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

Immune checkpoints in cardiac physiology and pathology: therapeutic targets for heart failure

Immune checkpoint molecules are physiological regulators of the adaptive immune response. Immune checkpoint inhibitors (ICIs), such as monoclonal antibodies targeting programmed cell death protein 1 or cytotoxic T lymphocyte-associated protein 4, have revolutionized cancer treatment and their clinical use is increasing. However, ICIs can cause various immune-related adverse events, including acute and chronic cardiotoxicity. Of these cardiovascular complications, ICI-induced acute fulminant myocarditis is the most studied, although emerging clinical and preclinical data are uncovering the importance of other ICI-related chronic cardiovascular complications, such as accelerated atherosclerosis and non-myocarditis-related heart failure. These complications could be more difficult to diagnose, given that they might only be present alongside other comorbidities. The occurrence of these complications suggests a potential role of immune checkpoint molecules in maintaining cardiovascular homeostasis, and disruption of physiological immune checkpoint signalling might thus lead to cardiac pathologies, including heart failure. Although inflammation is a long-known contributor to the development of heart failure, the therapeutic targeting of pro-inflammatory pathways has not been successful thus far. The increasingly recognized role of immune checkpoint molecules in the failing heart highlights their potential use as immunotherapeutic targets for heart failure. In this Review, we summarize the available data on ICI-induced cardiac dysfunction and heart failure, and discuss how immune checkpoint signalling is altered in the failing heart. Furthermore, we describe how pharmacological targeting of immune checkpoints could be used to treat heart failure.

AI/ML advances in non-small cell lung cancer biomarker discovery

Lung cancer is the leading cause of cancer deaths among both men and women, representing approximately 25% of cancer fatalities each year. The treatment landscape for non-small cell lung cancer (NSCLC) is rapidly evolving due to the progress made in biomarker-driven targeted therapies. While advancements in targeted treatments have improved survival rates for NSCLC patients with actionable biomarkers, long-term survival remains low, with an overall 5-year relative survival rate below 20%. Artificial intelligence/machine learning (AI/ML) algorithms have shown promise in biomarker discovery, yet NSCLC-specific studies capturing the clinical challenges targeted and emerging patterns identified using AI/ML approaches are lacking. Here, we employed a text-mining approach and identified 215 studies that reported potential biomarkers of NSCLC using AI/ML algorithms. We catalogued these studies with respect to BEST (Biomarkers, EndpointS, and other Tools) biomarker sub-types and summarized emerging patterns and trends in AI/ML-driven NSCLC biomarker discovery. We anticipate that our comprehensive review will contribute to the current understanding of AI/ML advances in NSCLC biomarker research and provide an important catalogue that may facilitate clinical adoption of AI/ML-derived biomarkers.

A prediction model for severe hematological toxicity of BTK inhibitors

Bruton's tyrosine kinase inhibitor (BTKi) has revolutionized the treatment of B-cell lymphomas. However, BTKi-related hematological toxicity hinders treatment continuity and may further affect clinical efficacy. To identify risk factors and predict the likelihood of BTKi-related hematological toxicities, we constructed and validated a prediction model for severe hematological toxicity of BTKi. Approved by the hospital medical science research ethics committee (No. M2022427), we collected real-world data in patients treated with BTKi from a Lymphoma Research Center in China. The outcome of interest was severe hematological toxicity caused by BTKi. 36 candidate variables were categorized into demographics, diagnostic and treatment information, laboratory data, and medical history. The study sample was randomly divided into training (70%) and validation (30%) sets. We developed and compared the performance of various modelling methods, including decision tree (DT), random forest (RF), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and logistic regression (LR). Finally, we constructed a Web-calculator of the optimal model to estimate the risk of hematological toxicity. This study was designed, conducted and reported strictly in compliance with the TRIPOD checklist. Data from a total 121 patients were included [median age, 65 years (range, 56-73 years); 74 (61.15%) men; 47 (38.84%) severe hematological toxicity]. The XGBoost model demonstrated better overall properties than other models, achieving high discrimination (AUC: 0.671; accuracy: 0.730; specificity: 0.913) and clinical benefit. The following 10 variables were used to develop the XGBoost model: white blood cell count (WBC), neutrophil count (Neut), red blood cell count (RBC), platelet count (PLT), fibrinogen (Fib), total protein (TP), aspartate aminotransferase (AST), lactate dehydrogenase (LDH), gender and type of BTKi. SHAP values demonstrated insightful associations between these variables and hematological toxicity. Finally, to facilitate clinical and research use, we also deploy the XGBoost model on a web-calculator for free access. The XGBoost model with promising accuracy was developed to predict the severe hematological toxicity of BTKi. It helps to strengthen the proactive monitoring and management of patients with hematological toxicity, and thus achieve long-term continuous BTKi treatment.

Machine-learning-based adverse drug event prediction from observational health data: A review

Adverse drug events (ADEs) are responsible for a significant number of hospital admissions and fatalities. Machine learning models have been developed to assess the individual patient risk of having an ADE. In this article, we have reviewed studies addressing the prediction of ADEs in observational health data with machine learning. The field of individualised ADE prediction is rapidly emerging through the increasing availability of additional data modalities (e.g., genetic data, screening data, wearables data) and advanced deep learning models such as transformers. Consequently, personalised adverse drug event predictions are becoming more feasible and tangible.

The artificial intelligence and machine learning in lung cancer immunotherapy

Since the past decades, more lung cancer patients have been experiencing lasting benefits from immunotherapy. It is imperative to accurately and intelligently select appropriate patients for immunotherapy or predict the immunotherapy efficacy. In recent years, machine learning (ML)-based artificial intelligence (AI) was developed in the area of medical-industrial convergence. AI can help model and predict medical information. A growing number of studies have combined radiology, pathology, genomics, proteomics data in order to predict the expression levels of programmed death-ligand 1 (PD-L1), tumor mutation burden (TMB) and tumor microenvironment (TME) in cancer patients or predict the likelihood of immunotherapy benefits and side effects. Finally, with the advancement of AI and ML, it is believed that "digital biopsy" can replace the traditional single assessment method to benefit more cancer patients and help clinical decision-making in the future. In this review, the applications of AI in PD-L1/TMB prediction, TME prediction and lung cancer immunotherapy are discussed.

Early evaluation of severe immune checkpoint inhibitor-associated myocarditis: a real-world clinical practice

PURPOSE

Immune checkpoint inhibitor (ICI)-associated myocarditis is a rare but severe complication for patients treated with immunotherapy. This study aims to explore the predictive significance of patients' clinical features and examination results for the severity of ICI-associated myocarditis.

METHODS

Data from a real-world cohort of 81 cancer patients who developed ICI-associated myocarditis after immunotherapy were retrospectively analyzed. The development of myocarditis of Common Terminology Criteria for Adverse Events (CTCAE) grades 3-5 and/or the major adverse cardiovascular event (MACE) was set as endpoints. Logistic regression was used to evaluate the predictive value of each factor.

RESULTS

CTCAE grades 3-5 and MACE developed in 43/81 (53.1%) and 28/81 (34.6%) cases, respectively. The likelihood of CTCAE grades 3-5 and MACE increased with the accumulation of organs affected by the ICI-associated adverse events and initial clinical symptoms. Concurrent systematic therapies during ICI treatment did not raise the risk of myocarditis severity, while prior chemotherapy did. Besides classical serum cardiac markers, a higher neutrophil ratio was also related to poorer cardiac outcomes, whereas higher lymphocyte and monocyte ratios were predictors of favorable cardiac outcomes. The CD4+ T cell ratio and CD4/CD8 ratio were negatively related to CTCAE grades 3-5. Several cardiovascular magnetic resonance parameters were associated with myocarditis severity, whereas the predictive value of echocardiography and electrocardiogram was weak.

CONCLUSION

This study comprehensively evaluated the prognostic value of patients' clinical characteristics and examination results and identified several predictors of severe ICI-associated myocarditis, which will facilitate early detection of severe ICI-associated myocarditis in patients receiving immunotherapy.

Immune checkpoint blockade for locally advanced or recurrent/metastatic cervical cancer: An update on clinical data

Immunotherapy has shown great promise in the field of oncology, and recent clinical trials have illustrated that immune checkpoint blockade (ICB) is safe and effective at treating a range of tumor types. Cervical cancer (CC) is the fourth most common malignancy in women. However, first-line treatments for locally advanced cervical cancer (LACC) and recurrent/metastatic (R/M) CC have limited efficacy. Thus, it is necessary to explore new treatment approaches. The National Comprehensive Cancer Network (NCCN) currently recommends pembrolizumab, a programmed cell death protein 1 (PD-1) monoclonal antibody, as a first line therapy for individuals with R/M CC. This study reviews the progress of ICB therapy for LACC and R/M CC and describes the current status of the combination of ICB therapy and other therapeutic modalities, including radiotherapy, chemotherapy, targeted therapy, and other immunotherapies. The focus is placed on studies published since 2018 with the aim of highlighting novel CC-specific immunotherapeutic approaches and treatment targets.

Cardiac imaging techniques for the assessment of immune checkpoint inhibitor-induced cardiotoxicity and their potential clinical applications

Immune checkpoint inhibitors (ICIs) have encouraged a paradigm shift in the clinical management of patients with cancer. Despite the dramatically improved tumor response and patient prognosis, ICIs have been associated with ICI-related myocarditis, which has a high fatality rate. Cardiac imaging plays a critical role in the assessment of cardiac injury. Echocardiography, cardiac magnetic resonance imaging, and targeted tracer-based cardiac molecular imaging techniques alone or in combination reflect pathophysiology and depict different aspects of lesions at different clinical stages, i.e., they have potentially complementary value. Imaging techniques for identifying ICI-induced cardiotoxicity at the early stage may reduce the incidence of adverse cardiovascular events. Particularly in planned ICI therapy among patients with cancer, improved monitoring approaches to identify patients who are at the highest risk of ICI-related myocarditis may help in refining clinical decisions, allowing treatment to be more accurately targeted toward patients who are most likely to benefit. In this study, we systematically reviewed the studies on cardiac imaging techniques for assessing ICI-induced cardiotoxicity. We elaborated about the potential applications of cardiac imaging techniques for the optimized management of patients with ICI-related myocarditis, including risk stratification, diagnosis, and prognosis.

Immune Checkpoint Inhibitor-Associated Cardiotoxicity in Solid Tumors: Real-World Incidence, Risk Factors, and Prognostic Analysis

Background

Immune checkpoint inhibitors (ICIs) have achieved acknowledged progress in cancer therapy. However, ICI-associated cardiotoxicity as one of the most severe adverse events is potentially life-threatening, with limited real-world studies reporting its predictive factors and prognosis. This study aimed to investigate the real-world incidence, risk factors, and prognosis of ICI-related cardiotoxicity in patients with advanced solid tumors.

Methods

Electronic medical records from patients with advanced solid tumors receiving ICIs in the First Affiliated Hospital of Xi’an Jiaotong University were retrospectively reviewed. All patients were divided into the cardiotoxicity group and control group, with logistic regression analysis being implemented to identify potential risk factors of ICI-related cardiotoxicity. Furthermore, survival analysis was also performed to investigate the prognosis of patients with ICI-related cardiotoxicity.

Results

A total of 1,047 participants were enrolled in this retrospective study. The incidence of ICI-related cardiotoxicity in our hospital is 7.0%, while grade 3 and above cardiotoxicity was 2.4%. The logistic regression analysis revealed that diabetes mellitus [odds ratio (OR):1.96, 95% confidence Interval (CI): 1.05–3.65, p = 0.034] was an independent risk factor, whereas baseline lymphocyte/monocyte ratio (LMR) (OR: 0.59, 95% CI: 0.36–0.97, p = 0.037) was the protective factor of ICI-related cardiotoxicity. Survival analysis indicated that severe cardiotoxicity (≥grade 3) was significantly correlated with bleak overall survival (OS) than mild cardiotoxicity (≤grade 2) (8.3 months vs. not reached, p = 0.001). Patients with ICI-related overlap syndrome had poorer overall survival than patients with mere cardiotoxicity (9.4 vs. 24.7 months, p = 0.033). However, the occurrence of ICI-related cardiotoxicity was not significantly associated with the OS of overall population with solid tumors. Subgroup analysis showed that lung cancer and PD-L1 usage were significantly correlated with a higher incidence of severe cases.

Conclusion

Immune checkpoint inhibitor-related cardiotoxicity is more common in the real-world setting than the previously published studies. Diabetes mellitus and baseline LMR are the potential predictive biomarkers of ICI-related cardiotoxicity. Although ICI-related cardiotoxicity is not correlated with the prognosis of these patients in our cohort, a systematic and comprehensive baseline examination and evaluation should be performed to avoid its occurrence.

Association of thyroid function abnormality and prognosis in non-small-cell lung cancer patients treated with PD-1 inhibitors

Background: Thyroid function abnormality (TFA) is one of the most common toxicities in non-small-cell lung cancer (NSCLC) patients receiving immune checkpoint inhibitors. However, the risk factors related to TFA and the relationship between TFA and prognosis in NSCLC are not fully clarified. Methods: We conducted a retrospective study of patients with advanced NSCLC who were treated with PD-1 inhibitors in Huzhou Central Hospital. Thyroid function test was carried out using electrochemiluminescent bridging immunoassay. The association between TFA and clinical outcome was investigated. Results: A total of 273 patients were included in this study. Patients who experienced TFA had longer progression-free survival (21.9 vs 6.4 months; p < 0.001) and overall survival (44.6 vs 24.1 months; p = 0.02) than patients without TFA. After multivariate analysis, TFA was an independent prognostic factor for progression-free and overall survival (p < 0.05). Conclusion: TFA is associated with better outcome in NSCLC patients who receive immunotherapy.

Multimodality Advanced Cardiovascular and Molecular Imaging for Early Detection and Monitoring of Cancer Therapy-Associated Cardiotoxicity and the Role of Artificial Intelligence and Big Data

Cancer mortality has improved due to earlier detection via screening, as well as due to novel cancer therapies such as tyrosine kinase inhibitors and immune checkpoint inhibitions. However, similarly to older cancer therapies such as anthracyclines, these therapies have also been documented to cause cardiotoxic events including cardiomyopathy, myocardial infarction, myocarditis, arrhythmia, hypertension, and thrombosis. Imaging modalities such as echocardiography and magnetic resonance imaging (MRI) are critical in monitoring and evaluating for cardiotoxicity from these treatments, as well as in providing information for the assessment of function and wall motion abnormalities. MRI also allows for additional tissue characterization using T1, T2, extracellular volume (ECV), and delayed gadolinium enhancement (DGE) assessment. Furthermore, emerging technologies may be able to assist with these efforts. Nuclear imaging using targeted radiotracers, some of which are already clinically used, may have more specificity and help provide information on the mechanisms of cardiotoxicity, including in anthracycline mediated cardiomyopathy and checkpoint inhibitor myocarditis. Hyperpolarized MRI may be used to evaluate the effects of oncologic therapy on cardiac metabolism. Lastly, artificial intelligence and big data of imaging modalities may help predict and detect early signs of cardiotoxicity and response to cardioprotective medications as well as provide insights on the added value of molecular imaging and correlations with cardiovascular outcomes. In this review, the current imaging modalities used to assess for cardiotoxicity from cancer treatments are discussed, in addition to ongoing research on targeted molecular radiotracers, hyperpolarized MRI, as well as the role of artificial intelligence (AI) and big data in imaging that would help improve the detection and prognostication of cancer-treatment cardiotoxicity.