Checkpoint Inhibitor-related Pneumonitis Research Articles

The Role of CT-Based Radiomics Nomogram in Differential Diagnosis of Immune Checkpoint Inhibitor-Related Pneumonitis from Radiation Pneumonitis for Patients with ESCC

The combination of immunotherapy and chemoradiotherapy has widely used for patients with esophageal squamous cell carcinoma (ESCC) and induced treatment-related adverse effects, particularly immune checkpoint inhibitor-related pneumonitis (CIP) and radiation pneumonitis (RP). The aim of this study is to differentiate between CIP and RP by the CT radiomics and clinical or radiological parameters. A total of 76 ESCC patients with pneumonitis were enrolled in this retrospective study and divided into training dataset (n = 53) and validation dataset (n = 23). A total of 837 radiomics features were extracted from regions of interest (ROIs) based on the lung parenchyma window of CT images. A radiomics signature was constructed on the basis of the predictive features by the least absolute shrinkage and selection operator (LASSO). A logistic regression was applied to develop radiomics nomogram. Receiver operating characteristics (ROC) curve and area under the curve (AUC) were applied to evaluate the performance of pneumonitis etiology identification. No significant difference was detected between training dataset and validation dataset. The radiomics signature which was made up of four radiomics features shown a favorable performance on differentiating between CIP and RP with the α-binormal-based and empirical AUC = 0.831 and 0.843. Patients with RP had a close relationship with location (p = 0.003) and shape of lesions (p = 0.002). The nomogram that combined with radiomics signature and clinical factors improved the classifying performance on discrimination in the training dataset (AUCαbin = 0.963 and AUCemp = 0.964). The results were verified in the validation dataset with AUC = 0.967 and 0.964. CT-based radiomics features have potential values for differentiating between patients with CIP and RP. Addition of bilateral changes and sharp border produced superior model performance on classifying, which could be a useful method to improve related clinical decision-making.

Clinical applications of radiomics in non-small cell lung cancer patients with immune checkpoint inhibitor-related pneumonitis.

Immune checkpoint inhibitors (ICIs) modulate the body's immune function to treat tumors but may also induce pneumonitis. Immune checkpoint inhibitor-related pneumonitis (ICIP) is a serious immune-related adverse event (irAE). Immunotherapy is currently approved as a first-line treatment for non-small cell lung cancer (NSCLC), and the incidence of ICIP in NSCLC patients can be as high as 5%-19% in clinical practice. ICIP can be severe enough to lead to the death of NSCLC patients, but there is a lack of a gold standard for the diagnosis of ICIP. Radiomics is a method that uses computational techniques to analyze medical images (e.g., CT, MRI, PET) and extract important features from them, which can be used to solve classification and regression problems in the clinic. Radiomics has been applied to predict and identify ICIP in NSCLC patients in the hope of transforming clinical qualitative problems into quantitative ones, thus improving the diagnosis and treatment of ICIP. In this review, we summarize the pathogenesis of ICIP and the process of radiomics feature extraction, review the clinical application of radiomics in ICIP of NSCLC patients, and discuss its future application prospects.

Deciphering pathogenic cellular module at single-cell resolution in checkpoint inhibitor-related pneumonitis

Checkpoint inhibitor pneumonitis (CIP) is the most common fatal immune-related adverse event; however, its pathophysiology remains largely unknown. Comprehensively dissecting the key cellular players and molecular pathways associated with CIP pathobiology is critical for precision diagnosis and develop novel therapy strategy of CIP. Herein, we performed a comprehensive single-cell transcriptome analysis to dissect the complexity of the immunological response in the bronchoalveolar lavage fluid (BALF) microenvironment. CIP was characterized by a dramatic accumulation of CXCL13+ T cells and hyperinflammatory CXCL9+ monocytes. T-cell receptor (TCR) analysis revealed that CXCL13+ T cells exhibited hyperexpanded- TCR clonotypes, and pseudotime analysis revealed a potential differentiation trajectory from naïve to cytotoxic effector status. Monocyte trajectories showed that LAMP3+ DCs derived from CXCL9+ monocytes possessed the potential to migrate from tumors to the BALF, whereas the differentiation trajectory to anti-inflammatory macrophages was blocked. Intercellular crosstalk analysis revealed the signaling pathways such as CXCL9/10/11-CXCR3, FASLG-FAS, and IFNGR1/2-IFNG were activated in CIP+ samples. We also proposed a novel immune signature with high diagnostic power to distinguish CIP+ from CIP− samples (AUC = 0.755). Our data highlighted key cellular players, signatures, and interactions involved in CIP pathogenesis.

Pre-existing Interstitial Lung Abnormalities and Immune Checkpoint Inhibitor-Related Pneumonitis in Solid Tumors: A Retrospective Analysis.

Immune checkpoint inhibitors (ICIs) have demonstrated efficacy over previous cytotoxic chemotherapies in clinical trials among various tumors. Despite their favorable outcomes, they are associated with a unique set of toxicities termed as immune-related adverse events (irAEs). Among the toxicities, ICI-related pneumonitis has poor outcomes with little understanding of its risk factors. This retrospective study aimed to investigate whether pre-existing interstitial lung abnormality (ILA) is a potential risk factor for ICI-related pneumonitis. Patients with non-small cell lung cancer, malignant melanoma, renal cell carcinoma, and gastric cancer, who was administered either nivolumab, pembrolizumab, or atezolizumab between September 2014 and January 2019 were retrospectively reviewed. Information on baseline characteristics, computed tomography findings before administration of ICIs, clinical outcomes, and irAEs were collected from their medical records. Pre-existing ILA was categorized based on previous studies. Two-hundred-nine patients with a median age of 68 years were included and 23 (11.0%) developed ICI-related pneumonitis. While smoking history and ICI agents were associated with ICI-related pneumonitis (P = .005 and .044, respectively), the categories of ILA were not associated with ICI-related pneumonitis (P = .428). None of the features of lung abnormalities were also associated with ICI-related pneumonitis. Multivariate logistic analysis indicated that smoking history was the only significant predictor of ICI-related pneumonitis (P = .028). This retrospective study did not demonstrate statistically significant association between pre-existing ILA and ICI-related pneumonitis, nor an association between radiologic features of ILA and ICI-related pneumonitis. Smoking history was independently associated with ICI-related pneumonitis. Further research is warranted for further understanding of the risk factors of ICI-related pneumonitis.

Radiological assessment of immunotherapy effects and immune checkpoint-related pneumonitis for lung cancer.

Immune checkpoint inhibitors (ICIs) therapy have revolutionized advanced lung cancer care. Interestingly, the host responses for patients received ICIs therapy are distinguishing from those with cytotoxic drugs, showing potential initial transient worsening of disease burden, pseudoprogression and delayed time to treatment response. Thus, a new imaging criterion to evaluate the response for immunotherapy should be developed. ICIs treatment is associated with unique adverse events, including potential life-threatening immune checkpoint inhibitor-related pneumonitis (ICI-pneumonitis) if treated patients are not managed promptly. Currently, the diagnosis and clinical management of ICI-pneumonitis remain challenging. As the clinical manifestation is often nonspecific, computed tomography (CT) scan and X-ray films play important roles in diagnosis and triage. This article reviews the complications of immunotherapy in lung cancer and illustrates various radiologic patterns of ICI-pneumonitis. Additionally, it is tried to differentiate ICI-pneumonitis from other pulmonary pathologies common to lung cancer such as radiation pneumonitis, bacterial pneumonia and coronavirus disease of 2019 (COVID-19) infection in recent months. Maybe it is challenging to distinguish radiologically but clinical presentation may help.

A nomogram model for predicting the risk of checkpoint inhibitor-related pneumonitis for patients with advanced non-small-cell lung cancer.

Immunotherapy extensively treats advanced non-small-cell lung cancer (NSCLC). Although immunotherapy is generally better tolerated than chemotherapy, it can cause multiple immune-related adverse events (irAEs) involving multiple organs. Checkpoint inhibitor-related pneumonitis (CIP) is a relatively uncommon irAE that, in severe cases, can be fatal. Potential risk factors for the occurrence of CIP are currently poorly understood. This study sought to develop a novel scoring system for predicting the risk of CIP based on a nomogram model. We retrospectively collected advanced NSCLC patients who received immunotherapy at our institution between January 1, 2018, and December 30, 2021. All patients who met the criteria were randomly divided into the training set and testing set (in a ratio of 7:3), and cases fulfilling the CIP diagnostic criteria were screened. The patients' baseline clinical characteristics, laboratory tests, imaging, and treatment information were extracted from the electronic medical records. The risk factors associated with the occurrence of CIP were identified based on the results of logistic regression analysis on the training set, and a nomogram prediction model was developed. The discrimination and prediction accuracy of the model was evaluated using the receiver operating characteristic (ROC) curve, the concordance index (C-index), and the calibration curve. Decision curve analysis (DCA) was used to evaluate the clinical applicability of the model. The training set comprised 526 (CIP: 42 cases), and the testing set comprised 226 (CIP: 18 cases) patients, respectively. In the training set, the final multivariate regression analysis revealed that age (p = 0.014; odds ratio [OR] = 1.056; 95% Confidence Interval [CI] =1.011-1.102), Eastern Cooperative Oncology Group performance status (p = 0.002; OR = 6.170; 95% CI = 1.943-19.590), history of prior radiotherapy (p < 0.001; OR = 4.005; 95% CI = 1.920-8.355), baseline white blood cell count (WBC) (p < 0.001; OR = 1.604; 95% CI = 1.250-2.059), and baseline absolute lymphocyte count (ALC) (p = 0.034; OR = 0.288; 95% CI = 0.091-0.909) were identified as independent risk factors for the occurrence of CIP. A prediction nomogram model was developed based on these five parameters. The area under the ROC curve and C-index of the prediction model in the training set and testing set were 0.787 (95% CI: 0.716-0.857) and 0.874 (95% CI: 0.792-0.957), respectively. The calibration curves are in good agreement. The DCA curves indicate that the model has good clinical utility. We developed a nomogram model that proved to be a good assistant tool for predicting the risk of CIP in advanced NSCLC. This model has the potential power to help clinicians in making treatment decisions.

Analysis of cytokines in bronchoalveolar lavage fluid in patients with checkpoint inhibitor pneumonitis and pulmonary infection: A case-control study.

The discovery of immune checkpoint inhibitors (ICIs) is a breakthrough in the field of cancer therapy. However, ICIs may cause immune-related adverse reactions, including checkpoint inhibitor-related pneumonitis (CIP). The aim of this study was to investigate cytokines in bronchoalveolar lavage fluid (BALF) of patients with CIP compared with patients with pulmonary infection and patients with cancer. We retrospectively analyzed 34 cytokine levels and T cell subsets in BALF supernatant samples from ICI-treated patients with CIP (n = 13), pulmonary infection (n = 10), and progressive cancer (n = 12). Cytokine levels and T cell subsets were compared among the three groups of patients. We observed significantly higher levels of IFN-γ-induced protein 10(IP-10) (p = 0.002), and percentage of CD3 + CD8 + T cells (p = 0.020) in BALF of patients with CIP compared with the other two groups. However, we found significantly lower levels of interleukin-21 (p = 0.008) in BALF of patients with progressive disease compared with the other two groups. Cytokine profile and character of cell subsets in BALF was helpful for the differential diagnosis of CIP. IP-10 may play an important role in pathophysiology for CIP and also be a potential therapeutic target.

Improving the care of patients with lung cancer hospitalized with immune checkpoint inhibitor-related pneumonitis: Implementation of a clinical pathway algorithm.

e18730 Background: Immune checkpoint inhibitor related pneumonitis (ICI-P) is one of the most frequent reasons for discontinuing immunotherapy. High mortality rates have been reported among those with grades ≥3 ICI-P. Early recognition and timely management are key to better patient outcomes. We conducted a quality improvement project that involved developing and implementing a clinical pathway algorithm to standardize the care of patients admitted to our Onco-Hospital Medicine (OHM) service. Methods: We included patients with lung cancer admitted to the OHM service with suspicion of ICI-P from January 1, 2020 to December 31, 2022. We developed a multi-modal educational intervention targeted to providers of the OHM service to promote the use of the developed pathway. Interventions were rolled out in 2 phases and included educational sessions (phase 1), distribution of flashcards, informational notepads, monthly emailers, and presentation of an animation of the clinical pathway (phase 2). Our primary outcome was the time to first ICI-P-directed treatment, i.e. time to treatment (TTT). We used the Kruskal-Wallis test to compare TTT between the pre-intervention and post-intervention phases. Results: Out of 82 patients admitted with a suspicion of ICI-P, 60 were confirmed to have ICI-P based on multi-disciplinary consensus. 19 patients were included in the pre-intervention group, 30 in post-intervention phase 1, and 11 in post-intervention phase 2. 92% of patients in our cohort had NSCLC, and 95% had stage 4 disease. Pembrolizumab was the most common ICI used (55%), followed by combination Ipilimumab+Nivolumab (15%). Pulmonology was consulted in 98% of patients. 98% of patients were treated with steroids. Median TTT(range) was 1 (0-12) day in the pre-intervention group, and 2 (0-17) days and 1 (0-6) day after post-intervention phases 1 and 2, respectively (p = 0.3). Utilization of immunotoxicity order set increased from 0% during pre-intervention to 20% and 27% after phase 1 and phase 2, respectively (p = 0.03). Prescription of Pneumocystis jirovecii pneumonia (PJP) prophylaxis among patients discharged on high-dose steroids increased from baseline but was not statistically significant (pre-intervention = 71%, phase 1 = 95%, phase 2 = 100%, p = 0.09). There was no significant change in ICU admissions or inpatient mortality from pre-intervention to post-intervention phases 1 and 2 (p = 0.5 and 0.6, respectively). Conclusions: We showed a decrease in time to intervention from baseline to post-intervention phase 2 after our educational interventions. While this change was not statistically significant, our multi-level approach was able to help increase the utilization of immunotoxicity tools on the OHM service. Continued education on the OHM service is needed to promote adherence to the developed pathway and help improve patient outcomes.

Predictive factors and prognosis of immune checkpoint inhibitor-related pneumonitis in non-small cell lung cancer patients.

To investigate the influencing factors and prognosis of immune checkpoint inhibitor-related pneumonitis (CIP) in advanced non-small cell lung cancer (NSCLC) patients during or after receiving immune checkpoint inhibitors(ICIs). The clinical and laboratory indicator data of 222 advanced NSCLC patients treated with PD-1/PD-L1 inhibitors at the First Affiliated Hospital of Zhengzhou University between December 2017 and November 2021 were collected retrospectively. The patients were divided into a CIP group (n=41) and a non-CIP group (n=181) according to whether they developed CIP or not before the end of follow-up. Logistic regression was used to evaluate risk factors of CIP, and Kaplan‒Meier curves were used to describe the overall survival (OS) of different groups. The log-rank test was used to compare the survival of different groups. There were 41 patients who developed CIP, and the incidence rate of CIP was 18.5%. Univariate and multivariate logistic regression analyses showed that low pretreatment hemoglobin (HB) and albumin (ALB) levels were independent risk factors for CIP. Univariate analysis suggested that history of chest radiotherapy was related to the incidence of CIP. The median OS of the CIP group and non-CIP were 15.63 months and 30.50 months (HR:2.167; 95%CI: 1.355-3.463, P<0.05), respectively. Univariate and multivariate COX analyses suggested that a high neutrophil-to-lymphocyte ratio (NLR) level, a low ALB level and the development of CIP were independent prognostic factors for worse OS of advanced NSCLC patients treated with ICIs. Additionally, the early-onset and high-grade CIP were related to shorter OS in the subgroup. Lower pretreatment HB and ALB levels were independent risk factors for CIP. A high NLR level, a low ALB level and the development of CIP were independent risk factors for the prognosis of advanced NSCLC patients treated with ICIs.

A Risk-Scoring Model for Severe Checkpoint Inhibitor-Related Pneumonitis: A Case-Control Study.

Checkpoint inhibitor-related pneumonitis (CIP) is one of the most common serious and fatal adverse events associated with immune checkpoint inhibitors (ICIs). The study sought to identify risk factors of all-grade and severe CIP and to construct a risk-scoring model specifically for severe CIP. This observational, retrospective case-control study involved 666 lung cancer patients who received ICIs between April 2018 and March 2021. The study analyzed patient demographic, preexisting lung diseases, and the characteristics and treatment of lung cancer to determine the risk factors for all-grade and severe CIP. A risk score for severe CIP was developed and validated in a separate patient cohort of 187 patients. Among 666 patients, 95 patients were afflicted with CIP, of which 37 were severe cases. Multivariate analysis revealed age ≥65 years, current smoking, chronic obstructive pulmonary disease, squamous cell carcinoma, prior thoracic radiotherapy, and extra-thoracic radiotherapy during ICI were independently associated with CIP events. Five factors, emphysema (odds ratio [OR] 2.87), interstitial lung disease (OR 4.76), pleural effusion (OR 3.00), history of radiotherapy during ICI (OR 4.30), and single-agent immunotherapy (OR 2.44) were independently associated with severe CIP and were incorporated into a risk-score model (score ranging 0-17). The area under the model receiver operating characteristic curve for the model was 0.769 in the development cohort and 0.749 in the validation cohort. The simple risk-scoring model may predict severe CIP in lung cancer patients receiving ICIs. For patients with high scores, clinicians should use ICIs with caution or strengthen the monitoring of these patients.

186P Elevated CXCL10:IL-8 ratio in bronchoalveolar lavage fluid of immune checkpoint inhibitor-related pneumonitis

186P Elevated CXCL10:IL-8 ratio in bronchoalveolar lavage fluid of immune checkpoint inhibitor-related pneumonitis

Characterization of immunomodulatory factors and cells in bronchoalveolar lavage fluid for immune checkpoint inhibitor-related pneumonitis.

As immune checkpoint inhibitors (ICIs) are widely used, a series of immune-related adverse events (irAEs) have been reported, including immune checkpoint inhibitor-related pneumonitis (ICI-pneumonitis). The incidence of ICI-pneumonitis is higher in reality than in clinical trials. The diagnosis is challenging, mainly based on clinical and imaging features, and requires the exclusion of other causes. The data on the biological mechanisms of ICI-pneumonitis are scarce, resulting in little knowledge of the best treatment for ICI-pneumonitis. Bronchoalveolar lavage (BAL) may be helpful to identify the biological differences or find predictive biomarkers, and may in turn help to develop phenotype-specific targeted drugs to treat ICI-pneumonitis. Herein, we outline the characterization of immunomodulatory factors and cells in bronchoalveolar lavage fluid for ICI-pneumonitis. Through careful sorting and literature review, we find crosstalk between pathogenic Th17/Th1 cells (i.e., Th17.1) and pro-inflammatory monocytes, and activation of Th17(/Th1)/IL-17A (/IFN-γ) pathways may play a key role in the pathogenesis of ICI-pneumonitis. Disruption of the interaction between pathogenic Th17/Th1 cells and pro-inflammatory monocytes (such as, anti-IL-23) may be a potential treatment for ICI-pneumonitis. We first describe the possible pathophysiological mechanisms of ICI-pneumonitis, hoping to contribute to the optimization of diagnosis and treatment, as well as provide readers with research inspiration.

Clinical characteristics and therapeutic effects of checkpoint inhibitor-related pneumonitis in patients with non-small cell lung cancer

BackgroundWith the application of immune checkpoint inhibitors (ICIs) in cancer treatment, more and more attention has been paid to checkpoint inhibitor-related pneumonitis (CIP), which requires a better understanding of its clinical characteristics and therapeutic effects.MethodsThe clinical and imaging data of 704 patients with non-small cell lung cancer (NSCLC) who received immunotherapy were analyzed retrospectively; the clinical characteristics of CIP were summarized, and the therapeutic regimens and effects of the patients were summarized.Results36 CIP patients were included in the research. The most common clinical symptoms were cough, shortness of breath and fever. The CT manifestations were summarized as follows: Organizing pneumonia (OP) in 14 cases (38.9%), nonspecific interstitial pneumonia (NSIP) in 14 cases (38.9%), hypersensitiviy pneumonitis(HP) in 2 cases (6.3%), diffuse alveolar damage in 1 case (3.1%) and atypical imaging manifestations in 5 cases (13.9%). 35 cases received glucocorticoid therapy, 6 patients were treated with gamma globulin and 1 patient was treated with tocilizumab. There were no deaths in CIP G1-2 patients and 7 deaths occured in CIP G3-4 patients. 4 patients were treated again with ICIs.ConclusionWe found that glucocorticoid 1–2 mg/kg was effective for most patients with moderate to severe CIP, and a few patients with hormone insensitivity needed early immunosuppressive therapy. A few patients can be rechallenged with ICIs, but CIP recurrence needs to be closely monitored.

Clinical and chest CT features of immune checkpoint inhibitor-related pneumonitis

Objective: To explore the clinical and chest computed tomography (CT) features and the outcome of immune checkpoint inhibitor-related pneumonitis (CIP). Methods: Clinical and chest CT data of 38 CIP patients with malignant tumors from the Cancer Hospital, Chinese Academy of Medical Sciences between August 2017 and April 2021 were retrospectively reviewed, and the outcomes of pneumonitis were followed up. Results: The median time from the administration of immune checkpoint inhibitors (ICIs) to the onset of CIP was 72.5 days in 38 patients with CIP, and 22 patients developed CIP within 3 months after the administration of ICIs. The median occurrence time of CIP in 24 lung cancer patients was 54.5 days, earlier than 119.0 days of non-lung cancer patients (P=0.138), with no significant statistical difference. 34 patients (89.5%) were accompanied by symptoms when CIP occurred. The common clinical symptoms were cough (29 cases) and dyspnea (27 cases). The distribution of CIP on chest CT was asymmetric in 31 cases and symmetrical in 7 cases. Among the 24 lung cancer patients, inflammation was mainly distributed ipsilateral to the primary lung cancer site in 16 cases and diffusely distributed throughout the lung in 8 cases. Ground glass opacities (37 cases) and consolidation (30 cases) were the common imaging manifestations, and organizing pneumonia (OP) pattern (15 cases) was the most common pattern. In 30 CIP patients who were followed up for longer than one month, 17 cases had complete absorption (complete absorption group), and 13 cases had partial absorption or kept stable (incomplete absorption group). The median occurrence time of CIP in the complete absorption group was 55 days, shorter than 128 days of the incomplete absorption group (P=0.022). Compared with the incomplete absorption group, there were less consolidation(P=0.010) and CIP were all classified as hypersensitivity pneumonitis (HP) pattern (P=0.004) in the complete absorption group. Conclusions: CIP often occurs within 3 months after ICIs treatment, and the clinical and CT findings are lack of specificity. Radiologic features may have a profound value in predicting the outcome of CIP.

Association of Clinical and Radiological Features with Disease Severity of Symptomatic Immune Checkpoint Inhibitor-Related Pneumonitis.

To investigate the predictive ability of clinical and chest computed tomography (CT) features to predict the severity of symptomatic immune checkpoint inhibitor-related pneumonitis (CIP). This study included 34 patients diagnosed with symptomatic CIP (grades 2-5) and divided into mild (grade 2) and severe CIP (grades 3-5) groups. The groups' clinical and chest CT features were analyzed. Three manual scores (extent, image finding, and clinical symptom scores) were conducted to evaluate the diagnostic performance alone and in combination. There were 20 cases of mild CIP and 14 cases of severe CIP. More severe CIP occurred within 3 months than after 3 months (11 vs. 3 cases, p = 0.038). Severe CIP was significantly associated with fever (p < 0.001) and the acute interstitial pneumonia/acute respiratory distress syndrome pattern (p = 0.001). The diagnostic performance of chest CT scores (extent score and image finding score) was better than that of clinical symptom score. The combination of the three scores demonstrated the best diagnostic value, with an area under the receiver operating characteristic curve of 0.948. The clinical and chest CT features have important application value in assessing the disease severity of symptomatic CIP. We recommend the routine use of chest CT in a comprehensive clinical evaluation.

Advances in CT features and radiomics of checkpoint inhibitor-related pneumonitis: A short review.

Checkpoint inhibitor-related pneumonitis (CIP) is a complication of immunotherapy for malignant tumors that severely limits the treatment cycles as well as endangers patients' health. The chest CT imaging features or typing of CIP and the application of radiomics will contribute to the precise prevention, early diagnosis and instant treatment of CIP. This article reviews the advances in the CT features and the application of radiomics in CIP.

Immune Checkpoint Inhibitor-Related Pneumonitis in Lung Cancer Patients with Interstitial Lung Disease: Significance of Radiological Pleuroparenchymal Fibroelastosis

Introduction: Pleuroparenchymal fibroelastosis (PPFE) findings are associated with poor prognosis in interstitial lung disease (ILD). However, the effect of PPFE findings on the development of immune checkpoint inhibitor-related pneumonitis (ICI-pneumonitis), a life-threatening adverse event, in lung cancer patients with ILD has not been elucidated. We aimed to determine whether PPFE findings are a risk factor for ICI-pneumonitis in lung cancer patients with ILD. Methods: We retrospectively examined 712 lung cancer patients, including 173 patients with background ILDs, who received ICI therapy in our institute between December 2015 and May 2021. Background ILDs were radiologically classified into three types: lone PPFE, other ILDs with PPFE, and other ILDs without PPFE. The cumulative ICI-pneumonitis incidence curves and median overall survival (mOS) were compared between the three radiological types, and risk factors for ICI-pneumonitis were evaluated. Results: Of 173 eligible patients with ILD, 23 patients (13.3%) experienced ICI-pneumonitis. The Kaplan-Meier method and the log-rank test showed that lone PPFE patients had significantly lower incidence of ICI-pneumonitis (p = 0.024) and longer mOS (575 vs. 326 days; p = 0.0096) than other ILDs patients. ICI-pneumonitis (p = 0.35) and mOS (p = 0.29) were not significantly different between other ILDs with and without PPFE. A multivariate Cox proportional hazards regression analysis revealed that lone PPFE pattern was an independent predictive factor for ICI-pneumonitis (hazard ratio, 0.20; 95% confidence interval, 0.043–0.93; p = 0.040). Conclusion: ICI therapy could be safer in lone PPFE patients than in other ILDs patients with lung cancer.

Immune checkpoint inhibitor-related pneumonitis and COVID-19: a case-matched comparison of CT findings.

To compare the radiological findings of immune checkpoint inhibitor-related pneumonitis (IRP) and COVID-19 pneumonia, evaluating the potential of the CO-RADS score to differentiate between them. Two readers blindly reviewed chest CTs from age- and sex-matched groups of 33 patients with IRP and 33 patients with COVID-19 pneumonia. Each examiner evaluated the presence of 13 CT features, semiquantitatively scored lung involvement, and assigned a CO-RADS score. Inter-reader reliability in the assessment of CT features and CO-RADS categories was evaluated with Cohen's κ. Distribution differences between groups were evaluated with the χ2, Fisher's, and Mann-Whitney U tests. Substantial or higher inter-reader reliability was found in CO-RADS assignments (κ = 0.664) and in the evaluation of CT features (κ ≥ 0.638), among which the sole feature found to significantly differentiate IRP from COVID-19 pneumonia was unilateral presentation (p < 0.001). Lung involvement semiquantitative scores and CO-RADS scores were significantly higher (p < 0.001) in COVID patients (median involvement score 4, IQR 4-6; median CO-RADS score 5, IQR 4-5) than in IRP patients (median involvement score 2.5, IQR 2-4; median CO-RADS score 3, IQR 3-4) but exploratory analysis of CO-RADS specificity revealed comparatively low values, ranging between 51.5% (Reader 1) and 54.6% (Reader 2). CTfeatures of IRP and COVID-19 pneumonia frequently overlap, save for the extent of lung involvement and bilaterality. In the current SARS-CoV-2 pandemic, the low specificity of the CO-RADS score for the differential diagnosis of COVID-19 pneumonia and IRP may prompt to reconsider the role of imaging in IRP work-up.

Risk Factors for Refractory Immune Checkpoint Inhibitor-related Pneumonitis in Patients With Lung Cancer.

Checkpoint inhibitor-related pneumonitis (CIP) is one of the most important immune checkpoint inhibitors side effects, and it is rare but fatal. Identifying patients at risk of refractory CIP before the start of CIP therapy is important for controlling CIP. We retrospectively analyzed the clinical data of 60 patients with lung cancer who developed CIP. Refractory CIP was defined as CIP with poor response to corticosteroid treatment, including CIP not relieved with corticosteroid administration or CIP recurrence during the corticosteroid tapering period. We analyzed clinical characteristics, peripheral blood biomarkers, treatment, and outcomes in nonrefractory and refractory CIP. Risk factors associated with refractory CIP were assessed. Among 60 patients with CIP, 16 (26.7%) had refractory CIP. The median onset time for patients with nonrefractory and those with refractory CIP was 16.57 (interquartile range [IQR], 6.82-28.14) weeks and 7.43 (IQR, 2.71-19.1) weeks, respectively. The level of lactate dehydrogenase (LDH) was significantly higher in the refractory CIP group at baseline (255 [222, 418] vs. 216 [183, 252], P =0.031) and at CIP onset (321.5 [216.75, 487.5] vs. 219 [198. 241], P =0.019). An LDH level >320U/L at CIP onset was an independent risk factor of refractory CIP (odds ratio [OR], 8.889; 95% confidence interval [CI]: 1.294-61.058; P =0.026). The incidence of refractory CIP is high among patients with CIP. An increased LDH level at CIP onset is independently associated with refractory CIP. Monitoring LDH levels during immune checkpoint inhibitors treatment is recommended.

Deep learning for predicting the risk of immune checkpoint inhibitor-related pneumonitis in lung cancer

To develop and validate a nomogram model that combines computed tomography (CT)-based radiological factors extracted from deep-learning and clinical factors for the early predictions of immune checkpoint inhibitor-related pneumonitis (ICI-P). Forty ICI-P patients and 101 patients without ICI-P were divided randomly into the training (n=113) and test (n=28) sets. The convolution neural network (CNN) algorithm was used to extract the CT-based radiological features of predictable ICI-P and calculated the CT score of each patient. A nomogram model to predict the risk of ICI-P was developed by logistic regression. CT score was calculated from five radiological features extracted by the residual neural network-50-V2 with feature pyramid networks. Four predictors of ICI-P in the nomogram model included a clinical feature (pre-existing lung diseases), two serum markers (absolute lymphocyte count and lactate dehydrogenase), and a CT score. The area under curve of the nomogram model in the training (0.910 versus 0.871 versus 0.778) and test (0.900 versus 0.856 versus 0.869) sets was better than the radiological and clinical models. The nomogram model showed good consistency and better clinical practicability. The nomogram model that combined CT-based radiological factors and clinical factors can be used as a new non-invasive tool for the early prediction of ICI-P in lung cancer patients after immunotherapy with low cost and low manual input.