Dataset Information

Machine Learning by Ultrasonography for Genetic Risk Stratification of Thyroid Nodules.

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 (?2?=?39.060; P?

SUBMITTER: Daniels K

PROVIDER: S-EPMC6813575 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning by Ultrasonography for Genetic Risk Stratification of Thyroid Nodules.

Daniels Kelly K Gummadi Sriharsha S Zhu Ziyin Z Wang Shuo S Patel Jena J Swendseid Brian B Lyshchik Andrej A Curry Joseph J Cottrill Elizabeth E Eisenbrey John J

JAMA otolaryngology-- head & neck surgery 20200101 1

<h4>Importance</h4>Thyroid nodules are common incidental findings. Ultrasonography and molecular testing can be used to assess risk of malignant neoplasm.<h4>Objective</h4>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.<h4>Design, setting, and participants</h4>This diagnostic study was conducted at a ...[more]

PMID: 31647509

Similar Datasets

Project description:IntroductionThyroid ultrasound (US) is crucial for clinical decision in the management of thyroid nodules. In this cross-sectional study, we aimed to test if the evaluation of thyroid nodules' vascularization could improve the risk stratification ability of the American College of Radiology (ACR) TI-RADS classification system.MethodsA total of 873 thyroid nodules undergoing fine-needle aspiration were classified according to ACR TI-RADS US classification. Three types of vascularization were identified: type 0, no vascular signals; type 1, peripheral vascular signals; type 2, peripheral and intralesional vascular signals. Cytology specimens were evaluated conforming to the Italian Reporting System for Thyroid Cytology, and TIR3b, TIR4, and TIR5 were defined as high risk for malignancy. Odds ratios (ORs) with 95% confidence intervals (CI) and the areas under the receiver operating characteristic curves (ROC-AUC) for high-risk cytology categories were calculated.ResultsThe 3 vascular patterns were differently distributed within the cytology categories: 52.4% of TIR1c, 15.9% of TIR2, 5.9% of TIR3a, 6.7% of TIR3b, 12.5% of TIR4, and 28.9% of TIR5 nodules had no vascular signals (p < 0.001). Nodule vascularity alone was not associated with a higher risk of malignant cytology (OR [95% CI] 0.75 [0.43-1.32], p = 0.32), without differences between peripheral (OR [95% CI] 0.65 [0.35-1.20]) and intranodular (OR [95% CI] 0.88 [0.48-1.62]) vascularization (p = 0.22). The ROC-AUC (95% CI) for the diagnosis of malignant cytology was similar when considering TI-RADS classification alone (0.736 [0.684-0.786]) and when considering TI-RADS classification plus the presence/absence of vascular signals (0.736 [0.683-0.789], p value for differences between the ROC-AUCs: 0.91). Among TR1, TR2, and TR3 TI-RADS classes, no nodules without vascular signals showed a malignant cytology, allowing the identification of nodules with benign cytology with 100% specificity within these US classes.ConclusionsColor Doppler study of thyroid nodules does not improve the risk stratification ability of the ACR TI-RADS US classification system.

Project description:BackgroundPapillary thyroid cancer (PTC) is one of the most common endocrine malignancies with different risk levels. However, preoperative risk assessment of PTC is still a challenge in the worldwide. Here, we first report a Preoperative Risk Assessment Classifier for PTC (PRAC-PTC) by multidimensional features including clinical indicators, immune indices, genetic feature, and proteomics.Materials and methodsThe 558 patients collected from June 2013 to November 2020 were allocated to three groups: discovery set (274 patients, 274 FFPE), retrospective test set (166 patients, 166 FFPE) and prospective test set (118 patients, 118 FNA). Proteomic profiling was conducted by formalin-fixed paraffin-embedded (FFPE) and fine-needle aspiration (FNA) tissues from the patients. Preoperative clinical information and blood immunological indices were collected. The BRAFV600E mutation were detected by the amplification refractory mutation system (ARMS).ResultsWe developed a machine learning model of 17 variables based on multidimensional features of 274 PTC patients from a retrospective cohort. The PRAC-PTC achieved areas under the curve (AUC) of 0.925 in the discovery set and validated externally by blinded analyses in a retrospective cohort of 166 PTC patients (0.787 AUC) and a prospective cohort of 118 PTC patients (0.799 AUC) from two independent clinical centres. Meanwhile, the preoperative predictive risk effectiveness of clinicians was improved with the assistance of PRAC-PTC, and the accuracies reached at 84.4% (95% CI 82.9-84.4) and 83.5% (95% CI 82.2-84.2) in the retrospective and prospective test sets, respectively.ConclusionThis study demonstrated that the PRAC-PTC that integrating clinical data, gene mutation information, immune indices, high-throughput proteomics and machine learning technology in multi-centre retrospective and prospective clinical cohorts can effectively stratify the preoperative risk of PTC and may decrease unnecessary surgery or overtreatment.

Project description:Diabetes mellitus is a group of metabolic diseases in which blood sugar levels are too high. About 8.8% of the world was diabetic in 2017. It is projected that this will reach nearly 10% by 2045. The major challenge is that when machine learning-based classifiers are applied to such data sets for risk stratification, leads to lower performance. Thus, our objective is to develop an optimized and robust machine learning (ML) system under the assumption that missing values or outliers if replaced by a median configuration will yield higher risk stratification accuracy. This ML-based risk stratification is designed, optimized and evaluated, where: (i) the features are extracted and optimized from the six feature selection techniques (random forest, logistic regression, mutual information, principal component analysis, analysis of variance, and Fisher discriminant ratio) and combined with ten different types of classifiers (linear discriminant analysis, quadratic discriminant analysis, naïve Bayes, Gaussian process classification, support vector machine, artificial neural network, Adaboost, logistic regression, decision tree, and random forest) under the hypothesis that both missing values and outliers when replaced by computed medians will improve the risk stratification accuracy. Pima Indian diabetic dataset (768 patients: 268 diabetic and 500 controls) was used. Our results demonstrate that on replacing the missing values and outliers by group median and median values, respectively and further using the combination of random forest feature selection and random forest classification technique yields an accuracy, sensitivity, specificity, positive predictive value, negative predictive value and area under the curve as: 92.26%, 95.96%, 79.72%, 91.14%, 91.20%, and 0.93, respectively. This is an improvement of 10% over previously developed techniques published in literature. The system was validated for its stability and reliability. RF-based model showed the best performance when outliers are replaced by median values.

Dataset Information

Machine Learning by Ultrasonography for Genetic Risk Stratification of Thyroid Nodules.

Publications

Machine Learning by Ultrasonography for Genetic Risk Stratification of Thyroid Nodules.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets