Kelly Daniels1, Sriharsha Gummadi2,3, Ziyin Zhu4, Shuo Wang2, Jena Patel5, Brian Swendseid5, Andrej Lyshchik2, Joseph Curry5, Elizabeth Cottrill5, John Eisenbrey2. 1. Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, Pennsylvania. 2. Department of Radiology, Thomas Jefferson University, Philadelphia, Pennsylvania. 3. Department of Surgery, Lankenau Medical Center, Wynnewood, Pennsylvania. 4. Beijing Friendship Hospital, Capital Medical University, Beijing, China. 5. Department of Otolaryngology-Head and Neck Surgery, Thomas Jefferson University, Philadelphia, Pennsylvania.
Abstract
Importance: Thyroid nodules are common incidental findings. Ultrasonography and molecular testing can be used to assess risk of malignant neoplasm. Objective: To examine whether a model developed through automated machine learning can stratify thyroid nodules as high or low genetic risk by ultrasonography imaging alone compared with stratification by molecular testing for high- and low-risk mutations. Design, Setting, and Participants: This diagnostic study was conducted at a single tertiary care urban academic institution and included patients (n = 121) who underwent ultrasonography and molecular testing for thyroid nodules from January 1, 2017, through August 1, 2018. Nodules were classified as high risk or low risk on the basis of results of an institutional molecular testing panel for thyroid risk genes. All thyroid nodules that underwent genetic sequencing for cytological results with Bethesda System categories III and IV were reviewed. Patients without diagnostic ultrasonographic images within 6 months of fine-needle aspiration or who received definitive treatment at an outside medical center were excluded. Main Outcomes and Measures: Thyroid nodules were categorized by the model as high risk or low risk using ultrasonographic images. Results were compared using genetic testing. Results: Among the 134 lesions identified in 121 patients (mean [SD] age, 55.7 [14.2] years; 102 women [84.3%]), 683 diagnostic ultrasonographic images were selected. Of the 683 images, 556 (81.4%) were used for training the model, 74 (10.8%) for validation, and 53 (7.8%) for testing. Most nodules had no mutation (75 [56.0%]), whereas 43 nodules (32.1%) had a high-risk mutation and 16 (11.9%) had an unknown or a low-risk mutation (χ2 = 39.060; P < .001). In total, 228 images (33.4%) were of nodules classified as genetically high risk (n = 43), and 455 (66.6%) were of low-risk nodules (n = 91). The model performed with a sensitivity of 45% (95% CI, 23.1%-68.5%), a specificity of 97% (95% CI, 84.2%-99.9%), a positive predictive value of 90% (95% CI, 55.2%-98.5%), a negative predictive value of 74.4% (95% CI, 66.1%-81.3%), and an overall accuracy of 77.4% (95% CI, 63.8%-97.7%). Conclusions and Relevance: The study found that the model developed through automated machine learning could produce high specificity for identifying nodules with high-risk mutations on molecular testing. This finding shows promise for the diagnostic applications of machine learning interpretation of sonographic imaging of indeterminate thyroid nodules.
Importance: Thyroid nodules are common incidental findings. Ultrasonography and molecular testing can be used to assess risk of malignant neoplasm. Objective: To examine whether a model developed through automated machine learning can stratify thyroid nodules as high or low genetic risk by ultrasonography imaging alone compared with stratification by molecular testing for high- and low-risk mutations. Design, Setting, and Participants: This diagnostic study was conducted at a single tertiary care urban academic institution and included patients (n = 121) who underwent ultrasonography and molecular testing for thyroid nodules from January 1, 2017, through August 1, 2018. Nodules were classified as high risk or low risk on the basis of results of an institutional molecular testing panel for thyroid risk genes. All thyroid nodules that underwent genetic sequencing for cytological results with Bethesda System categories III and IV were reviewed. Patients without diagnostic ultrasonographic images within 6 months of fine-needle aspiration or who received definitive treatment at an outside medical center were excluded. Main Outcomes and Measures: Thyroid nodules were categorized by the model as high risk or low risk using ultrasonographic images. Results were compared using genetic testing. Results: Among the 134 lesions identified in 121 patients (mean [SD] age, 55.7 [14.2] years; 102 women [84.3%]), 683 diagnostic ultrasonographic images were selected. Of the 683 images, 556 (81.4%) were used for training the model, 74 (10.8%) for validation, and 53 (7.8%) for testing. Most nodules had no mutation (75 [56.0%]), whereas 43 nodules (32.1%) had a high-risk mutation and 16 (11.9%) had an unknown or a low-risk mutation (χ2 = 39.060; P < .001). In total, 228 images (33.4%) were of nodules classified as genetically high risk (n = 43), and 455 (66.6%) were of low-risk nodules (n = 91). The model performed with a sensitivity of 45% (95% CI, 23.1%-68.5%), a specificity of 97% (95% CI, 84.2%-99.9%), a positive predictive value of 90% (95% CI, 55.2%-98.5%), a negative predictive value of 74.4% (95% CI, 66.1%-81.3%), and an overall accuracy of 77.4% (95% CI, 63.8%-97.7%). Conclusions and Relevance: The study found that the model developed through automated machine learning could produce high specificity for identifying nodules with high-risk mutations on molecular testing. This finding shows promise for the diagnostic applications of machine learning interpretation of sonographic imaging of indeterminate thyroid nodules.
Authors: Paul A Harris; Robert Taylor; Robert Thielke; Jonathon Payne; Nathaniel Gonzalez; Jose G Conde Journal: J Biomed Inform Date: 2008-09-30 Impact factor: 6.317
Authors: Franklin N Tessler; William D Middleton; Edward G Grant; Jenny K Hoang; Lincoln L Berland; Sharlene A Teefey; John J Cronan; Michael D Beland; Terry S Desser; Mary C Frates; Lynwood W Hammers; Ulrike M Hamper; Jill E Langer; Carl C Reading; Leslie M Scoutt; A Thomas Stavros Journal: J Am Coll Radiol Date: 2017-04-02 Impact factor: 5.532
Authors: Bryan R Haugen; Erik K Alexander; Keith C Bible; Gerard M Doherty; Susan J Mandel; Yuri E Nikiforov; Furio Pacini; Gregory W Randolph; Anna M Sawka; Martin Schlumberger; Kathryn G Schuff; Steven I Sherman; Julie Ann Sosa; David L Steward; R Michael Tuttle; Leonard Wartofsky Journal: Thyroid Date: 2016-01 Impact factor: 6.568
Authors: Yuri E Nikiforov; Sally E Carty; Simon I Chiosea; Christopher Coyne; Umamaheswar Duvvuri; Robert L Ferris; William E Gooding; Steven P Hodak; Shane O LeBeau; N Paul Ohori; Raja R Seethala; Mitchell E Tublin; Linwah Yip; Marina N Nikiforova Journal: Cancer Date: 2014-09-10 Impact factor: 6.860
Authors: Salvatore Sciacchitano; Luca Lavra; Alessandra Ulivieri; Fiorenza Magi; Gian Paolo De Francesco; Carlo Bellotti; Leila B Salehi; Maria Trovato; Carlo Drago; Armando Bartolazzi Journal: Oncotarget Date: 2017-07-25
Authors: Shuo Wang; Jiajun Xu; Aylin Tahmasebi; Kelly Daniels; Ji-Bin Liu; Joseph Curry; Elizabeth Cottrill; Andrej Lyshchik; John R Eisenbrey Journal: Front Oncol Date: 2020-11-12 Impact factor: 6.244