Contralateral patent processus vaginalis repair in boys: a single-center retrospective study.

To ascertain the prevalence of contralateral patent processus vaginalis (CPPV) in life and the significance of the prevalence trends for treatment. We performed a retrospective review of all inguinal hernias (IHs) that underwent repair in our hospital from 2014 to 2018. We analyzed the frequency of occurrence and treatment in boys. We assessed and compared the history, initial sides of hernia, CPPV and prognoses in different age groups. We assessed all IH cases repaired in our hospital and selected male patients of a variety of ages, including boys and men. Recurrent cases were not enrolled. A total of 3243 cases were enrolled: 2489 [right-sided IH 1411 (56.69%) vs. left-sided IH 975 (39.17%), bilateral IH 103 (4.14%)] in children and 754 [right-sided IH 485 (64.32%) vs. left-sided IH 236 (31.30%), bilateral IH 33 (4.38%)] in adults. A total of 1124 CPPVs were identified in children with unilateral IH (2386), and 12 were identified in adults (267) (p < 0.0001). There were no significant differences in recurrence rate between different subgroups of children (p > 0.05). The incidence of IH in boys was significantly higher than that in men. The number of incident cases declines rapidly with age in boys. The processus vaginalis is normally obliterated and involuted but may instead remain patent for a long period before closure; routine exploration on the contralateral side may eliminate the possibility of spontaneous PPV closure.

A heart sound classification method based on joint decision of extreme gradient boosting and deep neural network / 生物医学工程学杂志

Heart sound is one of the common medical signals for diagnosing cardiovascular diseases. This paper studies the binary classification between normal or abnormal heart sounds, and proposes a heart sound classification algorithm based on the joint decision of extreme gradient boosting (XGBoost) and deep neural network, achieving a further improvement in feature extraction and model accuracy. First, the preprocessed heart sound recordings are segmented into four status, and five categories of features are extracted from the signals based on segmentation. The first four categories of features are sieved through recursive feature elimination, which is used as the input of the XGBoost classifier. The last category is the Mel-frequency cepstral coefficient (MFCC), which is used as the input of long short-term memory network (LSTM). Considering the imbalance of the data set, these two classifiers are both improved with weights. Finally, the heterogeneous integrated decision method is adopted to obtain the prediction. The algorithm was applied to the open heart sound database of the PhysioNet Computing in Cardiology(CINC) Challenge in 2016 on the PhysioNet website, to test the sensitivity, specificity, modified accuracy and F score. The results were 93%, 89.4%, 91.2% and 91.3% respectively. Compared with the results of machine learning, convolutional neural networks (CNN) and other methods used by other researchers, the accuracy and sensibility have been obviously improved, which proves that the method in this paper could effectively improve the accuracy of heart sound signal classification, and has great potential in the clinical auxiliary diagnosis application of some cardiovascular diseases.