Predicting Elevated TSH Levels in the Physical Examination Population With a Machine Learning Model

Cheng, Xinqi; Li, Shicheng; Deng, Lizong; Luo, Wei; Wang, Dancheng; Cheng, Jin; Ma, Chaochao; Chen, Luming; Jiang, Taijiao; Qiu, Ling; Zhang, Guojun

doi:10.3389/fendo.2022.839829

Cited by 3 publications

(2 citation statements)

References 19 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Low alkaline phosphatase and high alanine aminotransferase levels were also found to be associated with hypothyroidism [60]. However, HDL and LDL, which were selected by RFE in this research, were not statistically significantly correlated with thyroid function in previous pharmacoepidemiological reports [61]. Their contributions might be masked by factorial interactions in statistical approaches.…”

Section: Feature Identification and Interpretationmentioning

confidence: 55%

Explainable Machine Learning Techniques To Predict Amiodarone-Induced Thyroid Dysfunction Risk: Multicenter, Retrospective Study With External Validation

Chao

Chiang

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background Machine learning offers new solutions for predicting life-threatening, unpredictable amiodarone-induced thyroid dysfunction. Traditional regression approaches for adverse-effect prediction without time-series consideration of features have yielded suboptimal predictions. Machine learning algorithms with multiple data sets at different time points may generate better performance in predicting adverse effects. Objective We aimed to develop and validate machine learning models for forecasting individualized amiodarone-induced thyroid dysfunction risk and to optimize a machine learning–based risk stratification scheme with a resampling method and readjustment of the clinically derived decision thresholds. Methods This study developed machine learning models using multicenter, delinked electronic health records. It included patients receiving amiodarone from January 2013 to December 2017. The training set was composed of data from Taipei Medical University Hospital and Wan Fang Hospital, while data from Taipei Medical University Shuang Ho Hospital were used as the external test set. The study collected stationary features at baseline and dynamic features at the first, second, third, sixth, ninth, 12th, 15th, 18th, and 21st months after amiodarone initiation. We used 16 machine learning models, including extreme gradient boosting, adaptive boosting, k-nearest neighbor, and logistic regression models, along with an original resampling method and 3 other resampling methods, including oversampling with the borderline-synthesized minority oversampling technique, undersampling–edited nearest neighbor, and over- and undersampling hybrid methods. The model performance was compared based on accuracy; Precision, recall, F1-score, geometric mean, area under the curve of the receiver operating characteristic curve (AUROC), and the area under the precision-recall curve (AUPRC). Feature importance was determined by the best model. The decision threshold was readjusted to identify the best cutoff value and a Kaplan-Meier survival analysis was performed. Results The training set contained 4075 patients from Taipei Medical University Hospital and Wan Fang Hospital, of whom 583 (14.3%) developed amiodarone-induced thyroid dysfunction, while the external test set included 2422 patients from Taipei Medical University Shuang Ho Hospital, of whom 275 (11.4%) developed amiodarone-induced thyroid dysfunction. The extreme gradient boosting oversampling machine learning model demonstrated the best predictive outcomes among all 16 models. The accuracy; Precision, recall, F1-score, G-mean, AUPRC, and AUROC were 0.923, 0.632, 0.756, 0.688, 0.845, 0.751, and 0.934, respectively. After readjusting the cutoff, the best value was 0.627, and the F1-score reached 0.699. The best threshold was able to classify 286 of 2422 patients (11.8%) as high-risk subjects, among which 275 were true-positive patients in the testing set. A shorter treatment duration; higher levels of thyroid-stimulating hormone and high-density lipoprotein cholesterol; and lower levels of free thyroxin, alkaline phosphatase, and low-density lipoprotein were the most important features. Conclusions Machine learning models combined with resampling methods can predict amiodarone-induced thyroid dysfunction and serve as a support tool for individualized risk prediction and clinical decision support.

show abstract

Section: Feature Identification and Interpretationmentioning

confidence: 55%

Explainable Machine Learning Techniques To Predict Amiodarone-Induced Thyroid Dysfunction Risk: Multicenter, Retrospective Study With External Validation

Chao

Chiang

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…Arti cial intelligence (AI) is a branch of computer science designed to tackle cognitive tasks akin to human intelligence. When dealing with large datasets, AI algorithms tend to outperform traditional linear models such as the Cox model, particularly in predicting clinical outcomes (15). For instance, in a previous study, we constructed an XGBOOST model to predict thyroid-stimulating hormone levels based on a substantial population undergoing physical examinations (16).…”

Section: Introductionmentioning

confidence: 99%

A fine-tuned machine learning model to predict survivals of breast cancer patients based on gamma-delta T cell markers

Zhou,

Weng,

Ding

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Gamma-delta (γδ) T cells influence cancer immunotherapy and prognosis by enhancing clinical responses to checkpoint inhibitors. However, identifying prognostic markers for γδ T cells remains a crucial challenge. Methods: Initially, we identified γδ T cell markers specific to breast cancer (BC) through single-cell analysis of GSE195861 dataset from the GEO database. Subsequently, we utilized LASSO regression to select prognostic genes for use as variables in artificial intelligence (AI) models. We performed survival analysis, assessed cancer microenvironment scores, and conducted biological functional analysis on these selected genes. Following this, we trained five commonly used machine learning models, and the best-performing model in the training set underwent careful tuning to optimize its performance. Tissues from five GEO datasets and our hospital were used for model validation. Results: Cells of BC were classified into 12 subclasses, and the γδT cells accounted for the majority. Totally, 310 markers of γδT cells were identified, among which 12 were proved to have the prognostic ability by the external validation of GSE20685 (Hazard Ratio (HR) = 1.634, p = 0.031), GSE3143 (HR = 2.887, p = 0.001), GSE19536 (HR = 2.713, p = 0.001), GSE202203 (HR = 2.088, p < 0.001) and GSE35629 (HR = 6.476, p = 0.001). The random forest (RF) model with the 10-fold cross-validation achieved the best accuracy of 0.824 among the trained models. Then performance of the RF model increased to the accuracy of 0.835 after fine-tuned. In the validation, the AUC /accuracy of the fine-tuned RF model is 0.81/0.849 in GSE20685, 0.75/ 0.812 in GSE3143, 0.75/ 0.807 in GSE19536, 0.80/ 0.841 in GSE202203, 0.78/ 0.821 in GSE35629 and 0.77/0.801 in the real-world cohort. Conclusions: We developed an efficient machine learning model based on γδT cell markers, which had a potent capability to predict the prognosis of BC patients.

show abstract

Artificial Intelligence in Thyroidology: A Narrative Review of the Current Applications, Associated Challenges, and Future Directions

Toro-Tobon,

Loor-Torres,

Duran

et al. 2023

Thyroid®

View full text Add to dashboard Cite

Predicting Elevated TSH Levels in the Physical Examination Population With a Machine Learning Model

Cited by 3 publications

References 19 publications

Explainable Machine Learning Techniques To Predict Amiodarone-Induced Thyroid Dysfunction Risk: Multicenter, Retrospective Study With External Validation

Explainable Machine Learning Techniques To Predict Amiodarone-Induced Thyroid Dysfunction Risk: Multicenter, Retrospective Study With External Validation

A fine-tuned machine learning model to predict survivals of breast cancer patients based on gamma-delta T cell markers

Artificial Intelligence in Thyroidology: A Narrative Review of the Current Applications, Associated Challenges, and Future Directions

Contact Info

Product

Resources

About