Application of the RIMARC algorithm to a large data set of action potentials and clinical parameters for risk prediction of atrial fibrillation.

Ex vivo recorded action potentials (APs) in human right atrial tissue from patients in sinus rhythm (SR) or atrial fibrillation (AF) display a characteristic spike-and-dome or triangular shape, respectively, but variability is huge within each rhythm group. The aim of our study was to apply the machine-learning algorithm ranking instances by maximizing the area under the ROC curve (RIMARC) to a large data set of 480 APs combined with retrospectively collected general clinical parameters and to test whether the rules learned by the RIMARC algorithm can be used for accurately classifying the preoperative rhythm status. APs were included from 221 SR and 158 AF patients. During a learning phase, the RIMARC algorithm established a ranking order of 62 features by predictive value for SR or AF. The model was then challenged with an additional test set of features from 28 patients in whom rhythm status was blinded. The accuracy of the risk prediction for AF by the model was very good (0.93) when all features were used. Without the seven AP features, accuracy still reached 0.71. In conclusion, we have shown that training the machine-learning algorithm RIMARC with an experimental and clinical data set allows predicting a classification in a test data set with high accuracy. In a clinical setting, this approach may prove useful for finding hypothesis-generating associations between different parameters.

Phenotype-dependent apoptosis signalling in mesothelioma cells after selenite exposure.

BACKGROUND: Selenite is a promising anticancer agent which has been shown to induce apoptosis in malignant mesothelioma cells in a phenotype-dependent manner, where cells of the chemoresistant sarcomatoid phenotype are more sensitive. METHODS: In this paper, we investigate the apoptosis signalling mechanisms in sarcomatoid and epithelioid mesothelioma cells after selenite treatment. Apoptosis was measured with the Annexin-PI assay. The mitochondrial membrane potential, the expression of Bax, Bcl-XL, and the activation of caspase-3 were assayed with flow cytometry and a cytokeratin 18 cleavage assay. Signalling through JNK, p38, p53, and cathepsins B, D, and E was investigated with chemical inhibitors. Furthermore, the expression, nuclear translocation and DNA-binding activity of p53 was investigated using ICC, EMSA and the monitoring of p21 expression as a downstream event. Levels of thioredoxin (Trx) were measured by ELISA. RESULTS: In both cell lines, 10 microM selenite caused apoptosis and a marked loss of mitochondrial membrane potential. Bax was up-regulated only in the sarcomatoid cell line, while the epithelioid cell line down-regulated Bcl-XL and showed greater caspase-3 activation. Nuclear translocation of p53 was seen in both cell lines, but very little p21 expression was induced. Chemical inhibition of p53 did not protect the cells from apoptosis. p53 lost its DNA binding ability after selenite treatment and was enriched in an inactive form. Levels of thioredoxin decreased after selenite treatment. Chemical inhibition of MAP kinases and cathepsins showed that p38 and cathepsin B had some mediatory effect while JNK had an anti-apoptotic role. CONCLUSION: We delineate pathways of apoptosis signalling in response to selenite, showing differences between epithelioid and sarcomatoid mesothelioma cells. These differences may partly explain why sarcomatoid cells are more sensitive to selenite.