What do patients learn about psychotropic medications on the web? A natural language processing study

Web Search Query Volume Correlates With Prescription Volumes of Antidepressants and Antipsychotics in the Netherlands and United Kingdom: An Explorative Study

BACKGROUND

The significant increase in Internet availability has resulted in a rise in search queries on health-related topics. Previous research has demonstrated the potential for analyzing web search query volume for nonpsychotropic prescription drugs, while studies on psychotropic drugs remain scarce. The aims of this study were to expand upon this scarce knowledge by investigating the relationship between web search query volumes and prescription volumes of antidepressants and antipsychotics in the United Kingdom and the Netherlands and to gain insight in topics of concern, such as withdrawal symptoms and discontinuation.

METHODS

Data were obtained for the United Kingdom and the Netherlands from January 2010 until January 2021. Prescription volume data for 5 antidepressants (paroxetine, fluoxetine, sertraline, citalopram, venlafaxine) and 5 antipsychotics (quetiapine, olanzapine, clozapine, aripiprazole, and risperidone) were obtained. Web search query volumes and data on related search queries of these substances were acquired from Google Trends. Descriptive statistics and Pearson correlation analyses were performed.

RESULTS

A strong, positive, and statistically significant correlation between web search query volume and prescription volume was observed for most included substances in both the Netherlands and the United Kingdom. The search queries related to the included antidepressants and antipsychotics indicate important topics of concern for specific substances, such as withdrawal symptoms and discontinuation.

CONCLUSIONS

Web search data from Google Trends could potentially be used as a proxy for prescribing trends of antidepressants and antipsychotics and to gain insight in topics of concern of users of these substances. These findings highlight the importance of providing reliable patient information, particularly regarding adverse effects, withdrawal, and discontinuation.

Maternal LiCl exposure disrupts thyroid-cerebral axis in neonatal albino rats

This work aimed to elucidate whether maternal lithium chloride (LiCl) exposure disturbs the thyroid-cerebral axis in neonatal albino rats. 50 mg of LiCl/kg b.wt. is orally given for pregnant Wistar rats from gestational day (GD) 1 to lactation day (LD) 28. The maternal administration of LiCl induced follicular dilatation and degeneration, hyperplasia, lumen obliteration and colloid vacuolation in the maternal and neonatal thyroid gland at postnatal days (PNDs) 14, 21 and 28. Neuronal degeneration (spongiform), gliosis, nuclear pyknosis, perivascular oedema, and meningeal hyperaemia were observed in the neonatal cerebral cortex of the maternal LiCl-treated group at examined PNDs. This disturbance appears to depend on intensification in the neonatal cerebral malondialdehyde (MDA), nitric oxide (NO), and hydrogen peroxide (H₂ O₂ ) levels, and attenuation in the glutathione (GSH), total thiol (t-SH), catalase (CAT), and superoxide dismutase (SOD) levels. In the neonatal cerebrum, the fold change in the relative mRNA expression of deiodinases (DII and DIII) increased significantly at PNDs 21 and 14, respectively, in the maternal LiCl-treated group. These data suggest that maternal LiCl may perturb the thyroid-cerebrum axis generating neonatal neurodevelopmental disorder.

Machine Learning and Natural Language Processing in Mental Health: Systematic Review

BACKGROUND

Machine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing (NLP), by using corpora and learning approaches, provides good performance in statistical tasks, such as text classification or sentiment mining.

OBJECTIVE

The primary aim of this systematic review was to summarize and characterize, in methodological and technical terms, studies that used machine learning and NLP techniques for mental health. The secondary aim was to consider the potential use of these methods in mental health clinical practice.

METHODS

This systematic review follows the PRISMA (Preferred Reporting Items for Systematic Review and Meta-analysis) guidelines and is registered with PROSPERO (Prospective Register of Systematic Reviews; number CRD42019107376). The search was conducted using 4 medical databases (PubMed, Scopus, ScienceDirect, and PsycINFO) with the following keywords: machine learning, data mining, psychiatry, mental health, and mental disorder. The exclusion criteria were as follows: languages other than English, anonymization process, case studies, conference papers, and reviews. No limitations on publication dates were imposed.

RESULTS

A total of 327 articles were identified, of which 269 (82.3%) were excluded and 58 (17.7%) were included in the review. The results were organized through a qualitative perspective. Although studies had heterogeneous topics and methods, some themes emerged. Population studies could be grouped into 3 categories: patients included in medical databases, patients who came to the emergency room, and social media users. The main objectives were to extract symptoms, classify severity of illness, compare therapy effectiveness, provide psychopathological clues, and challenge the current nosography. Medical records and social media were the 2 major data sources. With regard to the methods used, preprocessing used the standard methods of NLP and unique identifier extraction dedicated to medical texts. Efficient classifiers were preferred rather than transparent functioning classifiers. Python was the most frequently used platform.

CONCLUSIONS

Machine learning and NLP models have been highly topical issues in medicine in recent years and may be considered a new paradigm in medical research. However, these processes tend to confirm clinical hypotheses rather than developing entirely new information, and only one major category of the population (ie, social media users) is an imprecise cohort. Moreover, some language-specific features can improve the performance of NLP methods, and their extension to other languages should be more closely investigated. However, machine learning and NLP techniques provide useful information from unexplored data (ie, patients' daily habits that are usually inaccessible to care providers). Before considering It as an additional tool of mental health care, ethical issues remain and should be discussed in a timely manner. Machine learning and NLP methods may offer multiple perspectives in mental health research but should also be considered as tools to support clinical practice.

Sentiment Analysis of Online Reviews for Selective Serotonin Reuptake Inhibitors and Serotonin-Norepinephrine Reuptake Inhibitors

BACKGROUND

Depression affects millions worldwide, with drug therapy being the mainstay treatment. A variety of factors, including personal reviews, are involved in the success or failure of medication therapy. This study looked to characterize the sentiment of online medication reviews of Selective Serotonin Reuptake Inhibitors (SSRIs) and Serotonin-Norepinephrine Reuptake Inhibitor (SNRIs) used to treat depression.

METHODS

The publicly available data source used was the Drug Review Dataset from the University of California Irvine Machine Learning Repository. The dataset contained the following variables: ID, drug name, condition, review, rating, date, and usefulness count. This study utilized a sentiment analysis of free-text, online reviews via the sentimentr package. A Mann-Whitney U test was used for comparisons.

RESULTS

The average sentiment was higher in SSRIs compared to SNRIs (0.065 vs. 0.005, p < 0.001). The average sentiment was also found to be higher in high-rated reviews than in low-rated reviews (0.169 vs. -0.367, p < 0.001). Ratings were similar in the high-rated SSRI group and high-rated SNRI group (9.19 vs. 9.19).

CONCLUSIONS

This study supports the use of sentiment analysis using the AFINN lexicon, as the lexicon showed a difference in sentiment between high-rated reviews from low-rated reviews. This study also found that SNRIs have more negative sentiment and lower-rated reviews than SSRIs.

Distribution of agitation and related symptoms among hospitalized patients using a scalable natural language processing method

BACKGROUND

Agitation is a common feature of many neuropsychiatric disorders.

OBJECTIVE

Understanding the prevalence, implications, and characteristics of agitation among hospitalized populations can facilitate more precise recognition of disability arising from neuropsychiatric diseases.

METHODS

We developed two agitation phenotypes using an expansion of expert curated term lists. These phenotypes were used to characterize five years of psychiatric admissions. The relationship of agitation symptoms and length of stay was examined.

RESULTS

Among 4548 psychiatric admissions, 1134 (24.9%) included documentation of agitation based on the primary agitation phenotype. These symptoms were greater among individuals with public insurance, and those with mania and psychosis compared to major depressive disorder. Greater symptoms were associated with longer hospital stay, with ~0.9 day increase in stay for every 10% increase in agitation phenotype.

CONCLUSION

Agitation was common at hospital admission and associated with diagnosis and longer length of stay. Characterizing agitation-related symptoms through natural language processing may provide new tools for understanding agitated behaviors and their relationship to delirium.

Maternal lithium chloride exposure alters the neuroendocrine-cytokine axis in neonatal albino rats

The aim of this work was to clarify whether maternal lithium chloride (LiCl) exposure disrupts the neonatal neuroendocrine-cytokine axis. Pregnant Wistar rats were orally administrated 50 mg LiCl/kg b.wt. from gestational day (GD) 1 to postpartum day 28. Maternal administration of LiCl induced a hypothyroid state in both dams and their neonates compared to the control dams and neonates at lactation days (LDs) 14, 21 and 28, where the levels of serum free triiodothyronine (FT3) and free thyroxin (FT4) were decreased and the level of serum thyrotropin (TSH) level was increased. A noticeable depression in maternal body weight gain, neonatal body weight and neonatal serum growth hormone (GH) was observed on all examined postnatal days (PNDs; 14, 21 and 28). A single abortion case was recorded at GD 17, and three dead neonates were noted at birth in the LiCl-treated group. Maternal administration of LiCl disturbed the levels of neonatal serum tumor necrosis factor-alpha (TNF-α), transforming growth factor-beta (TGF-β), interleukin-1 beta (IL-1β), interferon-gamma (INF-γ), leptin, adiponectin and resistin at all tested PNDs compared to the control group. This administration produced a stimulatory action on the level of neonatal cerebral serotonin (5-HT) at PND 14 and on the level of neonatal cerebral norepinephrine (NE) at PNDs 21 and 28. However, this administration produced an inhibitory action on the level of neonatal cerebral dopamine (DA) at all examined PNDs and on the level of neonatal cerebral NE at PND 14 and the level of neonatal cerebral 5-HT at PNDs 21 and 28 compared to the corresponding control group. Thus, maternal LiCl exposure-induced hypothyroidism disrupts the neonatal neuroendocrine-cytokine system, which delay cerebral development.