Construction and validation of a 6-gene nomogram discriminating lung metastasis risk of breast cancer patients

Development and validation of an artificial intelligence model for predicting de novo distant bone metastasis in breast cancer: a dual-center study

OBJECTIVE

Breast cancer has become the most prevalent malignant tumor in women, and the occurrence of distant metastasis signifies a poor prognosis. Utilizing predictive models to forecast distant metastasis in breast cancer presents a novel approach. This study aims to utilize readily available clinical data and advanced machine learning algorithms to establish an accurate clinical prediction model. The overall objective is to provide effective decision support for clinicians.

METHODS

Data from 239 patients from two centers were analyzed, focusing on clinical blood biomarkers (tumor markers, liver and kidney function, lipid profile, cardiovascular markers). Spearman correlation and the least absolute shrinkage and selection operator regression were employed for feature dimension reduction. A predictive model was built using LightGBM and validated in training, testing, and external validation cohorts. Feature importance correlation analysis was conducted on the clinical model and the comprehensive model, followed by univariate and multivariate regression analysis of these features.

RESULTS

Through internal and external validation, we constructed a LightGBM model to predict de novo bone metastasis in newly diagnosed breast cancer patients. The area under the receiver operating characteristic curve values of this model in the training, internal validation test, and external validation test1 cohorts were 0.945, 0.892, and 0.908, respectively. Our validation results indicate that the model exhibits high sensitivity, specificity, and accuracy, making it the most accurate model for predicting bone metastasis in breast cancer patients. Carcinoembryonic Antigen, creatine kinase, albumin-globulin ratio, Apolipoprotein B, and Cancer Antigen 153 (CA153) play crucial roles in the model's predictions. Lipoprotein a, CA153, gamma-glutamyl transferase, α-Hydroxybutyrate dehydrogenase, alkaline phosphatase, and creatine kinase are positively correlated with breast cancer bone metastasis, while white blood cell ratio and total cholesterol are negatively correlated.

CONCLUSION

This study successfully utilized clinical blood biomarkers to construct an artificial intelligence model for predicting distant metastasis in breast cancer, demonstrating high accuracy. This suggests potential clinical utility in predicting and identifying distant metastasis in breast cancer. These findings underscore the potential prospect of developing economically efficient and readily accessible predictive tools in clinical oncology.

AI models predicting breast cancer distant metastasis using LightGBM with clinical blood markers and ultrasound maximum diameter

Breast cancer metastasis significantly impacts women's health globally. This study aimed to construct predictive models using clinical blood markers and ultrasound data to predict distant metastasis in breast cancer patients, ensuring clinical applicability, cost-effectiveness, relative non-invasiveness, and accessibility of these models. Analysis was conducted on data from 416 patients across two centers, focusing on clinical blood markers (tumor markers, liver and kidney function indicators, blood lipid markers, cardiovascular biomarkers) and maximum lesion diameter from ultrasound. Feature reduction was performed using Spearman correlation and LASSO regression. Two models were built using LightGBM: a clinical model (using clinical blood markers) and a combined model (incorporating clinical blood markers and ultrasound features), validated in training, internal test, and external validation (test1) cohorts. Feature importance analysis was conducted for both models, followed by univariate and multivariate regression analyses of these features. The AUC values of the clinical model in the training, internal test, and external validation (test1) cohorts were 0.950, 0.795, and 0.883, respectively. The combined model showed AUC values of 0.955, 0.835, and 0.918 in the training, internal test, and external validation (test1) cohorts, respectively. Clinical utility curve analysis indicated the combined model's superior net benefit in identifying breast cancer with distant metastasis across all cohorts. This suggests the combined model's superior discriminatory ability and strong generalization performance. Creatine kinase isoenzyme (CK-MB), CEA, CA153, albumin, creatine kinase, and maximum lesion diameter from ultrasound played significant roles in model prediction. CA153, CK-MB, lipoprotein (a), and maximum lesion diameter from ultrasound positively correlated with breast cancer distant metastasis, while indirect bilirubin and magnesium ions showed negative correlations. This study successfully utilized clinical blood markers and ultrasound data to develop AI models for predicting distant metastasis in breast cancer. The combined model, incorporating clinical blood markers and ultrasound features, exhibited higher accuracy, suggesting its potential clinical utility in predicting and identifying breast cancer distant metastasis. These findings highlight the potential prospects of developing cost-effective and accessible predictive tools in clinical oncology.

Development and validation of AI models using LR and LightGBM for predicting distant metastasis in breast cancer: a dual-center study

Objective

This study aims to develop an artificial intelligence model utilizing clinical blood markers, ultrasound data, and breast biopsy pathological information to predict the distant metastasis in breast cancer patients.

Methods

Data from two medical centers were utilized, Clinical blood markers, ultrasound data, and breast biopsy pathological information were separately extracted and selected. Feature dimensionality reduction was performed using Spearman correlation and LASSO regression. Predictive models were constructed using LR and LightGBM machine learning algorithms and validated on internal and external validation sets. Feature correlation analysis was conducted for both models.

Results

The LR model achieved AUC values of 0.892, 0.816, and 0.817 for the training, internal validation, and external validation cohorts, respectively. The LightGBM model achieved AUC values of 0.971, 0.861, and 0.890 for the same cohorts, respectively. Clinical decision curve analysis showed a superior net benefit of the LightGBM model over the LR model in predicting distant metastasis in breast cancer. Key features identified included creatine kinase isoenzyme (CK-MB) and alpha-hydroxybutyrate dehydrogenase.

Conclusion

This study developed an artificial intelligence model using clinical blood markers, ultrasound data, and pathological information to identify distant metastasis in breast cancer patients. The LightGBM model demonstrated superior predictive accuracy and clinical applicability, suggesting it as a promising tool for early diagnosis of distant metastasis in breast cancer.

Anterior Gradient 2 is a Significant Prognostic Biomarker in Bone Metastasis of Breast Cancer

Background: The study aimed to detect DEGs associated with BRCA bone metastasis, filter prognosis biomarkers, and explore possible pathways.

Methods: GSE175692 dataset was used to detect DEGs between BRCA bone metastatic cases and non-bone metastatic cases, followed by the construction of a PPI network among DEGs. The main module among the PPI network was then determined and pathway analysis on genes within the module was performed. Through performing Cox regression, Kaplan-Meier, nomogram, and ROC curve analyses using GSE175692 and GSE124647 datasets at the same time, the most significant prognostic biomarker was gradually filtered. Finally, important pathways associated with prognostic biomarkers were explored by GSEA analysis.

Results: The 74 DEGs were detected between bone metastasis and non-bone metastasis groups. A total of 15 nodes were included in the main module among the whole PPI network and they mainly correlated with the IL-17 signaling pathway. We then performed Cox analysis on 15 genes using two datasets and only enrolled the genes with p < 0.05 in Cox analysis into the further analyses. Kaplan-Meier analyses using two datasets showed that the common biomarker AGR2 expression was related to the survival time of BRCA metastatic cases. Further, the nomogram determined the greatest contribution of AGR2 on the survival probability and the ROC curve revealed its optimal prognostic performance. More importantly, high expression of AGR2 prolonged the survival time of BRCA bone metastatic patients. These results all suggested the importance of AGR2 in metastatic BRCA. Finally, we performed the GSEA analysis and found that AGR2 was negatively related to IL-17 and NF-kβ signaling pathways.

Conclusion: AGR2 was finally determined as the most important prognostic biomarker in BRCA bone metastasis, and it may play a vital role in cancer progression by regulating IL-17 and NF-kB signaling pathways.

The Asparagine Hydroxylase FIH: A Unique Oxygen Sensor

Significance: Limited oxygen availability (hypoxia) commonly occurs in a range of physiological and pathophysiological conditions, including embryonic development, physical exercise, inflammation, and ischemia. It is thus vital for cells and tissues to monitor their local oxygen availability to be able to adjust in case the oxygen supply is decreased. The cellular oxygen sensor factor inhibiting hypoxia-inducible factor (FIH) is the only known asparagine hydroxylase with hypoxia sensitivity. FIH uniquely combines oxygen and peroxide sensitivity, serving as an oxygen and oxidant sensor. Recent Advances: FIH was first discovered in the hypoxia-inducible factor (HIF) pathway as a modulator of HIF transactivation activity. Several other FIH substrates have now been identified outside the HIF pathway. Moreover, FIH enzymatic activity is highly promiscuous and not limited to asparagine hydroxylation. This includes the FIH-mediated catalysis of an oxygen-dependent stable (likely covalent) bond formation between FIH and selected substrate proteins (called oxomers [oxygen-dependent stable protein oligomers]). Critical Issues: The (patho-)physiological function of FIH is only beginning to be understood and appears to be complex. Selective pharmacologic inhibition of FIH over other oxygen sensors is possible, opening new avenues for therapeutic targeting of hypoxia-associated diseases, increasing the interest in its (patho-)physiological relevance. Future Directions: The contribution of FIH enzymatic activity to disease development and progression should be analyzed in more detail, including the assessment of underlying molecular mechanisms and relevant FIH substrate proteins. Also, the molecular mechanism(s) involved in the physiological functions of FIH remain(s) to be determined. Furthermore, the therapeutic potential of recently developed FIH-selective pharmacologic inhibitors will need detailed assessment. Antioxid. Redox Signal. 37, 913-935.

Prognostic tools at hospital arrival in acute myocardial infarction: copeptin and hepatocyte growth factor

BACKGROUND

Prompt evaluation and treatment of acute coronary syndrome has demonstrated to reduce mortality. Although several biomarkers have been studied for risk stratification and prognostic purposes, none is recommended to guide treatment based on its prognostic value. Copeptin and hepatocyte growth factor have been associated with poor outcome in patients with acute myocardial infarction. The aim of this study is to evaluate the early prognostic value of measurements of copeptin and hepatocyte growth factor for hospital mortality risk and 1-year-follow-up mortality, in patients with acute myocardial infarction. In our retrospective observational study, we measured hepatocyte growth factor and copeptin in blood samples collected at hospital arrival in patients with acute myocardial infarction; and follow-up them until 1-year.

RESULTS

84 patients with were included in the study, mainly male (65%) with a median age of 70.3 ± 13.56 years. Hospital mortality was 11.9%. Plasma levels of copeptin at hospital arrival were statistically significant higher in patients who died during hospital admission (145.60 pmol/L [52.21-588.50] vs. 24.79 pmol/L [10.90-84.82], p 0.01). However, we found no statistically significant association between plasma levels of hepatocyte growth factor and hospital mortality (381.05 pg/ml [189.95-736.65] vs. 355.24 pg/ml [175.55-521.76], p 0.73). 1-year follow-up mortality was 21.4%. Plasma levels of copeptin at hospital arrival were higher in those patients who died in the following year (112.28 pmol/L [25.10-418.27] vs. 23.82 pmol/L [10.96-77.30], p 0.02). In the case of HGF, we also find no association between hepatocyte growth factor plasma levels and 1 -year follow-up mortality (350.00 pg/ml [175.05-555.08] vs. 345.53 pg/ml [183.68-561.15], p 0.68).

CONCLUSIONS

In patients with acute myocardial infarction measurement of copeptin at hospital arrival could be a useful tool to assess the prognosis of these patients, since their elevation is associated with a higher hospital mortality and higher 1-year follow-up mortality. We have not found this association in the case of hepatocyte growth factor measurement.