Objective: The aim of this study was to determine the independent value of N-terminal pro b-type natriuretic peptide, high-sensitivity cardiac troponin T, and C-reactive protein to predict onset of cardiopulmonary disease in a large, multi-center systemic sclerosis cohort followed prospectively. Methods: Subjects from the Canadian Scleroderma Research Group registry with data on N-terminal pro b-type natriuretic peptide, high-sensitivity cardiac troponin T, and C-reactive protein were identified. Outcomes of interest were death, systolic dysfunction (left ventricular ejection fraction < 50% or medications for heart failure), pulmonary arterial hypertension by right heart catheterization, pulmonary hypertension by cardiac echocardiography (systolic pulmonary artery pressures ⩾ 45 mmHg), arrhythmias (pacemaker/implantable cardiac defibrillator or anti-arrhythmic medications), and interstitial lung disease. Multivariate Cox proportional hazard models were generated for each outcome. Results: A total of 675 subjects were included with a mean follow-up of 3.0 ± 1.8 years. Subjects were predominantly women (88.4%) with mean age of 58.2 ± 11.3 years and mean disease duration of 13.7 ± 9.1 years. One hundred and one (101, 15%) subjects died during follow-up, 37 (6.4 %) developed systolic dysfunction, 18 (2.9%) arrhythmias, 34 (5.1%) pulmonary arterial hypertension, 43 (7.3%) pulmonary hypertension, and 48 (12.3%) interstitial lung disease. In multivariate analyses, elevated levels of N-terminal pro b-type natriuretic peptide, high-sensitivity cardiac troponin T, and C-reactive protein were associated with increased risk of death, while elevated levels of N-terminal pro b-type natriuretic peptide and C-reactive protein were associated with increased risk of developing pulmonary hypertension. Conclusion: In systemic sclerosis, N-terminal pro b-type natriuretic peptide, high-sensitivity cardiac troponin T, and C-reactive protein have independent predictive value for death and pulmonary hypertension. A larger study would be required to determine the predictive value of these biomarkers for less common systemic sclerosis outcomes.

Early detection of faults in rotating machinery systems is crucial in preventing system failure, increasing safety, and reducing maintenance costs. Current methods of fault detection suffer from the lack of efficient feature extraction method, the need for designating a threshold producing minimal false alarm rates, and the need for expert domain knowledge, which is costly. In this paper, we propose a novel data-driven health division method based on convolutional neural networks using a graphical representation of time series data, called a nested scatter plot. The proposed method trains the model with a small amount of labeled data and does not require a threshold value to predict the health state of rotary machines. Notwithstanding the lack of datasets that show the ground truth of health stages, our experiments with two open datasets of run-to-failure bearing demonstrated that our method is able to detect the early symptoms of bearing wear earlier and more efficiently than other threshold-based health indicator methods.