The exponential increase in published articles makes a thorough and expedient review of literature increasingly challenging. This review delineated automated tools and platforms that employ artificial intelligence (AI) approaches and evaluated the reported benefits and challenges in using such methods. A search was conducted in 4 databases (Medline, Embase, CDSR, and Epistemonikos) up to April 2021 for systematic reviews and other related reviews implementing AI methods. To be included, the review must use any form of AI method, including machine learning, deep learning, neural network, or any other applications used to enable the full or semi-autonomous performance of one or more stages in the development of evidence synthesis. Twelve reviews were included, using nine different tools to implement 15 different AI methods. Eleven methods were used in the screening stages of the review (73%). The rest were divided: two in data extraction (13%) and two in risk of bias assessment (13%). The ambiguous benefits of the data extractions, combined with the reported advantages from 10 reviews, indicating that AI platforms have taken hold with varying success in evidence synthesis. However, the results are qualified by the reliance on the self-reporting of the review authors. Extensive human validation still appears required at this stage in implementing AI methods, though further evaluation is required to define the overall contribution of such platforms in enhancing efficiency and quality in evidence synthesis.

Background Systematic reviews and meta-analyses of randomized clinical trials (RCTs) have reported the benefits of ketogenic diets (KD) in various participants such as patients with epilepsy and adults with overweight or obesity. Nevertheless, there has been little synthesis of the strength and quality of this evidence in aggregate. Methods To grade the evidence from published meta-analyses of RCTs that assessed the association of KD, ketogenic low-carbohydrate high-fat diet (K-LCHF), and very low-calorie KD (VLCKD) with health outcomes, PubMed, EMBASE, Epistemonikos, and Cochrane database of systematic reviews were searched up to February 15, 2023. Meta-analyses of RCTs of KD were included. Meta-analyses were re-performed using a random-effects model. The quality of evidence per association provided in meta-analyses was rated by the GRADE (Grading of Recommendations, Assessment, Development, and Evaluations) criteria as high, moderate, low, and very low. Results We included 17 meta-analyses comprising 68 RCTs (median [interquartile range, IQR] sample size of 42 [20–104] participants and follow-up period of 13 [8–36] weeks) and 115 unique associations. There were 51 statistically significant associations (44%) of which four associations were supported by high-quality evidence (reduced triglyceride (n = 2), seizure frequency (n = 1) and increased low-density lipoprotein cholesterol (LDL-C) (n = 1)) and four associations supported by moderate-quality evidence (decrease in body weight, respiratory exchange ratio (RER), hemoglobin A1c, and increased total cholesterol). The remaining associations were supported by very low (26 associations) to low (17 associations) quality evidence. In overweight or obese adults, VLCKD was significantly associated with improvement in anthropometric and cardiometabolic outcomes without worsening muscle mass, LDL-C, and total cholesterol. K-LCHF was associated with reduced body weight and body fat percentage, but also reduced muscle mass in healthy participants. Conclusions This umbrella review found beneficial associations of KD supported by moderate to high-quality evidence on seizure and several cardiometabolic parameters. However, KD was associated with a clinically meaningful increase in LDL-C. Clinical trials with long-term follow-up are warranted to investigate whether the short-term effects of KD will translate to beneficial effects on clinical outcomes such as cardiovascular events and mortality.

No abstract

No abstract