Circulating tumour DNA is a promising biomarker for risk stratification of central chondrosarcoma with IDH1/2 and GNAS mutations

Mapping prenatal predictors and neurobehavioral outcomes of an epigenetic marker of neonatal inflammation - A longitudinal population-based study

BACKGROUND

DNA methylation levels at specific sites can be used to proxy C-reactive protein (CRP) levels, providing a potentially more stable and accurate indicator of sustained inflammation and associated health risk. However, its use has been primarily limited to adults or preterm infants, and little is known about determinants for - or offspring outcomes of - elevated levels of this epigenetic proxy in cord blood. The aim of this study was to comprehensively map prenatal predictors and long-term neurobehavioral outcomes of neonatal inflammation, as assessed with an epigenetic proxy of inflammation in cord blood, in the general pediatric population.

METHODS

Our study was embedded in the prospective population-based Generation R Study (n = 2,394). We created a methylation profile score of CRP (MPS-CRP) in cord blood as a marker of neonatal inflammation and validated it against serum CRP levels in mothers during pregnancy, as well as offspring at birth and in childhood. We then examined (i) which factors (previously associated with sustained inflammation) explain variability in MPS-CRP at birth, including a wide range of prenatal lifestyle and clinical conditions, pro-inflammatory exposures, as well as child genetic liability to elevated CRP levels; and (ii) whether MPS-CRP at birth associates with child neurobehavioral outcomes, including global structural MRI and DTI measures (child mean age 10 and 14 years) as well as psychiatric symptoms over time (Child Behavioral Checklist, at mean age 1.5, 3, 6, 10 and 14 years).

RESULTS

MPS-CRP at birth was validated with serum CRP in cord blood (cut-off > 1 mg/L) (AUC = 0.72). Prenatal lifestyle pro-inflammatory factors explained a small part (i.e., < 5%) of the variance in the MPS-CRP at birth. No other prenatal predictor or the polygenic score of CRP in the child explained significant variance in the MPS-CRP at birth. The MPS-CRP at birth prospectively associated with a reduction in global fractional anisotropy over time on mainly a nominal threshold (β = -0.014, SE = 0.007, p = 0.032), as well as showing nominal associations with structural differences (amygdala [(β = 0.016, SE = 0.006, p = 0.010], cerebellum [(β = -0.007, SE = 0.003, p = 0.036]). However, no associations with child psychiatric symptoms were observed.

CONCLUSION

Prenatal exposure to lifestyle-related pro-inflammatory factors was the only prenatal predictor that accounted for some of the individual variability in MPS-CRP levels at birth. Further, while the MPS-CRP prospectively associated with white matter alterations over time, no associations were observed at the behavioral level. Thus, the relevance and potential utility of using epigenetic data as a marker of neonatal inflammation in the general population remain unclear. In the future, the use of epigenetic proxies for a wider range of immune markers may lend further insights into the relationship between neonatal inflammation and adverse neurodevelopment within the general pediatric population.

Novel machine-learning prediction tools for overall survival of patients with chondrosarcoma: Based on recursive partitioning analysis

BACKGROUND

Chondrosarcoma (CHS), a bone malignancy, poses a significant challenge due to its heterogeneous nature and resistance to conventional treatments. There is a clear need for advanced prognostic instruments that can integrate multiple prognostic factors to deliver personalized survival predictions for individual patients. This study aimed to develop a novel prediction tool based on recursive partitioning analysis (RPA) to improve the estimation of overall survival for patients with CHS.

METHODS

Data from the Surveillance, Epidemiology, and End Results (SEER) database were analyzed, including demographic, clinical, and treatment details of patients diagnosed between 2000 and 2018. Using C5.0 algorithm, decision trees were created to predict survival probabilities at 12, 24, 60, and 120 months. The performance of the models was assessed through confusion scatter plot, accuracy rate, receiver operator characteristic (ROC) curve, and area under ROC curve (AUC).

RESULTS

The study identified tumor histology, surgery, age, visceral (brain/liver/lung) metastasis, chemotherapy, tumor grade, and sex as critical predictors. Decision trees revealed distinct patterns for survival prediction at each time point. The models showed high accuracy (82.40%-89.09% in training group, and 82.16%-88.74% in test group) and discriminatory power (AUC: 0.806-0.894 in training group, and 0.808-0.882 in test group) in both training and testing datasets. An interactive web-based shiny APP (URL: https://yangxg1209.shinyapps.io/chondrosarcoma_survival_prediction/) was developed, simplifying the survival prediction process for clinicians.

CONCLUSIONS

This study successfully employed RPA to develop a user-friendly tool for personalized survival predictions in CHS. The decision tree models demonstrated robust predictive capabilities, with the interactive application facilitating clinical decision-making. Future prospective studies are recommended to validate these findings and further refine the predictive model.

Local Therapies for Metastatic Sarcoma: Why, When, and How?

Management of patients with advanced sarcoma has been evolving in recent decades, from a one-fit-all perspective to a more refined, personalized, and multidisciplinary approach. In parallel, the evolution of local therapies (radiotherapy, surgical and interventional radiology techniques) has contributed to the improvement of survival of patients with advanced sarcoma. In this article, we review the evidence regarding local treatments in advanced sarcoma, as well as its integration with systemic therapies, to provide the reader a wider and deeper perspective on the management of patients with metastatic sarcoma.

Deep learning models for predicting the survival of patients with chondrosarcoma based on a surveillance, epidemiology, and end results analysis

Background

Accurate prediction of prognosis is critical for therapeutic decisions in chondrosarcoma patients. Several prognostic models have been created utilizing multivariate Cox regression or binary classification-based machine learning approaches to predict the 3- and 5-year survival of patients with chondrosarcoma, but few studies have investigated the results of combining deep learning with time-to-event prediction. Compared with simplifying the prediction as a binary classification problem, modeling the probability of an event as a function of time by combining it with deep learning can provide better accuracy and flexibility.

Materials and methods

Patients with the diagnosis of chondrosarcoma between 2000 and 2018 were extracted from the Surveillance, Epidemiology, and End Results (SEER) registry. Three algorithms—two based on neural networks (DeepSurv, neural multi-task logistic regression [NMTLR]) and one on ensemble learning (random survival forest [RSF])—were selected for training. Meanwhile, a multivariate Cox proportional hazards (CoxPH) model was also constructed for comparison. The dataset was randomly divided into training and testing datasets at a ratio of 7:3. Hyperparameter tuning was conducted through a 1000-repeated random search with 5-fold cross-validation on the training dataset. The model performance was assessed using the concordance index (C-index), Brier score, and Integrated Brier Score (IBS). The accuracy of predicting 1-, 3-, 5- and 10-year survival was evaluated using receiver operating characteristic curves (ROC), calibration curves, and the area under the ROC curves (AUC).

Results

A total of 3145 patients were finally enrolled in our study. The mean age at diagnosis was 52 ± 18 years, 1662 of the 3145 patients were male (53%), and mean survival time was 83 ± 67 months. Two deep learning models outperformed the RSF and classical CoxPH models, with the C-index on test datasets achieving values of 0.832 (DeepSurv) and 0.821 (NMTLR). The DeepSurv model produced better accuracy and calibrated survival estimates in predicting 1-, 3- 5- and 10-year survival (AUC:0.895-0.937). We deployed the DeepSurv model as a web application for use in clinical practice; it can be accessed through https://share.streamlit.io/whuh-ml/chondrosarcoma/Predict/app.py.

Conclusions

Time-to-event prediction models based on deep learning algorithms are successful in predicting chondrosarcoma prognosis, with DeepSurv producing the best discriminative performance and calibration.