Background: Social media has become a new source for obtaining real-world data on adverse drug reactions. Many studies have investigated the use of social media to detect early signals of adverse drug reactions. However, the trustworthiness of signals derived from social media is questionable. To confirm this, a confirmatory study with a positive control (eg, new black box warnings, labeling changes, or withdrawals) is required. Objective: This study aimed to evaluate the use of social media in detecting new black box warnings, labeling changes, or withdrawals in advance. Methods: This scoping review adhered to the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews checklist. A researcher searched PubMed and EMBASE in January 2021. Original studies analyzing black box warnings, labeling changes, or withdrawals from social media were selected, and the results of the studies were summarized. Results: A total of 14 studies were included in this scoping review. Most studies (8/14, 57.1%%) collected data from a single source, and 10 (71.4%) used specialized health care social networks and forums. The analytical methods used in these studies varied considerably. Three studies (21.4%) manually annotated posts, while 5 (35.7%) adopted machine learning algorithms. Nine studies (64.2%) concluded that social media could detect signals 3 months to 9 years before action from regulatory authorities. Most of these studies (8/9, 88.9%) were conducted on specialized health care social networks and forums. On the contrary, 5 (35.7%) studies yielded modest or negative results. Of these, 2 (40%) used generic social networking sites, 2 (40%) used specialized health care networks and forums, and 1 (20%) used both generic social networking sites and specialized health care social networks and forums. The most recently published study recommends not using social media for pharmacovigilance. Several challenges remain in using social media for pharmacovigilance regarding coverage, data quality, and analytic processing. Conclusions: Social media, along with conventional pharmacovigilance measures, can be used to detect signals associated with new black box warnings, labeling changes, or withdrawals. Several challenges remain; however, social media will be useful for signal detection of frequently mentioned drugs in specialized health care social networks and forums. Further studies are required to advance natural language processing and mine real-world data on social media.

Very low-carbohydrate diets or ketogenic diets (KDs) have garnered attention for weight loss in patients with overweight or obesity as well as for normal-weight adults, yet the adverse effects of KDs, such as dyslipidemia in normal-weight adults, have not been studied extensively. This meta-analysis aimed to identify the effects of KDs on the lipid profile in normal-weight (body mass index [BMI] < 25 kg/m²) adults from randomized controlled trials. PubMed and Embase databases were searched on November 21, 2021, using search terms representing KDs and lipid profiles. Two researchers independently screened articles according to PICOS inclusion criteria. General study information, dietary data, and lipid profiles were extracted from eligible studies. Risk of bias was assessed using the Cochrane risk of bias 2 tool. Fixed- or random-effects meta-analysis was performed to estimate the effects of KDs on total cholesterol (TC), high-density lipoprotein-cholesterol (HDL-C), low-density lipoprotein-cholesterol (LDL-C), triglycerides, apolipoprotein A (apoA), and apolipoprotein B (apoB), considering heterogeneity across studies. The certainty of evidence was assessed using the GRADE (Grading of Recommendations, Assessment, Development and Evaluation) approach. Three studies were selected for meta-analysis. A KD significantly increased TC by 1.47 mmol/L (95%CI, 0.72–2.22 mmol/L), LDL-C by 1.08 mmol/L (95%CI, 0.37–1.79 mmol/L), and apoB by 0.35 g/L (95%CI, 0.06–0.65 g/L). In addition, a KD significantly increased HDL-C by 0.35 mmol/L (95%CI, 0.27–0.42 mmol/L) and apoA by 0.34 g/L (95%CI, 0.28–0.41 g/L) compared with control diets. Triglyceride levels were not significantly different between KDs and control diets (P = 0.63). This study suggests unfavorable effects of KDs on TC and LDL-C in normal-weight adults. Although an increase in HDL-C can compensate for unfavorable changes in lipids, normal-weight individuals should consider the risk of hypercholesterolemia when consuming a KD. Results for triglycerides were inconsistent.

Background: Methylphenidate, a stimulant used to treat attention deficit hyperactivity disorder, has the potential to be used nonmedically, such as for studying and recreation. In an era when many people actively use social networking services, experience with the nonmedical use or side effects of methylphenidate might be shared on Twitter. Objective: The purpose of this study was to analyze tweets about the nonmedical use and side effects of methylphenidate using a machine learning approach. Methods: A total of 34,293 tweets mentioning methylphenidate from August 2018 to July 2019 were collected using searches for “methylphenidate” and its brand names. Tweets in a randomly selected training dataset (6860/34,293, 20.00%) were annotated as positive or negative for two dependent variables: nonmedical use and side effects. Features such as personal noun, nonmedical use terms, medical use terms, side effect terms, sentiment scores, and the presence of a URL were generated for supervised learning. Using the labeled training dataset and features, support vector machine (SVM) classifiers were built and the performance was evaluated using F1 scores. The classifiers were applied to the test dataset to determine the number of tweets about nonmedical use and side effects. Results: Of the 6860 tweets in the training dataset, 5.19% (356/6860) and 5.52% (379/6860) were about nonmedical use and side effects, respectively. Performance of SVM classifiers for nonmedical use and side effects, expressed as F1 scores, were 0.547 (precision: 0.926, recall: 0.388, and accuracy: 0.967) and 0.733 (precision: 0.920, recall: 0.609, and accuracy: 0.976), respectively. In the test dataset, the SVM classifiers identified 361 tweets (1.32%) about nonmedical use and 519 tweets (1.89%) about side effects. The proportion of tweets about nonmedical use was highest in May 2019 (46/2624, 1.75%) and December 2018 (36/2041, 1.76%). Conclusions: The SVM classifiers that were built in this study were highly precise and accurate and will help to automatically identify the nonmedical use and side effects of methylphenidate using Twitter.

Garlic-related misinformation is prevalent whenever a virus outbreak occurs. With the outbreak of COVID-19, garlic-related misinformation is spreading through social media, including Twitter. Bidirectional Encoder Representations from Transformers (BERT) can be used to classify misinformation from a vast number of tweets. This study aimed to apply the BERT model for classifying misinformation on garlic and COVID-19 on Twitter, using 5929 original tweets mentioning garlic and COVID-19 (4151 for fine-tuning, 1778 for test). Tweets were manually labeled as ‘misinformation’ and ‘other.’ We fine-tuned five BERT models (BERT_BASE, BERT_LARGE, BERTweet-base, BERTweet-COVID-19, and BERTweet-large) using a general COVID-19 rumor dataset or a garlic-specific dataset. Accuracy and F1 score were calculated to evaluate the performance of the models. The BERT models fine-tuned with the COVID-19 rumor dataset showed poor performance, with maximum accuracy of 0.647. BERT models fine-tuned with the garlic-specific dataset showed better performance. BERTweet models achieved accuracy of 0.897–0.911, while BERT_BASE and BERT_LARGE achieved accuracy of 0.887–0.897. BERTweet-large showed the best performance with maximum accuracy of 0.911 and an F1 score of 0.894. Thus, BERT models showed good performance in classifying misinformation. The results of our study will help detect misinformation related to garlic and COVID-19 on Twitter.

Coffee is widely consumed worldwide and impacts glucose metabolism. After a previous meta-analysis that evaluated the effects of coffee consumption on insulin resistance and sensitivity, additional randomized controlled trials (RCTs) were conducted. This meta-analysis aimed to evaluate the effects of coffee consumption on insulin resistance or sensitivity. We selected RCTs that evaluated the effects of coffee consumption for seven days or more on insulin sensitivity or resistance using surrogate indices (homeostasis model assessment for insulin resistance (HOMA-IR) and Matsuda index). The fixed-effects or random-effects model was used according to heterogeneity. Four studies with 268 participants were analyzed in this meta-analysis. Coffee consumption significantly decreased HOMA-IR compared to control (mean difference (MD) = −0.13; 95% CI = −0.24–−0.03; p-value = 0.01). However, the significance was not maintained in the sensitivity analysis (MD = −0.04; 95% CI = −0.18–0.10; p-value = 0.55) after excluding data from the healthy, young, normal-weight group. Matsuda index was not significantly different between coffee and control groups (standardized mean difference (SMD) = −0.33; 95% CI = −0.70–0.03; p-value = 0.08). In conclusion, long-term coffee consumption has a nonsignificant effect on insulin resistance and sensitivity. More studies evaluating the effects of coffee consumption in the healthy, young, and normal-weight individuals are needed.