Decision curve analysis in the evaluation of radiology research

Woo, Sungmin

doi:10.1007/s00330-022-08685-8

Cited by 20 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to multivariate Cox analysis, a higher risk score was revealed to be independently associated with poorer survival, supporting its potential for being an independent prognostic factor for HCC (p < 0.001, HR = 1.217, 95% CI: 1.166 - 1.217) ( Figure 5B ). Notably, DCA, a novel method that is used to assess clinical predictive models, diagnostic tests, and molecular markers ( 36 ), showed that our risk model achieves greater net benefit than any one single independent clinical parameter ( Figure 5C ). Additionally, the nomogram (C-index > 0.7) based on the clinical parameters and risk scores could effectively predict the probability of the1-, 2-, and 3- years OS ( Figure 5D ).…”

Section: Resultsmentioning

confidence: 99%

Bioinformatics analysis and experimental verification of the prognostic and biological significance mediated by fatty acid metabolism related genes for hepatocellular carcinoma

Zhu

Zhu²,

Chen³

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

BackgroundLiver cancer is among the leading causes of death related to cancer around the world. The most frequent type of human liver cancer is hepatocellular carcinoma (HCC). Fatty acid (FA) metabolism is an emerging hallmark that plays a promoting role in numerous malignancies. This study aimed to discover a FA metabolism-related risk signature and formulate a better model for HCC patients’ prognosis prediction.MethodsWe collected mRNA expression data and clinical parameters of patients with HCC using the TCGA databases, and the differential FA metabolism-related genes were explored. To create a risk prognostic model, we carried out the consensus clustering as well as univariate and multivariate Cox regression analyses. 16 genes were used to establish a prognostic model, which was then validated in the ICGC dataset. The accuracy of the model was performed using receiver operating characteristic (ROC) analyses, decision curve analysis (DCA) and nomogram. The immune cell infiltration level of risk genes was evaluated with single-sample GSEA (ssGSEA) algorithm. To reflect the response to immunotherapy, immunophenoscore (IPS) was obtained from TCGA-LIHC. Then, the expression of the candidate risk genes (p < 0.05) was validated by qRT-PCR, Western blotting and single-cell transcriptomics. Cellular function assays were performed to revealed the biological function of HAVCR1.ResultsAccording to the TCGA-LIHC cohort analysis, the majority of the FA metabolism-related genes were expressed differentially in the HCC and normal tissues. The prognosis of patients with high-risk scores was observed to be worse. Multivariate COX regression analysis confirmed that the model can be employed as an independent prognosis factor for HCC patients. Furthermore, ssGSEA analysis revealed a link between the model and the levels of immune cell infiltration. Our model scoring mechanism also provides a high predictive value in HCC patients receiving anti-PDL1 immunotherapy. One of the FA metabolism-related genes, HAVCR1, displays a significant differential expression between normal and HCC cell lines. Hepatocellular carcinoma cells (Huh7, and HepG2) proliferation, motility, and invasion were all remarkably inhibited by HAVCR1 siRNA.ConclusionOur study identified a novel FA metabolism-related prognostic model, revealing a better potential treatment and prevention strategy for HCC.

show abstract

Section: Resultsmentioning

confidence: 99%

Bioinformatics analysis and experimental verification of the prognostic and biological significance mediated by fatty acid metabolism related genes for hepatocellular carcinoma

Zhu

Zhu²,

Chen³

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Our study showed that the predicted probability was consistent with the actual probability. In the decision curve, 34 the theoretical relationship between the threshold probability and the relative value of false positive and false negative results was used to determine the clinical utility of the prediction model. These results verified the stability and reliability of our model.…”

Section: Discussionmentioning

confidence: 99%

The value of radiomics model based on ultrasound image features in the differentiation between minimal breast cancer and small benign breast masses

Lyu,

Zhang,

Zhang

et al. 2023

J of Clinical Ultrasound

View full text Add to dashboard Cite

BackgroundFemale breast cancer has surpassed lung cancer as the most common cancer, and is also the main cause of cancer death for women worldwide. Breast cancer <1 cm showed excellent survival rate. However, the diagnosis of minimal breast cancer (MBC) is challenging.ObjectiveThe purpose of our research is to develop and validate an radiomics model based on ultrasound images for early recognition of MBC.Methods302 breast masses with a diameter of <10 mm were retrospectively studied, including 159 benign and 143 malignant breast masses. The radiomics features were extracted from the gray‐scale ultrasound image of the largest face of each breast mass. The maximum relevance minimum reduncancy and recursive feature elimination methods were used to screen. Finally, 10 features with the most discriminating value were selected for modeling. The random forest was used to establish the prediction model, and the rad‐score of each mass was calculated. In order to evaluate the effectiveness of the model, we calculated and compared the area under the curve (AUC) value, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of the model and three groups with different experience in predicting small breast masses, and drew calibration curves and decision curves to test the stability and consistency of the model.ResultsWhen we selected 10 radiomics features to calculate the rad‐score, the prediction efficiency was the best, the AUC values for the training set and testing set were 0.840 and 0.793, which was significantly better than the insufficient experience group (AUC = 0.673), slightly better than the moderate experience group (AUC = 0.768), and was inferior to the experienced group (AUC = 0.877). The calibration curve and decision curve also showed that the radiomics model had satisfied stability and clinical application value.ConclusionThe radiomics model based on ultrasound image features has a satisfied predictive ability for small breast masses, and is expected to become a potential tool for the diagnosis of MBC, and it is a zero cost (in terms of patient participation and imaging time).

show abstract

“…However, the present work only aimed to build an optimised pipeline for automatic segmentation and quantitative analysis of chest CT, comparing different possible approaches for the AI modelling. For a more appropriate interpretation of the classifier performance, future developments should involve comparison with the performance of human readers and decision curve analysis [ 40 ] to verify whether Model3 actually provides added value in supporting clinical practice.…”

Section: Discussionmentioning

confidence: 99%

Artificial intelligence for differentiating COVID-19 from other viral pneumonias on CT: comparative analysis of different models based on quantitative and radiomic approaches

et al. 2023

View full text Add to dashboard Cite

Background To develop a pipeline for automatic extraction of quantitative metrics and radiomic features from lung computed tomography (CT) and develop artificial intelligence (AI) models supporting differential diagnosis between coronavirus disease 2019 (COVID-19) and other viral pneumonia (non-COVID-19). Methods Chest CT of 1,031 patients (811 for model building; 220 as independent validation set (IVS) with positive swab for severe acute respiratory syndrome coronavirus-2 (647 COVID-19) or other respiratory viruses (384 non-COVID-19) were segmented automatically. A Gaussian model, based on the HU histogram distribution describing well-aerated and ill portions, was optimised to calculate quantitative metrics (QM, n = 20) in both lungs (2L) and four geometrical subdivisions (GS) (upper front, lower front, upper dorsal, lower dorsal; n = 80). Radiomic features (RF) of first (RF1, n = 18) and second (RF2, n = 120) order were extracted from 2L using PyRadiomics tool. Extracted metrics were used to develop four multilayer-perceptron classifiers, built with different combinations of QM and RF: Model1 (RF1-2L); Model2 (QM-2L, QM-GS); Model3 (RF1-2L, RF2-2L); Model4 (RF1-2L, QM-2L, GS-2L, RF2-2L). Results The classifiers showed accuracy from 0.71 to 0.80 and area under the receiving operating characteristic curve (AUC) from 0.77 to 0.87 in differentiating COVID-19 versus non-COVID-19 pneumonia. Best results were associated with Model3 (AUC 0.867 ± 0.008) and Model4 (AUC 0.870 ± 0.011. For the IVS, the AUC values were 0.834 ± 0.008 for Model3 and 0.828 ± 0.011 for Model4. Conclusions Four AI-based models for classifying patients as COVID-19 or non-COVID-19 viral pneumonia showed good diagnostic performances that could support clinical decisions.

show abstract

Decision curve analysis in the evaluation of radiology research

Cited by 20 publications

References 5 publications

Bioinformatics analysis and experimental verification of the prognostic and biological significance mediated by fatty acid metabolism related genes for hepatocellular carcinoma

Bioinformatics analysis and experimental verification of the prognostic and biological significance mediated by fatty acid metabolism related genes for hepatocellular carcinoma

The value of radiomics model based on ultrasound image features in the differentiation between minimal breast cancer and small benign breast masses

Artificial intelligence for differentiating COVID-19 from other viral pneumonias on CT: comparative analysis of different models based on quantitative and radiomic approaches

Contact Info

Product

Resources

About