Search

Graphical abstract, Severity prediction of COVID-19 remains one of the major clinical challenges for the ongoing pandemic. Here, we have recruited a 144 COVID-19 patient cohort, resulting in a data matrix containing 3,065 readings for 124 types of measurements over 52 days. A machine learning model was established to predict the disease progression based on the cohort consisting of training, validation, and internal test sets. A panel of eleven routine clinical factors constructed a classifier for COVID-19 severity prediction, achieving accuracy of over 98% in the discovery set. Validation of the model in an independent cohort containing 25 patients achieved accuracy of 80%. The overall sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 0.70, 0.99, 0.93, and 0.93, respectively. Our model captured predictive dynamics of lactate dehydrogenase (LDH) and creatine kinase (CK) while their levels were in the normal range. This model is accessible at https://www.guomics.com/covidAI/ for research purpose.

Purpose We initially aimed to ascertain the application value of inflammatory indexes in predicting severe acute radiation pneumonitis (SARP). Furthermore, a novel nomogram and risk classification system integrating clinicopathologic, dosimetric, and biological parameters were built to provide individualized risk assessment and accurate prediction of SARP in patients with esophageal cancer who received radiation therapy. Methods and Materials All data were retrospectively collected from 416 esophageal cancer patients in 2 participating institutes. A novel nomogram was constructed that forecasted SARP based on logistic regression analyses. The concordance index, calibration curves, and decision curve analyses were used by both internal and external validation to demonstrate discriminatory and predictive capacity. Moreover, a corresponding risk classification system was generated by recursive partitioning analysis. Results The Subjective Global Assessment score, pulmonary fibrosis score, planning target volume/total lung volume, mean lung dose, and ratio of change regarding systemic immune inflammation index at 4 weeks in the course of treatment were independent predictors of SARP and finally incorporated into our nomogram. The concordance index of nomogram for SARP prediction was 0.852, which showed superior discriminatory power (range, 0.604-0.712). Calibration curves indicated favorable consistency between the nomogram prediction and the actual outcomes. Decision curve analyses exhibited satisfactory clinical utility. A risk classification system was established to perfectly divide patients into 3 different risk groups, which were low-risk group (6.1%, score 0-158), intermediate-risk group (37.3%, score 159-280), and high-risk group (78.9%, score >280). Conclusions The Subjective Global Assessment score, pulmonary fibrosis score, planning target volume/total lung volume, mean lung dose, and ratio of change regarding systemic immune inflammation index at 4 weeks were potential valuable markers in predicting SARP. The developed nomogram and corresponding risk classification system with superior prediction ability for SARP could assist in patient counseling and provide guidance when making treatment decisions.

Background Acute radiation-induced esophagitis (ARIE) is one of main toxicities complicated by thoracic radiotherapy, influencing patients' quality of life and radiotherapy proceeding seriously. It is difficult to be cured rapidly so far. Our phase I trial preliminarily showed that EGCG may be a promising strategy in the treatment of ARIE. Materials and methods We prospectively enrolled patients with stage III lung cancer from the Shandong Tumor Hospital & Institute in China from January 2013 to September 2014. All patients received concurrent or sequential chemo-radiotherapy, or radiotherapy only. EGCG was administrated once ARIE appeared. EGCG was given with the concentration of 440μmol/L during radiotherapy and additionally two weeks after radiotherapy. RTOG score, dysphagia and pain related to esophagitis were recorded every week. Results Thirty-seven patients with stage IIIA and IIIB lung cancer were enrolled in this trial. In comparison to the original, the RTOG score in the 1st, 2nd, 3rd, 4th, 5th week after EGCG prescription and the 1st, 2nd week after radiotherapy decreased significantly ( P =0.002, 0.000, 0.000, 0.001, 0.102, 0.000, 0.000, respectively). The pain score of each week was significantly lower than the baseline ( P =0.000, 0.000, 0.000, 0.000, 0.006, 0.000, 0.000, respectively). Conclusion This trial confirmed that the oral administration of EGCG is an effective and safe method to deal with ARIE. A phase III randomized controlled trial is expected to further corroborate the consequence of EGCG in ARIE treatment.

Purpose Accurate staging of mediastinal lymph nodes metastases is critical for determining the application of stereotactic body radiation therapy (SBRT) for patients with early stage non-small cell lung cancer (NSCLC). In this multicenter study the accuracy of 18 F-FDG PET/CT to detect lymph node metastases was evaluated for early stage NSCLC. Materials and methods The data from the patients with stage1 NSCLC who received preoperative 18 F-FDG PET/CT staging and radical surgery was retrospectively reviewed of five centers from February 2004 to August 2010. The lymph node metastases were confirmed histopathologically after radical surgery. And the sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) were calculated for PET/CT staging. Results Two hundred patients were enrolled. The sensitivity, specificity, accuracy, PPV and NPV for lymph node metastases on PET/CT were 44%, 83%, 78%, 29% and 91%, respectively. There were eight and 19 cases positive for lymph node metastases with central ( n =62) and peripheral ( n =138) NSCLC ( P> 0.05), respectively. Conclusion 18 F-FDG PET/CT was specific in N 0 staging for T 1–2 NSCLC. The NPV was about 91% in clinical N 0 patients, suggested that 18 F-FDG PET/CT may help to accurately stage N 0 patients and thus identify patients for SBRT.

Purpose: To determine the optimal clinical target volume (CTV) margins around the nodal gross tumor volume (GTV) in non–small-cell lung cancer (NSCLC) patients by assessing microscopic tumor extension beyond regional lymph node capsules. Methods and Materials: The incidence of nodal extracapsular extension (ECE) and relationship with nodal size were reviewed in 243 patients. Histologic sections of dissected regional lymph nodes up to 30 mm in size were examined to measure the extent of microscopic ECE. We determined the distribution of cases according to extent of ECE and the relationships between ECE extent and lymph node size, regional nodal disease extent, histologic type, and degree of differentiation. Results: The nodal ECE was seen in 41.6% of patients (101/243) and 33.4% of lymph nodes (214/640), and the incidence correlated to larger lymph node size positively. The extent of ECE was 0.7 mm in mean (range, 0–12.0 mm) and ≤3 mm in 95% of the nodes. Positive correlations were found between extent of ECE and larger lymph node size (≥20 mm vs. 10–19 mm or p = 0.005), advanced nodal stage (N2 vs. N1, p = 0.046), and moderate or poor (vs. good or unknown) nodal differentiation ( p = 0.002). ECE did not differ significantly by histologic type or nodal station. Conclusions: The incidence of ECE related to lymph node size, and ECE extent related to lymph node size, stage, and differentiation. It may be reasonable to recommend 3-mm CTV margins for pathologic lymph nodes