搜索结果：machine0

We constructed an early prediction model for postoperative pulmonary complications after thoracoscopic surgery using machine learning and deep learning algorithms. The artificial intelligence prediction models were built in Python, primarily using artificial intelligencealgorithms including both machine learning and deep learning algorithms. Correlation analysis showed that postoperative pulmonary complications were positively correlated with age and surgery duration, and negatively correlated with serum albumin. Using the light gradient boosting machine(LGBM) algorithm, weighted feature engineering revealed that single lung ventilation duration, history of smoking, surgery duration, ASA score, and blood glucose were the main factors associated with postoperative pulmonary complications. Results of artificial intelligence algorithms for predicting pulmonary complications after thoracoscopy in the test group: In terms of accuracy, the two best algorithms were Logistic Regression (0.831) and light gradient boosting machine(0.827); in terms of precision, the two best algorithms were Gradient Boosting (0.75) and light gradient boosting machine (0.742); in terms of recall, the three best algorithms were gaussian naive bayes (0.581), Logistic Regression (0.532), and pruning Bayesian neural network (0.516); in terms of F1 score, the two best algorithms were LogisticRegression (0.589) and pruning Bayesian neural network (0.566); and in terms of Area Under Curve(AUC), the two best algorithms were light gradient boosting machine(0.873) and pruning Bayesian neural network (0.869). The results of this study suggest that pruning Bayesian neural network (PBNN) can be used to assess the possibility of pulmonary complications after thoracoscopy, and to identify high-risk groups prior to surgery.

To evaluate the modified micro-push-out bond strengths of prefabricated glass fiber posts with silaneafter 35% phosphoric acid to resin cements. In the study, 40 glass fiber posts were randomly divided into 2 groups (20 posts in each group) for different surface treatments. Group 1, treated with silaneafter 35% phosphoric acid; group 2, no surface treatment (Control group). Then each group was randomly divided into 2 minor groups (modified group and traditional group), with each group with 10. So the four groups were group 1M (phosphoric acid + silane-modified), group 1T (phosphoric acid + silane-traditional), group 2M (control-modified), and group 2T (control-traditional). A modified micro-push-out bond strength test method was used in modified groups. In traditional groups, the 20 extracted human, single-rooted teeth were endodontically treated. Gutta-percha was removed with #1-2 Peeso Reamers (Mani), and the post space of each specimen was enlarged with a standard drill system from the corresponding fiber post system to create a 9 mm post space with at least 4 mm of filling material in the root apex. Following post cementation according to the manufacturer's instructions, the traditional micro-push-out bond strengths were tested using a universal testing machine(0.5 mm/min). Both failure modes were examined with a stereomicroscope. The data of the four groups were statistically analyzed using the one-way ANOVA test(&#x3b1;= 0.05). The bond strengths were (18.85&#xb1;1.42) MPa for group 1M, (19.39&#xb1;1.35) MPa for group 1T, (11.26&#xb1;1.57) MPa for group 2M, and (11.27&#xb1;1.83) MPa for group 2T. The bond strength of Group 1 was significantly higher than that of group 2(P<0.05), no matter which method was used. The fracture mode 100% in group M was the destruction of the post/resin interface, compared with 65.7% in group T. In contrasted to the traditional micro-push-out test, the modified test can evaluate the bond strength of fiber post to resin cement more effectively, and 35% phosphate acid + silane treatment can improve the bonding strength. &#x5efa;&#x7acb;&#x4e00;&#x79cd;&#x6539;&#x826f;&#x5f0f;&#x5fae;&#x63a8;&#x51fa;&#x65b9;&#x5f0f;&#x6d4b;&#x8bd5;&#x73bb;&#x7483;&#x7ea4;&#x7ef4;&#x6869;&#x8868;&#x9762;&#x7ecf;35%&#x78f7;&#x9178;+&#x7845;&#x70f7;&#x5076;&#x8054;&#x5242;&#x5904;&#x7406;&#x540e;&#x4e0e;&#x6811;&#x8102;&#x6c34;&#x95e8;&#x6c40;&#x7684;&#x7c98;&#x63a5;&#x5f3a;&#x5ea6;,&#x63a2;&#x8ba8;&#x6b64;&#x79cd;&#x6d4b;&#x8bd5;&#x6a21;&#x5f0f;&#x8bc4;&#x4ef7;&#x73bb;&#x7483;&#x7ea4;&#x7ef4;&#x6869;&#x4e0e;&#x6811;&#x8102;&#x6c34;&#x95e8;&#x6c40;&#x7c98;&#x63a5;&#x5f3a;&#x5ea6;&#x7684;&#x4ef7;&#x503c;&#x3002; &#x5148;&#x5c06;40&#x652f;&#x73bb;&#x7483;&#x7ea4;&#x7ef4;&#x6869;&#x968f;&#x673a;&#x5206;&#x6210;2&#x5927;&#x7ec4;,&#x6bcf;&#x7ec4;20&#x652f;,&#x7ec4;1&#x4e3a;&#x78f7;&#x9178;+&#x7845;&#x70f7;&#x5316;&#x7ec4;,&#x7ec4;2&#x4e3a;&#x5bf9;&#x7167;&#x7ec4;&#x3002;&#x518d;&#x5c06;&#x6bcf;&#x4e00;&#x5927;&#x7ec4;&#x968f;&#x673a;&#x5206;&#x4e3a;M(&#x6539;&#x826f;)&#x548c;T(&#x4f20;&#x7edf;)&#x4e24;&#x4e2a;&#x5c0f;&#x7ec4;,&#x6bcf;&#x7ec4;10&#x652f;,&#x5206;&#x522b;&#x7528;&#x6539;&#x826f;&#x5f0f;&#x5fae;&#x63a8;&#x51fa;&#x8bd5;&#x9a8c;&#x548c;&#x4f20;&#x7edf;&#x5fae;&#x63a8;&#x51fa;&#x8bd5;&#x9a8c;&#x6d4b;&#x5b9a;&#x7ea4;&#x7ef4;&#x6869;&#x4e0e;&#x6811;&#x8102;&#x6c34;&#x95e8;&#x6c40;&#x7684;&#x7c98;&#x63a5;&#x5f3a;&#x5ea6;&#x5e76;&#x89c2;&#x5bdf;&#x7834;&#x574f;&#x6a21;&#x5f0f;&#x3002; &#x7ec4;1M(&#x78f7;&#x9178;+&#x7845;&#x70f7;&#x5316;&#x7ec4;-&#x6539;&#x826f;)&#x5fae;&#x63a8;&#x51fa;&#x7c98;&#x63a5;&#x5f3a;&#x5ea6;&#x4e3a;(18.85&#xb1;1.42) MPa,&#x7ec4;1T(&#x78f7;&#x9178;+&#x7845;&#x70f7;&#x5316;&#x7ec4;-&#x4f20;&#x7edf;)&#x4e3a;(19.39&#xb1;1.35) MPa,&#x7ec4;2M(&#x5bf9;&#x7167;&#x7ec4;-&#x6539;&#x826f;)&#x4e3a;(11.26&#xb1;1.57)MPa,&#x7ec4;2T(&#x5bf9;&#x7167;&#x7ec4;-&#x4f20;&#x7edf;)&#x4e3a;(11.27&#xb1;1.83)MPa,&#x5728;&#x6539;&#x826f;&#x7ec4;&#x548c;&#x4f20;&#x7edf;&#x7ec4;&#x4e2d;,&#x78f7;&#x9178;+&#x7845;&#x70f7;&#x5316;&#x7ec4;&#x7c98;&#x63a5;&#x5f3a;&#x5ea6;&#x503c;&#x5747;&#x663e;&#x8457;&#x9ad8;&#x4e8e;&#x5bf9;&#x7167;&#x7ec4;(P<0.01),&#x4e14;&#x6539;&#x826f;&#x7ec4;&#x4e2d;&#x65ad;&#x88c2;&#x6a21;&#x5f0f;100%&#x4e3a;&#x6869;/&#x6811;&#x8102;&#x754c;&#x9762;&#x7834;&#x574f;,&#x76f8;&#x6bd4;&#x4f20;&#x7edf;&#x7ec4;&#x7684;65.7%,&#x66f4;&#x52a0;&#x96c6;&#x4e2d;&#x4f53;&#x73b0;&#x754c;&#x9762;&#x7c98;&#x63a5;&#x5f3a;&#x5ea6;&#x7684;&#x53d8;&#x5316;&#x3002; &#x76f8;&#x8f83;&#x4e8e;&#x4f20;&#x7edf;&#x7ec4;,&#x6539;&#x826f;&#x7ec4;&#x5fae;&#x63a8;&#x51fa;&#x8bd5;&#x9a8c;&#x80fd;&#x66f4;&#x6709;&#x6548;&#x5730;&#x8bc4;&#x4ef7;&#x7ea4;&#x7ef4;&#x6869;&#x4e0e;&#x6811;&#x8102;&#x6c34;&#x95e8;&#x6c40;&#x4e4b;&#x95f4;&#x7684;&#x7c98;&#x63a5;&#x5f3a;&#x5ea6;,&#x4e14;35%&#x78f7;&#x9178;+&#x7845;&#x70f7;&#x5316;&#x5904;&#x7406;&#x73bb;&#x7483;&#x7ea4;&#x7ef4;&#x6869;&#x8868;&#x9762;&#x53ef;&#x4ee5;&#x66f4;&#x6709;&#x6548;&#x5730;&#x63d0;&#x9ad8;&#x5176;&#x4e0e;&#x6811;&#x8102;&#x6c34;&#x95e8;&#x6c40;&#x7684;&#x7c98;&#x63a5;&#x5f3a;&#x5ea6;&#x3002;

This study evaluated the effect of epigallocatechin-3-gallate (EGCG) solution and thermal cycling on the bond strength (BS) of fiber posts to the root dentin using two different resin cements (conventional or self-adhesive). One hundred and forty-four bovine roots were endodontically treated. After post space preparation, specimens were randomly divided into six groups (n&#x2009;=&#x2009;24) according to dentin pretreatment [distilled water, 0.05% EGCG solution or 2% chlorhexidine (CHX) solution] and resin luting agent used for fiber post cementation (RelyX ARC or RelyX U200-3 M ESPE). Then, the samples were separated into two subgroups (n&#x2009;=&#x2009;12): storage in distilled water at 37 &#xb0;C for 24 h and thermal cycling (5 &#xb0;C/55 &#xb0;C, dwell time 30 s-12,000 cycles) during 6 months. After that, the specimens were subjected to the pull-out BS test (Universal Testing Machine-0.5 mm/min) and the failures pattern was analyzed in a stereomicroscope. According to the BS results (three-way ANOVA, Tukey's test, &#x3b1;&#x2009;=&#x2009;0.05), the highest values were reported in the group EGCG&#x2009;+&#x2009;RelyX U200, showing significant statistical differences compared to all the other experimental groups. For Control and CHX groups BS values, there was no significant difference (p&#x2009;>&#x2009;.05) between the resin cements. For conventional resin cement, there was no significant difference among treatment solutions (p&#x2009;>&#x2009;.05). The thermal cycling did not influence the BS results (p&#x2009;>&#x2009;.05). As reported by the failure mode analysis, adhesive failure was predominant in all groups. EGCG solution improved the bond strength of self-adhesive resin cement to root dentin.