Nomogram Based on Ultrasonography and Clinical Features for Predicting Malignancy in Soft Tissue Tumors

Wu, Mengjie; Hu, Yu; Ren, An‐Jing; Peng, Xiao-Fang; Ma, Qiang; Mao, Cui-Lian; Hang, Jing; Li, Ao

doi:10.2147/cmar.s296972

Cited by 7 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nomograms integrate multiple risk factors and quantify and visualize them by displaying the risk weight of each in a digital form (35)(36)(37). The strength of this study was using a nomogram to convert probabilities of CCVCs in diabetic patients into quantifiable risk factors.…”

Section: Discussionmentioning

confidence: 99%

Development and validation of a nomogram based on the hospital information system for quantitative assessment of the risk of cardiocerebrovascular complications of diabetes

Xi¹,

Yin²,

Wang³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

Background: Although the prevention and treatment of the cardiocerebrovascular complications (CCVCs) of diabetes have been clarified, their incidence is still high. This is largely due to the lack of predictive models to objectively assess the risk of CCVC in patients with type 2 diabetes mellitus (T2DM), reducing their treatment adherence. Despite the fact that the risk factors of CCVC in T2DM patients have been identified, no prediction model for identifying T2DM patients with the risk of CCVC is available. Therefore, the aim of this study is to establish a nomogram based on hospital information system data to quantitatively assess the risk of CCVCs in T2DM patients. This model is contributed to individualized therapeutic treatments and motivating T2DM patients to adhere to lifestyle interventions. Methods:The medical records of 1,556 T2DM patients, comprising 1,145 cases in the training cohort and 411 in the validation cohort were retrospectively analyzed. CCVCs of diabetes, including coronary heart disease, cerebral ischemia, and intracerebral hemorrhage, were extracted from the medical records.Univariate and multivariate logistic regression analyses were performed to screen the independent correlates of CCVCs from the demographic information and laboratory test data, which were utilized to establish a nomogram for predicting the risk of CCVCs in these patients. We used internal and external validation based on the training and validation cohorts to evaluate the model performance. Results:The incidence of CCVCs in the training cohort (26.99%) was similar to the validation cohort (25.79%). Disease duration, body mass index (BMI), systolic blood pressure (SBP), glycosylated hemoglobin (HbA1c), and uric acid (UA) levels were finally included in the established nomogram. In both the internal and external validation, the nomogram showed good discrimination [area under the curve (AUC) =0.850 and 0.825, respectively] and calibration (P=0.127 and P=0.096, respectively). Decision curve analysis showed that the nomogram produced a net benefit in both the training and validation cohorts. Conclusions:The nomogram developed for predicting the risk of CCVC in T2DM patients may help improve treatment adherence. Further multi-center prospective investigations are required to predict the timing of CVCC in T2DM patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Development and validation of a nomogram based on the hospital information system for quantitative assessment of the risk of cardiocerebrovascular complications of diabetes

Xi¹,

Yin²,

Wang³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

show abstract

“…This was the first study to calculate the number of vessels in a full objective way. In previous studies, semiquantitative methods such as Adler's classification 5 were widely adopted in visually counting the number of vessels in breast nodules, 30 solid renal tumors, 4 soft tissue tumors, 31 cervical cancer, 32 and TNs 33 . Xia et al 33 adopted Alder's classification to divide the number of vascularity in TNs into four categories, namely, grade 0 (no blood vessel), grade I (low blood flow with rod‐like blood flows), grade II (medium blood flow with 3–4 blood vessels and at least one blood vessel are longer than the radius of the nodule), and grade III (rich blood flow with >4 blood flow signals).…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Assisted Doppler Features for Enhancing Thyroid Cancer Diagnosis

Zhu

Jiang

et al. 2021

J of Ultrasound Medicine

View full text Add to dashboard Cite

Background This pilot study aims at exploiting machine learning techniques to extract color Doppler ultrasound (CDUS) features and to build an artificial neural network (ANN) model based on these CDUS features for improving the diagnostic performance of thyroid cancer classification. Methods A total of 674 patients with 712 thyroid nodules (TNs) (512 from internal dataset and 200 from external dataset) were randomly selected in this retrospective study. We used ANN to build a model (TDUS‐Net) for classifying malignant and benign TNs using both the automatically extracted quantitative CDUS features (whole ratio, intranodular ratio, peripheral ratio, and number of vessels) and gray‐scale ultrasound (US) features defined by the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI‐RADS). Then, we compared the diagnostic performance of the model, the performance of another ANN model based on the gray‐scale US features alone (TUS‐Net), and that of radiologists. Results The TDUS‐Net (0.898, 95% CI: 0.868–0.922) achieved a higher area under the curve (AUC) than that of TUS‐Net (0.881, 95% CI: 0.850–0.908) in the internal tests. Compared with radiologists, TDUS‐Net (AUC: 0.925, 95% CI: 0.880–0.958) performed better than radiologists (AUC: 0.810, 95% CI: 0.749–0.862) in the external tests. Conclusions Applying a machine learning model by combining both gray‐scale US features and CDUS features can achieve comparable or even higher performance than radiologists in classifying TNs.

show abstract

“…The nomogram is a clinical tool that allows clinicians to determine the prognosis of patients by adding the score of each risk variable in the model to obtain the total score and the corresponding survival rate ( Romano et al, 2008 ). In recent years, the nomogram has been widely used as one of the practical tools in the assessment of cancer prognosis ( Ohori Tatsuo Gondo And Riu Hamada et al, 2009 ; Zhou et al, 2021a ; Wang et al, 2021b ; Wu et al, 2021 ). Calibration curves are often used to evaluate the accuracy of a nomogram.…”

Section: Discussionmentioning

confidence: 99%

The Construction of a Prognostic Model Based on a Peptidyl Prolyl Cis–Trans Isomerase Gene Signature in Hepatocellular Carcinoma

Shi

Zhong

et al. 2021

Front. Genet.

View full text Add to dashboard Cite

Objective: The aim of the present study was to construct a prognostic model based on the peptidyl prolyl cis–trans isomerase gene signature and explore the prognostic value of this model in patients with hepatocellular carcinoma.Methods: The transcriptome and clinical data of hepatocellular carcinoma patients were downloaded from The Cancer Genome Atlas and the International Cancer Genome Consortium database as the training set and validation set, respectively. Peptidyl prolyl cis–trans isomerase gene sets were obtained from the Molecular Signatures Database. The differential expression of peptidyl prolyl cis–trans isomerase genes was analyzed by R software. A prognostic model based on the peptidyl prolyl cis–trans isomerase signature was established by Cox, Lasso, and stepwise regression methods. Kaplan–Meier survival analysis was used to evaluate the prognostic value of the model and validate it with an independent external data. Finally, nomogram and calibration curves were developed in combination with clinical staging and risk score.Results: Differential gene expression analysis of hepatocellular carcinoma and adjacent tissues showed that there were 16 upregulated genes. A prognostic model of hepatocellular carcinoma was constructed based on three gene signatures by Cox, Lasso, and stepwise regression analysis. The Kaplan–Meier curve showed that hepatocellular carcinoma patients in high-risk score group had a worse prognosis (p < 0.05). The receiver operating characteristic curve revealed that the area under curve values of predicting the survival rate at 1, 2, 3, 4, and 5 years were 0.725, 0.680, 0.644, 0.630, and 0.639, respectively. In addition, the evaluation results of the model by the validation set were basically consistent with those of the training set. A nomogram incorporating clinical stage and risk score was established, and the calibration curve matched well with the diagonal.Conclusion: A prognostic model based on 3 peptidyl prolyl cis–trans isomerase gene signatures is expected to provide reference for prognostic risk stratification in patients with hepatocellular carcinoma.

show abstract

Nomogram Based on Ultrasonography and Clinical Features for Predicting Malignancy in Soft Tissue Tumors

Cited by 7 publications

References 32 publications

Development and validation of a nomogram based on the hospital information system for quantitative assessment of the risk of cardiocerebrovascular complications of diabetes

Development and validation of a nomogram based on the hospital information system for quantitative assessment of the risk of cardiocerebrovascular complications of diabetes

Machine Learning Assisted Doppler Features for Enhancing Thyroid Cancer Diagnosis

The Construction of a Prognostic Model Based on a Peptidyl Prolyl Cis–Trans Isomerase Gene Signature in Hepatocellular Carcinoma

Contact Info

Product

Resources

About