEDURE NAME: name of the procedure/test (e.g. chest x-ray) [6], [79], [80], [75], [71], [81], [15], [1], [9], [82], [83], [60], [50], [43]…”

“…Frame Elements References STAGE: AJCC stage designation (e.g., T1, N1b) [2], [3], [25], [66], [60], [50], [40], [61] TIMING: used to indicate if the staging is clinical or pathological as per the rules of the AJCC manual [2], [3], [25], [66], [50], [40] NEGATION: any negated mention [2] TEMPORALITY: capture historical or future mentions that do not necessarily represent current mentions valid at the point in time when the mention was stated at the patient record [2] SUBJECT INVOLVED: capture TNM mentions related to family relatives or others [2] PERFORMANCE STATUS NAME: name of the performance status scale, used as a prognostic tool (e.g. ECOG, Karnofsky) [55], [40] SCORE: measure of functional status (ECOG score ranges from 0-5, whereas Karnofsky Scale' ranges from 0-100) [40] DIAGNOSTIC PROCEDURE PROCEDURE RESULT: result of a procedure mentioned in the report (e.g., Calcifications, hyperplasia etc.)…”