Clinical characteristics, time course, treatment and outcomes of patients with immune checkpoint inhibitor-associated myocarditis

Puzanov, Igor; Subramanian, Poornima; Yatsynovich, Yan; Jacobs, David M.; Chilbert, Maya R; Sharma, Umesh C; Ito, Fumito; Feuerstein, Steven; Stefanovic, Filip; Switzer, Benjamin; Hicar, Mark D.; Curtis, Anne B.; Spangenthal, Edward; Dy, Grace K.; Ernstoff, Marc S.; Vachhani, Pankit; Page, Brian; Agrawal, Nikhil; Khunger, Arjun; Kapoor, Ankita; Hattoum, Alexander; Jerome, Schentag J

doi:10.1136/jitc-2021-002553

Cited by 36 publications

(31 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our findings showed that troponin and LDH might contribute to recognizing severe myocarditis as soon as possible. Previous studies have demonstrated that monitoring troponin during treatment is reasonable ( Sarocchi et al, 2018 ; Liu et al, 2021 ; Puzanov et al, 2021 ), but the relationship between LDH and cardiotoxicity was never reported. Patients with severe myocarditis are more likely to have a higher LDH.…”

Section: Discussionmentioning

confidence: 99%

Intrinsic Differences in Immune Checkpoint Inhibitor-Induced Myocarditis: A Retrospective Analysis of Real World Data

et al. 2022

View full text Add to dashboard Cite

Immune-related myocarditis is a severe and even life-threatening immune-related adverse event (irAE) which may also be underestimated due to the challenge in diagnosis. The inherent difference between individuals with immune-associated myocarditis has received little attention. Our study aimed to identify which baseline characteristics could contribute to distinguishing mild from severe ICI myocarditis. A retrospective analysis was conducted between March 2019 and June 2020 in West China Hospital, and 18 patients with immune-related myocarditis were studied. Patients were classified as having mild (n = 12) or severe myocarditis (n = 6), according to the clinical manifestations and hemodynamic complications. Factors associated with severe myocarditis were identified by comparing covariates derived from medical records in various groups. In this retrospective analysis, the median age of the 18 patients was 60 years old. Most myocarditis cases occur early and approximately after the first or second ICI infusion. The severity of myocarditis may be correlated with lactate dehydrogenase (LDH) (p = 0.04) and troponin levels (p = 0.0057). The relationship between troponin and myocarditis was further confirmed in another cohort, which included 30 patients. In addition, patients are more likely to develop multi-irAEs, and myositis was the most common second irAE. Those who experience multi-irAEs usually had significantly higher LDH (p = 0.02) and myoglobin levels (p = 0.02) than those who did not experience them. All patients were treated with steroids timely, and the mortality rate was 5.6% in our study. In this study, we explored risk factors for severe myocarditis and emphasized the importance of a multidisciplinary team in assisting diagnosis and treatment options. It is critical to initiate corticosteroid therapy, regardless of the severity of the myocarditis.

show abstract

Section: Discussionmentioning

confidence: 99%

Intrinsic Differences in Immune Checkpoint Inhibitor-Induced Myocarditis: A Retrospective Analysis of Real World Data

et al. 2022

View full text Add to dashboard Cite

show abstract

“…We developed a NN model of a longitudinal cohort of patients treated with ICIs at Roswell Park Comprehensive Cancer center and developed elevated serum troponin concentrations of >0.06 ng/mL - upper limit of normal for the laboratory test. 47 Data were collected from electronic health records and included outpatient and inpatient health-care claims, clinical monitoring, laboratory and pharmacy data. The laboratory data include all tests performed and results.…”

Section: Methodsmentioning

confidence: 99%

“…An alternative machine learning approach applies Neural Network (NN) Models to the patient medical records of target cases that are enriched for the event in question, such as we previously used for understanding bleeding events from warfarin. 46 Having access to the medical records of well-defined irAE cases from a survey paper recently published by our clinical group 47 we then applied the NN modeling approach to better understand time and magnitude and treatment response in ICI-related myocarditis. This model leverages known clinical covariates in a structured scoring system in order to boost model performance, generalizability, and interpretability.…”

Section: Introductionmentioning

confidence: 99%

“…Previously, we examined 15 cases of ICI-related myocarditis retrospectively for determinants of severe disease and mortality using conventional statistical hazard modeling methods. 47 In this study, we utilize the rich time-series clinical data available from patient electronic health records to construct a NN-based predictive model of determinants of ICI-related myocarditis development, severity, response to treatments and resolution.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Net Modeling of Checkpoint Inhibitor Related Myocarditis and Steroid Response

Stefanovic¹,

Gomez-Caminero²,

Jacobs³

et al. 2022

CPAA

Self Cite

View full text Add to dashboard Cite

Background Serious but rare side effects associated with immunotherapy pose a difficult problem for regulators and practitioners. Immune checkpoint inhibitors (ICIs) have come into widespread use in oncology in recent years and are associated with rare cardiotoxicity, including potentially fatal myocarditis. To date, no comprehensive model of myocarditis progression and outcomes integrating time-series based laboratory and clinical signals has been constructed. In this paper, we describe a time-series neural net (NN) model of ICI-related myocarditis derived using supervised machine learning. Methods We extracted and modeled data from electronic medical records of ICI-treated patients who had an elevation in their troponin. All data collection was performed using an electronic case report form, with approximately 300 variables collected on as many occasions as available, yielding 6000 data elements per patient over their clinical course. Key variables were scored 0–5 and sequential assessments were used to construct the model. The NN model was developed in MatLab and applied to analyze the time course and outcomes of treatments. Results We identified 23 patients who had troponin elevations related to their ICI therapy, 15 of whom had ICI-related myocarditis, while the remaining 8 patients on ICIs had other causes for troponin elevation, such as myocardial infarction. Our model showed that troponin was the most predictive biomarker of myocarditis, in line with prior studies. Our model also identified early and aggressive use of steroid treatment as a major determinant of survival for cases of grade 3 or 4 ICI-related myocarditis. Conclusion Our study shows that a supervised learning NN can be used to model rare events such as ICI-related myocarditis and thus provide clinical insight into drivers of progression and treatment outcomes. These findings direct attention to early detection biomarkers and clinical symptoms as the best means of implementing early and potentially life-saving steroid treatment.

show abstract

“…Endocardial biopsy was the gold standard for the diagnosis of ICIs related myocarditis. One retrospective cohort study has indicated that routine troponin monitoring may be helpful to predict the mortality of tumor patients treated with ICI in the early stage and early detection of elevated troponin is helpful to early intervention and improve the prognosis of ICI associated myocarditis ( 11 ). However, real world evidence regarding the occurrence and predictive and protective factors of ICIs related myocarditis is lacking.…”

Section: Introductionmentioning

confidence: 99%

Cardiotoxicity Related to Immune Checkpoint Inhibitors: A Real-World Retrospective Analysis

She

Liu

et al. 2022

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

BackgroundCardiotoxicity related to immune checkpoint inhibitors (ICIs) is a rare but potentially lethal. In ICI-associated adverse events, evidence of cardiotoxicity and clinical predictive factors related to ICI is lacking. Here, we aim to assess the incidence and predictive factors of cardiotoxicity related to ICIs in real-world practice.ObjectiveWe retrospectively analyzed consecutive patients who received PD-1 or PD-L1 at the First Affiliated Hospital of Xi'an Jiaotong University. Clinical characteristics and cardiac lesion markers were collected both at baseline and during longitudinal follow-up from the Biobank database. Follow-up CKMB and NT-proBNP levels and ratios were then evaluated.ResultsA total of 2,304 patients with either PD-1 or PDL-1 utilization between August 2018 and April 2021 were collected. The average age was 59.44 ± 11.45 among PD-1 inhibitor utilizer and 58.97 ± 12.16 among PDL-1 inhibitor utilizer. The baseline creatine kinase isoenzyme MB (CKMB) levels were 17 ± 19 U/L in PD-1 inhibitor users and 17 ± 23 U/L in PDL-1 inhibitor users. Majority of patients were male, with advanced stage cancer, and received ICIs as second-line therapy. The longitudinal change of cardiac enzymes and NT-pro BNP were collected. Cardiac lesion as defined by three times increase of CKMB happens in only minority of patients receiving ICIs therapy. It is also identified that increased CKMB happened in PD-1 inhibitor groups, but not PDL-1 inhibitor groups.ConclusionWe evaluated the profile of cardiotoxicities caused by ICIs based on real-world experience. The cardiac lesion markers are generally unaltered, but it appears that the increased CKMB happened in PD-1 inhibitor groups, but not PDL-1 inhibitor groups.

show abstract

Clinical characteristics, time course, treatment and outcomes of patients with immune checkpoint inhibitor-associated myocarditis

Cited by 36 publications

References 32 publications

Intrinsic Differences in Immune Checkpoint Inhibitor-Induced Myocarditis: A Retrospective Analysis of Real World Data

Intrinsic Differences in Immune Checkpoint Inhibitor-Induced Myocarditis: A Retrospective Analysis of Real World Data

Neural Net Modeling of Checkpoint Inhibitor Related Myocarditis and Steroid Response

Cardiotoxicity Related to Immune Checkpoint Inhibitors: A Real-World Retrospective Analysis

Contact Info

Product

Resources

About