scholarly journals Predicting cardiac adverse events in patients receiving immune checkpoint inhibitors: a machine learning approach

2021 ◽  
Vol 9 (10) ◽  
pp. e002545
Author(s):  
Samuel Peter Heilbroner ◽  
Reed Few ◽  
Judith Mueller ◽  
Jitesh Chalwa ◽  
Francois Charest ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
High Risk ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Risk Group ◽  
Checkpoint Inhibitors ◽  
Low Risk ◽  
Cardiac Events ◽  
Programmed Death

BackgroundTreatment with immune checkpoint inhibitors (ICIs) has been associated with an increased rate of cardiac events. There are limited data on the risk factors that predict cardiac events in patients treated with ICIs. Therefore, we created a machine learning (ML) model to predict cardiac events in this at-risk population.MethodsWe leveraged the CancerLinQ database curated by the American Society of Clinical Oncology and applied an XGBoosted decision tree to predict cardiac events in patients taking programmed death receptor-1 (PD-1) or programmed death ligand-1 (PD-L1) therapy. All curated data from patients with non-small cell lung cancer, melanoma, and renal cell carcinoma, and who were prescribed PD-1/PD-L1 therapy between 2013 and 2019, were used for training, feature interpretation, and model performance evaluation. A total of 356 potential risk factors were included in the model, including elements of patient medical history, social history, vital signs, common laboratory tests, oncological history, medication history and PD-1/PD-L1-specific factors like PD-L1 tumor expression.ResultsOur study population consisted of 4960 patients treated with PD-1/PD-L1 therapy, of whom 418 had a cardiac event. The following were key predictors of cardiac events: increased age, corticosteroids, laboratory abnormalities and medications suggestive of a history of heart disease, the extremes of weight, a lower baseline or on-treatment percentage of lymphocytes, and a higher percentage of neutrophils. The final model predicted cardiac events with an area under the curve–receiver operating characteristic of 0.65 (95% CI 0.58 to 0.75). Using our model, we divided patients into low-risk and high-risk subgroups. At 100 days, the cumulative incidence of cardiac events was 3.3% in the low-risk group and 6.1% in the high-risk group (p<0.001).ConclusionsML can be used to predict cardiac events in patients taking PD-1/PD-L1 therapy. Cardiac risk was driven by immunological factors (eg, percentage of lymphocytes), oncological factors (eg, low weight), and a cardiac history.

scholarly journals GDPLichi: a DNA Damage Repair-Related Gene Classifier for Predicting Lung Adenocarcinoma Immune Checkpoint Inhibitors Response

2021 ◽  
Vol 11 ◽  
Author(s):  
Yang Leng ◽  
Shiying Dang ◽  
Fei Yin ◽  
Tianshun Gao ◽  
Xing Xiao ◽  
...  
Keyword(s):  
Dna Damage ◽  
T Cells ◽  
High Risk ◽  
Lung Adenocarcinoma ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Risk Group ◽  
Checkpoint Inhibitors ◽  
High Risk Group ◽  
Damage Repair

Lung cancer is one of the most common and mortal malignancies, usually with a poor prognosis in its advanced or recurrent stages. Recently, immune checkpoint inhibitors (ICIs) immunotherapy has revolutionized the treatment of human cancers including lung adenocarcinoma (LUAD), and significantly improved patients’ prognoses. However, the prognostic and predictive outcomes differ because of tumor heterogeneity. Here, we present an effective method, GDPLichi (Genes of DNA damage repair to predict LUAD immune checkpoint inhibitors response), as the signature to predict the LUAD patient’s response to the ICIs. GDPLichi utilized only 7 maker genes from 8 DDR pathways to construct the predictive model and classified LUAD patients into two subgroups: low- and high-risk groups. The high-risk group was featured by worse prognosis and decreased B cells, CD8+ T cells, CD8+ central memory T cells, hematopoietic stem cells (HSC), myeloid dendritic cells (MDC), and immune scores as compared to the low-risk group. However, our research also suggests that the high-risk group was more sensitive to ICIs, which might be explained by increased TMB, neoantigen, immune checkpoint molecules, and immune suppression genes’ expression, but lower TIDE score as compared to the low-risk group. This conclusion was verified in three other LUAD cohort datasets (GSE30219, GSE31210, GSE50081).

scholarly journals A Novel Nine-lncRNA Risk Signature Correlates With Immunotherapy in Hepatocellular Carcinoma

2021 ◽  
Vol 11 ◽  
Author(s):  
Ye Nie ◽  
Jianhui Li ◽  
Wenlong Wu ◽  
Dongnan Guo ◽  
Xinjun Lei ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Response Rate ◽  
Risk Group ◽  
Checkpoint Inhibitors ◽  
Risk Groups ◽  
Low Risk ◽  
Significant Difference ◽  
Checkpoint Genes

BackgroundHepatocellular carcinoma is one of the most common malignant tumors with a very high mortality rate. The emergence of immunotherapy has brought hope for the cure of hepatocellular carcinoma. Only a small number of patients respond to immune checkpoint inhibitors, and ferroptosis and tertiary lymphoid structure contribute to the increased response rate of immune checkpoint inhibitors; thus, we first need to identify those who are sensitive to immunotherapy and then develop different methods to improve sensitivity for different groups.MethodsThe sequencing data of hepatocellular carcinoma from The Cancer Genome Atlas and Gene Expression Omnibus was downloaded to identify the immune-related long non-coding RNAs (lncRNAs). LncRNAs related to survival data were screened out, and a risk signature was established using Cox proportional hazard regression model. R software was used to calculate the riskScore of each patient, and the patients were divided into high- and low-risk groups. The prognostic value of riskScore and its application in clinical chemotherapeutic drugs were confirmed. The relationship between riskScore and immune checkpoint genes, ferroptosis genes, and genes related to tertiary lymphoid structure formation was analyzed by Spearman method. TIMER, CIBERSORT, ssGSEA, and ImmuCellAI were used to evaluate the relative number of lymphocytes in tumor. The Wilcoxon signed-rank test confirmed differences in immunophenoscore between the high- and low-risk groups.ResultsData analysis revealed that our signature could well predict the 1-, 2-, 3-, and 5-year survival rates of hepatocellular carcinoma and to predict susceptible populations with Sorafenib. The risk signature were significantly correlated with immune checkpoint genes, ferroptosis genes, and tertiary lymphoid structure-forming genes, and predicted tumor-infiltrating lymphocyte status. There was a significant difference in IPS scores between the low-risk group and the high-risk group, while the low-risk group had higher scores.ConclusionThe riskScore obtained from an immune-related lncRNA signature could successfully predict the survival time and reflect the efficacy of immune checkpoint inhibitors. More importantly, it is possible to select different treatments for different hepatocellular carcinoma patients that increase the response rate of immune checkpoint inhibitors and will help improve the individualized treatment of hepatocellular carcinoma.

scholarly journals Identification of an Immune-Related LncRNA Signature in Gastric Cancer to Predict Survival and Response to Immune Checkpoint Inhibitors

2021 ◽  
Vol 9 ◽  
Author(s):  
Zuoyou Ding ◽  
Ran Li ◽  
Jun Han ◽  
Diya Sun ◽  
Lei Shen ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Overall Survival ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Risk Group ◽  
Checkpoint Inhibitors ◽  
High Risk Group ◽  
Low Risk ◽  
Predictive Capability ◽  
Invasive Capacity

Immune microenvironment in gastric cancer is closely associated with patient’s prognosis. Long non-coding RNAs (lncRNAs) are emerging as key regulators of immune responses. In this study, we aimed to construct a prognostic model based on immune-related lncRNAs (IRLs) to predict the overall survival and response to immune checkpoint inhibitors (ICIs) of gastric cancer (GC) patients. The IRL signature was constructed through a bioinformatics method, and its predictive capability was validated. A stratification analysis indicates that the IRL signature can distinguish different risk patients. A nomogram based on the IRL and other clinical variables efficiently predicted the overall survival of GC patients. The landscape of tumor microenvironment and mutation status partially explain this signature’s predictive capability. We found the level of cancer-associated fibroblasts, endothelial cells, M2 macrophages, and stroma cells was high in the high-risk group, while the number of CD8+ T cells and T follicular helper cells was high in the low-risk group. Immunophenoscore (IPS) is validated for ICI response, and the IRL signature low-risk group received higher IPS, representing a more immunogenic phenotype that was more inclined to respond to ICIs. In addition, we found RNF144A-AS1 was highly expressed in GC patients and promoted the proliferation, migration, and invasive capacity of GC cells. We concluded that the IRL signature represents a novel useful model for evaluating GC survival outcomes and could be implemented to optimize the selection of patients to receive ICI treatment.

scholarly journals Construction and validation of a novel pyroptosis-related signature to predict prognosis in patients with cutaneous melanoma

2021 ◽  
Vol 19 (1) ◽  
pp. 688-706
Author(s):  
Zehao Niu ◽  
◽  
Yujian Xu ◽  
Yan Li ◽  
Youbai Chen ◽  
...  
Keyword(s):  
Risk Score ◽  
Immune Checkpoint ◽  
Cutaneous Melanoma ◽  
Immune Checkpoint Inhibitors ◽  
Cox Regression ◽  
Risk Group ◽  
Checkpoint Inhibitors ◽  
External Validation ◽  
Low Risk ◽  
Health Concern

<abstract> <p>Skin cutaneous melanoma (SKCM) is one of the most malignant skin cancers and remains a health concern worldwide. Pyroptosis is a newly recognized form of programmed cell death and plays a vital role in cancer progression. We aim to construct a prognostic model for SKCM patients based on pyroptosis-related genes (PRGs). SKCM patients from The Cancer Genome Atlas (TCGA) were divided into training and validation cohorts. We used GSE65904 downloaded from GEO database as an external validation cohort. We performed Cox regression and the least absolute shrinkage and selection operator (LASSO) regression to identify prognostic genes and built a risk score. Patients were divided into high- and low-risk groups based on the risk score. Differently expressed genes (DEGs), immune cell infiltration and immune-related pathways activation were compared between the two groups. We established a model containing 4 PRGs, i.e., GSDMA, GSDMC, AIM2 and NOD2. The overall survival (OS) time was significantly different between the 2 groups. The risk score was an independent predictor for prognosis in both the uni- and multi-variable Cox regressions. Gene ontology (GO) and Kyoto Encylopedia of Genes and Genomes (KEGG) analyses showed that DEGs were enriched in immune-related pathways. Most types of immune cells were highly expressed in the low risk group. All immune pathways were significantly up-regulated in the low-risk group. In addition, low-risk patients had a better response to immune checkpoint inhibitors. Our novel pyroptosis-related gene signature could predict the prognosis of SKCM patients and their response to immune checkpoint inhibitors.</p> </abstract>

scholarly journals Risk Signature Related to Immunotherapy Reaction of Hepatocellular Carcinoma Based on the Immune-Related Genes Associated With CD8+ T Cell Infiltration

2021 ◽  
Vol 8 ◽  
Author(s):  
Yiping Zou ◽  
Zhihong Chen ◽  
Hongwei Han ◽  
Shiye Ruan ◽  
Liang Jin ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
T Cell ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Response Rate ◽  
Risk Group ◽  
Checkpoint Inhibitors ◽  
Cell Infiltration ◽  
T Cell Infiltration ◽  
Immune Related Genes

Background: Hepatocellular carcinoma (HCC) is the most common histological type of liver cancer, with an unsatisfactory long-term survival rate. Despite immune checkpoint inhibitors for HCC have got glories in recent clinical trials, the relatively low response rate is still a thorny problem. Therefore, there is an urgent need to screen biomarkers of HCC to predict the prognosis and efficacy of immunotherapy.Methods: Gene expression profiles of HCC were retrieved from TCGA, GEO, and ICGC databases while the immune-related genes (IRGs) were retrieved from the ImmPort database. CIBERSORT and WGCNA algorithms were combined to identify the gene module most related to CD8+ T cells in the GEO cohort. Subsequently, the genes in hub modules were subjected to univariate, LASSO, and multivariate Cox regression analyses in the TCGA cohort to develop a risk signature. Afterward, the accuracy of the risk signature was validated by the ICGC cohort, and its relationships with CD8+ T cell infiltration and PDL1 expression were explored.Results: Nine IRGs were finally incorporated into a risk signature. Patients in the high-risk group had a poorer prognosis than those in the low-risk group. Confirmed by TCGA and ICGC cohorts, the risk signature possessed a relatively high accuracy. Additionally, the risk signature was demonstrated as an independent prognostic factor and closely related to the CD8+ T cell infiltration and PDL1 expression.Conclusion: A risk signature was constructed to predict the prognosis of HCC patients and detect patients who may have a higher positive response rate to immune checkpoint inhibitors.

Immune checkpoint inhibitors and chemotherapy in first-line NSCLC: a meta-analysis

Immunotherapy ◽  
2021 ◽  
Author(s):  
Fausto Petrelli ◽  
Roberto Ferrara ◽  
Diego Signorelli ◽  
Antonio Ghidini ◽  
Claudia Proto ◽  
...  
Keyword(s):  
Immune Checkpoint ◽  
Evaluation System ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
Meta Analysis ◽  
First Line ◽  
Random Effects Models ◽  
Assessment Development ◽  
Programmed Death ◽  
Quantitative Synthesis

This study is a meta-analysis of randomized controlled trials involving first-line studies in which immune checkpoint inhibitors were added to chemotherapy and were compared with chemotherapy alone. The primary end point was overall survival (OS). The analyses used random-effects models and the Grading of Recommendations Assessment, Development, and Evaluation system to rate the quality of the evidence. Nine articles were included for qualitative and quantitative synthesis. A meta-analysis of the nine randomized trials showed a significant benefit in terms of OS (hazard ratio: 0.75 [95% CI: 0.66–0.85]; p < 0.01). Only programmed death ligand-1 positive-high cancers derive a significant OS benefit. In this meta-analysis, there is moderate evidence that the addition of immune checkpoint inhibitors to chemotherapy may improve both OS compared with chemotherapy alone.

Incidence and Economic Burden of Infections in Cancer Patients Receiving Immune Checkpoint Inhibitors: A Retrospective Cohort Study

2020 ◽  
Author(s):  
Swarna Nalluru ◽  
Paramrajan Piranavan ◽  
Anvesh Narimiti ◽  
Ahmad D. Siddiqui ◽  
George M. Abraham
Keyword(s):  
Risk Factors ◽  
Cancer Patients ◽  
Economic Burden ◽  
Immune Checkpoint ◽  
Average Cost ◽  
Immune Checkpoint Inhibitors ◽  
Multidisciplinary Approach ◽  
Checkpoint Inhibitors ◽  
Antitumor Effects ◽  
Cost Per Admission

Abstract BACKGROUNDAlong with antitumor effects, Immune Checkpoint Inhibitors (ICPI) have shown great potential in treating chronic infections such as HIV, Hepatitis B and malaria, in ex-vivo studies. However, several case reports and case series have suggested an increased infection risk in cancer patients. The purpose of our study was to assess the risk of infections in cancer patients receiving ICPI. We also attempted to evaluate the role of a multidisciplinary approach (Oncology and Infectious disease specialists) and the cost associated with treatment. METHODS:Records on all cancer patients over age ≥18 years old who had received at least one dose of ICPI between 2015 to 2018 at a major community teaching hospital in the central Massachusetts region were reviewed. Several risk factors associated with infection were identified. A two-tailed, unpaired t-test was used to analyze the association between risk factors and infection. We calculated the cumulative length of stay (LOS) and cost per admission with a multidisciplinary vs. non-multidisciplinary approach. The calculated total average cost per admission was compared to a matched population (without an oncologic diagnosis) admitted with infections similar to that in our study, to compare the economic burden. RESULTSRetrospective chart review of 169 cancer patients receiving ICPI showed sixty-two episodes of infection in thirty-seven (21.8%) patients and a mortality rate of 3.5% due to associated complications. Risk factors like COPD, prior chemotherapy and steroid use were significantly associated (P<0.05) with infections. Further sub-group analysis showed increase in cumulative LOS from 5.9 to 8.1 days but approximately similar average cost per admission ($52,047 vs. $54,510) with non-multidisciplinary vs. multidisciplinary approach. The calculated total cost per admission during an episode of infection in this cohort of patients was $35,484; three-fold higher when matched to similar infections in a general non-oncologic population ($11,527). CONCLUSIONSA significant incidence of infections and associated health care resource utilization continues to prevail in cancer patients despite the utility of ICPI. A multidisciplinary approach to manage the infections and associated complications in cancer patients receiving ICPI increased the cumulative LOS but not the average cost per admission.

Sign in / Sign up

Export Citation Format

Share Document