Effects of reduced platelet count on the prognosis for patients with non-small cell lung cancer treated with EGFR-TKI: a retrospective study

Development and validation of a deep learning-based model to predict response and survival of T790M mutant non-small cell lung cancer patients in early clinical phase trials using electronic medical record and pharmacokinetic data

Background

Epidermal growth factor receptor (EGFR) T790M mutation is the standard predictive biomarker for third-generation epidermal growth factor receptor tyrosine kinase inhibitor (EGFR-TKI) treatment. While not all T790M-positive patients respond to third-generation EGFR-TKIs and have a good prognosis, it necessitates novel tools to supplement EGFR genotype detection for predicting efficacy and stratifying EGFR-mutant patients with various prognoses. Mixture-of-experts (MoE) is designed to disassemble a large model into many small models. Meanwhile, it is also a model ensembling method that can better capture multiple patterns of intrinsic subgroups of enrolled patients. Therefore, the combination of MoE and Cox algorithm has the potential to predict efficacy and stratify survival in non-small cell lung cancer (NSCLC) patients with EGFR mutations.

Methods

We utilized the electronic medical record (EMR) and pharmacokinetic parameters of 326 T790M-mutated NSCLC patients, including 283 patients treated with Abivertinib in phase I (n=177, for training) and II (n=106, for validation) clinical trials and an additional validation cohort 2 comprising 43 patients treated with BPI-7711. Furthermore, 18 patients underwent whole-exome sequencing for biological interpretation of CoxMoE. We evaluated the predictive performance for therapeutic response using the area under the curve (AUC) and the Concordance index (C-index) for progression-free survival (PFS).

Results

CoxMoE exhibited AUCs of 0.73-0.83 for predicting efficacy defined by best overall response (BoR) and achieved C-index values of 0.64-0.65 for PFS prediction in training and validating cohorts. The PFS of 198 patients with a low risk [median, 6.0 (range, 1.0-23.3) months in the abivertinib treated cohort; median 16.5 (range, 1.4-27.4) months in BPI-7711 treated cohort] of being non-responder increased by 43% [hazard ratio (HR), 0.56; 95% confidence interval (CI), 0.40-0.78; P=0.0013] and 50% (HR, 0; 95% CI, 0-0; P=0.01) compared to those at high-risk [median, 4.2 (range, 1.0-35) months in the abivertinib treated cohort; median, 11.0 (range, 1.4-25.1) months in BPI-7711 treated cohort]. Additionally, activated partial thromboplastin time (APTT), creatinine clearance (Ccr), monocyte, and steady-state plasma trough concentration utilited to construct model were found significantly associated with drug resistance and aggressive tumor pathways. A robust correlation was observed between APTT and Ccr with PFS (log-rank test; P<0.01) and treatment response (Wilcoxon test; P<0.05), respectively.

Conclusions

CoxMoE offers a valuable approach for patient selection by forecasting therapeutic response and PFS utilizing laboratory tests and pharmacokinetic parameters in the setting of early-phase clinical trials. Simultaneously, CoxMoE could predict the efficacy of third-generation EGFR-TKI non-invasively for T790M-positive NSCLC patients, thereby complementing existing EGFR genotype detection.

High levels of PD-L1 on platelets of NSCLC patients contributes to the pharmacological activity of Atezolizumab

Several studies have associated platelets (PLTs) to NSCLC prognosis. To understand the role of PLTs in immunotherapy-treated patients, we used blood samples of NSCLC patients at different TNM stage. We found that PLTs count and the expression of PD-L1 (pPD-L1) were significantly higher in NSCLC patients at Stage IV than Stage I-III and healthy subjects. The presence of high pPD-L1 was associated to upregulated genes for the extracellular matrix organization and tumor immunosuppression. When patients' survival was correlated to the levels of pPD-L1, longer survival rate was observed, but not when progression disease occurred. The in vitro stimulation of pPD-L1 with Atezolizumab induced CXCL4 release, accompanied by higher levels of TGFβ at the time of drug resistance when the levels of CD16, CD32 and CD64 significantly increased. Leiden-clustering method defined the phenotype of PLTs which showed that the ezrin-radixin-moesin (ERM) family proteins, underlying the PD-L1 signalosome, were involved in high pPD-L1 and higher survival rate. These data imply that Stage IV NSCLC patients characterized by high pPD-L1 are associated with longer progression-free survival rate because the blockade of pPD-L1 by Atezolizumab avoids the exacerbation of a T cell-mediated immune-suppressive environment. pPD-L1 could be an easy-to-use clinical approach to predict ICI responsiveness.

Machine learning-based analysis of cancer cell-derived vesicular proteins revealed significant tumor-specificity and predictive potential of extracellular vesicles for cell invasion and proliferation - A meta-analysis

BACKGROUND

Although interest in the role of extracellular vesicles (EV) in oncology is growing, not all potential aspects have been investigated. In this meta-analysis, data regarding (i) the EV proteome and (ii) the invasion and proliferation capacity of the NCI-60 tumor cell lines (60 cell lines from nine different tumor types) were analyzed using machine learning methods.

METHODS

On the basis of the entire proteome or the proteins shared by all EV samples, 60 cell lines were classified into the nine tumor types using multiple logistic regression. Then, utilizing the Least Absolute Shrinkage and Selection Operator, we constructed a discriminative protein panel, upon which the samples were reclassified and pathway analyses were performed. These panels were validated using clinical data (n = 4,665) from Human Protein Atlas.

RESULTS

Classification models based on the entire proteome, shared proteins, and discriminative protein panel were able to distinguish the nine tumor types with 49.15%, 69.10%, and 91.68% accuracy, respectively. Invasion and proliferation capacity of the 60 cell lines were predicted with R2 = 0.68 and R2 = 0.62 (p < 0.0001). The results of the Reactome pathway analysis of the discriminative protein panel suggest that the molecular content of EVs might be indicative of tumor-specific biological processes.

CONCLUSION

Integrating in vitro EV proteomic data, cell physiological characteristics, and clinical data of various tumor types illuminates the diagnostic, prognostic, and therapeutic potential of EVs. Video Abstract.

Predicting the prognosis of operable gastric cancer patients by dynamic changes in platelets before and after surgery: a retrospective cohort study

PURPOSE

Since the relationship between postoperative platelet count and prognosis is still unclear, we designed a standardized index of platelet count to predict the prognosis of gastric cancer (GC).

METHODS

We designed a development validation cohort for the pre/post platelet ratio. We determined the ability of PPR to predict mortality in gastric cancer patients and validated them by a separate cohort. Survival was assessed by Kaplan-Meier analysis and associations explored by multivariate and multivariate analyses. The usefulness of the prediction was estimated by measuring the time-dependent ROC. Decision-curve analysis was used to validate the net clinical benefit.

RESULTS

The sample distribution was similar in the two cohorts, and the 1-, 3-, and 5-year OS evaluation of the postoperative/preoperative platelet ratio was the largest for AUC in the two cohorts. Meanwhile, PPR has a good predictive value and a net clinical benefit.

CONCLUSIONS

PPR has been identified and validated to be independently concerned about OS of patients with GC and was a reliable and economic indicator to evaluate the prognosis.

Full spectrum flow cytometry-powered comprehensive analysis of PBMC as biomarkers for immunotherapy in NSCLC with EGFR-TKI resistance

BACKGROUND

Clinical studies suggest that immune checkpoint inhibitor (ICI) monotherapy has limited benefits in non-small cell lung cancer (NSCLC) patients after epidermal growth factor receptor-tyrosine kinase inhibitor (EGFR-TKI) failure. However, data about efficacy of ICI plus chemotherapy remain controversial, probably attributed to the heterogeneity among such population, and robust efficacy biomarkers are urgent to explore.

METHODS

A total of 60 eligible patients who received ICI plus chemotherapy after EGFR-TKI treatment failure were enrolled, 24 of whom peripheral blood mononuclear cell (PBMC) samples were collected at baseline and after 2 cycles of treatment. We have designed a 23-color-antibody panel to detect PBMC by full spectrum flow cytometry.

RESULTS

For EGFR-TKI resistant NSCLC patients: 1) ICI plus chemotherapy achieved an objective response rate (ORR) of 21.7% and a median progression-free survival (PFS) of 6.4 months. 2) clinical characteristics associated with worse efficacy included liver metastasis and platelet-to-lymphocyte ratio (PLR) > 200. 3) the proportion of immune cell subset associated with better efficacy was higher baseline effective CD4⁺T cells (E4). 4) the baseline expression of immune checkpoint proteins (ICPs) on cell subsets associated with better efficacy included: higher expression of CD25 on dendritic cells (DC) and central memory CD8⁺T cells (CM8), and higher expression of Lymphocyte activation gene 3 (LAG-3) on effective memory CD8⁺T cells (EM8). 5) the expression of ICPs after 2 cycles of treatment associated with better efficacy included: higher expression of CD25 on CD8⁺T/EM8 /natural killer (NK) cells. 6) the dynamic changes of ICPs expression associated with worse efficacy included: significantly decrease of T cell immunoglobulin and ITIM domain (TIGIT) expression on regular T cells (Tregs) and decrease of V-domain immunoglobulin suppressor of T cell activation (VISTA) expression on Th1. 7) a prediction model for the efficacy of ICI plus chemotherapy was successfully constructed with a sensitivity of 62.5%, specificity of 100%, and area under curve (AUC) = 0.817.

CONCLUSIONS

Some EGFR-TKI-resistant NSCLC patients could indeed benefit from ICI plus chemotherapy, but most patients are primary resistant to immunotherapy. Comprehensive analysis of peripheral immune cells using full spectrum flow cytometry showed that compared to the proportion of cell subsets, the expression type and level of ICPs on immune cells, especially CD25, were significantly correlated with the efficacy of immunotherapy.

Successful osimertinib rechallenge after severe thrombocytopenia caused by osimertinib combined with sitagliptin: a case report

Osimertinib is recommended as the first-line treatment of advanced non-small cell lung cancer (NSCLC) in adults. The most commonly reported adverse events for osimertinib are skin effects, diarrhea, nausea, decreased appetite, fatigue, paronychia, and stomatitis. Severe thrombocytopenia is rarely reported. We present a case of severe thrombocytopenia in a 70-year-old NSCLC patient caused by osimertinib combined with sitagliptin. After remission of thrombocytopenia, the patient was well tolerated with osimertinib re-administration in the absence of sitagliptin. We speculated that declined platelet count might be related to the interaction between osimertinib and sitagliptin by acting with a synergistic effect on platelets. Osimertinib rechallenge can be considered after discontinuing drugs that may contribute to platelet decline if possible, and making a careful assessment of complete blood count and risk of bleeding.

Development and validation of postoperative and preoperative platelets ratio (PPR) to predict the prognosis of patients undergoing surgery for colorectal cancer: A dual-center retrospective cohort study

BACKGROUND

Platelets occupy a prominent place in tumor proliferation and metastasis, and platelet count is relevant to the prognosis of tumor patients. But preoperative platelet counts cannot be standardized and individualized due to the variability among individuals, instruments, and regions, and the connection between postoperative platelet count and prognosis remains unknown. A standardized indicator of platelet count was designed to forecast the prognosis of colorectal cancer (CRC).

METHODS

Five hundred and eighty six patients who suffered radical resection of CRC between 2013 and 2019 were collected. A development-validation cohort of standardized and individualized platelet counts for prognostic assessment of CRC was designed. We first determined the ability of PPR and other peripheral blood count-related indicators to predict the mortality of patients with CRC and validated them in a separate cohort. Kaplan-Meier analysis was executed to evaluate the survival and univariate and multivariate analyses were executed to explore the relevance. Time-dependent ROC was measured to estimate the predictive usefulness. Decision curve analysis was used to verify the clinical net benefit.

RESULTS

Important baseline variables showed a similar distribution in two independent queues. In the development cohort, postoperative platelet count and postoperative/preoperative platelets ratio (PPR) were independent predictors of prognosis in CRC patients. PPR showed the largest area under the curve (AUC) in evaluating 1-year and 5-year OS (AUC: 0.702 and 0.620) compared to others. In the validation cohort, platelet/lymphocyte ratio and PPR were validated to be independently concerned about OS of CRC patients and PPR showed the largest AUC in evaluating 1-year and 3-year OS (AUC: 0.663 and 0.673). PPR and joint index of platelet count and PPR showed better predictive value and clinical net benefit.

CONCLUSIONS

PPR has been identified and validated to be independently concerned about OS of patients with CRC and was a reliable and economic indicator to evaluate the prognosis.

Real-world outcomes of chemo-antiangiogenesis versus chemo-immunotherapy combinations in EGFR-mutant advanced non-small cell lung cancer patients after failure of EGFR-TKI therapy

BACKGROUND

Despite the potent efficacy of epidermal growth factor receptor (EGFR)-tyrosine kinase inhibitors (TKIs) in the treatment of EGFR-mutant non-small cell lung cancer (NSCLC) patients, drug resistance inevitably ensues, and there remains a paucity of treatment options in clinical practice.

METHODS

We identified patients with EGFR-mutant advanced NSCLC presenting to Shanghai Pulmonary Hospital and Shanghai Chest Hospital between January 2015 and December 2020 treated with chemo-antiangiogenesis or chemo-immunotherapy combinations after EGFR-TKI resistance. Patient information was collected, and the objective response rate (ORR), disease control rate (DCR), and progression-free survival (PFS) were assessed.

RESULTS

A total of 144 patients who met our inclusion criteria were enrolled. Chemo-immunotherapy combinations achieved a higher objective response rate (ORR) compared with chemo-antiangiogenesis combinations (29.5% vs. 13.0%, P=0.018). The DCR was similar between the two groups (93.0% vs. 88.6%, P=0.585), as was the median PFS (7.59 vs. 6.90 months, P=0.552). In the subgroup analyses, patients who developed secondary T790M mutations after EGFR-TKI treatment were less likely to benefit from chemo-immunotherapy combinations than their T790M-negative counterparts (3.42 vs. 7.63 months, P=0.028). For patients who received chemo-antiangiogenesis combinations after TKI resistance, no significant difference was observed in the median PFS between T790M-positive and T790M-negative patients (median PFS: 5.33 vs. 7.46 months, P=0.202). Additionally, multivariate analysis showed that an elevated platelet count was independently associated with a worse PFS for both groups.

CONCLUSIONS

The efficacy of chemo-immunotherapy combinations was comparable to chemo-antiangiogenesis combinations after failure of EGFR-TKI therapy. For patients harboring EGFR T790M mutations, chemo-antiangiogenesis combinations may be the preferred therapeutic option. In addition, platelet count could be a potential prognostic factor for patients after failure of EGFR-TKI therapy. Further research should be conducted on larger populations and in a prospective setting.

Platelets: The Emerging Clinical Diagnostics and Therapy Selection of Cancer Liquid Biopsies

Due to the inherent molecular heterogeneity of metastatic tumours and the dynamic evolution ability of tumour genomes, tumour tissues obtained through biopsy and other methods cannot capture all of the features of tumour genomes. A new diagnostic concept called “liquid biopsy” has received widespread attention in recent years. Liquid biopsy has changed the clinical practice of oncology and is widely used to guide targeted drug utilization, monitor disease progression and track drug resistance. The latest research subject in liquid biopsy is platelets. Platelets originate from multifunctional haematopoietic stem cells in the bone marrow haematopoietic system. They are small cells from the cytoplasm of bone marrow megakaryocytes. Their main physiological functions are to participate in the processes of physiological haemostasis and coagulation. Tumour cells transfer biomolecules (such as RNA) to platelets through direct contact and release of exosomes, which changes the platelet precursor RNA. Under the stimulation of tumour cells and the tumour microenvironment, platelet precursor mRNA is spliced into mature RNA and converted into functional protein to respond to external stimuli, forming tumour-educated platelets (TEPs). The detection of TEPs in the peripheral blood of patients is expected to be used in clinical tumour diagnosis. This emerging liquid biopsy method can replace and supplement the current tumour detection methods. Further research on the role of platelets in tumour diagnosis will help provide a novel theoretical basis for clinical tumour diagnosis.