Background: Computed tomography (CT) is commonly performed when evaluating trauma patients with up to 55% showing incidental findings. Current workflows to identify and inform patients are time-consuming and prone to error. Our objective was to automatically identify thyroid and adrenal lesions in radiology reports using deep learning.
Materials And Methods: All trauma patients who presented to an accredited Level 1 Trauma Center between January 2008 and January 2019 were included. Radiology reports of CT scans that included either a thyroid or adrenal gland were obtained. Preprocessing included word tokenization, removal of stop words, removal of punctuation, and replacement of misspellings. A word2vec model was trained using 1.4 million radiology reports. Both training and testing reports were selected at random, manually reviewed, and were considered the gold standard. True positive cases were defined as any lesions in the thyroid or adrenal gland, respectively. Training data was used to create models that would identify reports that contained either thyroid or adrenal lesions. Our primary outcomes were sensitivity and specificity of the models using predetermined thresholds on a separate testing dataset.
Results: A total of 51,771 reports were identified on 35,859 trauma patients. A total of 1,789 reports were annotated for training and 500 for testing. The thyroid model predictions resulted in a 90.0% sensitivity and 95.3% specificity. The adrenal model predictions resulted in a 92.3% sensitivity and a 91.1% specificity. A total of 240 reports were confirmed to have thyroid incidentals (mean age 69.1 yrs ± 18.9, 35% M) and 214 reports with adrenal incidentals (mean age 68.7 yrs ± 16.9, 50.5% M).
Conclusions: Both the thyroid and adrenal models have excellent performance with sensitivities and specificities in the 90s. Our deep learning model has the potential to reduce administrative costs and improve the process of informing patients.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jss.2021.03.060 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Transformation of lung adenocarcinoma to small cell lung cancer following osimertinib treatment: a case report and literature review.
Anticancer Drugs
January 2025
Department of Thoracic Surgery, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
Epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitors (TKIs) effectively treat EGFR-mutant lung adenocarcinoma, demonstrating initial efficacy but eventually leading to acquired resistance. Small cell transformation is a rare resistance mechanism to EGFR-TKIs in lung adenocarcinoma, which can complicate clinical diagnosis and treatment. We present a patient with lung adenocarcinoma who underwent a prior pneumonectomy and adjuvant chemotherapy and was treated with osimertinib after the recurrence of lung cancer.
View Article and Find Full Text PDFManagement, biomarkers and prognosis in people developing endocrinopathies associated with immune checkpoint inhibitors.
Nat Rev Endocrinol
January 2025
Department of Endocrinology and Diabetes, Nagoya University Graduate School of Medicine, Nagoya, Japan.
Immune-related adverse events (irAEs), including endocrine irAEs, can occur in response to cancer immunotherapy using immune checkpoint inhibitors (ICIs). Of the endocrine irAEs, pituitary and thyroid irAEs are most frequently observed, followed by primary adrenal insufficiency, type 1 diabetes mellitus and hypoparathyroidism. Notably, pituitary irAEs and type 1 diabetes mellitus can be lethal if overlooked, potentially leading to adrenal crisis and diabetic ketoacidosis, respectively.
View Article and Find Full Text PDFThe impact of immune-related adverse events on the outcome of advanced gastric cancer patients with immune checkpoint inhibitor treatment.
Front Immunol
January 2025
Department of Rheumatology and Immunology, The Fourth Hospital of Hebei Medical University, Shijiazhuang, China.
Background: The occurrence of immune-related adverse events (irAEs) seemed to be associated with better outcomes in advanced gastric cancer (AGC) patients. However, research focusing on the impact of the single-organ irAE (uni-irAE) or multi-organ irAEs (multi-irAEs) on the AGC outcome is relatively limited. In this study, we investigated individually the impact of the different irAEs on AGC survival as well as the co-occurrence patterns of multi-irAEs.
View Article and Find Full Text PDFA clinical challenge: delayed diagnosis of autoimmune polyglandular syndrome type II in a patient with thyroid eye disease.
Orbit
January 2025
Department of Ophthalmology and Visual Sciences, Roy J. and Lucille A. Carver College of Medicine, University of Iowa, Iowa City, Iowa, USA.
A 35-year-old woman with thyroid eye disease (TED) was found to have autoimmune polyglandular syndrome type II (APS-II) 1 year after developing symptoms of this rare syndrome, during which she underwent 8 emergency department visits before receiving a targeted endocrinology workup. Thyroid disease is the second most common autoimmune syndrome associated with APS-II after primary adrenal insufficiency. Identification of this syndrome is critical as it can be life-threatening if left untreated.
View Article and Find Full Text PDFPediatric Endocrinology Education Among Trainees: A Scoping Review.
Clin Teach
February 2025
Department of Pediatrics, McMaster University, Hamilton, Ontario, Canada.
Introduction: Pediatric endocrinology education is a fundamental part of all pediatric endocrinology training. Hence, understanding the current methods used for training learners on skills required and understanding methods or topics that may be underexplored could help improve the quality of training.
Objective: This study aims to explore training and assessment strategies used in pediatric endocrinology training across medical education programs through a scoping review.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!