UNASSIGNED: To date, no specific studies have reported the use of dynamic serum tumor markers (STMs) as prognostic factors in patients with advanced non-small-cell lung cancer (NSCLC) who receive first-line immunotherapy. Therefore, it is unclear whether STMs can be used as a prognostic factor for first-line immunotherapy in advanced NSCLC.
UNASSIGNED: To elucidate the role of STMs in monitoring immunotherapy response in advanced NSCLC. Patients were treated with first-line programmed cell death-1/programmed cell death ligand-1 inhibitors at four Chinese centers.
UNASSIGNED: This was a multicenter retrospective study.
UNASSIGNED: Blood samples were collected at baseline and after 6-8 weeks of treatment. Computed tomography scans were used to evaluate treatment efficacy according to Response Evaluation Criteria in Solid Tumors (RECIST) 1.1. Post-treatment drops in STMs [Serum carcinoembryonic antigen (CEA), neuron-specific enolase (NSE), cytokeratin fragment 19 (CYFRA21-1), carbohydrate antigen 19-9 (CA19-9), and carbohydrate antigen 125 (CA125)] were decreased ⩾20% (Group C) over baseline was used as cutoff level for defining a marker response. If STMs were increased by ⩾20% after treatment, the therapeutic effect was limited (Group A). Patients with STM changes between a 20% increase or decrease were enrolled in Group B. In univariate and multivariate stepwise Cox regression analyses, STMs and RECIST responses were analyzed for their impact on progression-free survival (PFS) and overall survival (OS).
UNASSIGNED: The analysis included 716 patients. By multivariate analysis, CEA, NSE, CYFRA21-1, CA19-9, and CA125 (Group A versus Group B and Group A versus Group C) were associated with significant differences in PFS. Similar results were observed in the OS analysis. Similar results were observed in the adenocarcinoma subgroup analyses. In squamous cell carcinoma subgroup analyses, there was no statistical difference in PFS (p = 0.147) or OS (p = 0.068) between Group A and Group B for CA125.
UNASSIGNED: The increase and decrease in serum levels of STMs might be reliable prognostic factors for immunotherapy efficacy in NSCLC patients.

BACKGROUND: Timely identification of epidermal growth factor receptor (EGFR) mutation and anaplastic lymphoma kinase (ALK) rearrangement status in patients with non-small cell lung cancer (NSCLC) is essential for tyrosine kinase inhibitors (TKIs) administration. We aimed to use artificial intelligence (AI) models to predict EGFR mutations and ALK rearrangement status using common demographic features, pathology and serum tumor markers (STMs).
METHODS: In this single-center study, demographic features, pathology, EGFR mutation status, ALK rearrangement, and levels of STMs were collected from Wuhan Union Hospital. One retrospective set (N = 1089) was used to train diagnostic performance using one deep learning model and five machine learning models, as well as the stacked ensemble model for predicting EGFR mutations, uncommon EGFR mutations, and ALK rearrangement status. A consecutive testing cohort (n = 1464) was used to validate the predictive models.
RESULTS: The final AI model using the stacked ensemble yielded optimal diagnostic performance with areas under the curve (AUC) of 0.897 and 0.883 for predicting EGFR mutation status and 0.995 and 0.921 for predicting ALK rearrangement in the training and testing cohorts, respectively. Furthermore, an overall accuracy of 0.93 and 0.83 in the training and testing cohorts, respectively, were achieved in distinguishing common and uncommon EGFR mutations, which were key evidence in guiding TKI selection.
CONCLUSIONS: In this study, driverless AI based on robust variables could help clinicians identify EGFR mutations and ALK rearrangement status and provide vital guidance in TKI selection for targeted therapy in NSCLC patients.

BACKGROUND: The dynamic monitoring of perioperative carcinoembryonic antigen (CEA) is recommended by current colorectal cancer (CRC) guidelines, while the benefits of additional measurements of carbohydrate antigen 19-9 (CA19-9) and carbohydrate antigen 125 (CA125) have remained controversial.
METHODS: This retrospective longitudinal cohort included 3539 CRC patients who underwent curative resection. Distinct trajectory groups were identified by the latent class growth mixed model. Patients were grouped into subgroups jointly by CEA, CA19-9, and CA125 according to preoperative levels and longitudinal trajectories, respectively. The end points were overall survival (OS) and recurrence-free survival (RFS).
RESULTS: Three distinct trajectory groups were characterized for serum CEA, CA19-9, and CA125: low-stable, early-rising, and later-rising. Jointly, patients were grouped into six preoperative (trajectory) joint groups. Compared with the three-low group, the adjusted hazard ratios (HRs) and 95% confidence intervals (CIs) associated with death were 1.87 (1.29-2.70), 3.82 (2.37-6.17), 1.87 (0.97-3.61), 2.81 (1.93-4.11), and 4.99 (2.80-8.86) for the CEA-high, CA19-9-high, CA125-high, two-high, and three-high group, respectively. And compared with the three-stable trajectory group, the corresponding HRs (95% CIs) were 1.59 (1.10-2.30), 1.55 (0.77-3.10), 6.25 (4.02-9.70), 4.05 (2.73-6.02), and 12.40 (5.77-26.70) for the five rising trajectory groups, respectively. Similar associations between joint groups and RFS were observed. Notably, the trajectory joint group still had prognostic significance after adjusting for preoperative levels. The CA19-9-high group (HR: 3.82, 95% CI: 2.37-6.17) was associated with higher risk of death than the two-high group (HR: 2.81, 95% CI: 1.93-4.11). Likewise, for the CA125-rising trajectory group and two-rising trajectory group, the HRs (95% CIs) were 6.13 (3.75-10.00) and 3.99 (2.63-6.05) for death, and 3.08 (2.07-4.58) and 2.10 (1.52-2.90) for recurrence.
CONCLUSIONS: In addition to CEA, the dynamic measurements of CA19-9 and CA125 are recommended to monitor the prognosis of CRC patients.
BACKGROUND: National Natural Science Foundation of China [81973147, 82001986, 81960592, 82073569, 81660545].