Checkpoint Inhibitor-related Pneumonitis Research Articles

Predicting Immune Checkpoint Inhibitor-Related Pneumonitis via Computed Tomography and Whole-Lung Analysis Deep Learning

Background: Immune checkpoint inhibitor-related pneumonitis (ICI-P) is a fatal adverse event of immunotherapy. However, there is a lack of methods to identify patients who have a high risk of developing ICI-P in immunotherapy. Purpose: We aim at predicting the individualized risk of developing ICI-P by computed tomography (CT) images and deep learning to assist in personalized immunotherapy planning. Methods: We first explored the prognostic value of the commonly used clinical factors. Moreover, we proposed a novel whole-lung analysis deep learning (DL) model, which is constructed using a combination of Densely Connected Convolutional Networks (DenseNet) and Feature Pyramid Networks (FPN). This DL model mines global lung information from CT images for predicting the risk of developing ICI-P, and it is fully automated and does not require manually annotating images. Finally, 157 patients were collected and randomly divided into training and testing sets for performance evaluation. Results: In the testing set, the clinical model achieved an Area Under the Curve (AUC) of 0.710 and accuracy of 0.625. By mining global lung information, the DL model achieved AUC=0.780 and accuracy=0.729 in the testing set, where the DL score revealed a significant difference between ICI-P and non-ICI-P patients. Through deep learning visualization technique, we found that many areas outside of tumor (e.g., pleural retraction, pleural effusion, and the abnormalities in vessels) are important for predicting the risk of developing ICI-P in immunotherapy. Conclusions: The whole-lung analysis DL model provides an easy-to-use method for identifying patients at high risk of developing ICI-P by CT images, which is important for individualized treatment planning in immunotherapy. The performance improvement over the clinical model indicates that mining whole-lung information in CT images is effective for prognostic prediction in immunotherapy.

First-line chemoimmunotherapy for patients with small-cell lung cancer and interstitial lung abnormality: CIP risk and prognostic analysis.

Patients with non-small-cell lung cancer (NSCLC) receiving immunotherapy face a potential risk of developing checkpoint inhibitor-related pneumonitis (CIP). However, there is no clear understanding of the specific link between interstitial lung abnormality (ILA) and CIP in patients with small-cell lung cancer (SCLC). In addition, the prognosis of SCLC patients with ILA who receive chemoimmunotherapy is uncertain. Our study aimed to investigate the effect of ILA on the occurrence of CIP in SCLC patients receiving first-line chemoimmunotherapy and to assess its relationship with prognosis. We conducted a retrospective analysis of SCLC patients who received chemoimmunotherapy as a first-line treatment between January 2018 and April 2024. The diagnosis of ILA was assessed by two experienced pulmonologists based on pretreatment chest computed tomography images. We investigated independent risk factors for CIP using logistic regression analysis and factors affecting PFS and OS using Cox regression analysis. A total of 128 patients with SCLC were included in the study. ILA was present in 41 patients (32.03%), and CIP occurred in 16 patients (12.50%). In multivariate logistic regression analysis, previous ILA (OR, 5.419; 95% CI, 1.574-18.652; p = 0.007) and thoracic radiation therapy (TRT) (OR, 5.259; 95% CI, 1.506-18.365; p = 0.009) were independent risk factors for CIP. ILA (HR, 2.083; 95% CI, 1.179-3.681; p = 0.012) and LDH (HR, 1.002; 95% CI, 1.001-1.002; p < 0.001) were statistically significant for increased mortality risk in multivariate Cox regression analysis. In SCLC patients receiving first-line chemoimmunotherapy, baseline ILA is a risk factor for CIP and is associated with poorer prognosis.

Single-cell landscape of bronchoalveolar immune cells in patients with immune checkpoint inhibitor-related pneumonitis

The pathophysiology of immune checkpoint inhibitor-related pneumonitis remains incompletely understood. We conducted single-cell and T-cell receptor transcriptomic sequencing on the bronchoalveolar lavage fluid from five patients with grade ≥2 immune checkpoint inhibitor-related pneumonitis. Our analyses revealed a prominent enrichment of T cells in the bronchoalveolar lavage fluid of patients with immune checkpoint inhibitor-related pneumonitis. Within the CD4 + T cell subset, Tfh-like T cells were highly enriched and exhibited signatures associated with inflammation and clonal expansion. Regulatory T cells were also enriched and displayed enhanced inhibitory functions. Within the CD8 + T-cell subset, effector memory/tissue-resident memory T cells with an elevated cytotoxic phenotype were highly infiltrated. Among myeloid cells, alveolar macrophages were depleted, while pro-inflammatory intermediate monocytes were elevated. Dendritic cells demonstrated enhanced antigen presentation capabilities. Cytokines CXCR4, CXCL13, TNF-α, IFN-α, IFN-γ, and TWEAK were elevated. Through a comprehensive single-cell analysis, we depicted the landscape of immune checkpoint inhibitor-related pneumonitis.

Derived neutrophil-to-lymphocyte ratio has the potential to predict safety and outcomes of durvalumab after chemoradiation in non-small cell lung cancer

The usefulness of the derived neutrophil-to-lymphocyte ratio (dNLR) and its dynamics before/after durvalumab consolidation therapy to predict safety or efficacy remains unclear. We retrospectively reviewed patients with locally advanced non-small cell lung cancer treated with durvalumab consolidation therapy after chemoradiotherapy (D group) or chemoradiotherapy alone (non-D group) at multiple institutions. We investigated the association between dNLR, or its dynamics, and pneumonitis, checkpoint inhibitor-related pneumonitis (CIP), irAEs, and efficacy. Ninety-eight and fifty-six patients were enrolled in the D and non-D groups, respectively. The dNLR at baseline was significantly lower in patients who experienced irAEs or CIP than in those who did not. The low dNLR group, 28 days following durvalumab consolidation therapy (dNLR28 ≤ 3), demonstrated longer progression-free survival (PFS) and overall survival (OS) than the high dNLR group (dNLR28 > 3) (PFS, hazard ratio [HR] 0.44, 95% confidence interval [CI] 0.22–0.88, p = 0.020; OS, HR 0.39, 95% CI 0.16–0.94, p = 0.037). Among patients with high dNLR at baseline (dNLR > 3), the dNLR28 ≤ 3 group showed longer PFS than the dNLR28 > 3 group (p = 0.010). The dNLR is a predictive factor for irAEs and CIP in patients receiving durvalumab consolidation therapy. The dNLR at 28 days after durvalumab consolidation therapy and its dynamics predict favorable outcomes.

High-Resolution CT Patterns of Anti-PD1 Checkpoint Inhibitor-Related Pneumonitis in Patients With Lung Cancer.

Lung cancer has the highest morbidity and mortality in the world, and immunotherapies have been developed for this disease in recent years. However, activation of the immune system can cause immune-related adverse events (irAEs), and checkpoint inhibitor-related pneumonitis (CIP), can be the most severe and fatal. But few reports have systematically examined the spectrum of imaging findings of this condition. Therefore, the objective of this paper is to investigate the high-resolution computed tomography (HRCT) characteristics of CIP in patients with lung cancer. To investigate the HRCT characteristics of CIP in patients with lung cancer. HRCT patterns in 41 lung cancer patients who developed CIP after treatment with immune checkpoint inhibitors were retrospectively characterized by interstitial lung disease classification, and their severity was graded. Specific HRCT characteristics related to CIP were identified. There are 4 types of immunotherapy-induce pneumonitis patterns (organizing pneumonia OP 19 cases, nonspecific interstitial pneumonia NSIP 8 cases, acute interstitial pneumonia AIP 7 cases, 7 cases of undetermined type) and image grade (13 cases of grade 1, 17 cases of grade 2, 11 cases of grade 3, 0 cases of grade 4) were identified. Spatial distribution characteristics of these lesions were noted (17 cases predominantly distributed in tumor-containing lobes, 6 cases predominantly distributed in non-tumor-containing lobes, and no specific predilection in 18 cases). Specific CT imaging features found in CIP included, in the order of prevalence, the following: ground glass opacities (38 cases), subpleural/vertical line (37 cases), interstitial thickening around the bronchovascular bundles (36 cases), reticulation (34 cases), fine reticular shadow (31 cases), consolidation (31 cases), small cystic shadow (24 cases, may not having honeycombing), small nodules (17 cases), bronchiectasis (15 cases), honeycombing (11 cases), mosaic sign (11 cases), and pleural effusion (18 cases). HRCT of CIP predominantly manifests as ground glass opacities, reticulation, subpleural/vertical line, interstitial thickening around the bronchovascular bundle, and consolidation.

The application of bronchoscopy in the assessment of immune checkpoint inhibitor-related pneumonitis severity and recurrence

To explore the role of bronchoscopy for the assessment of checkpoint inhibitor pneumonitis (CIP), a retrospective single-center study was conducted to assess patients diagnosed with CIP at grade 2 or above and also underwent bronchoscopy between January 2020 and December 2022. Clinical data and bronchoscopic findings were recorded. The treatment data and prognosis information were collected. Twenty-one patients who underwent bronchoscopy and were diagnosed with CIP were enrolled in this study. All patients underwent bronchoalveolar lavage fluid (BALF) analysis. Of them, T lymphocyte subsets of BALF were tested in 15 cases. Transbronchial cryobiopsy (TBCB) was performed in 8 patients, and transbronchial lung biopsy was performed in 5 patients. 3 patients developed pneumothorax after TBCB and all recovered without serious compilations.14 patients experienced grade 2 CIP, while 7 patients ≥ grade 3 CIP. Symptoms were improved in 19 (90.5%) patients after standard treatment adhering to CIP guidelines. However, 5 patients relapsed during steroid tapering. Factors related to the severity and recurrence of CIP were analyzed. Patients with previous interstitial lung disease (ILD) were more likely to develop high grade CIP than those without [83.3% (5/6) versus 15.4% (3/15), P = 0.011].The odds ratio (OR) was 32.5 (95% CI 2.284–443.145, P = 0.009). Increased BALF lymphocyte percentage was associated with high grade CIP, OR 1.095 (95% CI 1.001–1.197, P = 0.047), and higher possibility of CIP relapse, OR 1.123 (95% CI, 1.005–1.225, P = 0.040). Lymphocyte subsets were tested in 15 patients. CD4/CD8 > 1 was found in 80% (4/5) of relapsed patients and 20% (2/10) of patients without relapse (P = 0.047). The OR was 16.00 (95% CI 1.093–234.24, P = 0.043). In this retrospective study, patients with previous ILD was more likely to develop high grade CIP. Higher lymphocyte percentage in BALF was associated with high grade CIP and susceptibility to relapse during treatment of CIP. A CD4/CD8 ratio greater than 1 in lymphocyte subsets of BALF was associated with higher possibility of CIP relapse. We found that TBCB is a safe procedure in CIP patients.

AI-based radiomics model for predicting immune checkpoint inhibitor–related pneumonitis (CIP) in patients with advanced NSCLC: An external validation study.

12136 Background: The growing implementation of immunotherapy in advanced non-small cell lung cancer (NSCLC) management has led to an increase in adverse events, notably immune checkpoint inhibitor-related pneumonitis (CIP). CIP, a significant and potentially fatal complication, often necessitates the discontinuation of immunotherapy, thereby impacting patient outcomes severely. The absence of biomarkers for early detection and management of CIP represents an urgent and unmet clinical need. This expanded study explores the potential of Artificial Intelligence (AI) algorithms in predicting CIP in NSCLC patients undergoing immunotherapy from pre-treatment CT scans. Methods: A cohort of 220 stage III-IV NSCLC patients receiving immunotherapy was considered. The patients were divided into a training set (D1, n=105, Institution A), an internal validation set (D2, n=45, Institution A), and an external validation set (D3, N=70, Institutions B and C). Manual delineation of the tumor on baseline CT was performed by three physicians working in consensus. The Picture Health Px platform was employed for AI-powered deep phenotyping of the tumor and its surrounding habitat, including segmentation of the tumor associated vasculature and featurization. Quantitative features relating to the twistedness of the tumor-associated vasculature and tumoral heterogeneity patterns were extracted. These features were used to train a neural network classifier for CIP prediction. Weighting techniques during training were used to compensate for the rarity of CIP. A threshold for CIP classification was set within D1 and applied to the testing sets. Results: 43.6% of patients received an immunotherapy-only regimen and 56.4% received combined immunochemotherapy. Of these, 18.2.% experienced pneumonitis events, with 50.0% being CIP. The CIP subgroup had 50.0% grade 1 CIP, 30.0% grade 2, and 20.0% grade 3. The cross-validated AUC on D1 was 0.76 (95% CI: 0.62-0.90). The AUC was 0.61, 0.62, and 0.64, respectively, on D2, D3, and all validation data combined (D2+D3). The model correctly identified 71.4% of grade 1/2 CIP events and 33.3% of grade 3 CIP, with a corresponding false positive rate of 33.0%. Severe/grade 3 IO-related pneumonitis prediction was likely limited by the small number of severe cases from the training institution (n=1). Conclusions: We demonstrated a radiomic AI signature could identify patients at risk of CIP prior to treatment across multiple external institutions. This approach could improve the identification and management of CIP in NSCLC patients on immunotherapy, thereby enhancing patient outcomes. Expanded training and validation to account for rare, but possibly fatal, high grade CIPs is needed to expand the clinical benefit of radiologic predictors of pneumonitis to the most severe cases.

Harmonization radiomics model to predict immune checkpoint inhibitor-related pneumonitis (CIP) in patients with non-small cell lung cancer (NSCLC).

12142 Background: The increasing use of immunotherapy in advanced non-small cell lung cancer (NSCLC) presents a significant challenge in managing adverse events, particularly checkpoint inhibitor-associated pneumonitis (CIP). This potentially life-threatening complication often necessitates discontinuation of immunotherapy, even in patients experiencing tumor response. Presently, there are no reliable models to predict the onset of CIP. This research utilizes CT radiomics to create an innovative approach for anticipating the risk of CIP in patients with NSCLC. Methods: This IRB-approved, retrospective study analyzed data from 159 stage III-IV NSCLC patients undergoing immunotherapy. We categorized patients into pneumonitis (further subdivided into immunotherapy-induced, radiation-induced, and others) and non-pneumonitis groups. Using LIFEx software, we extracted 3D-radiomic features from both tumors and surrounding 1cm thick peritumoral regions. To address scanner-associated variations, a linear mixed-effect radiomics harmonization model was applied. A Random Forest algorithm was then used to develop a classification model predicting CIP occurrence based on the pre-treatment CT radiomic and clinical data. The dataset was split into training (70%) and test (30%) sets. The accuracy of predictions was evaluated using confusion matrix statistics and bootstrapping with 1,000 iterations for median and 95% confidence interval (CI). The performance metrics included sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the ROC curve (AUC). Results: 159 patients were analyzed, of which only 19 had checkpoint inhibitor-related pneumonitis. Among which, 17 (54.8%) patients had grade 1 pneumonitis, 12 (38.7%) patients had grade 2 pneumonitis, 2 (6.5%) patients had grade 3 pneumonitis, and none had grade 4 or grade 5 pneumonitis. The model achieved a sensitivity of 0.98 (0.97, 0.99), a specificity of 0.08 (0.05, 0.14), a PPV of 0.91 (0.90, 0.91), and an NPV of 0.33 ± 0.23 for predicting CIP. The AUC of 0.59 (0.56, 0.66) indicates that the model may predict checkpoint inhibitor-associated pneumonitis with an accuracy of 59%. Conclusions: The study provides insights into the potential of radiomic analysis coupled with AI algorithms and the use of harmonization model in predicting CIP among NSCLC patients treated with immunotherapy. However, larger studies are needed to validate our findings and the utility of harmonization models in predicting CIP.

Risk factors of immune checkpoint inhibitor-related pneumonitis after neoadjuvant immunochemotherapy for resectable NSCLC

BackgroundThe incidence of checkpoint inhibitor-associated pneumonitis (CIP) in advanced non-small cell lung cancer (NSCLC) has been substantiated through large-scale clinical trials or real-world studies. However, reports on CIP incidence within the context of neoadjuvant immunotherapy for resectable NSCLC remain scarce. This study endeavors to investigate the incidence, risk factors, and outcomes of CIP in patients with resectable NSCLC receiving neoadjuvant immunochemotherapy.MethodsA retrospective, case-control study was conducted on patients diagnosed with NSCLC stages IIA–IIIB who received neoadjuvant immunochemotherapy between January 2018 and September 2022. Patients were stratified into two groups based on the presence or absence of CIP, facilitating a comparative analysis of clinical characteristics, treatment modalities, physiological indicators, and prognostic outcomes .ResultsThe study cohort comprised 245 patients, with 11.4% (28/245) experiencing CIP. The median period of CIP onset was 70 (range, 40–221) days. The incidence of severe CIP (grade 3–4) was 3.7% (9/245). Patients with CIP showed a higher all-cause mortality rate of 21.4% (6/28) compared to that of patients without CIP. Those who developed CIP exhibited elevated body mass index (BMI) values (p = 0.028) and increased fibrinogen (FIB) levels (p < 0.001), alongside a significant decrease in both diffusing capacity for carbon monoxide (DLCO)% pred (p = 0.001) and DLCO/VA% pred (p = 0.021) after neoadjuvant therapy compared to pre-indicators. Receiver operating characteristic curve (ROC) analysis showed that the area under the ROC curve of three assessed variables (FIB levels, BMI, DLCO) reached 0.806 in predicting CIP occurrence at an early stage.ConclusionsThis cohort demonstrated that elevated BMI, increased FIB levels, and decreased pulmonary diffusion function after neoadjuvant therapy are risk factors of CIP occurrence. Early assessment and continuous monitoring of these indicators are imperative for the predictive identification of CIP, enhancing patient management and outcomes.

Autoimmunity Against Surfactant Protein B Is Associated with Pneumonitis During Checkpoint Blockade.

Rationale: Immune checkpoint inhibitor (ICI)-related pneumonitis is a serious autoimmune event affecting as many as 20% of patients with non-small-cell lung cancer (NSCLC), yet the factors underpinning its development in some patients and not others are poorly understood. Objectives: To investigate the role of autoantibodies and autoreactive T cells against surfactant-related proteins in the development of pneumonitis. Methods: The study cohort consisted of patients with NSCLC who provided blood samples before and during ICI treatment. Serum was used for proteomics analyses and to detect autoantibodies present during pneumonitis. T-cell stimulation assays and single-cell RNA sequencing were performed to investigate the specificity and functionality of peripheral autoreactive T cells. The findings were confirmed in a validation cohort comprising patients with NSCLC and patients with melanoma. Measurements and Main Results: Across both cohorts, patients in whom pneumonitis developed had higher pretreatment levels of immunoglobulin G autoantibodies targeting surfactant protein (SP)-B. At the onset of pneumonitis, these patients also exhibited higher frequencies of CD4+ IFN-γ-positive SP-B-specific T cells and expanding T-cell clonotypes recognizing this protein, accompanied by a proinflammatory serum proteomic profile. Conclusions: Our data suggest that the cooccurrence of SP-B-specific immunoglobulin G autoantibodies and CD4+ T cells is associated with the development of pneumonitis during ICI therapy. Pretreatment levels of these antibodies may represent a potential biomarker for an increased risk of developing pneumonitis, and on-treatment levels may provide a diagnostic aid.

Abstract 7529: Harmonization radiomics model to predict immune checkpoint inhibitor-related pneumonitis (CIP) in non small cell lung cancer (NSCLC) in patients treated with immunotherapy

Abstract Background: With the increasing use of immunotherapy in advanced non-small cell lung cancer (NSCLC), managing adverse events, particularly checkpoint inhibitor-associated pneumonitis (CIP), poses a significant challenge. CIP often necessitates discontinuation of immunotherapy, even in cases of tumor response. Currently there are no effective models in predicting CIP. This study leverages artificial intelligence (AI) algorithms and the use of harmonization models to analyze radiomic features from chest CT scans, aiming to predict the occurrence of CIP in patients with NSCLC. Methods: This retrospective study examined data from 152 stage III-IV NSCLC patients undergoing immunotherapy. Tumor segmentation was performed using LIFEx software (IMIV/CEA, Orsay, France). 3D-radiomic features were extracted from both the tumor and the surrounding 1 cm thick peritumoral regions. The Random Forest (RF) algorithm was employed to develop a classification model to differentiate between CIP and non-CIP. A harmonization model was deployed to account for the scanner-related differences by using spleen and normal lung signals. The dataset was divided into a training set (75%) and a test set (25%). Bootstrapping with 1,000 iterations was performed to estimate the model's performance by calculating the median and 95% confidence interval (CI) estimate. The accuracy of the model's predictions was evaluated by creating a confusion matrix. The model's performance was assessed by calculating the sensitivity, specificity, positive predictive values (PPV), negative predictive values (NPV), and area under the ROC curve (AUC) for CIP prediction. Results: Among 152 patients, 87 (57.23%) are female and 65 (42.76%) are male. The median age was 59 years. Histology types included were Adenocarcinoma 111 (73%), Squamous cell carcinoma 27 (17.8%), and others 14 (9.2%). CIP was seen in 30 (19.73%) patients. Among the 30 patients with CIP, 17 (56.7%) patients had grade 1 pneumonitis, 11 (36.7%) patients had grade 2 pneumonitis, 2 (6.6%) patients had grade 3 pneumonitis, and none had grade 4 or grade 5 pneumonitis. The model achieved a sensitivity of 0.57, a specificity of 0.67, a PPV of 0.48, and NPV of 0.38 for predicting CIP. The AUC of 0.59 indicates that the model may predict checkpoint inhibitor-associated pneumonitis with an accuracy of 59%. Conclusions: The study provides insights into the potential of radiomic analysis coupled with AI algorithms and the use of harmonization model in predicting CIP among NSCLC patients treated with immunotherapy. Larger studies are needed to validate our findings and the utility of harmonization models in predicting CIP. Citation Format: Monica Yadav, Jeeyeon Lee, Peter Haseok Kim, Seyoung Lee, Taegyu Um, Salie Lee, Maria Jose Chuchuca, Trie Arni Djunadi, Liam Il-Young Chung, Jisang Yu, Darren Rodrigues, Nicolo Gennaro, Leeseul Kim, Myungwoo Nam, Youjin Oh, Sungmi Yoon, Zunairah Shah, Yuchan Kim, Ilene Hong, Jessica Jang, Grace Kang, Amy Cho, Soowon Lee, Timothy Hong, Cecilia Nam, Yury S Velichko, Young Kwang Chae. Harmonization radiomics model to predict immune checkpoint inhibitor-related pneumonitis (CIP) in non small cell lung cancer (NSCLC) in patients treated with immunotherapy [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 7529.

Abstract 2594: AI-powered radiomics model predicts immune checkpoint inhibitor-related pneumonitis (CIP) in advanced NSCLC patients

Abstract Background: With the escalating integration of immunotherapy in the management of advanced non-small cell lung cancer (NSCLC), the emergence of adverse events, particularly immune checkpoint inhibitor-related pneumonitis (CIP), poses important challenges. CIP is not uncommon and can be life-threatening. It often necessitates the discontinuation of immunotherapy, even in patients with an otherwise favorable response. Prevention, early detection and early management of CIP can enhance patient outcomes, yet no such predictive models have been established. This study investigates the use of Artificial Intelligence (AI) algorithms in analyzing radiomic features for the prediction of CIP in NSCLC patients receiving immunotherapy. Methods: A cohort of 105 stage III-IV NSCLC patients receiving immunotherapy was examined. Half of the patients were randomly split to a training set, while the remaining half were reserved for algorithm testing. The manual segmentation was performed by three physicians annotating in consensus using LIFEx software v7.3.0 (IMIV/CEA, Orsay, France). The Picture Health Px platform was utilized to perform an AI-powered deep phenotyping of the tumor and its surrounding habitat. A number of interpretable feature measures were extracted from baseline CT scans, which were in turn used to train a deep learning classifier for the detection of pneumonitis. Weighting techniques were applied to compensate for the imbalance of pneumonitis cases. Results: Among the 105 patients, 63 (60.0%) received immunotherapy-only regimen and 42 (40.0%) received combination immunochemotherapy. 18 (17.1%) patients had pneumonitis events. Within this subset, 10 (55.6%) had CIP. Among the CIP group, six patients (60.0%) had grade 1 pneumonitis, three patients (30.0%) had grade 2 pneumonitis, and one patient (10.0%) had grade 3 pneumonitis, and none had grade 4 or grade 5 pneumonitis. Within the training set (n=51), the cross-validated area under the ROC curve (AUC) was 0.71 (95% CI: 0.68-0.74). When applied to the test set, the model predicted pneumonitis with AUC=0.63. Across the two datasets, the model correctly identified 4/6 (66.7%) grade 1 pneumonitis events and 2/3 (66.7%) grade 2 pneumonitis events, but misclassified the only available grade 3 event. Conclusion: The utilization of CT-based radiomic features demonstrates promise in predicting CIP in NSCLC patients undergoing immunotherapy. This approach holds potential for enhancing the identification and management of CIP, among NSCLC patients treated with immunotherapy. Citation Format: Seyoung Lee, Amogh Hiremath, Jeeyeon Lee, Peter Haseok Kim, Kai Zhang, Salie Lee, Monica Yadav, Maria J. Chuchuca, Taegyu Um, Myungwoo Nam, Liam Il-Young Chung, Hye Sung Kim, Jisang Yu, Trie Arni Djunadi, Leeseul Kim, Youjin Oh, Sungmi Yoon, Zunairah Shah, Yuchan Kim, Ilene Hong, Grace Kang, Jessica Jang, Amy Cho, Soowon Lee, Cecilia Nam, Timothy Hong, Yuri S. Velichko, Vamsidhar Velcheti, Anant Madabhushi, Nathaniel Braman, Young Kwang Chae. AI-powered radiomics model predicts immune checkpoint inhibitor-related pneumonitis (CIP) in advanced NSCLC patients [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2594.

Clinical Characteristics, Management and Prognostic Factors of Immune Checkpoint Inhibitor-Associated Pneumonia in Chinese Cancer Patients.

To investigate the clinical characteristics, treatment methods, outcomes, and variables influencing the outcomes of checkpoint inhibitor-related pneumonitis (CIP) among Chinese cancer patients. Descriptive Study. Place and Duration of the Study: Department of Pharmacy, Hunan Cancer Hospital, The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha, China, from January 2019 to December 2022. Patients with CIP were inducted. Clinical data including patient characteristics, ICI protocols; and the clinical features, treatments, and outcomes of CIP were collected and analysed. One hundred and forty-six patients were included. Median time to onset in the CIP was 17.0 weeks (range: 0.4 - 74.7). Mild CIP and severe CIP accounted for 84.93% and 15.07% of cases, respectively. All patients with CIP received methylprednisolone treatment, with an average starting dose of 1.64 mg/kg (0.59-6.00 mg/kg), and 79 (54.11%) of them received anti-infective therapy. One hundred and thirteen (77.04%) patients had improved symptoms of pneumonia, with only 33 (22.60%) patients displaying no improvement. Multivariate analysis revealed that the severity of CIP [OR = 0.167 (95% CI 0.061-0.461), p <0.001] and the starting dose of methylprednisolone [OR = 0.314 (95% CI 0.129-0.764), p <0.001] were independent predictors of outcomes of CIP, while the use of antibiotic was not. The severity of CIP and the initial dosage of methylprednisolone administered are significant factors that impact the outcomes of CIP in Chinese cancer patients after ICI treatment. Appropriate use of glucocorticoids and antibiotics is a necessary managementstrategy to control CIP effectively. Immune checkpoint inhibitors, Immune-related adverse events, Checkpoint inhibitor-related pneumonitis, Glucocorticosteroids, Antibiotics, Prognostic factors.

Treatment patterns and outcomes of high-grade immune checkpoint inhibitor-related pneumonitis in an oncology hospitalist service.

Immune checkpoint inhibitors (ICI) have become standard of care for some types of lung cancer. Along with expanding usage comes the emergence of immune-related adverse events (irAEs), including ICI-related pneumonitis (ICI-P). Treatment guidelines for managing irAEs have been developed; however, how clinicians manage irAEs in the real-world setting is less well known. We aimed to describe the outcomes and care patterns of grade ≥ 3 ICI-P in an onco-hospitalist service. We included patients with lung cancer treated with ICI who were admitted to an oncology hospitalist service with a suspicion of ICI-P. We described the hospitalization characteristics, treatment patterns, discharge practices, and clinical outcomes of patients with confirmed ICI-P. The primary outcome was time to start treatment for ICI-P. Among 49 patients admitted with a suspicion of ICI-P, 31 patients were confirmed to have ICI-P and subsequently received ICI-P directed treatment. Pulmonology was consulted in 97% of patients. Median time to start treatment for ICI-P was 1day (IQR 0-3.5days). All 31 patients received corticosteroids. Inpatient mortality was 32%. Majority of patients discharged with steroids were prescribed prophylaxis for gastritis and opportunistic infections. Thirty-eight percent of patients were seen by pulmonology and 86% were seen by the oncology team post-discharge. Our study confirms prior findings of high mortality among patients with high-grade ICI-P. Early diagnosis and treatment are key to improving clinical outcomes. Understanding the care patterns and adherence to treatment guidelines of clinicians caring for this patient population may help identify ways to further standardize management practices and improve patient outcomes.

Immune checkpoint inhibitor-related pneumonitis: research advances in prediction and management.

The advent of immune-checkpoint inhibitors (ICIs) has revolutionized the treatment of malignant solid tumors in the last decade, producing lasting benefits in a subset of patients. However, unattended excessive immune responses may lead to immune-related adverse events (irAEs). IrAEs can manifest in different organs within the body, with pulmonary toxicity commonly referred to as immune checkpoint inhibitor-related pneumonitis (CIP). The CIP incidence remains high and is anticipated to rise further as the therapeutic indications for ICIs expand to encompass a wider range of malignancies. The diagnosis and treatment of CIP is difficult due to the large individual differences in its pathogenesis and severity, and severe CIP often leads to a poor prognosis for patients. This review summarizes the current state of clinical research on the incidence, risk factors, predictive biomarkers, diagnosis, and treatment for CIP, and we address future directions for the prevention and accurate prediction of CIP.

Advancing the Boundaries of Immunotherapy in Lung Adenocarcinoma with Idiopathic Pulmonary Fibrosis by a Biomimetic Proteinoid Enabling Selective Endocytosis.

The coexistence of lung adenocarcinoma (LUAD) with idiopathic pulmonary fibrosis (IPF), which has been extensively documented as a prominent risk factor for checkpoint inhibitor-related pneumonitis (CIP) in patients undergoing immunotherapy, has long been considered a restricted domain for the use of immune checkpoint inhibitors (ICIs). To overcome it, an approach was employed herein to specifically target PD-L1 within the cellular interior, surpassing the conventional focus solely on the cytomembrane, thereby facilitating the development of ICIs capable of distinguishing between LUAD cells and noncancerous cells based on their distinctive endocytic propensities. By exploiting the aurophilicity-driven self-assembly of a PD-L1 binding peptide (PDBP) and subsequently encapsulating it within erythrocyte membranes (EM), the resulting biomimetic ICIs protein EMS-PDBP exhibited extraordinary selectivity in internalizing LUAD cells, effectively targeting PD-L1 within cancer cells while hindering its membrane translocation. The EMS-PDBP treatment not only reactivated the antitumor immune response in the LUAD orthotopic allograft mouse model but also demonstrated a favorable safety profile by effectively eliminating any immune-related adverse events (irAEs). Most significantly, EMS-PDBP successfully and safely restored the antitumor immune response in a mouse model of LUAD with coexistent IPF, thus shattering the confines of ICIs immunotherapy. The reported EMS-PDBP collectively offers a potential strategy for immune reactivation to overcome the limitations of immunotherapy in LUAD coexisting with IPF.

Development and Validation of a Machine Learning–Based Model Using CT Radiomics for Predicting Immune Checkpoint Inhibitor-related Pneumonitis in Patients With NSCLC Receiving Anti-PD1 Immunotherapy: A Multicenter Retrospective Case[sbnd]Control Study

This study aimed to develop and evaluate a radiomics-based model combined with clinical and qualitative radiological (semantic feature [SF]) features to predict immune checkpoint inhibitor-related pneumonitis (CIP) in patients with non-small cell lung cancer (NSCLC) treated with programmed cell death protein 1 inhibitors. This was a multicenter retrospective casecontrol study conducted from January 1, 2018, to December 31, 2022, at three centers. Patients with NSCLC treated with anti-PD1 were enrolled and randomly divided into two groups (7:3): training (n=95) and validation (n=39). Logistic regression (LR) and support vector machine (SVM) algorithms were used to transform features into the models. The study comprised 134 participants from three independent centers (male, 114/134, 85%; mean [±standard deviation] age, 63.92 [±7.9]years). The radiomics score (RS) models built based on the LR and SVM algorithms could accurately predict CIP (area under the receiver operating characteristics curve [AUC], 0.860 [0.780, 0.939] and 0.861 [0.781, 0.941], respectively). The AUCs for the RS-clinic-SF combined model were 0.903 (0.839, 0.967) and 0.826 (0.688, 0.964) in the training and validation cohorts, respectively. Decision curve analysis showed that the combined models achieved high clinical net benefit across the majority of the range of reasonable threshold probabilities. This study demonstrated that the combined model constructed by the identified features of RS, clinical features, and SF has the potential to precisely predict CIP. The RS-clinic-SF combined model has the potential to be used more widely as a practical tool for the noninvasive prediction of CIP to support individualized treatment planning.

Potential mechanisms and treatment progress of immune checkpoint inhibitor-related pneumonitis in non-small cell lung cancer

Background: Recent use of immune checkpoint inhibitors (ICIs) in non-small cell lung cancer (NSCLC) extends survival, but immune-related adverse events (irAEs), especially immune checkpoint inhibitor pneumonitis (CIP), pose a significant threat, progressing swiftly and impacting patient well-being and, in some cases, survival. Objectives: This review aims to analyze the literature related to immune checkpoint inhibitor-associated pneumonia in terms of potential mechanisms, risk factors, predictors and diagnostic treatment, so as to provide a reference for preclinical studies and clinical management. Methods: Using the literature summarizing method, the keywords "NSCLC" and “immune checkpoint inhibitors” were entered in PUBMED (https://pubmed.ncbi.nlm.nih.gov/), and 3968 papers were obtained. The main points of literature discovery are obtained by compressing, categorizing and summarizing literature for reporting. Results: We systematically summarized Checkpoint inhibitor-associated pneumonia incidence and onset time; Checkpoint inhibitor-associated pneumonia potential mechanisms; Risk factors for checkpoint inhibitor-associated pneumonia; Checkpoint inhibitor-associated pneumonia potential predictors; Diagnosis and treatment of checkpoint inhibitor-associated pneumonia. Together, this review provides important literature information to understand the relationship between ICIs and NSCLC. Conclusions: We summarized the potential mechanisms of immune checkpoint inhibitor-associated pneumonia in NSCLC and advances in treatment, and provided the reference for related research and related personnel.

Antiplatelet drugs may increase the risk for checkpoint inhibitor-related pneumonitis in advanced cancer patients

Immune checkpoint inhibitors (ICIs) are indicated for various cancers and are the mainstay of cancer immunotherapy. They are often associated with ICI-related pneumonitis (CIP), however, hindering a favorable clinical course. Recently, non-oncology concomitant drugs have been reported to affect the efficacy and toxicity of ICIs; however, the association between these drugs and the risk for CIP is uncertain. The aim of this study was to assess the impact of baseline concomitant drugs on CIP incidence in ICI-treated advanced cancer patients. This was a single-center retrospective study that included a cohort of 511 patients with advanced cancer (melanoma and non-small-cell lung, head and neck, genitourinary, and other types of cancer) treated with ICIs. Univariable analysis was conducted to identify baseline co-medications associated with CIP incidence. A propensity score matching analysis was used to adjust for potential CIP risk factors, and multivariable analysis was carried out to assess the impact of the identified co-medications on CIP risk. Forty-seven (9.2%) patients developed CIP. In these patients, the organizing pneumonia pattern was the dominant radiological phenotype, and 42.6% had grade ≥3 CIP, including one patient with grade 5. Of the investigated baseline co-medications, the proportion of antiplatelet drugs (n= 50, 9.8%) was higher in patients with CIP (23.4% versus 8.4%). After propensity score matching, the CIP incidence was higher in patients with baseline antiplatelet drugs (22% versus 6%). Finally, baseline antiplatelet drug use was demonstrated to increase the risk for CIP incidence regardless of cancer type (hazard ratio, 3.46; 95% confidence interval 1.21-9.86). An association between concomitant antiplatelet drug use at baseline and an increased risk for CIP was seen in our database. This implies the importance of assessing concomitant medications for CIP risk management.

1016O Autoimmunity against surfactant protein B drives immune checkpoint inhibitor-related pneumonitis in patients with NSCLC

1016O Autoimmunity against surfactant protein B drives immune checkpoint inhibitor-related pneumonitis in patients with NSCLC