Assessment of Deep Natural Language Processing in Ascertaining Oncologic Outcomes From Radiology Reports

Abstract

IMPORTANCE A rapid learning health care system for oncology will require scalable methods for extracting clinical end points from electronic health records (EHRs). Outside of clinical trials, end points such as cancer progression and response are not routinely encoded into structured data. OBJECTIVE To determine whether deep natural language processing can extract relevant cancer outcomes from radiologic reports, a ubiquitous but unstructured EHR data source. DESIGN, SETTING, AND PARTICIPANTS A retrospective cohort study evaluated 1112 patients who underwent tumor genotyping for a diagnosis of lung cancer and participated in the Dana-Farber Cancer Institute PROFILE study from June 26, 2013, to July 2, 2018. EXPOSURES Patients were divided into curation and reserve sets. Human abstractors applied a structured framework to radiologic reports for the curation set to ascertain the presence of cancer and changes in cancer status over time (ie, worsening/progressing vs improving/responding). Deep learning models were then trained to capture these outcomes from report text and subsequently evaluated in a 10% held-out test subset of curation patients. Cox proportional hazards regression models compared human and machine curations of disease-free survival, progression-free survival, and time to improvement/ response in the curation set, and measured associations between report classification and overall survival in the curation and reserve sets. MAIN OUTCOMES AND MEASURES The primary outcome was area under the receiver operating characteristic curve (AUC) for deep learning models; secondary outcomes were time to improvement/response, disease-free survival, progression-free survival, and overall survival. RESULTS A total of 2406 patients were included (mean [SD] age, 66.5 [10.8] years; 1428 female [59.7%]; 2170 [90.2%] white). Radiologic reports (n = 14 230) were manually reviewed for 1112 patients in the curation set. In the test subset (n = 109), deep learning models identified the presence of cancer, improvement/response, and worsening/ progression with accurate discrimination (AUC >0.90). Machine and human curation yielded similar measurements of disease-free survival (hazard ratio [HR] for machine vs human curation, 1.18; 95% CI, 0.71-1.95); progression-free survival (HR, 1.11; 95% CI, 0.71-1.71); and time to improvement/response (HR, 1.03; 95% CI, 0.65-1.64). Among 15 000 additional reports for 1294 reserve set patients, algorithm-detected cancer worsening/progression was associated with decreased overall survival (HR for mortality, 4.04; 95% CI, 2.78-5.85), and improvement/response was associated with increased overall survival (HR, 0.41; 95% CI, 0.22-0.77). CONCLUSIONS AND RELEVANCE Deep natural language processing appears to speed curation of relevant cancer outcomes and facilitate rapid learning from EHR data.

Knowledge Mapping of Drug-Induced Liver Injury: A Scientometric Investigation (2010–2019)

“…For example, the possibility of homonyms of authors would not be excluded, but these data cannot be obtained accurately by these existing tools. These problems may be solved in the future with the development of machine learning, natural language processing, and data science (Kehl et al, 2019). Lastly, the publications in 2020 were not included because of the inadequate data.…”

Natural language processing for abstraction of cancer treatment toxicities: accuracy versus human experts

“… 20 Separate from semantically extracting information from notes, other recent studies have focused on the use of aggregate data for outcome prediction. 8 , 21 …”

“…Accurate extraction of clinical elements from the free text may offer refined and rational features for predictive models, building on studies where aggregate text provided utility in predicting clinical outcomes. 8 , 21 Our team recently completed one of the first prospective, randomized studies of machine learning, utilizing EHR data to generate accurate predictions of acute care, and direct supportive care. 12 NLP offers an additional source of insights from routine clinical data that may augment its performance for clinical decision support.…”

“… 5–7 Continued evolutions in machine learning such as deep learning have subsequently facilitated specific use-cases where underlying patterns in text can be associated directly with specific concepts, such as clinical outcomes. 8 …”

A Natural Language Processing Pipeline of Chinese Free-Text Radiology Reports for Liver Cancer Diagnosis

“…NLP-based feature extraction has advantages for massive text processing compared with timeconsuming manual extraction flow. Hence, NLP-based feature extraction has been effectively used in radiology for diagnostic surveillance, cohort building, quality assessment, and clinical support services [8][9][10][11]. Nevertheless, previous NLP studies of radiology reports primarily focused on documents written in English.…”