METHODS: The most important climatic factors that contribute to dengue outbreaks were identified in the current work. Correlation analyses were performed in order to determine these factors and these factors were used as input parameters for machine learning models. Top five machine learning classification models (Bayes network (BN) models, support vector machine (SVM), RBF tree, decision table and naive Bayes) were chosen based on past research. The models were then tested and evaluated on the basis of 4-year data (January 2010 to December 2013) collected in Malaysia.
RESULTS: This research has two major contributions. A new risk factor, called the TempeRain factor (TRF), was identified and used as an input parameter for the model of dengue outbreak prediction. Moreover, TRF was applied to demonstrate its strong impact on dengue outbreaks. Experimental results showed that the Bayes Network model with the new meteorological risk factor identified in this study increased accuracy to 92.35% for predicting dengue outbreaks.
CONCLUSIONS: This research explored the factors used in dengue outbreak prediction systems. The major contribution of this study is identifying new significant factors that contribute to dengue outbreak prediction. From the evaluation result, we obtained a significant improvement in the accuracy of a machine learning model for dengue outbreak prediction.
METHODS: A retrospective review of all cases of computed tomography-confirmed acute diverticulitis from November 2015 to April 2018 was performed. Data collated included basic demographics, computed tomography scan results (uncomplicated versus complicated diverticulitis), treatment modality (conservative versus intervention), outcomes and follow-up colonoscopy results within 12 months of presentation. The patients were divided into no adenoma (A) and adenoma (B) groups. Visceral fat area (VFA), subcutaneous fat area (SFA) and VFA/SFA ratio (V/S) were measured at L4/L5 level. Statistical analysis was performed to evaluation the association of VFA, SFA, V/S and different thresholds with the risk of adenoma formation.
RESULTS: A total of 169 patients were included in this study (A:B = 123:46). The mean ± standard deviation for VFA was higher in group B (201 ± 87 cm2 versus 176 ± 79 cm2 ) with a trend towards statistical significance (P = 0.08). There was no difference in SFA and V/S in both groups. When the VFA >200 cm2 was analysed, it was associated with a threefold risk of adenoma formation (odds ratio 2.7, 95% confidence interval 1.35-5.50, P = 0.006). Subgroup analysis of gender with VFA, SFA and V/S found that males have a significantly higher VFA in group B (220.0 ± 95.2 cm2 versus 187.3 ± 69.2 cm2 ; P = 0.05).
CONCLUSIONS: The radiological measurement of visceral adiposity is a useful tool for opportunistic assessment of risk of colorectal adenoma.
METHODS: Scopus, PubMed, and Wiley Online Libraries were searched up to the date November 24, 2019. Two reviewers were requested to independently extract study characteristics and to assess the bias and applicability risks with reference to the study inclusion criteria. Meta-analyses were performed to specify the relationship between dietary intake and the risk of ovarian cancer identifying 97 cohort studies.
RESULTS: No significant association was found between dietary intake and risk of ovarian cancer. The results of subgroup analyses indicated that green leafy vegetables (RR = 0.91, 95%, 0.85-0.98), allium vegetables (RR = 0.79, 95% CI 0.64-0.96), fiber (RR = 0.89, 95% CI 0.81-0.98), flavonoids (RR = 0.83, 95% CI 0.78-0.89) and green tea (RR = 0.61, 95% CI 0.49-0.76) intake could significantly reduce ovarian cancer risk. Total fat (RR = 1.10, 95% CI 1.02-1.18), saturated fat (RR = 1.11, 95% CI 1.01-1.22), saturated fatty acid (RR = 1.19, 95% CI 1.04-1.36), cholesterol (RR = 1.13, 95% CI 1.04-1.22) and retinol (RR = 1.14, 95% CI 1.00-1.30) intake could significantly increase ovarian cancer risk. In addition, acrylamide, nitrate, water disinfectants and polychlorinated biphenyls were significantly associated with an increased risk of ovarian cancer.
CONCLUSION: These results could support recommendations to green leafy vegetables, allium vegetables, fiber, flavonoids and green tea intake for ovarian cancer prevention.