Epidemiology and predictors of hyponatremia in a contemporary cohort of patients with malignancy: a retrospective cohort study

Background. Hyponatremia is associated with worse outcomes among patients with malignancy. However, contemporary cohort data on epidemiology and risk factors are lacking. Methods. In this single-centre, retrospective cohort study, patients who received intravenous antineoplastic agents from 2018 to 2020 at Nagoya City University Hospital were enrolled. Associations of demographics, antineoplastic agents, types of malignancy and concomitant medications with hyponatremia, defined as serum sodium concentration <= 130 mmol/l, were analysed by mixed-effects logistic regression and the machine learning-based LightGBM model artificial intelligence technology. Results. Among 2644 patients, 657 (24.8%) developed at least one episode of hyponatremia. Approximately 80% of hyponatremia was due to sodium wasting from the kidneys. Variables associated with hyponatremia both by mixed-effects logistic regression and the LightGBM model were older age, hypoalbuminemia and higher estimated glomerular filtration rate. Among antineoplastic agents, cisplatin {odds ratio [OR] 1.52 [95% confidence interval (CI) 1.18-1.96]}, pembrolizumab [OR 1.42 (95% CI 1.02-1.97)] and bortezomib [OR 3.04 (95% CI 1.96-4.71)] were associated with hyponatremia and these variables also had a positive impact on predicted hyponatremia in the LightGBM model. Conclusions. Hyponatremia was common among patients with malignancy. In addition to older age and poor nutritional status, novel antineoplastic agents, including immune checkpoint inhibitors and bortezomib, should be recognized as risk factors for hyponatremia. In this study we demonstrated that hyponatremia is common among patients with malignancy in a contemporary cohort. Most of hyponatremia was caused by sodium wasting from the kidneys. In addition to known risk factors of hyponatremia, such as older age, poor oral intake, vinca alkaloids, small cell lung cancer and pancreatic cancer, immune checkpoint inhibitors and bortezomib were associated with a higher incidence of hyponatremia both by conventional statistics and by a machine learning prediction model.