Predicting System Degradation with a Guided Neural Network Approach.

Evaluating the physical degradation behavior and estimating the lifetime of engineering systems and structures is crucial to ensure their safe and reliable operation. However, measuring lifetime through actual operating conditions can be a difficult and slow process. While valuable and quick in measuring lifetimes, accelerated life testing is often oversimplified and does not provide accurate simulations of the exact operating environment. This paper proposes a data-driven framework for time-efficient modeling of field degradation using sensor measurements from short-term actual operating conditions degradation tests. The framework consists of two neural networks: a physics discovery neural network and a predictive neural network. The former models the underlying physics of degradation, while the latter makes probabilistic predictions for degradation intensity. The physics discovery neural network guides the predictive neural network for better life estimations. The proposed framework addresses two main challenges associated with applying neural networks for lifetime estimation: incorporating the underlying physics of degradation and requirements for extensive training data. This paper demonstrates the effectiveness of the proposed approach through a case study of atmospheric corrosion of steel test samples in a marine environment. The results show the proposed framework's effectiveness, where the mean absolute error of the predictions is lower by up to 76% compared to a standard neural network. By employing the proposed data-driven framework for lifetime prediction, systems safety and reliability can be evaluated efficiently, and maintenance activities can be optimized.

EVALUATION OF 5-FLUOROURACIL-INDUCED CARDIOTOXICITY: ROLE OF CARDIAC BIOMARKERS.

BACKGROUND: Side effects of chemotherapy in cancer patients need to be investigated in more detail. AIM: To determine the incidence of cardiotoxicity in patients treated with different chemotherapy regimens containing 5-fluorouracil (5-FU) in Zanjan, Iran. PATIENTS AND METHODS: In a prospective cohort study, patients with different types of solid gastrointestinal tumors who were candidates for 5-FU based chemotherapy regimens were enrolled. The study population consisted of 100 patients (48 females and 52 males) with a mean age of 63.99 ± 12.40 years. We measured serum cardiac troponin I (cTnI) levels before and during each chemotherapy cycle and determined the occurrence of cardiotoxicity in patients based on the levels of cTnI, clinical signs and symptoms as well as electrocardiogram findings. In addition, we assessed a history of diabetes, hypertension, smoking, dyslipidemia and previous chest radiation as potential risk factors for cardiotoxicity. RESULTS: The incidence of cardiotoxicity was 8%, of which 5 patients were diagnosed with acute coronary syndrome, 2 patients with arrhythmias and one with hypotension. In addition, there was no significant association between studied risk factors and 5-FU induced cardiotoxicity. CONCLUSION: The incidence of cardiotoxicity in patients receiving 5-FU infusion regimens was notable. Thus, paying more attention to the 5-FU-induced cardiotoxicity is necessary in order to improve the prognosis of patients with cancer.

Health system responsiveness for care of patients with heart failure: evidence from a university hospital.

BACKGROUND: Responsiveness refers to non-clinical aspects of the health system and responds to this question that whether health system is responsive to rightful expectations of people. The present study was conducted to determine the health system responsiveness about chronic heart failure patients in one of the main heart centers in Tehran during 2012 - 2013. METHODS: In this cross-sectional study 300 patients have completed a valid questionnaire that designed by World Health Organization (WHO) for measurement of responsiveness. Analysis of data was based on analysis WHO multi-country study that was designed to evaluate responsiveness in health care systems. RESULTS: In outpatient services, worst performance was related to choice and prompt attention domains (35.8% and 35.1%). Autonomy (31.5%) has the worst performance of inpatient services. Both in outpatient and inpatient services "confidentiality of information" has the best performance (87.8% and 85.6%). Responsiveness of the health system in inpatient services has the worst performance comparing to outpatient services (57.2% versus 66.5%). Most important domains from patient's view were prompt attention and dignity (47% and 23%). CONCLUSION: More attention to patient's rights, giving them opportunity to choose health care services (choice), providing fast access to emergency care (prompt attention) and considering autonomy are most important aspects of health responsiveness.  From patient's view "prompt attention" was reported as the most important aspect of responsiveness.