1
|
Drobni ZD, Gongora C, Taron J, Suero-Abreu GA, Karady J, Gilman HK, Supraja S, Nikolaidou S, Leeper N, Merkely B, Maurovich-Horvat P, Foldyna B, Neilan TG. Impact of immune checkpoint inhibitors on atherosclerosis progression in patients with lung cancer. J Immunother Cancer 2023; 11:e007307. [PMID: 37433718 DOI: 10.1136/jitc-2023-007307] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/25/2023] [Indexed: 07/13/2023] Open
Abstract
BACKGROUND Patients with lung cancer face a heightened risk of atherosclerosis-related cardiovascular events. Despite the strong scientific rationale, there is currently a lack of clinical evidence examining the impact of immune checkpoint inhibitors (ICIs) on the advancement of atherosclerosis in patients with lung cancer. The objective of our study was to investigate whether there is a correlation between ICIs and the accelerated progression of atherosclerosis among individuals with lung cancer. METHODS In this case-control (2:1 matched by age and gender) study, total, non-calcified, and calcified plaque volumes were measured in the thoracic aorta using sequential contrast-enhanced chest CT scans. Univariate and multivariate rank-based estimation regression models were developed to estimate the effect of ICI therapy on plaque progression in 40 cases (ICI) and 20 controls (non-ICI). RESULTS The patients had a median age of 66 years (IQR: 58-69), with 50% of them being women. At baseline, there were no significant differences in plaque volumes between the groups, and their cardiovascular risk profiles were similar. However, the annual progression rate for non-calcified plaque volume was 7 times higher in the ICI group compared with the controls (11.2% vs 1.6% per year, p=0.001). Conversely, the controls showed a greater progression in calcified plaque volume compared with the ICI group (25% vs 2% per year, p=0.017). In a multivariate model that considered cardiovascular risk factors, the use of an ICI was associated with a more substantial progression of non-calcified plaque volume. Additionally, individuals treated with combination ICI therapy exhibited greater plaque progression. CONCLUSIONS ICI therapy was associated with more non-calcified plaque progression. These findings underscore the importance of conducting studies aimed at identifying the underlying mechanisms responsible for plaque advancement in patients undergoing ICI treatment. TRIAL REGISTRATION NUMBER NCT04430712.
Collapse
Affiliation(s)
- Zsofia Dora Drobni
- Cardiovascular Imaging Research Center (CIRC), Department of Radiology and Division of Cardiology, Massachusetts General Hospital Department of Radiology, Boston, Massachusetts, USA
- Heart and Vascular Center, Semmelweis University, Budapest, Hungary
| | - Carlos Gongora
- Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Jana Taron
- Department of Radiology, Medical Center, University of Freiburg, Freiburg im Breisgau, Germany
| | - Giselle A Suero-Abreu
- Cardiovascular Imaging Research Center (CIRC), Department of Radiology and Division of Cardiology, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Julia Karady
- Cardiovascular Imaging Research Center (CIRC), Department of Radiology and Division of Cardiology, Massachusetts General Hospital Department of Radiology, Boston, Massachusetts, USA
| | - Hannah K Gilman
- Cardiovascular Imaging Research Center (CIRC), Department of Radiology and Division of Cardiology, Massachusetts General Hospital Department of Radiology, Boston, Massachusetts, USA
| | - Sama Supraja
- Cardiovascular Imaging Research Center (CIRC), Department of Radiology and Division of Cardiology, Massachusetts General Hospital Department of Radiology, Boston, Massachusetts, USA
| | - Sofia Nikolaidou
- Cardiovascular Imaging Research Center (CIRC), Department of Radiology and Division of Cardiology, Massachusetts General Hospital Department of Radiology, Boston, Massachusetts, USA
| | - Nicolas Leeper
- Department of Surgery, Stanford University, Stanford, California, USA
| | - Béla Merkely
- Heart and Vascular Center, Semmelweis University, Budapest, Hungary
| | | | - Borek Foldyna
- Cardiovascular Imaging Research Center (CIRC), Department of Radiology and Division of Cardiology, Massachusetts General Hospital Department of Radiology, Boston, Massachusetts, USA
| | - Tomas G Neilan
- Cardiovascular Imaging Research Center (CIRC), Department of Radiology and Division of Cardiology, Massachusetts General Hospital Department of Radiology, Boston, Massachusetts, USA
| |
Collapse
|
2
|
Ghanzouri I, Amal S, Ho V, Safarnejad L, Cabot J, Brown-Johnson CG, Leeper N, Asch S, Shah NH, Ross EG. Performance and usability testing of an automated tool for detection of peripheral artery disease using electronic health records. Sci Rep 2022; 12:13364. [PMID: 35922657 PMCID: PMC9349186 DOI: 10.1038/s41598-022-17180-5] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2022] [Accepted: 07/21/2022] [Indexed: 11/18/2022] Open
Abstract
Peripheral artery disease (PAD) is a common cardiovascular disorder that is frequently underdiagnosed, which can lead to poorer outcomes due to lower rates of medical optimization. We aimed to develop an automated tool to identify undiagnosed PAD and evaluate physician acceptance of a dashboard representation of risk assessment. Data were derived from electronic health records (EHR). We developed and compared traditional risk score models to novel machine learning models. For usability testing, primary and specialty care physicians were recruited and interviewed until thematic saturation. Data from 3168 patients with PAD and 16,863 controls were utilized. Results showed a deep learning model that utilized time engineered features outperformed random forest and traditional logistic regression models (average AUCs 0.96, 0.91 and 0.81, respectively), P < 0.0001. Of interviewed physicians, 75% were receptive to an EHR-based automated PAD model. Feedback emphasized workflow optimization, including integrating risk assessments directly into the EHR, using dashboard designs that minimize clicks, and providing risk assessments for clinically complex patients. In conclusion, we demonstrate that EHR-based machine learning models can accurately detect risk of PAD and that physicians are receptive to automated risk detection for PAD. Future research aims to prospectively validate model performance and impact on patient outcomes.
Collapse
Affiliation(s)
- I Ghanzouri
- Division of Vascular Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA
| | - S Amal
- Division of Vascular Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA
| | - V Ho
- Division of Vascular Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA
| | - L Safarnejad
- Division of Vascular Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA
| | - J Cabot
- Division of Vascular Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA
| | - C G Brown-Johnson
- Department of Medicine, Primary Care and Population Health, Stanford, CA, USA
| | - N Leeper
- Division of Vascular Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA
| | - S Asch
- Department of Medicine, Primary Care and Population Health, Stanford, CA, USA
| | - N H Shah
- Department of Medicine, Center for Biomedical Informatics Research, Stanford University School of Medicine, 780 Welch Road, CJ350, Stanford, CA, 94305, USA
| | - E G Ross
- Division of Vascular Surgery, Department of Surgery, Stanford University School of Medicine, Stanford, CA, USA. .,Department of Medicine, Center for Biomedical Informatics Research, Stanford University School of Medicine, 780 Welch Road, CJ350, Stanford, CA, 94305, USA.
| |
Collapse
|