Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival.
Ontology highlight
ABSTRACT:
SUBMITTER: Kim S
PROVIDER: S-EPMC8635726 | biostudies-literature | 2021
REPOSITORIES: biostudies-literature
Publications
Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival.
Kim Sunkyu S Lee Choong-Kun CK Choi Yonghwa Y Baek Eun Sil ES Choi Jeong Eun JE Lim Joon Seok JS Kang Jaewoo J Shin Sang Joon SJ
Frontiers in oncology 20211117
Most electronic medical records, such as free-text radiological reports, are unstructured; however, the methodological approaches to analyzing these accumulating unstructured records are limited. This article proposes a deep-transfer-learning-based natural language processing model that analyzes serial magnetic resonance imaging reports of rectal cancer patients and predicts their overall survival. To evaluate the model, a retrospective cohort study of 4,338 rectal cancer patients was conducted. ...[more]
Similar Datasets
Project description:BackgroundIn the era of datafication, it is important that medical data are accurate and structured for multiple applications. Especially data for oncological staging need to be accurate to stage and treat a patient, as well as population-level surveillance and outcome assessment. To support data extraction from free-text radiological reports, Dutch natural language processing (NLP) algorithm was built to quantify T-stage of pulmonary tumors according to the tumor node metastasis (TNM) classification. This structuring tool was translated and validated on English radiological free-text reports. A rule-based algorithm to classify T-stage was trained and validated on, respectively, 200 and 225 English free-text radiological reports from diagnostic computed tomography (CT) obtained for staging of patients with lung cancer. The automated T-stage extracted by the algorithm from the report was compared to manual staging. A graphical user interface was built for training purposes to visualize the results of the algorithm by highlighting the extracted concepts and its modifying context.ResultsAccuracy of the T-stage classifier was 0.89 in the validation set, 0.84 when considering the T-substages, and 0.76 when only considering tumor size. Results were comparable with the Dutch results (respectively, 0.88, 0.89 and 0.79). Most errors were made due to ambiguity issues that could not be solved by the rule-based nature of the algorithm.ConclusionsNLP can be successfully applied for staging lung cancer from free-text radiological reports in different languages. Focused introduction of machine learning should be introduced in a hybrid approach to improve performance.
| S-EPMC8192634 | biostudies-literature
Project description:Reports are the standard way of communication between the radiologist and the referring clinician. Efforts are made to improve this communication by, for instance, introducing standardization and structured reporting. Natural Language Processing (NLP) is another promising tool which can improve and enhance the radiological report by processing free text. NLP as such adds structure to the report and exposes the information, which in turn can be used for further analysis. This paper describes pre-processing and processing steps and highlights important challenges to overcome in order to successfully implement a free text mining algorithm using NLP tools and machine learning in a small language area, like Dutch. A rule-based algorithm was constructed to classify T-stage of pulmonary oncology from the original free text radiological report, based on the items tumor size, presence and involvement according to the 8th TNM classification system. PyContextNLP, spaCy and regular expressions were used as tools to extract the correct information and process the free text. Overall accuracy of the algorithm for evaluating T-stage was 0,83 in the training set and 0,87 in the validation set, which shows that the approach in this pilot study is promising. Future research with larger datasets and external validation is needed to be able to introduce more machine learning approaches and perhaps to reduce required input efforts of domain-specific knowledge. However, a hybrid NLP approach will probably achieve the best results.
| S-EPMC7522136 | biostudies-literature
Project description:ImportanceA 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.ObjectiveTo determine whether deep natural language processing can extract relevant cancer outcomes from radiologic reports, a ubiquitous but unstructured EHR data source.Design, setting, and participantsA 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.ExposuresPatients 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 measuresThe 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.ResultsA 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 relevanceDeep natural language processing appears to speed curation of relevant cancer outcomes and facilitate rapid learning from EHR data.
| S-EPMC6659158 | biostudies-literature
Project description:BackgroundDiagnostic neurovascular imaging data are important in stroke research, but obtaining these data typically requires laborious manual chart reviews.ObjectiveWe aimed to determine the accuracy of a natural language processing (NLP) approach to extract information on the presence and location of vascular occlusions as well as other stroke-related attributes based on free-text reports.MethodsFrom the full reports of 1320 consecutive computed tomography (CT), CT angiography, and CT perfusion scans of the head and neck performed at a tertiary stroke center between October 2017 and January 2019, we manually extracted data on the presence of proximal large vessel occlusion (primary outcome), as well as distal vessel occlusion, ischemia, hemorrhage, Alberta stroke program early CT score (ASPECTS), and collateral status (secondary outcomes). Reports were randomly split into training (n=921) and validation (n=399) sets, and attributes were extracted using rule-based NLP. We reported the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the overall accuracy of the NLP approach relative to the manually extracted data.ResultsThe overall prevalence of large vessel occlusion was 12.2%. In the training sample, the NLP approach identified this attribute with an overall accuracy of 97.3% (95.5% sensitivity, 98.1% specificity, 84.1% PPV, and 99.4% NPV). In the validation set, the overall accuracy was 95.2% (90.0% sensitivity, 97.4% specificity, 76.3% PPV, and 98.5% NPV). The accuracy of identifying distal or basilar occlusion as well as hemorrhage was also high, but there were limitations in identifying cerebral ischemia, ASPECTS, and collateral status.ConclusionsNLP may improve the efficiency of large-scale imaging data collection for stroke surveillance and research.
| S-EPMC8132979 | biostudies-literature
Project description:ObjectivesProvide physicians and researchers an efficient way to extract information from weakly structured radiology reports with natural language processing (NLP) machine learning models.MethodsWe evaluate seven different German bidirectional encoder representations from transformers (BERT) models on a dataset of 857,783 unlabeled radiology reports and an annotated reading comprehension dataset in the format of SQuAD 2.0 based on 1223 additional reports.ResultsContinued pre-training of a BERT model on the radiology dataset and a medical online encyclopedia resulted in the most accurate model with an F1-score of 83.97% and an exact match score of 71.63% for answerable questions and 96.01% accuracy in detecting unanswerable questions. Fine-tuning a non-medical model without further pre-training led to the lowest-performing model. The final model proved stable against variation in the formulations of questions and in dealing with questions on topics excluded from the training set.ConclusionsGeneral domain BERT models further pre-trained on radiological data achieve high accuracy in answering questions on radiology reports. We propose to integrate our approach into the workflow of medical practitioners and researchers to extract information from radiology reports.Clinical relevance statementBy reducing the need for manual searches of radiology reports, radiologists' resources are freed up, which indirectly benefits patients.Key points• BERT models pre-trained on general domain datasets and radiology reports achieve high accuracy (83.97% F1-score) on question-answering for radiology reports. • The best performing model achieves an F1-score of 83.97% for answerable questions and 96.01% accuracy for questions without an answer. • Additional radiology-specific pretraining of all investigated BERT models improves their performance.
| S-EPMC10791738 | biostudies-literature
Project description:Allergic reactions to medication range from mild to severe or even life-threatening. Proper documentation of patient allergy information is critical for safe prescription, avoiding drug interactions, and reducing healthcare costs. Allergy information is regularly obtained during the medical interview, but is often poorly documented in electronic health records (EHRs). While many EHRs allow for structured adverse drug reaction (ADR) reporting, a free-text entry is still common. The resulting information is neither interoperable nor easily reusable for other applications, such as clinical decision support systems and prescription alerts. Current approaches require pharmacists to review and code ADRs documented by healthcare professionals. Recently, the effectiveness of machine algorithms in natural language processing (NLP) has been widely demonstrated. Our study aims to develop and evaluate different NLP algorithms that can encode unstructured ADRs stored in EHRs into institutional symptom terms. Our dataset consists of 79,712 pharmacist-reviewed drug allergy records. We evaluated three NLP techniques: Naive Bayes-Support Vector Machine (NB-SVM), Universal Language Model Fine-tuning (ULMFiT), and Bidirectional Encoder Representations from Transformers (BERT). We tested different general-domain pre-trained BERT models, including mBERT, XLM-RoBERTa, and WanchanBERTa, as well as our domain-specific AllergyRoBERTa, which was pre-trained from scratch on our corpus. Overall, BERT models had the highest performance. NB-SVM outperformed ULMFiT and BERT for several symptom terms that are not frequently coded. The ensemble model achieved an exact match ratio of 95.33%, a F1 score of 98.88%, and a mean average precision of 97.07% for the 36 most frequently coded symptom terms. The model was then further developed into a symptom term suggestion system and achieved a Krippendorff's alpha agreement coefficient of 0.7081 in prospective testing with pharmacists. Some degree of automation could both accelerate the availability of allergy information and reduce the efforts for human coding.
| S-EPMC9352066 | biostudies-literature
Project description:This study aimed to develop Natural Language Processing (NLP) approaches to supplement manual outcome validation, specifically to validate pneumonia cases from chest radiograph reports.We trained one NLP system, ONYX, using radiograph reports from children and adults that were previously manually reviewed. We then assessed its validity on a test set of 5000 reports. We aimed to substantially decrease manual review, not replace it entirely, and so, we classified reports as follows: (1) consistent with pneumonia; (2) inconsistent with pneumonia; or (3) requiring manual review because of complex features. We developed processes tailored either to optimize accuracy or to minimize manual review. Using logistic regression, we jointly modeled sensitivity and specificity of ONYX in relation to patient age, comorbidity, and care setting. We estimated positive and negative predictive value (PPV and NPV) assuming pneumonia prevalence in the source data.Tailored for accuracy, ONYX identified 25% of reports as requiring manual review (34% of true pneumonias and 18% of non-pneumonias). For the remainder, ONYX's sensitivity was 92% (95% CI 90-93%), specificity 87% (86-88%), PPV 74% (72-76%), and NPV 96% (96-97%). Tailored to minimize manual review, ONYX classified 12% as needing manual review. For the remainder, ONYX had sensitivity 75% (72-77%), specificity 95% (94-96%), PPV 86% (83-88%), and NPV 91% (90-91%).For pneumonia validation, ONYX can replace almost 90% of manual review while maintaining low to moderate misclassification rates. It can be tailored for different outcomes and study needs and thus warrants exploration in other settings.
| S-EPMC3811072 | biostudies-literature
Project description:Deep learning (DL) approaches may also inform the analysis of human brain activity. Here, a state-of-art DL tool for natural language processing, the Generative Pre-trained Transformer version 2 (GPT-2), is shown to generate meaningful neural encodings in functional MRI during narrative listening. Linguistic features of word unpredictability (surprisal) and contextual importance (saliency) were derived from the GPT-2 applied to the text of a 12-min narrative. Segments of variable duration (from 15 to 90 s) defined the context for the next word, resulting in different sets of neural predictors for functional MRI signals recorded in 27 healthy listeners of the narrative. GPT-2 surprisal, estimating word prediction errors from the artificial network, significantly explained the neural data in superior and middle temporal gyri (bilaterally), in anterior and posterior cingulate cortices, and in the left prefrontal cortex. GPT-2 saliency, weighing the importance of context words, significantly explained the neural data for longer segments in left superior and middle temporal gyri. These results add novel support to the use of DL tools in the search for neural encodings in functional MRI. A DL language model like the GPT-2 may feature useful data about neural processes subserving language comprehension in humans, including next-word context-related prediction.
| S-EPMC9596412 | biostudies-literature
Project description:AimsStress echocardiography (SE) findings and interpretations are commonly documented in free-text reports. Reusing SE results requires laborious manual reviews. This study aimed to develop and validate an automated method for abstracting SE reports in a large cohort.Methods and resultsThis study included adult patients who had SE within 30 days of their emergency department visit for suspected acute coronary syndrome in a large integrated healthcare system. An automated natural language processing (NLP) algorithm was developed to abstract SE reports and classify overall SE results into normal, non-diagnostic, infarction, and ischaemia categories. Randomly selected reports (n = 140) were double-blindly reviewed by cardiologists to perform criterion validity of the NLP algorithm. Construct validity was tested on the entire cohort using abstracted SE data and additional clinical variables. The NLP algorithm abstracted 6346 consecutive SE reports. Cardiologists had good agreements on the overall SE results on the 140 reports: Kappa (0.83) and intraclass correlation coefficient (0.89). The NLP algorithm achieved 98.6% specificity and negative predictive value, 95.7% sensitivity, positive predictive value, and F-score on the overall SE results and near-perfect scores on ischaemia findings. The 30-day acute myocardial infarction or death outcomes were highest among patients with ischaemia (5.0%), followed by infarction (1.4%), non-diagnostic (0.8%), and normal (0.3%) results. We found substantial variations in the format and quality of SE reports, even within the same institution.ConclusionsNatural language processing is an accurate and efficient method for abstracting unstructured SE reports. This approach creates new opportunities for research, public health measures, and care improvement.
| S-EPMC9779789 | biostudies-literature
Project description:ImportanceClinical text reports from head computed tomography (CT) represent rich, incompletely utilized information regarding acute brain injuries and neurologic outcomes. CT reports are unstructured; thus, extracting information at scale requires automated natural language processing (NLP). However, designing new NLP algorithms for each individual injury category is an unwieldy proposition. An NLP tool that summarizes all injuries in head CT reports would facilitate exploration of large data sets for clinical significance of neuroradiological findings.ObjectiveTo automatically extract acute brain pathological data and their features from head CT reports.Design, setting, and participantsThis diagnostic study developed a 2-part named entity recognition (NER) NLP model to extract and summarize data on acute brain injuries from head CT reports. The model, termed BrainNERD, extracts and summarizes detailed brain injury information for research applications. Model development included building and comparing 2 NER models using a custom dictionary of terms, including lesion type, location, size, and age, then designing a rule-based decoder using NER outputs to evaluate for the presence or absence of injury subtypes. BrainNERD was evaluated against independent test data sets of manually classified reports, including 2 external validation sets. The model was trained on head CT reports from 1152 patients generated by neuroradiologists at the Yale Acute Brain Injury Biorepository. External validation was conducted using reports from 2 outside institutions. Analyses were conducted from May 2020 to December 2021.Main outcomes and measuresPerformance of the BrainNERD model was evaluated using precision, recall, and F1 scores based on manually labeled independent test data sets.ResultsA total of 1152 patients (mean [SD] age, 67.6 [16.1] years; 586 [52%] men), were included in the training set. NER training using transformer architecture and bidirectional encoder representations from transformers was significantly faster than spaCy. For all metrics, the 10-fold cross-validation performance was 93% to 99%. The final test performance metrics for the NER test data set were 98.82% (95% CI, 98.37%-98.93%) for precision, 98.81% (95% CI, 98.46%-99.06%) for recall, and 98.81% (95% CI, 98.40%-98.94%) for the F score. The expert review comparison metrics were 99.06% (95% CI, 97.89%-99.13%) for precision, 98.10% (95% CI, 97.93%-98.77%) for recall, and 98.57% (95% CI, 97.78%-99.10%) for the F score. The decoder test set metrics were 96.06% (95% CI, 95.01%-97.16%) for precision, 96.42% (95% CI, 94.50%-97.87%) for recall, and 96.18% (95% CI, 95.151%-97.16%) for the F score. Performance in external institution report validation including 1053 head CR reports was greater than 96%.Conclusions and relevanceThese findings suggest that the BrainNERD model accurately extracted acute brain injury terms and their properties from head CT text reports. This freely available new tool could advance clinical research by integrating information in easily gathered head CT reports to expand knowledge of acute brain injury radiographic phenotypes.
| S-EPMC9382443 | biostudies-literature