Background Ischemic cardiovascular diseases (ICVD) risk predict models are valuable but limited by its requirement for multidimensional medical information including that from blood drawing. A convenient and affordable alternative is in demand. Objectives To develop and validate a deep learning algorithm to predict 10-year ICVD risk using retinal fundus photographs in Chinese population. Methods We firstly labeled fundus photographs with natural logarithms of ICVD risk estimated by a previously validated 10-year Chinese ICVD risk prediction model for 390,947 adults randomly selected (95%) from a health checkup dataset. An algorithm using convolutional neural network was then developed to predict the estimated 10-year ICVD risk by fundus images. The algorithm was validated using both internal dataset (the other 5%) and external dataset from an independent source (sample size = 1,309). Adjusted R2 and area under the receiver operating characteristic curve (AUC) were used to evaluate the goodness of fit. Results The adjusted R2 between natural logarithms of the predicted and calculated ICVD risks was 0.876 and 0.638 in the internal and external validations, respectively. For detecting ICVD risk ≥ 5% and ≥ 7.5%, the algorithm achieved an AUC of 0.971 (95% CI: 0.967 to 0.975) and 0.976 (95% CI: 0.973 to 0.980) in internal validation, and 0.859 (95% CI: 0.822 to 0.895) and 0.876 (95% CI: 0.816 to 0.837) in external validation. Conclusions The deep learning algorithm developed in the study using fundus photographs to predict 10-year ICVD risk in Chinese population had fairly good capability in predicting the risk and may have values to be widely promoted considering its advances in easy use and lower cost. Further studies with long term follow up are warranted. Keywords Deep learning, Ischemic cardiovascular diseases, risk prediction.

Background Lower low-density lipoprotein cholesterol (LDL-C) is significantly associated with improved prognosis in patients with coronary artery disease (CAD). However, LDL-C reduction does not decrease all-cause mortality among CAD patients when renal function impairs. There are currently no studies examining the association of low baseline LDL-C concentration (<1.8 mmol/L) with mortality among patients with CAD and advanced kidney disease (AKD). We aimed to evaluate prognostic value of low baseline LDL-C level for all-cause death in these patients. Methods In this observational study, 803 CAD patients complicated with AKD (eGFR <30 mL/min/1.73 m 2) were enrolled between January 2008 to December 2018. Patients were divided into two groups (LDL-C <1.8 mmol/L, n=138; LDL-C ≥1.8 mmol/L, n=665). We used Kaplan-Meier methods and Cox regression analyses to assess the association between baseline low LDL-C levels and long-term all-cause mortality. Results Among 803 participants (mean age 67.4 years; 68.5% male), there were 315 incidents of all-cause death during a median follow-up of 2.7 years. Kaplan–Meier analysis showed that low LDL-C levels were associated with worse prognosis. After adjusting for full 24 confounders (e.g., age, diabetes, heart failure, and dialysis, etc.), multivariate Cox regression analysis revealed that lower LDL-C level (<1.8mmol/L) was significantly associated with higher risk of all-cause death (adjusted HR, 1.38; 95% CI, 1.01–1.89). Conclusions Our data demonstrated that among patients with CAD and AKD, a lower baseline LDLC level (<1.8mmol/L) did not present a higher survival rate but was related to a worse prognosis, suggesting a cautiousness of too low LDL-C levels among patients with CAD and AKD. FUNDunding Acknowledgement Type of funding sources: Foundation. Main funding source(s): This study was supported by the National Natural Science Foundation of China (Grant No. 81670339 and Grant No. 81970311), Cardiovascular Research Foundation Project of the Chinese Medical Doctor Association (SCRFCMDA201216) and Beijing Lisheng Cardiovascular Health Foundation (LHJJ20141751).

The classification of music information using various deep learning models is increasingly popular in the field of Music Information Retrieval research. However, as most proposed works focus on western music and musical instruments, little attention is given to traditional Chinese music. This paper proposes a 1-D Convolutional Neural Network (1-D CNN) using only raw audio waveform as input, to undertake the task of traditional Chinese musical instruments classification. This paper starts with a review of the current state of research on the related field, then discuss the proposed model and its data in detail, followed by its performance metrics and then a conclusion on the experiment. The result shows that 1-D CNN provides competitive and even superior results when compared to its 2-D versions as well as when compared to traditional models.