Clinical utility of [18F]FDG PET/CT in the assessment of mediastinal lymph node disease after neoadjuvant chemoimmunotherapy for non-small cell lung cancer.

OBJECTIVES: The performance of positron emission tomography/computed tomography (PET/CT) for the prediction of ypN2 disease in non-small cell lung cancer (NSCLC) after neoadjuvant chemoimmunotherapy has not been reported. This multicenter study investigated the utility of PET/CT to assess ypN2 disease in these patients. METHODS: A total of 181 consecutive patients (chemoimmunotherapy = 86, chemotherapy = 95) at four institutions were enrolled in this study. Every patient received a PET/CT scan prior to surgery and complete resection with systematic nodal dissection. The diagnostic performance was evaluated through area under the curve (AUC). Kaplan-Meier method and Cox analysis were performed to identify the risk factors affecting recurrences. RESULTS: The sensitivity, specificity, and accuracy of PET/CT for ypN2 diseases were 0.667, 0.835, and 0.779, respectively. Therefore, the AUC was 0.751. Compared with the false positive cases, the mean value of max standardized uptake value (SUVmax) (6.024 vs. 2.672, p < 0.001) of N2 nodes was significantly higher in true positive patients. Moreover, the SUVmax of true positive (7.671 vs. 5.976, p = 0.365) and false (2.433 vs. 2.339, p = 0.990) positive cases were similar between chemoimmunotherapy and chemotherapy, respectively. Survival analysis proved that pathologic N (ypN) 2 patients could be stratified by PET/CT-N2(+ vs. -) for both chemoimmunotherapy (p = 0.023) and chemotherapy (p = 0.010). CONCLUSIONS: PET/CT is an accurate and non-invasive test for mediastinal restaging of NSCLC patients who receive neoadjuvant chemoimmunotherapy. The ypN2 patients with PET/CT-N2( +) are identified as an independent prognostic factor compared with PET/CT-N2(-). CLINICAL RELEVANCE STATEMENT: Imaging with 18F-fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) plays an integral role during disease diagnosis, staging, and therapeutic response assessments in patients with NSCLC. PET/CT could be an effective non-invasive tool for predicting ypN2 diseases after neoadjuvant chemoimmunotherapy. KEY POINTS: • PET/CT could serve as an effective non-invasive tool for predicting ypN2 diseases. • The ypN2 patients with PET/CT-N2( +) were a strong and independent prognostic factor. • The application of PET/CT for restaging should be encouraged in clinical practice.

Invasiveness assessment by artificial intelligence against intraoperative frozen section for pulmonary nodules ≤ 3 cm.

PURPOSE: To investigate the performance of an artificial intelligence (AI) algorithm for assessing the malignancy and invasiveness of pulmonary nodules in a multicenter cohort. METHODS: A previously developed deep learning system based on a 3D convolutional neural network was used to predict tumor malignancy and invasiveness. Dataset of pulmonary nodules no more than 3 cm was integrated with CT images and pathologic information. Receiver operating characteristic curve analysis was used to evaluate the performance of the system. RESULTS: A total of 466 resected pulmonary nodules were included in this study. The areas under the curves (AUCs) of the deep learning system in the prediction of malignancy as compared with pathological reports were 0.80, 0.80, and 0.75 for all, subcentimeter, and solid nodules, respectively. Additionally, the AUC in the AI-assisted prediction of invasive adenocarcinoma (IA) among subsolid lesions (n = 184) was 0.88. Most malignancies that were misdiagnosed by the AI system as benign diseases with a diameter measuring greater than 1 cm (26/250, 10.4%) presented as solid nodules (19/26, 73.1%) on CT. In an exploratory analysis involving nodules underwent intraoperative pathologic examination, the concordance rate in identifying IA between the AI model and frozen section examination was 0.69, with a sensitivity of 0.50 and specificity of 0.97. CONCLUSION: The deep learning system can discriminate malignant diseases for pulmonary nodules measuring no more than 3 cm. The AI model has a high positive predictive value for invasive adenocarcinoma with respect to intraoperative frozen section examination, which might help determine the individualized surgical strategy.

Prediction of acute kidney injury in ICU with gradient boosting decision tree algorithms.

PURPOSE: To predict acute kidney injury (AKI) in a large intensive care unit (ICU) database. MATERIALS AND METHODS: A total of 30,020 ICU admissions with 17,222 AKI episodes were extracted from the Medical Information Mart from Intensive Care (MIMIC)-III database. These were randomly divided into a training set and an independent testing set in a ratio of 4:1. Data pertaining to demographics, admission information, vital signs, laboratory tests, critical illness scores, medications, comorbidities, and intervention measures were collected. Logistic regression, random forest, LightGBM, XGBoost, and an ensemble model was used for early prediction of AKI occurrence and important feature extraction. The SHAP analysis was adopted to reveal the impact of prediction for each feature. RESULTS: The ensemble model had the best overall performance for predicting AKI before 24 h, 48 h and 72 h. The F1 values were 0.915, 0.893, and 0.878, respectively. AUCs were 0.923, 0.903, and 0.895, respectively. CONCLUSIONS: Based on readily available electronic medical record (EMR) data, gradient boosting decision tree models are highly accurate at early AKI prediction in critically ill patients.