RESUMEN
Aims: There are no comprehensive machine learning (ML) tools used by oncologists to assist with risk identification and referrals to cardio-oncology. This study applies ML algorithms to identify oncology patients at risk for cardiovascular disease for referrals to cardio-oncology and to generate risk scores to support quality of care. Methods and results: De-identified patient data were obtained from Vanderbilt University Medical Center. Patients with breast, kidney, and B-cell lymphoma cancers were targeted. Additionally, the study included patients who received immunotherapy drugs for treatment of melanoma, lung cancer, or kidney cancer. Random forest (RF) and artificial neural network (ANN) ML models were applied to analyse each cohort: A total of 20 023 records were analysed (breast cancer, 6299; B-cell lymphoma, 9227; kidney cancer, 2047; and immunotherapy for three covered cancers, 2450). Data were divided randomly into training (80%) and test (20%) data sets. Random forest and ANN performed over 90% for accuracy and area under the curve (AUC). All ANN models performed better than RF models and produced accurate referrals. Conclusion: Predictive models are ready for translation into oncology practice to identify and care for patients who are at risk of cardiovascular disease. The models are being integrated with electronic health record application as a report of patients who should be referred to cardio-oncology for monitoring and/or tailored treatments. Models operationally support cardio-oncology practice. Limited validation identified 86% of the lymphoma and 58% of the kidney cancer patients with major risk for cardiotoxicity who were not referred to cardio-oncology.
RESUMEN
Mesenchymal stem cells (MSCs) were shown to improve cell survival and alleviate cardiac arrhythmias when transplanted into cardiac tissue; however, little is known about the mechanism by which MSCs modify the electrophysiological properties of cardiac tissue. We aimed to distinguish the influence of cell-cell coupling between myocytes and MSCs from that of MSC-derived paracrine factors on the spontaneous activity and conduction velocity (θ) of multicellular cardiomyocyte preparations. HL-1 cells were plated on microelectrode arrays and their spontaneous activity and θ was determined from field potential recordings. In heterocellular cultures of MSCs and HL-1 cells the beating frequency was attenuated (t(0h): 2.26 ± 0.18 Hz; t(4h): 1.98 ± 0.26 Hz; P < 0.01) concomitant to the intercellular coupling between MSCs and cardiomyocytes. In HL-1 monolayers supplemented with MSC conditioned media (ConM) or tyrode (ConT) θ significantly increased in a time-dependent manner (ConT: t(0h): 2.4 cm/s ± 0.2; t(4h): 3.1 ± 0.4 cm/s), whereas the beating frequency remained constant. Connexin (Cx)43 mRNA and protein expression levels also increased after ConM or ConT treatment over the same time period. Enhanced low-density lipoprotein receptor-related protein 6 (LRP6) phosphorylation after ConT treatment implicates the Wnt signaling pathway. Suppression of Wnt secretion from MSCs (IWP-2; 5 µmol/l) reduced the efficacy of ConT to induce phospho-LRP6 and to increase θ. Inhibition of ß-catenin (cardamonin; 10 µmol/l) or GSK3-α/ß (LiCl; 5 mmol/l) also suppressed changes in θ, further supporting the hypothesis that MSC-mediated Cx43 upregulation occurs in part through secreted Wnt ligands and activation of the canonical Wnt signaling pathway.