The Construction and Development of a Clinical Prediction Model to Assess Lymph Node Metastases in Osteosarcoma

Development and validation of a machine learning-based nomogram for predicting HLA-B27 expression

BACKGROUND

HLA-B27 positivity is normal in patients undergoing rheumatic diseases. The diagnosis of many diseases requires an HLA-B27 examination.

METHODS

This study screened totally 1503 patients who underwent HLA-B27 examination, liver/kidney function tests, and complete blood routine examination in First Affiliated Hospital of Guangxi Medical University. The training cohort included 509 cases with HLA-B27 positivity whereas 611 with HLA-B27 negativity. In addition, validation cohort included 147 cases with HLA-B27 positivity whereas 236 with HLA-B27 negativity. In this study, 3 ML approaches, namely, LASSO, support vector machine (SVM) recursive feature elimination and random forest, were adopted for screening feature variables. Subsequently, to acquire the prediction model, the intersection was selected. Finally, differences among 148 cases with HLA-B27 positivity and negativity suffering from ankylosing spondylitis (AS) were investigated.

RESULTS

Six factors, namely red blood cell count, human major compatibility complex, mean platelet volume, albumin/globulin ratio (ALB/GLB), prealbumin, and bicarbonate radical, were chosen with the aim of constructing the diagnostic nomogram using ML methods. For training queue, nomogram curve exhibited the value of area under the curve (AUC) of 0.8254496, and C-value of the model was 0.825. Moreover, nomogram C-value of the validation queue was 0.853, and the AUC value was 0.852675. Furthermore, a significant decrease in the ALB/GLB was noted among cases with HLA-B27 positivity and AS cases.

CONCLUSION

To conclude, the proposed ML model can effectively predict HLA-B27 and help doctors in the diagnosis of various immune diseases.

A new nomogram for assessing complete response (CR) in gastric diffuse large B-cell lymphoma (DLBCL) patients after chemotherapy

PURPOSE

Achieving complete response (CR) after first-line chemotherapy in gastric DLBCL patients often results in longer disease-free survival. We explored whether a model based on imaging features combined with clinicopathological factors could assess the CR to chemotherapy in patients with gastric DLBCL.

METHODS

Univariate (P < 0.10) and multivariate (P < 0.05) analyses were used to identify factors associated with a CR to treatment. As a result, a system was developed to evaluate whether gastric DLBCL patients had a CR to chemotherapy. Evidence was found to support the model's ability to predict outcomes and demonstrate clinical value.

RESULTS

We retrospectively analysed 108 people who had been diagnosed gastric DLBCL; 53 were in CR. Patients were divided at random into a 5:4 training/testing dataset split. β2 microglobulin before and after chemotherapy and lesion length after chemotherapy were independent predictors of the CR of gastric DLBCL patients after chemotherapy. These factors were used in the predictive model construction. In the training dataset, the area under the curve (AUC) of the model was 0.929, the specificity was 0.806, and the sensitivity was 0.862. In the testing dataset, the model had an AUC of 0.957, specificity of 0.792, and sensitivity of 0.958. The AUC did not differ significantly between the training and testing dates (P > 0.05).

CONCLUSION

A model constructed using imaging features combined with clinicopathological factors could effectively evaluate the CR to chemotherapy in gastric DLBCL patients. The predictive model can facilitate the monitoring of patients and be used to adjust individualised treatment plans.

A degradome-based prognostic signature that correlates with immune infiltration and tumor mutation burden in breast cancer

Introduction

Female breast cancer is the most common malignancy worldwide, with a high disease burden. The degradome is the most abundant class of cellular enzymes that play an essential role in regulating cellular activity. Dysregulation of the degradome may disrupt cellular homeostasis and trigger carcinogenesis. Thus we attempted to understand the prognostic role of degradome in breast cancer by means of establishing a prognostic signature based on degradome-related genes (DRGs) and assessed its clinical utility in multiple dimensions.

Methods

A total of 625 DRGs were obtained for analysis. Transcriptome data and clinical information of patients with breast cancer from TCGA-BRCA, METABRIC and GSE96058 were collected. NetworkAnalyst and cBioPortal were also utilized for analysis. LASSO regression analysis was employed to construct the degradome signature. Investigations of the degradome signature concerning clinical association, functional characterization, mutation landscape, immune infiltration, immune checkpoint expression and drug priority were orchestrated. Cell phenotype assays including colony formation, CCK8, transwell and wound healing were conducted in MCF-7 and MDA-MB-435S breast cancer cell lines, respectively.

Results

A 10-gene signature was developed and verified as an independent prognostic predictor combined with other clinicopathological parameters in breast cancer. The prognostic nomogram based on risk score (calculated based on the degradome signature) showed favourable capability in survival prediction and advantage in clinical benefit. High risk scores were associated with a higher degree of clinicopathological events (T4 stage and HER2-positive) and mutation frequency. Regulation of toll-like receptors and several cell cycle promoting activities were upregulated in the high-risk group. PIK3CA and TP53 mutations were dominant in the low- and high-risk groups, respectively. A significantly positive correlation was observed between the risk score and tumor mutation burden. The infiltration levels of immune cells and the expressions of immune checkpoints were significantly influenced by the risk score. Additionally, the degradome signature adequately predicted the survival of patients undergoing endocrinotherapy or radiotherapy. Patients in the low-risk group may achieve complete response after the first round of chemotherapy with cyclophosphamide and docetaxel, whereas patients in the high-risk group may benefit from 5-flfluorouracil. Several regulators of the PI3K/AKT/mTOR signaling pathway and the CDK family/PARP family were identified as potential molecular targets in the low- and high-risk groups, respectively. In vitro experiments further revealed that the knockdown of ABHD12 and USP41 significantly inhibit the proliferation, invasion and migration of breast cancer cells.

Conclusion

Multidimensional evaluation verified the clinical utility of the degradome signature in predicting prognosis, risk stratification and guiding treatment for patients with breast cancer.

Difference between the blood samples of patients with bone and joint tuberculosis and patients with tuberculosis studied using machine learning

Background

Tuberculosis (TB) is a chronic infectious disease. Bone and joint TB is a common type of extrapulmonary TB and often occurs secondary to TB infection. In this study, we aimed to find the difference in the blood examination results of patients with bone and joint TB and patients with TB by using machine learning (ML) and establish a diagnostic model to help clinicians better diagnose the disease and allow patients to receive timely treatment.

Methods

A total of 1,667 patients were finally enrolled in the study. Patients were randomly assigned to the training and validation cohorts. The training cohort included 1,268 patients: 158 patients with bone and joint TB and 1,110 patients with TB. The validation cohort included 399 patients: 48 patients with bone and joint TB and 351 patients with TB. We used three ML methods, namely logistic regression, LASSO regression, and random forest, to screen the differential variables, obtained the most representative variables by intersection to construct the prediction model, and verified the performance of the proposed prediction model in the validation group.

Results

The results revealed a great difference in the blood examination results of patients with bone and joint TB and those with TB. Infectious markers such as hs-CRP, ESR, WBC, and NEUT were increased in patients with bone and joint TB. Patients with bone and joint TB were found to have higher liver function burden and poorer nutritional status. The factors screened using ML were PDW, LYM, AST/ALT, BUN, and Na, and the nomogram diagnostic model was constructed using these five factors. In the training cohort, the area under the curve (AUC) value of the model was 0.71182, and the C value was 0.712. In the validation cohort, the AUC value of the model was 0.6435779, and the C value was 0.644.

Conclusion

We used ML methods to screen out the blood-specific factors-PDW, LYM, AST/ALT, BUN, and Na⁺-of bone and joint TB and constructed a diagnostic model to help clinicians better diagnose the disease in the future.

A novel nomogram for adult primary perihilar cholangiocarcinoma and considerations concerning lymph node dissection

Objective

To construct a reliable nomogram available online to predict the postoperative survival of patients with perihilar cholangiocarcinoma.

Methods

Data from 1808 patients diagnosed with perihilar cholangiocarcinoma between 2004 and 2015 were extracted from the National Cancer Institute Surveillance, Epidemiology, and End Results (SEER) database. They were randomly divided into training and validation sets. The nomogram was established by machine learning and Cox model. The discriminant ability and prediction accuracy of the nomogram were evaluated by concordance index (C-index), receiver operator characteristic (ROC) curve and calibration curve. Kaplan-Meier curves show the prognostic value of the associated risk factors and classification system.

Results

Machine learning and multivariate Cox risk regression model showed that sex, age, tumor differentiation, primary tumor stage(T), lymph node metastasis(N), TNM stage, surgery, radiation, chemotherapy, lymph node dissection were associated with the prognosis of perihilar cholangiocarcinoma patients relevant factors (P < 0.05). A novel nomogram was established. The calibration plots, C-index and ROC curve for predictions of the 1-, 3-, and 5-year OS were in excellent agreement. In patients with stage T1 and N0 perihilar cholangiocarcinoma, the prognosis of ≥4 lymph nodes dissected was better than that of 1- 3 lymph nodes dissected (P < 0.01).

Conclusion

The nomogram prognostic prediction model can provide a reference for evaluating the prognosis and survival rate of patients with perihilar cholangiocarcinoma. Patients with stage T1 and N0 perihilar cholangiocarcinoma have more benefits by increasing the number of lymph node dissection.

Association between aspartate aminotransferase to alanine aminotransferase ratio and the risk of diabetes in Chinese prediabetic population: A retrospective cohort study

Background

Accumulating evidence has revealed that the aspartate aminotransferase to alanine aminotransferase (AST/ALT) ratio is a promising novel biomarker for insulin resistance (IR) and metabolic diseases. However, research on the association between the AST/ALT ratio and the incidence of diabetes progressing from prediabetes remains lacking. Herein, this study aimed to evaluate the relationship between the baseline AST/ALT ratio and risks of diabetes in patients with prediabetes.

Methods

This was a retrospective cohort study involving a total of 82,683 participants across 32 regions and 11 cities in China from 2010 to 2016. Data was obtained based on the DATADRYAD database from the health check screening program. Participants were stratified according to the interquartile range of the AST/ALT ratio (groups Q1 to Q4). The Cox proportional hazard model and smooth curve fitting were used to explore the relationship between the baseline AST/ALT ratio and the risk of diabetes in prediabetic patients. In addition, subgroup analysis was used to further validate the stability of the results.

Results

The mean age of the selected participants was 49.9 ± 14.0 years, with 66.8% of them being male. During the follow-up period 1,273 participants (11.3%) developed diabetes progressing from prediabetes during the follow-up period. Participants who developed diabetes were older and were more likely to be male. The fully-adjusted Cox proportional hazard model revealed that the AST/ALT ratio was negatively associated with the risk of diabetes in prediabetic patients (HR = 0.40, 95% CI: 0.33 to 0.48, P < 0.001). Higher AST/ALT ratio groups (Q4) also presented with a lower risk of progressing into diabetes (HR = 0.35, 95% CI: 0.29 to 0.43, P < 0.001, respectively) compared with the lowest quintile group (Q1). Through subgroup analysis and interaction tests, it was found that the association stably existed in all subgroup variables, and there were a stronger interactive effects in people with age < 45 years, and TG ≤ 1.7 mmol/L in the association between AST/ALT ratio and diabetes incidences in patients with prediabetes (P for interaction < 0.05).

Conclusion

According to our study, a higher AST/ALT ratio is associated with a lower risk of progressing into diabetes from prediabetes. Regular monitoring of AST/ALT ratio dynamics and corresponding interventions can help prevent or slow prediabetes progression for diabetes.

Web-Based Prediction Models for Overall Survival and Cancer-Specific Survival of Patients With Primary Urachal Carcinoma: A Study Based on SEER Database

Objective:

We aimed to establish nomograms to predict the overall survival (OS) and cancer-specific survival (CSS) of patients with primary urachal carcinoma (UrC).

Methods

Information on patients diagnosed with UrC from 1975 to 2018 was collected from the Surveillance, Epidemiology, and End Results (SEER) Program Research Data. The independent prognostic factors were determined using univariate and multivariate Cox regression. Backward variable elimination according to the Akaike information criterion (AIC) identified the most accurate and parsimonious model. Nomograms were built based on regression coefficients. The C-index, calibration plot, Brier score, integrated discrimination improvement (IDI), area under the receiver operating curve (AUC), and decision curve analysis (DCA) curve were used to evaluate the efficiency of models.

Results

In total, 236 patients obtained from SEER were divided randomly into training and validation cohorts in a 70:30 ratio (166 and 70 patients, respectively). In the training cohort, multivariate Cox regression analysis indicated that pTNM/Sheldon/Mayo staging systems (included respectively), age, and tumor grade were independent prognostic factors for OS. A similar result was also found in CSS. While other variables, such as radiotherapy and chemotherapy, did not identify significant correlations. In predicting OS and CSS at 3- and 5- years, the nomograms based on pTNM showed superior discriminative and calibration capabilities in comparison to multiple statistical tools. The C-index values for the training cohort were 0.770 for OS and 0.806 for CSS, and similar outcomes were shown in further internal validation (C-index 0.693 for OS and 0.719 for CSS). We also discovered that the link between age at diagnosis and survival follows a U-shaped curve, indicating that the risk of poor prognosis decreases first and then increases with age.

Conclusion

The efficacy of pTNM in predicting the prognosis of patients with UrC was greater than that of the Sheldon and Mayo staging system. Therefore, we recommend pTNM as the preferred system to stage UrC. The novel constructed nomograms based on pTNM, age, and tumor grade showed high accuracy and specificity and could be applied clinically to predict the prognosis of patients with UrC.

A Visualized Dynamic Prediction Model for Lymphatic Metastasis in Ewing's Sarcoma for Smart Medical Services

Background

This study aims to predict the lymphatic metastasis in Ewing's sarcoma (ES) patients by nomogram. The risk of lymphatic metastasis in patients with ES was predicted by the built model, which provided guidance for the clinical diagnosis and treatment planning.

Methods

A total of 929 patients diagnosed with ES were enrolled from the year of 2010 to 2016 in the Surveillance, Epidemiology, and End Results (SEER) database. The nomogram was established to determine predictive factors of lymphatic metastasis according to univariate and multivariate logistic regression analysis. The validation of the model performed using multicenter data (n = 51). Receiver operating characteristics (ROC) curves and calibration plots were used to evaluate the prediction accuracy of the nomogram. Decision curve analysis (DCA) was implemented to illustrate the practicability of the nomogram clinical application. Based on the nomogram, we established a web calculator to visualize the risk of lymphatic metastases. We further plotted Kaplan-Meier overall survival (OS) curves to compare the survival time of patients with and without lymphatic metastasis.

Results

In this study, the nomogram was established based on six significant factors (survival time, race, T stage, M stage, surgery, and lung metastasis), which were identified for lymphatic metastasis in ES patients. The model showed significant diagnostic accuracy with the value of the area under the curve (AUC) was 0.743 (95%CI: 0.714–0.771) for SEER internal validation and 0.763 (95%CI: 0.623–0.871) for multicenter data external validation. The calibration plot and DCA indicated that the model had vital clinical application value.

Conclusion

In this study, we constructed and developed a nomogram with risk factors to predict lymphatic metastasis in ES patients and validated accuracy of itself. We found T stage (Tx OR = 2.540, 95%CI = 1.433–4.503, P < 0.01), M stage (M1, OR = 2.061, 95%CI = 1.189–3.573, P < 0.05) and survival time (OR = 0.982, 95%CI = 0.972–0.992, P < 0.001) were important independent factors for lymphatic metastasis in ES patients. Furthermore, survival time in patients with lymphatic metastasis or unclear situation (P < 0.0001) was significantly lower. It can help clinicians make better decisions to provide more accurate prognosis and treatment for ES patients.

Machine Learning-Based Prediction of Lymph Node Metastasis Among Osteosarcoma Patients

Background

Regional lymph node metastasis is a contributor for poor prognosis in osteosarcoma. However, studies on risk factors for predicting regional lymph node metastasis in osteosarcoma are scarce. This study aimed to develop and validate a model based on machine learning (ML) algorithms.

Methods

A total of 1201 patients, with 1094 cases from the surveillance epidemiology and end results (SEER) (the training set) and 107 cases (the external validation set) admitted from four medical centers in China, was included in this study. Independent risk factors for the risk of lymph node metastasis were screened by the multifactorial logistic regression models. Six ML algorithms, including the logistic regression (LR), the gradient boosting machine (GBM), the extreme gradient boosting (XGBoost), the random forest (RF), the decision tree (DT), and the multilayer perceptron (MLP), were used to evaluate the risk of lymph node metastasis. The prediction model was developed based on the bestpredictive performance of ML algorithm and the performance of the model was evaluatedby the area under curve (AUC), prediction accuracy, sensitivity and specificity. A homemade online calculator was capable of estimating the probability of lymph node metastasis in individuals.

Results

Of all included patients, 9.41% (113/1201) patients developed regional lymph node metastasis. ML prediction models were developed based on nine variables: age, tumor (T) stage, metastasis (M) stage, laterality, surgery, radiation, chemotherapy, bone metastases, and lung metastases. In multivariate logistic regression analysis, T and M stage, surgery, and chemotherapy were significantly associated with lymph node metastasis. In the six ML algorithms, XGB had the highest AUC (0.882) and was utilized to develop as prediction model. A homemade online calculator was capable of estimating the probability of CLNM in individuals.

Conclusions

T and M stage, surgery and Chemotherapy are independent risk factors for predicting lymph node metastasis among osteosarcoma patients. XGB algorithm has the best predictive performance, and the online risk calculator can help clinicians to identify the risk probability of lymph node metastasis among osteosarcoma patients.

An External-Validated Prediction Model to Predict Lung Metastasis among Osteosarcoma: A Multicenter Analysis Based on Machine Learning

Background

Lung metastasis greatly affects medical therapeutic strategies in osteosarcoma. This study aimed to develop and validate a clinical prediction model to predict the risk of lung metastasis among osteosarcoma patients based on machine learning (ML) algorithms.

Methods

We retrospectively collected osteosarcoma patients from the Surveillance Epidemiology and End Results (SEER) database and from four hospitals in China. Six ML algorithms, including logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), random forest (RF), decision tree (DT), and multilayer perceptron (MLP), were applied to build predictive models for predicting lung metastasis using patient's demographics, clinical characteristics, and therapeutic variables from the SEER database. The model was internally validated using 10-fold cross-validation to calculate the mean area under the curve (AUC) and the model was externally validated using the Chinese multicenter osteosarcoma data. Relative importance ranking of predictors was plotted to understand the importance of each predictor in different ML algorithms. The correlation heat map of predictors was plotted to understand the correlation of each predictor, selecting the 10-fold cross-validation with the highest AUC value in the external validation ROC curve to build a web calculator.

Results

Of all enrolled patients from the SEER database, 17.73% (194/1094) developed lung metastasis. The multiple logistic regression analysis showed that sex, N stage, T stage, surgery, and bone metastasis were all independent risk factors for lung metastasis. In predicting lung metastasis, the mean AUCs of the six ML algorithms ranged from 0.711 to 0.738 in internal validation and 0.697 to 0.729 in external validation. Among the six ML algorithms, the extreme gradient boosting (XGBoost) model had the highest AUC value with an average internal AUC of 0.738 and an external AUC of 0.729. The best performing ML algorithm model was used to build a web calculator to facilitate clinicians to calculate the risk of lung metastasis for each patient.

Conclusions

The XGBoost model may have the best prediction effect and the online calculator based on this model can help doctors to determine the lung metastasis risk of osteosarcoma patients and help to make individualized medical strategies.

A Machine Learning-Based Predictive Model for Predicting Lymph Node Metastasis in Patients With Ewing's Sarcoma

Objective

In order to provide reference for clinicians and bring convenience to clinical work, we seeked to develop and validate a risk prediction model for lymph node metastasis (LNM) of Ewing’s sarcoma (ES) based on machine learning (ML) algorithms.

Methods

Clinicopathological data of 923 ES patients from the Surveillance, Epidemiology, and End Results (SEER) database and 51 ES patients from multi-center external validation set were retrospectively collected. We applied ML algorithms to establish a risk prediction model. Model performance was checked using 10-fold cross-validation in the training set and receiver operating characteristic (ROC) curve analysis in external validation set. After determining the best model, a web-based calculator was made to promote the clinical application.

Results

LNM was confirmed or unable to evaluate in 13.86% (135 out of 974) ES patients. In multivariate logistic regression, race, T stage, M stage and lung metastases were independent predictors for LNM in ES. Six prediction models were established using random forest (RF), naive Bayes classifier (NBC), decision tree (DT), xgboost (XGB), gradient boosting machine (GBM), logistic regression (LR). In 10-fold cross-validation, the average area under curve (AUC) ranked from 0.705 to 0.764. In ROC curve analysis, AUC ranged from 0.612 to 0.727. The performance of the RF model ranked best. Accordingly, a web-based calculator was developed (https://share.streamlit.io/liuwencai2/es_lnm/main/es_lnm.py).

Conclusion

With the help of clinicopathological data, clinicians can better identify LNM in ES patients. Risk prediction models established in this study performed well, especially the RF model.

Identification of risk model based on glycolysis-related genes in the metastasis of osteosarcoma

BACKGROUND

Glycolytic metabolic pathway has been confirmed to play a vital role in the proliferation, survival, and migration of malignant tumors, but the relationship between glycolytic pathway-related genes and osteosarcoma (OS) metastasis and prognosis remain unclear.

METHODS

We performed Gene set enrichment analysis (GSEA) on the osteosarcoma dataset in the TARGET database to explore differences in glycolysis-related pathway gene sets between primary osteosarcoma (without other organ metastases) and metastatic osteosarcoma patient samples, as well as glycolytic pathway gene set gene difference analysis. Then, we extracted OS data from the TCGA database and used Cox proportional risk regression to identify prognosis-associated glycolytic genes to establish a risk model. Further, the validity of the risk model was confirmed using the GEO database dataset. Finally, we further screened OS metastasis-related genes based on machine learning. We selected the genes with the highest clinical metastasis-related importance as representative genes for in vitro experimental validation.

RESULTS

Using the TARGET osteosarcoma dataset, we identified 5 glycolysis-related pathway gene sets that were significantly different in metastatic and non-metastatic osteosarcoma patient samples and identified 29 prognostically relevant genes. Next, we used multivariate Cox regression to determine the inclusion of 13 genes (ADH5, DCN, G6PD, etc.) to construct a prognostic risk score model to predict 1- (AUC=0.959), 3- (AUC=0.899), and 5-year (AUC=0.895) survival under the curve. Ultimately, the KM curves pooled into the datasets GSE21257 and GSE39055 also confirmed the validity of the prognostic risk model, with a statistically significant difference in overall survival between the low- and high-risk groups (P<0.05). In addition, machine learning identified INSR as the gene with the highest importance for OS metastasis, and the transwell assay verified that INSR significantly promoted OS cell metastasis.

CONCLUSIONS

A risk model based on seven glycolytic genes (INSR, FAM162A, GLCE, ADH5, G6PD, SDC3, HS2ST1) can effectively evaluate the prognosis of osteosarcoma, and in vitro experiments also confirmed the important role of INSR in promoting OS migration.