Predicting checkpoint inhibitors pneumonitis in non-small cell lung cancer using a dynamic online hypertension nomogram

MRI-Based Machine Learning Fusion Models to Distinguish Encephalitis and Gliomas

This paper aims to compare the performance of the classical machine learning (CML) model and the deep learning (DL) model, and to assess the effectiveness of utilizing fusion radiomics from both CML and DL in distinguishing encephalitis from glioma in atypical cases. We analysed the axial FLAIR images of preoperative MRI in 116 patients pathologically confirmed as gliomas and clinically diagnosed with encephalitis. The 3 CML models (logistic regression (LR), support vector machine (SVM) and multi-layer perceptron (MLP)), 3 DL models (DenseNet 121, ResNet 50 and ResNet 18) and a deep learning radiomic (DLR) model were established, respectively. The area under the receiver operating curve (AUC) and sensitivity, specificity, accuracy, negative predictive value (NPV) and positive predictive value (PPV) were calculated for the training and validation sets. In addition, a deep learning radiomic nomogram (DLRN) and a web calculator were designed as a tool to aid clinical decision-making. The best DL model (ResNet50) consistently outperformed the best CML model (LR). The DLR model had the best predictive performance, with AUC, sensitivity, specificity, accuracy, NPV and PPV of 0.879, 0.929, 0.800, 0.875, 0.867 and 0.889 in the validation sets, respectively. Calibration curve of DLR model shows good agreement between prediction and observation, and the decision curve analysis (DCA) indicated that the DLR model had higher overall net benefit than the other two models (ResNet50 and LR). Meanwhile, the DLRN and web calculator can provide dynamic assessments. Machine learning (ML) models have the potential to non-invasively differentiate between encephalitis and glioma in atypical cases. Furthermore, combining DL and CML techniques could enhance the performance of the ML models.

Development and validation of a nomogram for predicting immune-related pneumonitis after sintilimab treatment

BACKGROUND

Immune-related pneumonitis is a rare and potentially fatal adverse event associated with sintilimab. We aimed to develop and validate a nomogram for predicting the risk of immune-related pneumonitis in patients treated with sintilimab.

METHODS

The least absolute shrinkage and selection operator (LASSO) regression was used to determine risk factors. Multivariable logistic regression was used to establish a prediction model. Its clinical validity was evaluated using calibration, discrimination, decision, and clinical impact curves. Internal validation was performed against the validation set and complete dataset.

RESULTS

The study included 632 patients; 59 were diagnosed with immune-related pneumonitis. LASSO regression analysis identified that the risk factors for immune-related pneumonitis were pulmonary metastases (odds ratio [OR], 4.015; 95% confidence interval [CI]: 1.725-9.340) and metastases at >3 sites (OR, 2.687; 95% CI: 1.151-6.269). The use of combined antibiotics (OR, 0.247; 95% CI: 0.083-0.738) and proton pump inhibitors (OR, 0.420; 95% CI: 0.211-0.837) were protective factors. The decision and clinical impact curves showed that the nomogram had clinical value for patients treated with sintilimab.

CONCLUSIONS

We have developed and validated a practical nomogram model of sintilimab-associated immune-related pneumonitis, which provides clinical value for determining the risk of immune-related pneumonitis and facilitating the safe administration of sintilimab therapy.

Common methodological pitfalls in ICI pneumonitis risk prediction studies

Background

Pneumonitis is one of the most common adverse events induced by the use of immune checkpoint inhibitors (ICI), accounting for a 20% of all ICI-associated deaths. Despite numerous efforts to identify risk factors and develop predictive models, there is no clinically deployed risk prediction model for patient risk stratification or for guiding subsequent monitoring. We believe this is due to systemic suboptimal approaches in study designs and methodologies in the literature. The nature and prevalence of different methodological approaches has not been thoroughly examined in prior systematic reviews.

Methods

The PubMed, medRxiv and bioRxiv databases were used to identify studies that aimed at risk factor discovery and/or risk prediction model development for ICI-induced pneumonitis (ICI pneumonitis). Studies were then analysed to identify common methodological pitfalls and their contribution to the risk of bias, assessed using the QUIPS and PROBAST tools.

Results

There were 51 manuscripts eligible for the review, with Japan-based studies over-represented, being nearly half (24/51) of all papers considered. Only 2/51 studies had a low risk of bias overall. Common bias-inducing practices included unclear diagnostic method or potential misdiagnosis, lack of multiple testing correction, the use of univariate analysis for selecting features for multivariable analysis, discretization of continuous variables, and inappropriate handling of missing values. Results from the risk model development studies were also likely to have been overoptimistic due to lack of holdout sets.

Conclusions

Studies with low risk of bias in their methodology are lacking in the existing literature. High-quality risk factor identification and risk model development studies are urgently required by the community to give the best chance of them progressing into a clinically deployable risk prediction model. Recommendations and alternative approaches for reducing the risk of bias were also discussed to guide future studies.

Pre- and Post-Operative Online Prediction of Outcome in Patients Undergoing Endovascular Coiling after Aneurysmal Subarachnoid Hemorrhage: Visual and Dynamic Nomograms

BACKGROUND

Aneurysmal subarachnoid hemorrhage (aSAH) causes long-term functional dependence and death. Early prediction of functional outcomes in aSAH patients with appropriate intervention strategies could lower the risk of poor prognosis. Therefore, we aimed to develop pre- and post-operative dynamic visualization nomograms to predict the 1-year functional outcomes of aSAH patients undergoing coil embolization.

METHODS

Data were obtained from 400 aSAH patients undergoing endovascular coiling admitted to the People's Hospital of Hunan Province in China (2015-2019). The key indicator was the modified Rankin Score (mRS), with 3-6 representing poor functional outcomes. Multivariate logistic regression (MLR)-based visual nomograms were developed to analyze baseline characteristics and post-operative complications. The evaluation of nomogram performance included discrimination (measured by C statistic), calibration (measured by the Hosmer-Lemeshow test and calibration curves), and clinical usefulness (measured by decision curve analysis).

RESULTS

Fifty-nine aSAH patients (14.8%) had poor outcomes. Both nomograms showed good discrimination, and the post-operative nomogram demonstrated superior discrimination to the pre-operative nomogram with a C statistic of 0.895 (95% CI: 0.844-0.945) vs. 0.801 (95% CI: 0.733-0.870). Each was well calibrated with a Hosmer-Lemeshow p-value of 0.498 vs. 0.276. Moreover, decision curve analysis showed that both nomograms were clinically useful, and the post-operative nomogram generated more net benefit than the pre-operative nomogram. Web-based online calculators have been developed to greatly improve the efficiency of clinical applications.

CONCLUSIONS

Pre- and post-operative dynamic nomograms could support pre-operative treatment decisions and post-operative management in aSAH patients, respectively. Moreover, this study indicates that integrating post-operative variables into the nomogram enhanced prediction accuracy for the poor outcome of aSAH patients.

Predictors of immune checkpoint inhibitor-related adverse events in older patients with lung cancer: a prospective real-world analysis

PURPOSE

Older patients with cancer are underrepresented in pivotal trials of immune checkpoint inhibitors (ICIs). This study aimed to investigate immune-related adverse events (irAEs) that occur in older patients with lung cancer treated with ICIs, and explore predictors of the occurrence of irAEs.

METHODS

A prospective analysis was performed on older patients with lung cancer aged ≥ 65 years who were treated with anti-programmed cell death-1/-ligand 1 (PD-1/PD-L1) inhibitors in Beijing Hospital from January 2018 to December 2022. The incidence and risk factors of irAEs were estimated by the Chi-square test or Wilcoxon rank-sum tests. The predictive power of Geriatric-8 (G-8) for irAEs was tested by receiver operating characteristic (ROC) curve analysis. Lymphocyte counts were measured by flow cytometry. Cytokine levels were tested by Enzyme-linked immunosorbent assay, respectively. Kaplan-Meier method was used to calculated progression-free survival (PFS) curves, and the log-rank test was used to evaluate differences.

RESULTS

A total of 201 older patients aged ≥ 65 years with lung cancer were enrolled in this study. The most common irAEs were interstitial pneumonia, dermatological toxicity and hypothyroidism, with rates of 17.2%, 16.1% and 5.6%, respectively. ROC showed that G-8 could predict the occurrence of irAEs in patients aged 65-71 years (≥ G2 irAEs: AUC = 0.757, p < 0.001; ≥ G3 irAEs: AUC = 0.862, p < 0.001), but not for patients aged ≥ 71 years. NLR, LMR, PNI, hypertension and diabetes were associated with irAEs. Lower CD4 + T cells and B cells, and lower levels of IL-10 were associated with the development of irAEs.

CONCLUSION

Our study confirmed the accuracy of G-8 for predicting irAEs in older patients. We also identified several predictors of irAEs in older patients with lung cancer.

A nomogram for predicting overall survival of patients with squamous cell carcinoma of the floor of the mouth: a population-based study

BACKGROUND

Floor of mouth squamous cell carcinoma (SCCFOM) is a rare but aggressive malignancy with 5-year overall survival (OS) rates below 40% in published studies. However, the clinicopathological predictors of the prognosis of SCCFOM remain undefined. We aimed to establish a model to predict the survival outcomes of SCCFOM.

METHODS

We searched the Surveillance, Epidemiology, and End Results (SEER) database for patients diagnosed with SCCFOM between 2000 and 2017. Data on patient demographics, treatment modalities, and survival outcomes were retrieved. Risk factors for OS were evaluated by survival and Cox regression analyses. A nomogram for OS was developed based on the multivariate model and split the patients into high- and low-risk cohorts based on cutoff values.

RESULTS

Overall, 2014 SCCFOM patients were included in this population-based study. Multivariate Cox regression showed that age, married status, grade, American Joint Committee on Cancer stage, radiotherapy, chemotherapy, and surgery were significant risk factors for survival. A nomogram was established using the regression model. The C-indices, areas under the receiver operating characteristic curves, and calibration plots demonstrated the reliable performance of the nomogram. Patients assigned to the high-risk group had a significantly lower survival rate.

CONCLUSIONS

The nomogram predicting survival outcomes of SCCFOM patients based on clinical information showed good discriminative ability and prognostic accuracy. Our nomogram could be used to predict the survival probabilities for SCCFOM patients at different timepoints.