[Segmentation of heart sound signals based on duration hidden Markov model].

Heart sound segmentation is a key step before heart sound classification. It refers to the processing of the acquired heart sound signal that separates the cardiac cycle into systolic and diastolic, etc. To solve the accuracy limitation of heart sound segmentation without relying on electrocardiogram, an algorithm based on the duration hidden Markov model (DHMM) was proposed. Firstly, the heart sound samples were positionally labeled. Then autocorrelation estimation method was used to estimate cardiac cycle duration, and Gaussian mixture distribution was used to model the duration of sample-state. Next, the hidden Markov model (HMM) was optimized in the training set and the DHMM was established. Finally, the Viterbi algorithm was used to track back the state of heart sounds to obtain S1, systole, S2 and diastole. 500 heart sound samples were used to test the performance of our algorithm. The average evaluation accuracy score (F1) was 0.933, the average sensitivity was 0.930, and the average accuracy rate was 0.936. Compared with other algorithms, the performance of our algorithm was more superior. It is proved that the algorithm has high robustness and anti-noise performance, which might provide a novel method for the feature extraction and analysis of heart sound signals collected in clinical environments.

RIRS versus mPCNL for single renal stone of 2-3 cm: clinical outcome and cost-effective analysis in Chinese medical setting.

The aim of the study was to compare the clinical outcome and the cost-effectiveness between retrograde intra renal surgery (RIRS) and mini-percutaneous nephrolithotripsy (mPCNL) for the management of single renal stone of 2-3 cm in Chinese medical setting. From May 2005 to February 2011, 115 patients with solitary renal calculi were treated either by RIRS or mPCNL. 56 patients were in RIRS group while 59 were in mPCNL group. Patients' demographics between the two groups, in terms of gender, age, BMI, history of ESWL as well as stone side, stone location and stone size were comparable. Peri-operative course, clinical outcome, complication rates and medical cost were compared. The effective quotient (EQ) of two groups was calculated. Data were analyzed using Fisher's exact test, Chi-square test and Student's t test. EQ for RIRS and mPCNL were 0.52 and 0.90. The initial stone-free rate (SFR) of RIRS group and mPCNL group was 71.4 and 96.6 %, respectively (P = 0.000). The mean procedure number was 1.18 in RIRS group and 1.03 in mPCNL group, respectively (P = 0.035). The operative time for RIRS was longer (P = 0.000) while the mean hospital stay was shorter (P = 0.000). There was no statistical difference in peri-operative complications between the groups. The initial hospitalization cost, laboratory and radiology test cost of RIRS group were lower (P = 0.000). However, counting the retreatment cost in the two groups, the total medical expenditure including the overall hospitalization cost, overall laboratory and radiology test cost and post-operative out-patient department (OPD) visit cost was similar between two groups. In conclusion, with similar total medical cost, mPCNL achieved faster stone clearance and lower retreatment rate without major complications, which implied higher cost-effectiveness for the treatment of single renal stone of 2-3 cm in Chinese medical setting. RIRS is also a safe and reliable choice for patients having contraindications or preference against mPCNL.