RESUMO
Feature extraction methods and classifier selection are two critical steps in heart sound classification. To capture the pathological features of heart sound signals, this paper introduces a feature extraction method that combines mel-frequency cepstral coefficients (MFCC) and power spectral density (PSD). Unlike conventional classifiers, the adaptive neuro-fuzzy inference system (ANFIS) was chosen as the classifier for this study. In terms of experimental design, we compared different PSDs across various time intervals and frequency ranges, selecting the characteristics with the most effective classification outcomes. We compared four statistical properties, including mean PSD, standard deviation PSD, variance PSD, and median PSD. Through experimental comparisons, we found that combining the features of median PSD and MFCC with heart sound systolic period of 100-300 Hz yielded the best results. The accuracy, precision, sensitivity, specificity, and F1 score were determined to be 96.50%, 99.27%, 93.35%, 99.60%, and 96.35%, respectively. These results demonstrate the algorithm's significant potential for aiding in the diagnosis of congenital heart disease.
Assuntos
Humanos , Ruídos Cardíacos , Redes Neurais de Computação , Algoritmos , Cardiopatias CongênitasRESUMO
Objective To investigate the drug resistance and the distribution situation of the related drug resistant genes in Staphylococcus aureus (SA), and to provide a basis for the clinical rational use of antibiotics and the hospital control of infection. Methods A total of 135 strains of SA were collected from the Second Affiliated Hospital of Baotou Medical College during January to December 2017. BD Phoenix TM-100 automatic microorganism identification and drug sensitivity systems and K-B agar diffusion method were used to identify SA colony and analyze its drug susceptibility; the related drug resistant genes were detected by polymerase chain reaction (PCR). Results Among 135 strains of SA, 16 (11.9%) methicillin-resistant SA (MRSA) and 119 (88.1%) methicillin-sensitive SA (MSSA) were detected. In the 14 strains of MRSA, the resistance rates to ampicillin, penicillin and erythromycin were high (91.9%, 91.1% and 64.4%, respectively), and no vancomycin, teicoplanin and linezolid-resistant strains were found. Additionally, the resistance rates of MRSA to ciprofloxacin were significantly higher than that of MSSA [31.3% (5/16) vs. 5.0% (6/119), P < 0.05]. Among 135 strains of SA, the detection rates of mecA, aac(6')/aph(2"), erm(A), erm(B), erm(C), and tetM were 4.4% (6/135), 10.4% (14/135), 0.7% (1/135), 27.4% (37/135), 31.4% (46/135) and 0.7% (1/135), respectively. In MRSA, the detection rates of mecA [37.5% (6/16) vs. 0 (0/119)], aac(6')/aph(2") [31.3% (5/16) vs. 7.6% (9/119)], and ermB [31.3% (5/16) vs. 26.9% (32/119)] were significantly higher than those in MSSA. It is noteworthy that the detection rate of mecA in MRSA was only 37.5% (6/16). Conclusions The MRSA detection rate of our hospital was below the national average level. The detection rates of resistance genes mecA, aac(6')/aph(2") and ermB were higher, which may be an important cause of drug resistance. Moreover, the detection of MRSA by mecA alone may lead to missed diagnosis, that should be paid attention to.
RESUMO
Objective To compare the effects of propofol and sevoflurane on oxidative stress re-sponses in patients undergoing one-lung ventilation. Methods Eighty American Society of Anesthesiolo-gists physical statusⅠorⅡpatients with lung cancer, aged 42-53 yr, weighing 52-83 kg, scheduled for e-lective pulmonary lobectomy performed via a thoracoscope, were divided into 2 groups ( n=40 each) using a random number table method: group propofol and group sevoflurane. Propofol was intravenously infused at 4-10 mg·kg-1 ·h-1 in group propofol. In group sevoflurane, 1％-3％ sevoflurane was inhaled. Forced expiratory volume (FEV), forced vital capacity (FVC), FEV in first second (FEV1), FEV∕FVC, and maximal expiratory flow ( MEF) were measured at 24 h after operation. Blood samples were obtained from the median cubital vein for determination of the levels of plasma malondialdehyde ( MDA) , catalase ( CAT) and superoxide dismutase ( SOD) and expression of NOX2 and NOX4 subunits-containing NADPH oxidase, SP-D and CC16 ( by Western blot) . Results Compared with group sevoflurane, FEV, FVC, FEV1, FEV∕FVC and MEF were significantly increased, the activity of plasma SOD and CAT was increased, MDA con-centration was decreased, the expression of NOX2 and NOX4 subunits-containing NADPH oxidase and SP-D was down-regulated, and the expression of CC16 was up-regulated in group propofol (P<0. 05). Conclu-sion Propofol provides better efficacy in protecting lung function of patients undergoing one-lung ventilation when compared with sevoflurane, which is related to inhibiting oxidative stress responses.