Prediction of new-onset atrial fibrillation in patients with non-small cell lung cancer treated with curative-intent conventional radiotherapy

Fariba Tohidinezhad; Leonard Nürnberg; Femke Vaassen; Rachel Ma Ter Bekke; Hugo Jwl Aerts; Lizza El Hendriks; Andre Dekker; Dirk De Ruysscher; Alberto Traverso

doi:10.1016/j.radonc.2024.110544

Prediction of new-onset atrial fibrillation in patients with non-small cell lung cancer treated with curative-intent conventional radiotherapy

Radiother Oncol. 2024 Dec:201:110544. doi: 10.1016/j.radonc.2024.110544. Epub 2024 Sep 26.

Authors

Fariba Tohidinezhad¹, Leonard Nürnberg², Femke Vaassen¹, Rachel Ma Ter Bekke³, Hugo Jwl Aerts⁴, Lizza El Hendriks⁵, Andre Dekker¹, Dirk De Ruysscher¹, Alberto Traverso⁶

Affiliations

¹ Department of Radiation Oncology (Maastro Clinic), School for Oncology and Reproduction (GROW), Maastricht University Medical Center, Maastricht, the Netherlands.
² Department of Radiation Oncology (Maastro Clinic), School for Oncology and Reproduction (GROW), Maastricht University Medical Center, Maastricht, the Netherlands; Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA; Department of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, the Netherlands.
³ Department of Cardiology, Cardiovascular Research Institute Maastricht, Maastricht University Medical Center, Maastricht, the Netherlands.
⁴ Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA; Department of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, the Netherlands; Departments of Radiation Oncology and Radiology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, USA.
⁵ Department of Pulmonary Diseases, School for Oncology and Reproduction (GROW), Maastricht University Medical Center, Maastricht, the Netherlands.
⁶ Department of Radiation Oncology (Maastro Clinic), School for Oncology and Reproduction (GROW), Maastricht University Medical Center, Maastricht, the Netherlands; School of Medicine, Libera Università Vita-Salute San Raffaele, Milan, Italy. Electronic address: traverso.alberto@hsr.it.

PMID: 39341504
DOI: 10.1016/j.radonc.2024.110544

Abstract

Background: Atrial fibrillation (AF) is an important side effect of thoracic Radiotherapy (RT), which may impair quality of life and survival. This study aimed to develop a prediction model for new-onset AF in patients with Non-Small Cell Lung Cancer (NSCLC) receiving RT alone or as a part of their multi-modal treatment.

Patients and methods: Patients with stage I-IV NSCLC treated with curative-intent conventional photon RT were included. The baseline electrocardiogram (ECG) was compared with follow-up ECGs to identify the occurrence of new-onset AF. A wide range of potential clinical predictors and dose-volume measures on the whole heart and six automatically contoured cardiac substructures, including chambers and conduction nodes, were considered for statistical modeling. Internal validation with optimism-correction was performed. A nomogram was made.

Results: 374 patients (mean age 69 ± 10 years, 57 % male) were included. At baseline, 9.1 % of patients had AF, and 42 (11.2 %) patients developed new-onset AF. The following parameters were predictive: older age (OR=1.04, 95 % CI: 1.013-1.068), being overweight or obese (OR=1.791, 95 % CI: 1.139-2.816), alcohol use (OR=4.052, 95 % CI: 2.445-6.715), history of cardiac procedures (OR=2.329, 95 % CI: 1.287-4.215), tumor located in the upper lobe (OR=2.571, 95 % CI: 1.518-4.355), higher forced expiratory volume in 1 s (OR=0.989, 95 % CI: 0.979-0.999), higher creatinine (OR=1.008, 95 % CI: 1.002-1.014), concurrent chemotherapy (OR=3.266, 95 % CI: 1.757 to 6.07) and left atrium D_max (OR=1.022, 95 % CI: 1.012-1.032). The model showed good discrimination (area under the curve = 0.80, 95 % CI: 0.76-0.84), calibration and positive net benefits.

Conclusion: This prediction model employs readily available predictors to identify patients at high risk of new-onset AF who could potentially benefit from active screening and timely management of post-RT AF.

Keywords: Atrial fibrillation; Lung cancer; Machine learning; Prediction model; Radiotherapy.

MeSH terms

Aged
Atrial Fibrillation* / etiology
Carcinoma, Non-Small-Cell Lung* / radiotherapy
Electrocardiography
Female
Humans
Lung Neoplasms* / pathology
Lung Neoplasms* / radiotherapy
Male
Middle Aged
Nomograms