Abstract 322P
Background
Extensive-stage small cell lung cancer (ES-SCLC) is a highly aggressive neuroendocrine tumor characterized by rapid growth and early metastasis. The combination of immune checkpoint inhibitors (ICIs) and chemotherapy has become the standard treatment. However, the lack of predictive biomarkers remains a significant barrier to personalized treatment. This study aimed to investigate whether small extracellular vesicle (sEV)-derived microRNAs (miRNAs) could serve as predictive biomarkers for the efficacy of immunochemotherapy in ESSCLC patients.
Methods
We prospectively collected clinical data and serum samples from chemotherapy-naïve ES-SCLC patients at Shanghai Chest Hospital, who were subsequently treated with chemoimmunotherapy. Serum sEV miRNAs were isolated and sequenced prior to treatment. Differential expression analysis was performed to identify miRNAs that were differentially expressed between treatment responders and non-responders. Machine learning algorithms were applied to develop predictive models for treatment response.
Results
The screening identified 10 candidate miRNAs, three of which were overexpressed in responders and seven in non-responders. Functional enrichment analysis revealed the biological significance of these differentially expressed sEV miRNAs, including hsa-miR-125a-5p and hsa-miR-150-5p, et al. Among the eight predictive models tested, the Extra Trees algorithm demonstrated superior accuracy, achieving a mean AUC of 0.848, sensitivity of 0.82, specificity of 0.72, and a cutoff value of 0.61. These results suggest its potential for clinical application in prospective samples.
Conclusions
Our research demonstrated that sEV-derived miRNAs have potential as predictive biomarkers for immunochemotherapy outcomes in ES-SCLC. The Extra Trees model represented a valuable tool for personalizing treatment strategies, which could advance precision medicine for ES-SCLC patients.
Legal entity responsible for the study
The authors.
Funding
National Natural Science Foundation of China.
Disclosure
All authors have declared no conflicts of interest.