What Are the Biomarkers for Immunotherapy in SCLC?

Comprehensive genomic and spatial immune infiltration analysis of survival outliers in extensive-stage small cell lung cancer receiving first-line chemoimmunotherapy

BACKGROUND

A minority of patients with extensive-stage small cell lung cancer (ES-SCLC) exhibit prolonged survival following first-line chemoimmunotherapy, which warrants the use of reliable biomarkers. Here, we investigated the disparities in genomics and immune cell spatial distribution between long- and short-term survival of patients with ES-SCLC.

METHODS

We retrospectively recruited 11 long-term (>2 years) and 13 short-term (<9 months) ES-SCLC survivors receiving first-line chemoimmunotherapy. The samples were processed using targeted next-generation sequencing (tNGS), programmed death ligand-1 staining, multiplex immunohistochemical staining for immune cells (mIHC), tumor mutation burden (TMB), and chromosomal instability score measurements. The expression of putative genes in SCLC at the bulk and single-cell RNA-sequencing levels, as well as the role of putative genes in pan-cancer immunotherapy cohorts, were analyzed.

RESULTS

At the genomic level, a greater proportion of the smoking signature and higher TMB (>3.1) were associated with favorable survival. At the single-gene and pathway levels, tNGS revealed that MCL1 and STMN1 amplification and alterations in the apoptosis pathway were more common in short-term survivors, whereas alterations in the DLL3, KMT2B, HGF, EPHA3, ADGRB3, lysine deprivation, and HGF-cMET pathways were observed more frequently in long-term survivors. mIHC analysis of immune cells with different spatial distributions revealed that long-term survivors presented increased numbers of M1-like macrophages in all locations and decreased numbers of CD8+ T cells in the tumor stroma. Bulk transcriptomic analysis demonstrated that high levels of STMN1 and DLL3 represented an immune-suppressive tumor immune microenvironment (TIME), whereas HGF indicated an immune-responsive TIME. The expression levels of our putative genes were comparative in both TP53/RB1 mutant-type and TP53/RB1 wild-type. At the single-cell level, STMN1, MCL1, and DLL3 were highly expressed among all molecular subtypes (SCLC-A, SCLC-N, and SCLC-P), with STMN1 being enriched in cell division and G2M checkpoint pathways.

CONCLUSIONS

For ES-SCLC patients receiving first-line chemoimmunotherapy, alterations in DLL3, KMT2B, HGF, EPHA3, and ADGRB3 and a greater proportion of M1-like macrophages infiltration in all locations were predictors of favorable survival, while MCL1 and STMN1 amplification, as well as a greater proportion of CD8+ T cells infiltrating the tumor stroma, predicted worse survival.

Personalized treatment using predictive biomarkers in solid organ malignancies: A review

In recent years, the influence of specific biomarkers in the diagnosis and prognosis of solid organ malignancies has been increasingly prominent. The relevance of the use of predictive biomarkers, which predict cancer response to specific forms of treatment provided, is playing a more significant role than ever before, as it affects diagnosis and initiation of treatment, monitoring for efficacy and side effects of treatment, and adjustment in treatment regimen in the long term. In the current review, we explored the use of predictive biomarkers in the treatment of solid organ malignancies, including common cancers such as colorectal cancer, breast cancer, lung cancer, prostate cancer, and cancers associated with high mortalities, such as pancreatic cancer, liver cancer, kidney cancer and cancers of the central nervous system. We additionally analyzed the goals and types of personalized treatment using predictive biomarkers, and the management of various types of solid organ malignancies using predictive biomarkers and their relative efficacies so far in the clinical settings.

HMOX1 regulates ferroptosis via mic14 and its impact on chemotherapy resistance in small-cell lung cancer

This study aimed to investigate the role and molecular mechanism of heme oxygenase-1 (HMOX1) in chemotherapy resistance in small-cell lung cancer (SCLC). Employed bioinformatics, qPCR, and Western Blot to assess HMOX1 levels in SCLC versus normal tissues and its prognostic relevance. CCK-8, flow cytometry, and thiobarbituric acid assays determined HMOX1's impact on SCLC chemosensitivity, ferroptosis markers, lipid peroxidation, and mic14's role in chemoresistance. In the GSE40275 and GSE60052 cohorts, HMOX1 expression was downregulated in SCLC tissues compared to normal tissues. Higher HMOX1 expression was associated with improved prognosis in the Sun Yat-sen University Cancer Hospital cohort and GSE60052 cohort. The RNA and protein levels of HMOX1 were reduced in drug-resistant SCLC cell lines compared to chemosensitive cell lines. Upregulation of HMOX1 increased chemosensitivity and reduced drug resistance in SCLC, while downregulation of HMOX1 decreased chemosensitivity and increased drug resistance. Upregulation of HMOX1 elevated the expression of ferroptosis-related proteins ACSL4, CD71, Transferrin, Ferritin Heavy Chain, and Ferritin Light Chain, while decreasing the expression of GPX4 and xCT. Conversely, downregulation of HMOX1 decreased the expression of ACSL4, CD71, Transferrin, Ferritin Heavy Chain, and Ferritin Light Chain, while increasing the expression of GPX4 and xCT. Upregulation of HMOX1 promoted cellular lipid peroxidation, whereas downregulation of HMOX1 inhibited cellular lipid peroxidation. Upregulation of HMOX1 reduced the RNA level of mic14, while downregulation of HMOX1 increased the RNA level of mic14. mic14 exhibited inhibitory effects on cellular lipid peroxidation in SCLC cells and contributed to reduced chemosensitivity and increased drug resistance in chemoresistant SCLC cell lines. HMOX1 plays a role in ferroptosis by regulating mic14 expression, thereby reversing chemoresistance in SCLC.

Alterations in Peripheral Lymphocyte Subsets under Immunochemotherapy in Stage IV SCLC Patients: Th17 Cells as Potential Early Predictive Biomarker for Response

UICC stage IV small-cell lung cancer (SCLC) is a highly aggressive malignancy without curative treatment options. Several randomized trials have demonstrated improved survival rates through the addition of checkpoint inhibitors to first-line platin-based chemotherapy. Consequently, a combination of chemo- and immunotherapy has become standard palliative treatment. However, no reliable predictive biomarkers for treatment response exist. Neither PD-L1 expression nor tumor mutational burden have proven to be effective predictive biomarkers. In this study, we compared the cellular immune statuses of SCLC patients to a healthy control cohort and investigated changes in peripheral blood B, T, and NK lymphocytes, as well as several of their respective subsets, during treatment with immunochemotherapy (ICT) using flow cytometry. Our findings revealed a significant decrease in B cells, while T cells showed a trend to increase throughout ICT. Notably, high levels of exhausted CD4+ and CD8+ cells, alongside NK subsets, increased significantly during treatment. Furthermore, we correlated decreases/increases in subsets after two cycles of ICT with survival. Specifically, a decrease in Th17 cells indicated a better overall survival. Based on these findings, we suggest conducting further investigation into Th17 cells as a potential early predictive biomarkers for response in patients receiving palliative ICT for stage IV SCLC.

Prognostic value of PAX8 in small cell lung cancer

Objectives

Small cell lung cancer (SCLC) shows poor prognosis since it metastasizes widely at early stage. Paired box gene (PAX) 8 is a transcriptional factor of PAX family, of which the expression in lung cancer is a controversial issue, and its prognostic value of PAX8 in SCLC is still unclear.

Materials and methods

Overall, 184 subjects who were pathologically diagnosed with SCLC were enrolled in the study. Immunohistochemical analysis of PAX8 and Ki-67 were performed. The correlations between PAX8 expression and clinical features or Ki-67 index were further analyzed. Subsequently, an analysis of the association between PAX8, stage, Ki-67 status, and overall survival (OS) were performed in 169 subjects with follow-up information.

Results

PAX8 was positive in 53.8% (99/184) SCLC specimens. The positive rate is significantly higher in extensive-stage specimens (61.0%) than in limited-stage specimens (45.24%). PAX8 expression is positively correlated with Ki-67 index (P = 0.001) while negatively correlated with OS (HR = 3.725, 95% CI 1.943-7.139, P＜0.001). In combination groups, the PAX8 negative and limited stage group had the most promising OS.

Conclusion

PAX8 expression rate in SCLC specimens is not low. It has prognostic value in small cell lung cancer.

Prognostic Nutritional Index Predicts Efficacy and Immune-Related Adverse Events of First-Line Chemoimmunotherapy in Patients with Extensive-Stage Small-Cell Lung Cancer

Background

Currently, there is a lack of well-established markers to predict the efficacy of chemoimmunotherapy in small-cell lung cancer (SCLC). Neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), advanced lung cancer inflammation index (ALI) and prognostic nutritional index (PNI) are associated with prognosis in several tumors, whereas their predictive role in SCLC remains unclear.

Methods

A retrospective study was conducted at Sun Yat-sen University Cancer Center, involving extensive-stage SCLC (ES-SCLC) patients who received first-line chemoimmunotherapy between January 2020 and December 2021. Peripheral blood biomarkers were extracted from medical records and their correlation with prognosis and immune-related adverse events (IRAEs) was analyzed.

Results

A total of 114 patients were included. Patients with a low PLR, high ALI and high PNI had prolonged progression-free survival (PFS) compared to those with a high PLR, low ALI and low PNI. Patients with a low NLR, low PLR, high ALI and high PNI had prolonged overall survival (OS) compared to those with a high NLR, high PLR, low ALI and low PNI. Cox regression model showed that PNI was an independent risk factor for both PFS and OS. ROC curve showed that PNI outperforms NLR, PLR and ALI in predicting both PFS and OS. The PNI-based nomogram demonstrated strong predictive capability for both PFS and OS. In addition, there was a significant correlation between PNI and IRAEs.

Conclusion

A high baseline PNI might be associated with improved prognosis and the occurrence of IRAEs in ES-SCLC patients treated with first-line chemoimmunotherapy.

ES-SCLC Patients with PD-L1+ CTCs and High Percentages of CD8+PD-1+T Cells in Circulation Benefit from Front-Line Immunotherapy Treatment

SCLC is an aggressive cancer type with high metastatic potential and bad prognosis. CTCs are a valuable source of tumor cells in blood circulation and are among the major contributors to metastasis. In this study we evaluated the number of CTCs that express PD-L1 in treatment-naïve ES-SCLC patients receiving ICI in a front-line setting. Moreover, we explored the percentages of different immune T-cell subsets in circulation to assess their potential role in predicting responses. A total of 43 patients were enrolled-6 of them with LS-SCLC, and 37 with ES-SCLC disease. In addition, PBMCs from 10 healthy donors were used as a control group. Different T-cell subtypes were examined through multicolor FACS analysis and patients' CTCs were detected using immunofluorescence staining. SCLC patients had higher percentages of PD-1-expressing CD3+CD4+ and CD3+CD8+ T-cells, as well as elevated PD-1 protein expression compared to healthy individuals. Additionally, in ES-SCLC patients, a positive correlation between CD3+CD8+PD-1+ T-cells and PD-L1+ CTCs was detected. Importantly, patients harboring higher numbers of CD3+CD8+PD-1+ T-cells together with PD-L1+CTCs had a survival advantage when receiving front-line immunotherapy. Thus, this study proposes, for first time possible, immune cell-CTCs interaction, as well as a potential novel clinical biomarker for ICI responses in ES-SCLC patients.

Updates on lung neuroendocrine neoplasm classification

Lung neuroendocrine neoplasms (NENs) are a heterogeneous group of pulmonary neoplasms showing different morphological patterns and clinical and biological characteristics. The World Health Organisation (WHO) classification of lung NENs has been recently updated as part of the broader attempt to uniform the classification of NENs. This much-needed update has come at a time when insights from seminal molecular characterisation studies revolutionised our understanding of the biological and pathological architecture of lung NENs, paving the way for the development of novel diagnostic techniques, prognostic factors and therapeutic approaches. In this challenging and rapidly evolving landscape, the relevance of the 2021 WHO classification has been recently questioned, particularly in terms of its morphology-orientated approach and its prognostic implications. Here, we provide a state-of-the-art review on the contemporary understanding of pulmonary NEN morphology and the potential contribution of artificial intelligence, the advances in NEN molecular profiling with their impact on the classification system and, finally, the key current and upcoming prognostic factors.

Identification of Immune Subtypes and Candidate mRNA Vaccine Antigens in Small Cell Lung Cancer

BACKGROUND

Immune checkpoint inhibitors (ICIs) have demonstrated promising outcomes in small cell lung cancer (SCLC), but not all patients benefit from it. Thus, developing precise treatments for SCLC is a particularly urgent need. In our study, we constructed a novel phenotype for SCLC based on immune signatures.

METHODS

We clustered patients with SCLC hierarchically in 3 publicly available datasets according to the immune signatures. ESTIMATE and CIBERSORT algorithm were used to evaluate the components of the tumor microenvironment. Moreover, we identified potential mRNA vaccine antigens for patients with SCLC, and qRT-PCR were performed to detect the gene expression.

RESULTS

We identified 2 SCLC subtypes and named Immunity High (Immunity_H) and Immunity Low (Immunity_L). Meanwhile, we obtained generally consistent results by analyzing different datasets, suggesting that this classification was reliable. Immunity_H contained the higher number of immune cells and a better prognosis compared to Immunity_L. Gene-set enrichment analysis revealed that several immune-related pathways such as cytokine-cytokine receptor interaction, programmed cell death-Ligand 1 expression and programmed cell death-1 checkpoint pathway in cancer were hyperactivated in the Immunity_H. However, most of the pathways enriched in the Immunity_L were not associated with immunity. Furthermore, we identified 5 potential mRNA vaccine antigens of SCLC (NEK2, NOL4, RALYL, SH3GL2, and ZIC2), and they were expressed higher in Immunity_L, it indicated that Immunity_L maybe more suitable for tumor vaccine development.

CONCLUSIONS

SCLC can be divided into Immunity_H and Immunity_L subtypes. Immunity_H may be more suitable for treatment with ICIs. NEK2, NOL4, RALYL, SH3GL2, and ZIC2 may be act as potential antigens for SCLC.

ITGB4 Serves as an Identification and Prognosis Marker Associated with Immune Infiltration in Small Cell Lung Carcinoma

Integrin beta 4 (ITGB4) is a vital factor for numerous cancers. However, no reports regarding ITGB4 in small cell lung carcinoma (SCLC) have been found in the existing literature. This study systematically investigated the expression and clinical value of ITGB4 in SCLC using multi-center and large-sample (n = 963) data. The ITGB4 expression levels between SCLC and control tissues were compared using standardized mean difference and Wilcoxon rank-sum test. The clinical significance of the gene in SCLC was observed using Cox regression and Kaplan-Meier curves. ITGB4 is overexpressed in multiple cancers and represents significant value in distinguishing among cancer samples (AUC = 0.91) and predicting the prognoses (p < 0.05) of patients with different cancers. In contrast, decreased ITGB4 mRNA expression was determined in SCLC (SMD < 0), and this finding was further confirmed at protein levels using in-house specimens (p < 0.05). This decrease in expression may be attributed to the regulatory role of estrogen receptor 1. ITGB4 may participate in the progression of SCLC by affecting several signaling pathways (e.g., tumor necrosis factor signaling pathway) and a series of immune cells (e.g., dendritic cells) (p < 0.05). The gene may serve as a potential marker for predicting the disease status (AUC = 0.97) and prognoses (p < 0.05) of patients with SCLC. Collectively, ITGB4 was identified as an identification and prognosis marker associated with immune infiltration in SCLC.

POU2F3: A Sensitive and Specific Diagnostic Marker for Neuroendocrine-low/negative Small Cell Lung Cancer

POU2F3 (POU class 2 homeobox 3) is a novel transcription factor used to define the special molecular subtype of small cell lung cancer (SCLC) known as SCLC-P. Nevertheless, the sensitivity and specificity of POU2F3 immunohistochemical (IHC) staining have not been fully investigated. In this study, we explored the expression of POU2F3 by IHC in a large cohort of SCLC clinical samples (n=246), other common lung cancer types (n=2207), and various other cancer types (n=194). The results showed that POU2F3 was strongly nuclear stained in 13.41% (33/246) of SCLC cases, with negative or minimal labeling for thyroid transcription factor-1 and neuroendocrine (NE) markers. Compared with POU2F3-negative SCLC, SCLC-P harbored fewer TP53 and RB1 mutations. POU2F3 was also expressed in 3.13% (8/256) of squamous cell carcinomas (SCCs) and 20% (2/10) of large cell NE carcinomas (LCNECs), whereas other lung cancer types were negative. In addition to lung cancer, POU2F3 was positive in 22.2% (4/18) of thymic tumors. All other tumors were POU2F3-negative except for thymic carcinoma, although sparsely distributed weak nuclear staining was observed in lung adenocarcinoma, cervical SCC, and colorectal carcinoma. The sensitivity and specificity of POU2F3 in NE-low/negative SCLC were 82.1% and 99.4%, respectively. Notably, some rare unique patterns of POU2F3 expression were observed. One case of thymic SCC was characterized by diffuse and uniform cytomembrane staining. One case of esophageal NE tumor was nuclear-positive, while the normal proliferating squamous epithelium was strongly membrane-stained. This is the largest cohort of clinical samples to confirm that POU2F3 is a highly sensitive and specific diagnostic marker for NE-low/negative SCLC.

Assessing treatment outcomes of chemoimmunotherapy in extensive-stage small cell lung cancer: an integrated clinical and radiomics approach

BACKGROUND

Small cell lung cancer (SCLC) is a highly malignant cancer characterized by metastasis and an extremely poor prognosis. Although combined chemoimmunotherapy improves the prognosis of extensive-stage (ES)-SCLC, the survival benefits remain limited. Furthermore, no reliable biomarker is available so far to predict the treatment outcomes for chemoimmunotherapy.

METHODS

This retrospective study included patients with ES-SCLC treated with first-line combined atezolizumab or durvalumab with standard chemotherapy between Janauray 1, 2019 and October 1, 2022 at five medical centers in China as the chemoimmunotherapy group. The patients were divided into one training cohort and two independent external validation cohorts. Additionally, we created a control group of ES-SCLC who was treated with first-line standard chemotherapy alone. The Radiomics Score was derived using machine learning algorithms based on the radiomics features extracted in the regions of interest delineated on the chest CT obtained before treatment. Cox proportional hazards regression analysis was performed to identify clinical features associated with therapeutic efficacy. The log-rank test, time-dependent receiver operating characteristic curve, and Concordance Index (C-index) were used to assess the effectiveness of the models.

RESULTS

A total of 341 patients (mean age, 62±8.7 years) were included in our study. After a median follow-up time of 12.1 months, the median progression-free survival (mPFS) was 7.1 (95% CI 6.6 to 7.7) months, whereas the median overall survival (mOS) was not reached. The TNM stage, Eastern Cooperative Oncology Group performance status, and Lung Immune Prognostic Index showed significant correlations with PFS. We proposed a predictive model based on eight radiomics features to determine the risk of chemoimmunotherapy resistance among patients with SCLC (validation set 1: mPFS, 12.0 m vs 5.0 m, C-index=0.634; validation set 2: mPFS, 10.8 m vs 6.1 m, C-index=0.617). By incorporating the clinical features associated with PFS into the radiomics model, the predictive efficacy was substantially improved. Consequently, the low-progression-risk group exhibited a significantly longer mPFS than the high-progression-risk group in both validation set 1 (mPFS, 12.8 m vs 4.5 m, HR=0.40, p=0.028) and validation set 2 (mPFS, 9.2 m vs 4.6 m, HR=0.30, p=0.012). External validation set 1 and set 2 yielded the highest 6-month area under the curve and C-index of 0.852 and 0.820, respectively. Importantly, the integrated prediction model also exhibited considerable differentiation power for survival outcomes. The HR for OS derived from the low-progression-risk and high-progression-risk groups was 0.28 (95% CI 0.17 to 0.48) in all patients and 0.20 (95% CI 0.08 to 0.54) in validation set. By contrast, no significant differences were observed in PFS and OS, between high-progression-risk patients receiving chemoimmunotherapy and the chemotherapy cohort (mPFS, 5.5 m vs 5.9 m, HR=0.90, p=0.547; mOS, 14.5 m vs 13.7 m, HR=0.97, p=0.910).

CONCLUSIONS

The integrated clinical and radiomics model can predict the treatment outcomes in patients with ES-SCLC receiving chemoimmunotherapy, rendering a convenient and low-cost prognostic model for decision-making regarding patient management.

Cancer Cell-Intrinsic Alterations Associated with an Immunosuppressive Tumor Microenvironment and Resistance to Immunotherapy in Lung Cancer

Despite the great clinical success of immunotherapy in lung cancer patients, only a small percentage of them (<40%) will benefit from this therapy alone or combined with other strategies. Cancer cell-intrinsic and cell-extrinsic mechanisms have been associated with a lack of response to immunotherapy. The present study is focused on cancer cell-intrinsic genetic, epigenetic, transcriptomic and metabolic alterations that reshape the tumor microenvironment (TME) and determine response or refractoriness to immune checkpoint inhibitors (ICIs). Mutations in KRAS, SKT11(LKB1), KEAP1 and TP53 and co-mutations of these genes are the main determinants of ICI response in non-small-cell lung cancer (NSCLC) patients. Recent insights into metabolic changes in cancer cells that impose restrictions on cytotoxic T cells and the efficacy of ICIs indicate that targeting such metabolic restrictions may favor therapeutic responses. Other emerging pathways for therapeutic interventions include epigenetic modulators and DNA damage repair (DDR) pathways, especially in small-cell lung cancer (SCLC). Therefore, the many potential pathways for enhancing the effect of ICIs suggest that, in a few years, we will have much more personalized medicine for lung cancer patients treated with immunotherapy. Such strategies could include vaccines and chimeric antigen receptor (CAR) cells.

Safety evaluation of immune checkpoint inhibitors combined with chemotherapy for the treatment of small cell lung cancer: A meta-analysis of randomized controlled trials

BACKGROUND

The addition of immune checkpoint inhibitors (ICIs) to chemotherapy is the new standard of care in the first-line treatment of small cell lung cancer (SCLC). However, although the concomitant use of immunotherapy and chemotherapy can increase the antitumor efficacy, it can also increase toxicity. The present study evaluated the tolerability of immune-based combinations in the first-line treatment of SCLC.

METHODS

Relevant trials were identified by searching electronic databases and conference meetings. Seven phase II and III randomized controlled trials and 3766 SCLC patients were included in the meta-analysis (immune-based combinations = 2133; chemotherapy = 1633). Outcomes of interest included treatment-related adverse events (TRAEs) and the rate of discontinuation due to TRAEs.

RESULTS

Immune-based combination treatment was associated with a higher risk of grade 3-5 TRAEs (odds ratio [OR], 1.16; 95% confidence interval [CI]: 1.01-1.35). Immune-based combinations were associated with a higher risk of TRAEs leading to discontinuation (OR, 2.30; 95% CI: 1.17-4.54). No differences were observed in grade 5 TRAEs (OR, 1.56; 95% CI: 0.93-2.63).

CONCLUSION

This meta-analysis indicates that the addition of immunotherapy to chemotherapy in SCLC patients is associated with a higher risk of toxicity and probably of treatment discontinuation. Tools for identifying SCLC patients that would not benefit from immune-based therapy are urgently needed.

Potential predictors of immunotherapy in small cell lung cancer

Lung cancer is one of the leading causes of cancer-related deaths worldwide, with small cell lung cancer (SCLC) having the worst prognosis. SCLC is diagnosed late in the disease's progression, limiting treatment options. The most common treatment for SCLC is chemotherapy. As the disease progresses, immunotherapy, most commonly checkpoint inhibitor medication, becomes more important. Efforts should be made in the development of immunotherapy to map specific biomarkers, which play a role in properly assigning a type of immunotherapy to the right cohort of patients, where the benefits outweigh any risks or adverse effects. The objective of this review was to provide a thorough assessment of current knowledge about the nature of the tumor process and treatment options for small cell lung cancer, with a focus on predictive biomarkers. According to the information obtained, the greatest potential, which has already been directly demonstrated in some studies, has characteristics such as tumor microenvironment composition, tumor mutation burden, and molecular subtyping of SCLC. Several other aspects appear to be promising, but more research, particularly prospective studies on a larger number of probands, is required. However, it is clear that this field of study will continue to expand, as developing a reliable method to predict immunotherapy response is a very appealing goal of current medicine and research in the field of targeted cancer therapy.

Interpretable deep learning survival predictive tool for small cell lung cancer

Background

Small cell lung cancer (SCLC) is an aggressive and almost universally lethal neoplasm. There is no accurate predictive method for its prognosis. Artificial intelligence deep learning may bring new hope.

Methods

By searching the Surveillance, Epidemiology, and End Results database (SEER), 21,093 patients' clinical data were eventually included. Data were then divided into two groups (train dataset/test dataset). The train dataset (diagnosed in 2010-2014, N = 17,296) was utilized to conduct a deep learning survival model, validated by itself and the test dataset (diagnosed in 2015, N = 3,797) in parallel. According to clinical experience, age, sex, tumor site, T, N, M stage (7th American Joint Committee on Cancer TNM stage), tumor size, surgery, chemotherapy, radiotherapy, and history of malignancy were chosen as predictive clinical features. The C-index was the main indicator to evaluate model performance.

Results

The predictive model had a 0.7181 C-index (95% confidence intervals, CIs, 0.7174-0.7187) in the train dataset and a 0.7208 C-index (95% CIs, 0.7202-0.7215) in the test dataset. These indicated that it had a reliable predictive value on OS for SCLC, so it was then packaged as a Windows software which is free for doctors, researchers, and patients to use.

Conclusion

The interpretable deep learning survival predictive tool for small cell lung cancer developed by this study had a reliable predictive value on their overall survival. More biomarkers may help improve the prognostic predictive performance of small cell lung cancer.

Anti-programmed death ligand 1 immunotherapy in patients with limited-stage small cell lung cancer: a real-world exploratory study

The aim of this study was to investigate the safety and efficacy of anti-programmed death ligand 1 (PD-L1) immunotherapy plus chemoradiotherapy for patients with limited-stage small cell lung cancer (LS-SCLC) in clinical practice. Patients with LS-SCLC treated with anti-PD-L1 (atezolizumab/durvalumab) plus chemoradiotherapy (CRT) as the initial treatment at three general hospitals between March 2020 and December 2021 were retrospectively analysed. 1:2 propensity score matching for controls that receive CRT only was performed. Clinical data (age, sex, history of cancer treatment, adverse events, etc.) were collected to evaluate toxicity, progression-free survival (PFS) and objective response rate (ORR). Researchers used univariate Chi-squared analyses to determine if anti-PD-L1 immunotherapy had a significant association with toxicity or ORR. Kaplan-Meier survival analysis, and the log-rank test were used to compare survival curves between the two groups. In the anti-PD-L1 plus CRT and CRT groups, 15 and 30 patients were analyzed; median follow-up was 16.39 months and 16.64 months, respectively. Incidence of toxicity between the two groups was similar and there were no new safety signals. Anti-PD-L1 immunotherapy significantly improved PFS (P = 0.02). The median PFS was not reached in the anti-PD-L1 plus CRT group versus 8.18 months [95% confidence interval (CI), 6.14-10.22 months] in the CRT group. The ORR were 93.33% and 76.67%, respectively (P = 0.34). This study supports adding anti-PD-L1 immunotherapy (atezolizumab/durvalumab) to CRT as an initial treatment option in patients with LS-SCLC for its favorable safety profile and efficacy.