Missing data are a universal data quality problem in many domains, leading to misleading analysis and inaccurate decisions. Much research has been done to investigate the different mechanisms of missing data and the proper techniques in handling various data types. In the last decade, machine learning has been utilized to replace conventional methods to address the problem of missing values more efficiently. By studying and analyzing recently proposed methods using machine learning approaches, vital adoptions in accuracy, performance, and time consumed can be highlighted. This study aimed to help data analysts and researchers address the limitations of machine learning imputation methods by conducting a systematic literature review to provide a comprehensive overview of using such methods to impute missing values. Novel proposed machine learning approaches used for data imputation are analyzed and summarized to assist researchers in selecting a proper machine learning method based on several factors and settings. The review was performed on research studies published between 2016 and 2021 on adopting machine learning to impute missing values, focusing on their strengths and limitations. A total of 684 research articles from various scientific databases were analyzed using search engines, and 94 of them were selected as primary studies. Finally, several recommendations were given to guide future researchers in applying machine learning to impute missing values.

The beneficial effects of a vegetarian diet on blood pressure (BP) control have been reported in previous systematic reviews; however, so far, their relative effectiveness is not well established. Here, we performed a systematic review together with trial sequential analysis to determine the effect of a vegetarian diet on the reduction of blood pressure. We searched the randomized controlled trial (RCT) through Medline, PubMed and Cochrane Central Register. Fifteen eligible RCTs with 856 subjects were entered into the analysis. The pooled results demonstrated that vegetarian diet consumption significantly lowered the systolic blood pressure (weighted mean difference (WMD), −2.66 mmHg (95% confidence interval (CI) = −3.76, −1.55, p < 0.001) and diastolic BP was WMD, −1.69 95% CI = −2.97, −0.41, p < 0.001) as compared to an omnivorous diet. In subgroup analysis, a vegan diet demonstrated a greater reduction in systolic BP (WMD, −3.12 mmHg; 95% CI = −4.54, −1.70, p < 0.001) as compared with a lacto-ovo-vegetarian diet (WMD, −1.75 mmHg, 95% CI −5.38, 1.88, p = 0.05). The vegan diet has showed a similar trend in terms of diastolic blood pressure reduction (WMD, −1.92 mmHg (95% CI = −3.18, −0.66, p < 0.001) but those with a lacto-ovo-vegetarian diet showed no changes in diastolic BP reduction (WMD, 0.00, 95% CI = 0.00, 0.00), p = 0.432). In conclusion, vegetarian diets are associated with significant reductions in BP compared with omnivorous diets, suggesting that they may play a key role in the primary prevention and overall management of hypertension.

Previous literature has reported that patients with diabetes in pregnancy (DIP) are at risk of developing antepartum depression but the results have been inconsistent in cohort studies. We conducted a systematic review and performed a meta-analysis to quantify the association between DIP and risk of antepartum depression in cohort studies. Medline, Cinahl, and PubMed databases were searched for studies investigating DIP involving pregnant women with pre-existing diabetes and gestational diabetes mellitus and their risk of antepartum depression that were published in journals from inception to 27 December 2019. We derived the summary estimates using a random-effects model and reported the findings as pooled relative risks (RR) and confidence interval (CI). Publication bias was assessed using a funnel plot and was quantified by Egger and Begg’s tests. Ten studies, involving 71,036 pregnant women were included in this meta-analysis. The pooled RR to develop antepartum depression was (RR = 1.430, 95% CI: 1.251–1.636) among women with gestational diabetes mellitus. Combining pregnant women with pre-existing diabetes mellitus and gestational diabetes mellitus, they had a significant increased risk of developing antepartum depression (RR = 1.431, 95% CI: 1.205–1.699) compared with those without it. In comparison, we found no association between pre-existing diabetes mellitus in pregnancy (RR = 1.300, 95% CI: 0.736–2.297) and the risk of developing antepartum depression. This study has a few limitations: first, different questionnaire and cut-off points were used in evaluation of depression across the studies. Second, there was a lack of data on history of depression prior to pregnancy, which lead to confounding bias that could not be solved by this meta-analysis. Third, data were dominated by studies in Western countries; this is due to the studies from Eastern countries failing to meet our inclusion criteria for statistical analysis. Women with gestational diabetes mellitus have an increased risk of developing antepartum depression compared to those without the disease. Therefore, more attention on the mental health status should be given on pregnant women diagnosed with pre-existing diabetes mellitus and gestational diabetes mellitus.

The protective effects of probiotic supplementation against radiation-induced diarrhea (RID) have been reported in previous systematic reviews; however so far, only non-conclusive results have been obtained. The objective of this study was to systematically update and evaluate the available evidence for probiotic supplementation. The protocol of this systematic review has been registered (CRD42018106059) with the International Prospective Register of Systematic Reviews (PROSPERO). The primary efficacy outcome was the incidence of RID. Secondary outcomes were the incidence of watery stool, soft stool, and antidiarrheal medication use. There were eight trials, and a total of 1116 participants were included in the primary analysis. Compared with placebo, probiotics were associated with a lower risk of RID [risk ratio (RR) = 0.62, 95% CI = 0.46, 0.83]. A requisite heterogeneity-adjusted trial sequential analysis indicated conclusive evidence for this beneficial effect. No statistically significant reduction in RID (RR = 0.52, 95% CI = 0.14, 1.91) was observed on subgroup analysis in patients receiving both radiation therapy and chemotherapy. However, those patients receiving only radiation therapy (RT) demonstrated significant benefit (RR = 0.61, 95% CI = 0.48, 0.78). There was a significant difference in the antidiarrheal medication use (RR = 0.54, 95% CI = 0.35, 0.84) observed with the use of probiotics. However, no significant difference was observed for the incidence of soft and watery stool. The use of probiotics is beneficial in preventing RID in patients receiving RT.