Effectiveness of Psychotherapies and Psychotropic Drugs against Mental Illness/Psychotherapies for eating disorders

Effectiveness of Psychotherapies and Psychotropic Drugs against Mental Illness Psychotherapies for eating disorders Psychotherapies for psychosis Psychotherapies for suicide prevention Loading libraries library(dplyr) library(meta) Part 1: Data At https://docs.metapsy.org/databases/ed-psyctr/ you can download documents in PDF format and data in ZIP format related to a meta-analysis conducted by researchers entitled "Eating Disorders: Cognitive Behavioral Treatment vs. Control." This meta-analysis analyzed 44 clinical trials of cognitive behavioral therapy for eating disorders, comparing treatment and control groups. The CSV dataset contains the Hedges' effect size "g" with its corresponding standard deviation for each study, the variable "condition_arm1," which contains the type of psychotherapy used in the study (in this case, only cognitive behavioral therapy). The variable "condition_arm2," which contains the type of group the psychotherapy group is compared to: (CAU = Treatment as Usual, WL = Waiting List: Where patients receive no immediate treatment, Oth = Other), and the variable "diagnosis," which can take the following values: bulimia, binge eating disorder, mixed, anorexia nervosa. Loading and viewing the first 6 studies: df <- read.csv("data.csv", sep = ";", dec = ",", stringsAsFactors = FALSE) df %>% select(study,.g,.g_se,condition_arm1,condition_arm2, diagnosis) %>% head() study .g .g_se condition_arm1 condition_arm2 diagnosis Agras, 1989 1.14522945143373 0.407545348701245 cbt wl bulimia Agras, 1995 2.04683970309038 0.427857881472037 cbt wl binge eating disorder Allen, 1999 1.02698177615511 0.480380408810349 cbt wl binge eating disorder Banasiak, 2005 0.744300126430892 0.198185845387966 cbt wl bulimia Barakat, 2023 1.35702153189127 0.263997724158586 cbt wl bulimia Cachelin, 2019 1.15651831938656 0.343007993645662 cbt wl binge eating disorder Part 2: Meta-analysis Calculating Hedges' g We calculate Hedges' g in meta-analyses of studies and perform the Egger test to assess whether there is publication bias due to the fact that studies with positive results and high g are more likely to be published than those with modest or negative results. Since the p-value is <0.05, there is indeed publication bias in the test, so we use Duval and Tweedie's "trim and fill" procedure, which estimates the number of missing studies and recalculates g, obtaining g = 0.52 with a 95% confidence interval: [ 0.31 , 0.72 ] so in this case the effect on eating disorders is medium: df_eff <- df %>% filter(!is.na(.g), !is.na(.g_se)) meta_eff <- metagen( TE = .g, seTE = .g_se, studlab = study, data = df_eff, sm = "SMD", method.tau = "REML", # random effects method.random.ci = "HK" # Hartung-Knapp ) # Test Egger for publication bias metabias(meta_eff, method.stat = "linreg") Linear regression test of funnel plot asymmetry Test result: t = 3.25, df = 42, p-value = 0.0023 Bias estimate: 2.6445 (SE = 0.8147) Details: - multiplicative residual heterogeneity variance (tau^2 = 3.1554) - predictor: standard error - weight: inverse variance - reference: Egger et al. (1997), BMJ m_g<- trimfill(meta_eff) print(paste("g =",round(m_g$TE.random,2),"; 95%CI: [",round(m_g$lower.random,2),",",round(m_g$upper.random,2),"]")) "g = 0.52; 95%CI: [ 0.31, 0.72 ]" Measuring g for the various diagnoses, we find that cognitive behavioral therapy has the highest g (g = -0.97) for bulimia, binge eating disorder (g = 0.89), etc. , so the effect on eating disorders, barring publication bias, is high, although g is low on anorexia nervosa: for (p in unique(df_eff$diagnosis)) { df_post <- df_eff %>% filter( diagnosis==p) m_pst<-metagen(TE = .g, seTE = .g_se, data = df_post, studlab = study, sm = "SMD", random = TRUE, method.random.ci = "HK" ) print(paste(p,": g=",round(m_pst$TE.random,2),"; 95%CI: [",round(m_pst$lower.random,2),",",round(m_pst$upper.random,2),"]")) } [1] "bulimia: g= 0.97; 95%CI: [ 0.61 , 1.33 ]" [1] "binge eating disorder: g= 0.89; 95%CI: [ 0.67 , 1.1 ]" [1] "mixed: g= 0.73; 95%CI: [ -0.39 , 1.85 ]" [1] "anorexia nervosa: g= 0.13; 95%CI: [ -0.18 , 0.44 ]"