Accuracy of machine learning in preoperative identification of genetic mutation status in lung cancer: A systematic review and meta-analysis.

BACKGROUND AND PURPOSE: We performed this systematic review and meta-analysis to investigate the performance of ML in detecting genetic mutation status in NSCLC patients. MATERIALS AND METHODS: We conducted a systematic search of PubMed, Cochrane, Embase, and Web of Science up until July 2023. We discussed the genetic mutation status of EGFR, ALK, KRAS, and BRAF, as well as the mutation status at different sites of EGFR. RESULTS: We included a total of 128 original studies, of which 114 constructed ML models based on radiomic features mainly extracted from CT, MRI, and PET-CT data. From a genetic mutation perspective, 121 studies focused on EGFR mutation status analysis. In the validation set, for the detection of EGFR mutation status, the aggregated c-index was 0.760 (95%CI: 0.706-0.814) for clinical feature-based models, 0.772 (95%CI: 0.753-0.791) for CT-based radiomics models, 0.816 (95%CI: 0.776-0.856) for MRI-based radiomics models, and 0.750 (95%CI: 0.712-0.789) for PET-CT-based radiomics models. When combined with clinical features, the aggregated c-index was 0.807 (95%CI: 0.781-0.832) for CT-based radiomics models, 0.806 (95%CI: 0.773-0.839) for MRI-based radiomics models, and 0.822 (95%CI: 0.789-0.854) for PET-CT-based radiomics models. In the validation set, the aggregated c-indexes for radiomics-based models to detect mutation status of ALK and KRAS, as well as the mutation status at different sites of EGFR were all greater than 0.7. CONCLUSION: The use of radiomics-based methods for early discrimination of EGFR mutation status in NSCLC demonstrates relatively high accuracy. However, the influence of clinical variables cannot be overlooked in this process. In addition, future studies should also pay attention to the accuracy of radiomics in identifying mutation status of other genes in EGFR.

Association between albumin-to-globulin ratio and the risk of overall survival in advanced non-small cell lung cancer patients with anlotinib treatment: a retrospective cohort study.

OBJECTIVE: Researches about the association between serum albumin-to-globulin ratio (AGR) and the prognosis of lung cancer are limited. We aimed to investigate the relationship between AGR and overall survival (OS) in patients with advanced non-small-cell lung cancer (NSCLC) treated with anlotinib. METHODS: A retrospective cohort study was conducted on 196 advanced NSCLC patients with anlotinib treatment between June 1, 2018 and June 1, 2021. The exposure was AGR, calculated by baseline serum albumin / (serum total protein - serum albumin). The outcome was OS, defined as the period from the date of initial treatment with anlotinib to death or the last follow-up. The univariate and multivariate linear regression models and generalized additive models (GAM) were used to analyze the relationship between AGR and OS. The Kaplan-Meier method was used to analyze the OS. RESULTS: After adjusting for potential confounders, a non-linear relationship was observed between AGR and OS, which had an inflection point of 1.24. The hazard ratio and the confidence intervals on the left and the right sides of the inflection point were 13.05 (0.52 to 327.64) and 0.20 (0.07 to 0.57), respectively. It suggested that AGR was positively associated with OS when AGR was larger than 1.24, for every 1 unit increase in AGR, the risk of death lowered approximately by 80%. CONCLUSIONS: The relationship between AGR and the OS for advanced NSCLC patients with anlotinib is non-linear. AGR level is an independent protective factor for OS in advanced NSCLC patients who received anlotinib therapy.

Pretreatment prediction of tumour spread through air spaces in clinical stage I non-small-cell lung cancer.

OBJECTIVES: The aim of this study was to construct a nomogram prediction model for tumour spread through air spaces (STAS) in clinical stage I non-small-cell lung cancer (NSCLC) and discuss its potential application value. METHODS: A total of 380 patients with clinical stage I NSCLC in Tianjin Chest Hospital were collected as the training cohort and 285 patients in Fujian Provincial Hospital were collected as the validation cohort. Univariable and multivariable logistic regression analyses were performed to determine independent factors for STAS in the training cohort. Based on the results of the multivariable analysis, the nomogram prediction model of STAS was constructed by R software. RESULTS: The incidence of STAS in the training cohort was 39.2%. STAS was associated with worse overall survival and recurrence-free survival (P < 0.01). Univariable analysis showed that maximum tumour diameter, consolidation-to-tumour ratio, spiculation, vacuole and carcinoembryonic antigen were associated with STAS (P < 0.05). Multivariable analysis showed that maximum tumour diameter, consolidation-to-tumour ratio, spiculation sign and vacuole were independent risk factors for STAS (P < 0.05). Based on this, the nomogram prediction model of STAS in clinical stage I NSCLC was constructed and internally validated by bootstrap. The Hosmer-Lemeshow test showed a χ2 value of 7.218 (P = 0.513). The area under the receiver operating characteristic curve and C-index were 0.724 (95% confidence interval: 0.673-0.775). The external validation conducted on the validation cohort produced an area under the receiver operating characteristic curve of 0.759 (95% confidence interval: 0.703-0.816). CONCLUSIONS: The constructed nomogram prediction model of STAS in clinical stage I NSCLC has good calibration and can potentially be applied to guide treatment selection.