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.

The objective of this study was to determine whether the circadian rhythm of heart rate or step count using wearable devices was related to that of the salivary cortisol levels and to test the possibility that the data from wearable devices could be used as an indicator of circadian rhythm misalignment, which is emerging as a cause of insomnia and mood disorders. Methods: The heart rate and step count were continuously measured in 12 healthy young adults using wearable wrist devices for 5 days, and saliva was sampled every 4 hours, excluding sleeping time, for a total of 48 hours to measure the circadian rhythm of salivary cortisol concentration. Cortisol concentrations were assessed using the enzyme-linked immunosorbent assay. The cosinor analysis for the three measurements, salivary cortisol concentrations, heart rate, and step count, was used to estimate the circadian rhythm. Results: The mean values of the acrophase of the cosine-fitted curve of cortisol, heart rate, and step count were 9.06, 15.84, and 19.09, respectively, while those of the amplitude were 7.70, 12.60, and 10.68, respectively. In addition, the mean values of the mesor of the cosine-fitted curve for cortisol, heart rate, and step count were 17.19, 73.55, and 45.45, respectively, and those of robustness were 0.82, 0.56, and 0.18, respectively. There was a possible positive correlation between the acrophase of the cosine-fitted curve of salivary cortisol and that of heart rate (r=0.55, p=0.064). However, there was no correlation between the acrophase of the cosine-fitted curve of salivary cortisol and that of step count (r=-0.2, p=0.533). Conclusion: The findings suggest that the heart rate measured using the wearable activity tracker was a relatively reliable biomarker of circadian rhythm.

No abstract

Background and PurposeWandering is one of the most common behavioral and psychological symptoms of dementia, and associated with some of the adverse outcomes in dementia, such as getting lost or even death. The etiology of wandering is not yet clearly known. As depression and wandering are both very common among the patients with dementia, this study examined the relationship between the depression and wandering among the community dwelling patients with dementia.MethodsFifty community dwelling patients diagnosed with dementia were included in this study if they had primary family caregiver, older than age 18 in Seoul, South Korea. The Geriatric Depression Scale, Korean Version (GDS-K), Korean Version of the Mini-Mental State Examination (K-MMSE) and Korean Version of Revised Algase Wandering Scale-Community Version (K-RAWS-CV) were used to measure the severity of depression, cognitive function and wandering.ResultsThirty percents of the patients showed wandering. Mean score of GDS-K was significantly higher in wanderers than non-wanderers. Severity of depression was significantly correlated with the total score of K-RAWS-CV and subscales of persistent walking, repetitive walking, eloping behavior, and mealtime impulsivity in whole sample. K-MMSE score also was related to wandering behavior. The prevalence odds ratio for wandering in depressed patients compared with undepressed group was 8.386 (95% confidence interval: 1.978–35.561).ConclusionsThis study implicates that not only cognitive impairment but also psychosocial aspects should be considered in wandering patients with dementia and suggests assessing the depression in patients would be helpful in identifying the causes of wandering.

BACKGROUND Methylphenidate, a stimulant used to treat attention deficit hyperactivity disorder (ADHD), has the potential for nonmedical uses such as study and recreation. In the era of active use of social networking services (SNSs), experience with the nonmedical use or side effects of methylphenidate might be shared on Twitter. OBJECTIVE To analyze monthly tweets about methylphenidate, its nonmedical use and side effects, and user sentiments about methylphenidate. METHODS Tweets mentioning methylphenidate from August 2018 to July 2019 were collected using search terms for methylphenidate and its brand names. Only tweets written in English were included. The monthly number of tweets about methylphenidate and the number of tweets containing keywords related to the nonmedical use and side effects of methylphenidate were analyzed. Precision was calculated as the number of true nonmedical use or side effects divided by the number of tweets containing each keywords. Sentiment analysis was conducted using the text and emoji in tweets, and tweets were categorized as very negative (less than -3), negative (-3 to -1), neutral (0), positive (1 to 3), or very positive (more than 3), depending on the sentiment score. RESULTS A total of 4,169 tweets were ultimately selected for analysis. The number of tweets per month was lowest in August (n=264) and highest in May (n=435). There were 292 (7.0%) tweets about nonmedical uses of methylphenidate. Among those, 200 (4.8%) described use for studying, and 15 (0.4%) described use for recreation. In 91 (2.2%) tweets, snorting methylphenidate was mentioned. Side effects of methylphenidate, mainly poor appetite (n=74, 1.8%) and insomnia (n=54, 1.3%), were reported in 316 (7.6%) tweets. The average sentiment score was 0.027 ± 1.475, and neutral tweets were the most abundant (n=1,593, 38.2%). CONCLUSIONS Tweets about methylphenidate were most abundant in May, mentioned nonmedical use for study or recreation, and contained information about side effects. Analysis of Twitter has the advantage of saving the cost and time needed to conduct a survey, and could help identify nonmedical uses and side effects of drugs.