ABSTRACT
OBJECTIVES: To assess the feasibility of using a natural language processing (NLP) application for extraction of free-text online activity mentions in adolescent mental health patient electronic health records (EHRs). SETTING: The Clinical Records Interactive Search system allows detailed research based on deidentified EHRs from the South London and Maudsley NHS Foundation Trust, a large south London Mental Health Trust providing secondary and tertiary mental healthcare. PARTICIPANTS AND METHODS: We developed a gazetteer of online activity terms and annotation guidelines, from 5480 clinical notes (200 adolescents, aged 11-17 years) receiving specialist mental healthcare. The preprocessing and manual curation steps of this real-world data set allowed development of a rule-based NLP application to automate identification of online activity (internet, social media, online gaming) mentions in EHRs. The context of each mention was also recorded manually as: supportive, detrimental or neutral in a subset of data for additional analysis. RESULTS: The NLP application performed with good precision (0.97) and recall (0.94) for identification of online activity mentions. Preliminary analyses found 34% of online activity mentions were considered to have been documented within a supportive context for the young person, 38% detrimental and 28% neutral. CONCLUSION: Our results provide an important example of a rule-based NLP methodology to accurately identify online activity recording in EHRs, enabling researchers to now investigate associations with a range of adolescent mental health outcomes.
Subject(s)
Electronic Health Records , Mental Health , Humans , Adolescent , Feasibility Studies , Natural Language Processing , LondonABSTRACT
BACKGROUND: Depression and anxiety are major public health concerns among adolescents. Computerized cognitive behavioral therapy (cCBT) has emerged as a potential intervention, but its efficacy in adolescents remains unestablished. OBJECTIVE: This review aimed to systematically review and meta-analyze findings on the efficacy of cCBT for the treatment of adolescent depression and anxiety. METHODS: Embase, PsycINFO, and Ovid MEDLINE were systematically searched for randomized controlled trials in English, which investigated the efficacy of cCBT for reducing self-reported depression or anxiety in adolescents aged 11 to 19 years. Titles, abstracts, and full texts were screened for eligibility by 2 independent researchers (TB and LC). A random-effects meta-analysis was conducted to pool the effects of cCBT on depression and anxiety symptom scores compared with the control groups. Study quality was assessed using the Cochrane Collaboration Risk of Bias tool. RESULTS: A total of 16 randomized controlled trials were eligible for inclusion in this review, of which 13 (81%) were included in the meta-analysis. The quality of the studies was mixed, with 5 (31%) studies rated as good overall, 2 (13%) rated as fair, and 9 (56%) rated as poor. Small but statistically significant effects of cCBT were detected, with cCBT conditions showing lower symptom scores at follow-up compared with control conditions for both anxiety (standardized mean difference -0.21, 95% CI -0.33 to -0.09; I2=36.2%) and depression (standardized mean difference -0.23, 95% CI -0.39 to -0.07; I2=59.5%). Secondary analyses suggested that cCBT may be comparable with alternative, active interventions (such as face-to-face therapy or treatment as usual). CONCLUSIONS: This meta-analysis reinforces the efficacy of cCBT for the treatment of anxiety and depression and is the first to examine this exclusively in adolescents. Future research could aim to identify the active components of these interventions toward optimizing their development and increasing the feasibility and acceptability of cCBT in this age group. TRIAL REGISTRATION: PROSPERO CRD42019141941; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=141941.