APPRAISE-RS: Automated, updated, participatory, and personalized treatment recommender systems based on GRADE methodology.

Purpose: Clinical practice guidelines (CPGs) have become fundamental tools for evidence-based medicine (EBM). However, CPG suffer from several limitations, including obsolescence, lack of applicability to many patients, and limited patient participation. This paper presents APPRAISE-RS, which is a methodology that we developed to overcome these limitations by automating, extending, and iterating the methodology that is most commonly used for building CPGs: the GRADE methodology. Method: APPRAISE-RS relies on updated information from clinical studies and adapts and automates the GRADE methodology to generate treatment recommendations. APPRAISE-RS provides personalized recommendations because they are based on the patient's individual characteristics. Moreover, both patients and clinicians express their personal preferences for treatment outcomes which are considered when making the recommendation (participatory). Rule-based system approaches are used to manage heuristic knowledge. Results: APPRAISE-RS has been implemented for attention deficit hyperactivity disorder (ADHD) and tested experimentally on 28 simulated patients. The resulting recommender system (APPRAISE-RS/TDApp) shows a higher degree of treatment personalization and patient participation than CPGs, while recommending the most frequent interventions in the largest body of evidence in the literature (EBM). Moreover, a comparison of the results with four blinded psychiatrist prescriptions supports the validation of the proposal. Conclusions: APPRAISE-RS is a valid methodology to build recommender systems that manage updated, personalized and participatory recommendations, which, in the case of ADHD includes at least one intervention that is identical or very similar to other drugs prescribed by psychiatrists.

Gender analysis of the frequency and course of depressive disorders and relationship with personality traits in general population: A prospective cohort study.

BACKGROUND: We aimed to determine the prevalence and course of subthreshold depressive symptomatology (sDS) and probable major depressive episode (MDE) and to examine their association with personality traits among men and women. METHODS: A community-based sample aged 35 years or older was examined in two waves (median follow-up of 6.9 years). The Patient Health Questionnaire-9 (PHQ-9) was used to assess sDS and MDE. The 10-item version of the Big Five Inventory was used to assess personality traits. Prevalence was assessed at baseline (n = 5,557) and incidence and persistence-recurrence rates were computed at follow up (n = 3,102). Logistic regression models were adjusted to explore the association of personality traits with prevalence and course of depressive disorders. RESULTS: The prevalence of sDS and MDE was 14.04% (95% CI = 17.04-19.08) and 8.54 (95% CI=7.82-9.31), the incidence was 14.30 per 1,000 person-years (95% CI=12.49-16.31) and 4.34 per 1,000 person-years (95% CI=3.46-5.36), and the persistence-recurrence was 35.04 per 1,000 person-years (95% CI=29.00-41.96) and 28.8 per 1,000 person-years (95% CI=20.49-38.14). The gender gap was higher for MDE. Personality traits were differentially associated with the prevalence and course of depressive disorders between men and women. LIMITATIONS: Because this study used questionnaires to assess depressive disorders and personality traits, information bias could not be ruled out. CONCLUSIONS: The gender gap was higher for the prevalence and course of the probable MDE. There were more personality traits related with the course of the sDS and they had a major role in the course of the probable MDE in women.

Placebo Response and Its Predictors in Attention Deficit Hyperactivity Disorder: A Meta-Analysis and Comparison of Meta-Regression and MetaForest.

BACKGROUND: High placebo response in attention deficit hyperactivity disorder (ADHD) can reduce medication-placebo differences, jeopardizing the development of new medicines. This research aims to (1) determine placebo response in ADHD, (2) compare the accuracy of meta-regression and MetaForest in predicting placebo response, and (3) determine the covariates associated with placebo response. METHODS: A systematic review with meta-analysis of randomized, placebo-controlled clinical trial investigating pharmacological interventions for ADHD was performed. Placebo response was defined as the change from baseline in ADHD symptom severity assessed according to the 18-item, clinician-rated, DSM-based rating scale. The effect of study design-, intervention-, and patient-related covariates in predicting placebo response was studied by means of meta-regression and MetaForest. RESULTS: Ninety-four studies including 6614 patients randomized to placebo were analyzed. Overall, placebo response was -8.9 points, representing a 23.1% reduction in the severity of ADHD symptoms. Cross-validated accuracy metrics for meta-regression were R2 = 0.0012 and root mean squared error = 3.3219 for meta-regression and 0.0382 and 3.2599 for MetaForest. Placebo response among ADHD patients increased by 63% between 2001 and 2020 and was larger in the United States than in other regions of the world. CONCLUSIONS: Strong placebo response was found in ADHD patients. Both meta-regression and MetaForest showed poor performance in predicting placebo response. ADHD symptom improvement with placebo has markedly increased over the last 2 decades and is greater in the United States than the rest of the world.

Relationship Between Treatment Duration and Efficacy of Pharmacological Treatment for ADHD: A Meta-Analysis and Meta-Regression of 87 Randomized Controlled Clinical Trials.

Objective: To determine the relationship between treatment duration and the efficacy of pharmacological treatment for reducing ADHD symptoms. Method: We conducted a systematic review of randomized, double-blind, placebo-controlled clinical trials investigating the efficacy of pharmacological interventions in patients with ADHD. The last bibliographic search was performed in April 15, 2019. The effect of treatment duration on efficacy was studied using meta-regression. Results: A total of 87 studies lasting from 3 to 28 weeks were included. Pharmacological treatment improved ADHD symptom severity by -7.35 points. Treatment duration did not moderate the efficacy of pharmacological treatment. Consistent results were found for psychostimulant drugs, methylphenidate, amphetamine derivatives, atomoxetine, and α2-agonists. A negative correlation was found between baseline ADHD severity efficacy (Coefficient = -.250, p = .013). Conclusion: The efficacy of pharmacological treatment for ADHD remains stable over time. A greater efficacy in more severe patients is suggested.

Diagnosing comorbid psychiatric disorders in substance abusers: validity of the Spanish versions of the Psychiatric Research Interview for Substance and Mental Disorders and the Structured Clinical Interview for DSM-IV.

OBJECTIVE: The authors' goal was to assess the validity of DSM-IV diagnoses obtained with the Spanish versions of the Psychiatric Research Interview for Substance and Mental Disorders (PRISM) and the Structured Clinical Interview for DSM-IV (SCID) compared with the longitudinal, expert, all data (LEAD) procedure in a group of substance abusers. METHOD: A total of 105 substance abusers recruited at a drug abuse treatment center in Barcelona, Spain, were assessed. The PRISM and SCID were administered blindly by independent research interviewers. LEAD diagnoses were made by two senior psychiatrists who were blind to PRISM and SCID diagnoses. The kappa statistic was used to measure concordance between the LEAD procedure and the PRISM and SCID. RESULTS: Affective and anxiety disorders were diagnosed more frequently by the PRISM and SCID than by the LEAD procedure. Use of the PRISM resulted in more diagnoses of substance-induced depression, and use of the SCID resulted in more diagnoses of primary major depression than the LEAD procedure. Kappas between the LEAD procedure and the PRISM in current major depression, past substance-induced depression, and borderline personality disorder were better than those obtained between the LEAD procedure and the SCID. The concordance among the three methods for diagnoses of current dependence disorders was good or excellent for alcohol, anxiolytic, cocaine, and heroin dependence and fair for cannabis dependence. Abuse diagnoses showed poor concordance. CONCLUSIONS: Using the LEAD procedure as a "gold standard," the authors conclude that the Spanish version of the PRISM seems to be a better instrument than the Spanish version of the SCID for diagnosing major depression and borderline personality disorders in substance abusers.