RESUMO
Coronavirus Disease 2019 (COVID-19), instigated by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has hugely impacted global public health. To identify and intervene in critically ill patients early, this paper proposes an efficient, intelligent prediction model based on the machine learning approach, which combines the improved whale optimization algorithm (RRWOA) with the k-nearest neighbor (KNN) classifier. In order to improve the problem that WOA is prone to fall into local optimum, an improved version named RRWOA is proposed based on the random contraction strategy (RCS) and the Rosenbrock method. To verify the capability of the proposed algorithm, RRWOA is tested against nine classical metaheuristics, nine advanced metaheuristics, and seven well-known WOA variants based on 30 IEEE CEC2014 competition functions, respectively. The experimental results in mean, standard deviation, the Friedman test, and the Wilcoxon signed-rank test are considered, proving that RRWOA won first place on 18, 24, and 25 test functions, respectively. In addition, a binary version of the algorithm, called BRRWOA, is developed for feature selection problems. An efficient prediction model based on BRRWOA and KNN classifier is proposed and compared with seven existing binary metaheuristics based on 15 datasets of UCI repositories. The experimental results show that the proposed algorithm obtains the smallest fitness value in eleven datasets and can solve combinatorial optimization problems, indicating that it still performs well in discrete cases. More importantly, the model was compared with five other algorithms on the COVID-19 dataset. The experiment outcomes demonstrate that the model offers a scientific framework to support clinical diagnostic decision-making. Therefore, RRWOA is an effectively improved optimizer with efficient value.
RESUMO
BACKGROUND: This study aimed to assess the survival outcomes among patients with out-of-hospital cardiac arrest (CA) who received cardiopulmonary resuscitation (CPR) in China. METHODS: Relevant studies, published between January 1, 2010 and September 5, 2022, were retrieved from databases, including EMBASE, PubMed, Cochrane Library, the China Biology Medicine disk, China National Knowledge Infrastructure, and Wanfang databases. We included clinical studies in which all patients were diagnosed with CA and underwent out-of-hospital CPR, and the outcome variables were at least one of the following: return of spontaneous circulation (ROSC), survival to admission, survival to hospital discharge, 1-month survival, achieved good neurological outcomes, and 1-year survival. Two investigators independently extracted the study data and assessed its quality using a modified Newcastle-Ottawa Scale tool. The data were pooled using random-effects models. RESULTS: Of the 3620 identified studies, 49 (63,378 patients) were included in the meta-analysis. The pooled ROSC rate was 9.0% (95% confidence interval [CI] 7.5-10.5%, I2 = 97%), the pooled survival to admission rate was 5.0% (95% CI 2.7-8.0%, I2 = 98%), and the pooled survival to discharge rate was 1.8% (95% CI 1.2-2.5%, I2 = 95%). Additionally, the ROSC rate of patients with bystander CPR was significantly higher than that of those without bystander CPR, and the pooled odds ratio (OR) was 7.92 (95% CI 4.32-14.53, I2 = 85%). The ROSC rate of participants who started CPR within 5 min was significantly higher than that of those who started CPR after 5 min, and the pooled OR was 5.92 (95% CI 1.92-18.26, I2 = 85%). The ROSC rate of participants with defibrillation was significantly higher than that of those without defibrillation, and the pooled OR was 8.52 (95% CI 3.72-19.52, I2 = 77%). CONCLUSION: The survival outcomes of out-of-hospital CPR in China are far below the world average. Therefore, the policy of providing automated external defibrillators (AEDs) in public places and strengthening CPR training for healthcare providers and public personnel should be encouraged and disseminated nationwide. Trial registration This study was registered in PROSPERO (CRD42022326165) on 29 April 2022.
