ObjectiveThrough comparing the therapeutic efficacy of robot-assisted surgery (RS) and conventional surgery (CS) for mitral valve disease by meta-analysis to guide the choice of clinical operation.MethodsDatabases including The Cochrane Library, PubMed, EMbase, China National Knowledge Infrastructure (CNKI), China Biology Medicine disc (CBMdisc) and Wanfang Database were searched by computer from inception to June 2020. The literature of efficacy comparison between RS and CS was collected. Two reviewers independently screened the literature according to inclusion and exclusion criteria, extracted the data, and evaluated the quality of the literature. Meta-analysis was performed using RevMan 5.4 software.ResultsWe identified 11 studies of RS versus CS with 4 330 patients. Among them, 2 212 patients underwent RS and 2 118 underwent CS. Meta-analysis demonstrated that compared with the CS, RS had longer cross-clamp time (MD=25.00, 95%CI 15.04 to 34.95, P<0.000 01), cardiopulmonary bypass time (MD=44.11, 95%CI 29.26 to 58.96, P<0.000 01) and operation time (MD=46.40, 95%CI 31.55 to 61.26, P<0.000 01). However, ICU stay (MD=–22.13, 95%CI –31.88 to –12.38, P<0.000 01) and hospital stay (MD=–1.81, 95%CI –2.69 to –0.92, P<0.000 01) were significantly shorter in the RS group; and the incidences of blood transfusion (OR=0.38, 95%CI 0.16 to 0.89, P=0.03) and complications (OR=0.73, 95%CI 0.57 to 0.94, P=0.01) were significantly lower in the RS group.ConclusionAlthough RS has a longer operation time than CS, it has less damage, less bleeding, faster recovery and better curative efficacy.
Accurate neurological outcome assessment after cardiac arrest is critical for clinical diagnosis and treatment. Existing electroencephalogram (EEG) prediction models suffer from high computational complexity, redundant full-channel data, and insufficient fusion of time-frequency domain features. This study proposes a lightweight deep learning model, WaveConv-SR-RepVGG, based on adaptive time-frequency feature fusion and reparameterized convolution. Taking the reparameterized visual convolutional network (RepVGG) as the baseline framework, the model introduces a shrinkage (SR) mechanism into the time-domain branch to suppress interference from low signal-to-noise ratio EEG signals. A multi-scale wavelet convolution (MS-Conv) module is constructed to extract multi-scale spectral features, and time-frequency features are fused to form joint representations for prognostic classification. Experiments were conducted on the PhysioNet 2023 dataset. Under the 18-channel setting, the model achieved an accuracy of 81.7%, an F1 score of 86.1%, and an AUC of 0.847. Under the 4-channel setting, the accuracy reached 81.2%, the F1 score reached 86.7%, and the AUC reached 0.877, with overall performance outperforming various mainstream deep learning algorithms. The proposed model enables neurological outcome prediction for patients after cardiac arrest and maintains stable and excellent classification performance with fewer EEG acquisition channels.