Thyroid Ultrasound Reports: Will the Thyroid Imaging, Reporting, and Data System Improve Natural Language Processing Capture of Critical Thyroid Nodule Features?

Identification of pancreatic cancer risk factors from clinical notes using natural language processing

OBJECTIVES

Screening for pancreatic ductal adenocarcinoma (PDAC) is considered in high-risk individuals (HRIs) with established PDAC risk factors, such as family history and germline mutations in PDAC susceptibility genes. Accurate assessment of risk factor status is provider knowledge-dependent and requires extensive manual chart review by experts. Natural Language Processing (NLP) has shown promise in automated data extraction from the electronic health record (EHR). We aimed to use NLP for automated extraction of PDAC risk factors from unstructured clinical notes in the EHR.

METHODS

We first developed rule-based NLP algorithms to extract PDAC risk factors at the document-level, using an annotated corpus of 2091 clinical notes. Next, we further improved the NLP algorithms using a cohort of 1138 patients through patient-level training, validation, and testing, with comparison against a pre-specified reference standard. To minimize false-negative results we prioritized algorithm recall.

RESULTS

In the test set (n = 807), the NLP algorithms achieved a recall of 0.933, precision of 0.790, and F1-score of 0.856 for family history of PDAC. For germline genetic mutations, the algorithm had a high recall of 0.851, while precision and F1-score were lower at 0.350 and 0.496 respectively. Most false positives for germline mutations resulted from erroneous recognition of tissue mutations.

CONCLUSIONS

Rule-based NLP algorithms applied to unstructured clinical notes are highly sensitive for automated identification of PDAC risk factors. Further validation in a large primary-care patient population is warranted to assess real-world utility in identifying HRIs for pancreatic cancer screening.

Applications of natural language processing tools in the surgical journey

Background

Natural language processing tools are becoming increasingly adopted in multiple industries worldwide. They have shown promising results however their use in the field of surgery is under-recognised. Many trials have assessed these benefits in small settings with promising results before large scale adoption can be considered in surgery. This study aims to review the current research and insights into the potential for implementation of natural language processing tools into surgery.

Methods

A narrative review was conducted following a computer-assisted literature search on Medline, EMBASE and Google Scholar databases. Papers related to natural language processing tools and consideration into their use for surgery were considered.

Results

Current applications of natural language processing tools within surgery are limited. From the literature, there is evidence of potential improvement in surgical capability and service delivery, such as through the use of these technologies to streamline processes including surgical triaging, data collection and auditing, surgical communication and documentation. Additionally, there is potential to extend these capabilities to surgical academia to improve processes in surgical research and allow innovation in the development of educational resources. Despite these outcomes, the evidence to support these findings are challenged by small sample sizes with limited applicability to broader settings.

Conclusion

With the increasing adoption of natural language processing technology, such as in popular forms like ChatGPT, there has been increasing research in the use of these tools within surgery to improve surgical workflow and efficiency. This review highlights multifaceted applications of natural language processing within surgery, albeit with clear limitations due to the infancy of the infrastructure available to leverage these technologies. There remains room for more rigorous research into broader capability of natural language processing technology within the field of surgery and the need for cross-sectoral collaboration to understand the ways in which these algorithms can best be integrated.

Extracting Thyroid Nodules Characteristics from Ultrasound Reports Using Transformer-based Natural Language Processing Methods

The ultrasound characteristics of thyroid nodules guide the evaluation of thyroid cancer in patients with thyroid nodules. However, the characteristics of thyroid nodules are often documented in clinical narratives such as ultrasound reports. Previous studies have examined natural language processing (NLP) methods in extracting a limited number of characteristics (<9) using rule-based NLP systems. In this study, a multidisciplinary team of NLP experts and thyroid specialists, identified thyroid nodule characteristics that are important for clinical care, composed annotation guidelines, developed a corpus, and compared 5 state-of-the-art transformer-based NLP methods, including BERT, RoBERTa, LongFormer, DeBERTa, and GatorTron, for extraction of thyroid nodule characteristics from ultrasound reports. Our GatorTron model, a transformer-based large language model trained using over 90 billion words of text, achieved the best strict and lenient F1-score of 0.8851 and 0.9495 for the extraction of a total number of 16 thyroid nodule characteristics, and 0.9321 for linking characteristics to nodules, outperforming other clinical transformer models. To the best of our knowledge, this is the first study to systematically categorize and apply transformer-based NLP models to extract a large number of clinical relevant thyroid nodule characteristics from ultrasound reports. This study lays ground for assessing the documentation quality of thyroid ultrasound reports and examining outcomes of patients with thyroid nodules using electronic health records.

Multistep Automated Data Labelling Procedure (MADLaP) for thyroid nodules on ultrasound: An artificial intelligence approach for automating image annotation

Machine learning (ML) for diagnosis of thyroid nodules on ultrasound is an active area of research. However, ML tools require large, well-labeled datasets, the curation of which is time-consuming and labor-intensive. The purpose of our study was to develop and test a deep-learning-based tool to facilitate and automate the data annotation process for thyroid nodules; we named our tool Multistep Automated Data Labelling Procedure (MADLaP). MADLaP was designed to take multiple inputs including pathology reports, ultrasound images, and radiology reports. Using multiple step-wise 'modules' including rule-based natural language processing, deep-learning-based imaging segmentation, and optical character recognition, MADLaP automatically identified images of a specific thyroid nodule and correctly assigned a pathology label. The model was developed using a training set of 378 patients across our health system and tested on a separate set of 93 patients. Ground truths for both sets were selected by an experienced radiologist. Performance metrics including yield (how many labeled images the model produced) and accuracy (percentage correct) were measured using the test set. MADLaP achieved a yield of 63 % and an accuracy of 83 %. The yield progressively increased as the input data moved through each module, while accuracy peaked part way through. Error analysis showed that inputs from certain examination sites had lower accuracy (40 %) than the other sites (90 %, 100 %). MADLaP successfully created curated datasets of labeled ultrasound images of thyroid nodules. While accurate, the relatively suboptimal yield of MADLaP exposed some challenges when trying to automatically label radiology images from heterogeneous sources. The complex task of image curation and annotation could be automated, allowing for enrichment of larger datasets for use in machine learning development.

Assessment of Electronic Health Record for Cancer Research and Patient Care Through a Scoping Review of Cancer Natural Language Processing

PURPOSE

The advancement of natural language processing (NLP) has promoted the use of detailed textual data in electronic health records (EHRs) to support cancer research and to facilitate patient care. In this review, we aim to assess EHR for cancer research and patient care by using the Minimal Common Oncology Data Elements (mCODE), which is a community-driven effort to define a minimal set of data elements for cancer research and practice. Specifically, we aim to assess the alignment of NLP-extracted data elements with mCODE and review existing NLP methodologies for extracting said data elements.

METHODS

Published literature studies were searched to retrieve cancer-related NLP articles that were written in English and published between January 2010 and September 2020 from main literature databases. After the retrieval, articles with EHRs as the data source were manually identified. A charting form was developed for relevant study analysis and used to categorize data including four main topics: metadata, EHR data and targeted cancer types, NLP methodology, and oncology data elements and standards.

RESULTS

A total of 123 publications were selected finally and included in our analysis. We found that cancer research and patient care require some data elements beyond mCODE as expected. Transparency and reproductivity are not sufficient in NLP methods, and inconsistency in NLP evaluation exists.

CONCLUSION

We conducted a comprehensive review of cancer NLP for research and patient care using EHRs data. Issues and barriers for wide adoption of cancer NLP were identified and discussed.

Ambiguous and Incomplete: Natural Language Processing Reveals Problematic Reporting Styles in Thyroid Ultrasound Reports

OBJECTIVE

 Natural language processing (NLP) systems convert unstructured text into analyzable data. Here, we describe the performance measures of NLP to capture granular details on nodules from thyroid ultrasound (US) reports and reveal critical issues with reporting language.

METHODS

 We iteratively developed NLP tools using clinical Text Analysis and Knowledge Extraction System (cTAKES) and thyroid US reports from 2007 to 2013. We incorporated nine nodule features for NLP extraction. Next, we evaluated the precision, recall, and accuracy of our NLP tools using a separate set of US reports from an academic medical center (A) and a regional health care system (B) during the same period. Two physicians manually annotated each test-set report. A third physician then adjudicated discrepancies. The adjudicated "gold standard" was then used to evaluate NLP performance on the test-set.

RESULTS

 A total of 243 thyroid US reports contained 6,405 data elements. Inter-annotator agreement for all elements was 91.3%. Compared with the gold standard, overall recall of the NLP tool was 90%. NLP recall for thyroid lobe or isthmus characteristics was: laterality 96% and size 95%. NLP accuracy for nodule characteristics was: laterality 92%, size 92%, calcifications 76%, vascularity 65%, echogenicity 62%, contents 76%, and borders 40%. NLP recall for presence or absence of lymphadenopathy was 61%. Reporting style accounted for 18% errors. For example, the word "heterogeneous" interchangeably referred to nodule contents or echogenicity. While nodule dimensions and laterality were often described, US reports only described contents, echogenicity, vascularity, calcifications, borders, and lymphadenopathy, 46, 41, 17, 15, 9, and 41% of the time, respectively. Most nodule characteristics were equally likely to be described at hospital A compared with hospital B.

CONCLUSIONS

 NLP can automate extraction of critical information from thyroid US reports. However, ambiguous and incomplete reporting language hinders performance of NLP systems regardless of institutional setting. Standardized or synoptic thyroid US reports could improve NLP performance.

Risk Stratifying Indeterminate Thyroid Nodules With Machine Learning

BACKGROUND

Up to 30% of thyroid nodules are classified as indeterminate after fine needle aspiration biopsy. These indeterminate thyroid nodules (ITNs) require surgical pathology for definitive diagnosis. Molecular testing provides additional pre-operative cancer risk stratification but adds expense and invasive testing. The purpose of this study is to utilize a machine learning (ML) algorithm to predict malignancy of ITNs using data available from less invasive tests.

MATERIALS AND METHODS

We conducted a retrospective study using medical records from one academic and one community center. Thyroid nodules with an indeterminate diagnosis on fine needle aspiration biopsy and completed diagnostic pathology were included. Linear, non-linear, and non-linear-ensemble ML methods were tested for accuracy when predicting malignancy using 10-fold cross-validation. Classifiers were evaluated using area under the receiver operating characteristics curve (AUROC).

RESULTS

A total of 355 nodules met inclusion criteria. Of these, 171 (48.2%) were diagnosed with cancer. A Random Forest classifier performed the best, producing an accuracy of 79.1%, a sensitivity of 75.5%, specificity of 82.4%, positive predicative value of 80.3%, negative predictive value of 79.0%, and an AUROC of 0.859.

CONCLUSIONS

ML methods accurately risk stratify ITNs using data gathered from existing, non-invasive, and inexpensive diagnostic tests. Applying an ML model with existing data can become a cost-effective alternative to molecular testing. Future studies will prospectively evaluate the performance of this ML approach when combined with expert judgment.