Accurate and interpretable gene expression imputation on scRNA-seq data using IGSimpute.

Single-cell ribonucleic acid sequencing (scRNA-seq) enables the quantification of gene expression at the transcriptomic level with single-cell resolution, enhancing our understanding of cellular heterogeneity. However, the excessive missing values present in scRNA-seq data hinder downstream analysis. While numerous imputation methods have been proposed to recover scRNA-seq data, high imputation performance often comes with low or no interpretability. Here, we present IGSimpute, an accurate and interpretable imputation method for recovering missing values in scRNA-seq data with an interpretable instance-wise gene selection layer (GSL). IGSimpute outperforms 12 other state-of-the-art imputation methods on 13 out of 17 datasets from different scRNA-seq technologies with the lowest mean squared error as the chosen benchmark metric. We demonstrate that IGSimpute can give unbiased estimates of the missing values compared to other methods, regardless of whether the average gene expression values are small or large. Clustering results of imputed profiles show that IGSimpute offers statistically significant improvement over other imputation methods. By taking the heart-and-aorta and the limb muscle tissues as examples, we show that IGSimpute can also denoise gene expression profiles by removing outlier entries with unexpectedly high expression values via the instance-wise GSL. We also show that genes selected by the instance-wise GSL could indicate the age of B cells from bladder fat tissue of the Tabula Muris Senis atlas. IGSimpute can impute one million cells using 64 min, and thus applicable to large datasets.

Dimensionality reduction and visualization of single-cell RNA-seq data with an improved deep variational autoencoder.

Single-cell RNA sequencing (scRNA-seq) is a revolutionary breakthrough that determines the precise gene expressions on individual cells and deciphers cell heterogeneity and subpopulations. However, scRNA-seq data are much noisier than traditional high-throughput RNA-seq data because of technical limitations, leading to many scRNA-seq data studies about dimensionality reduction and visualization remaining at the basic data-stacking stage. In this study, we propose an improved variational autoencoder model (termed DREAM) for dimensionality reduction and a visual analysis of scRNA-seq data. Here, DREAM combines the variational autoencoder and Gaussian mixture model for cell type identification, meanwhile explicitly solving 'dropout' events by introducing the zero-inflated layer to obtain the low-dimensional representation that describes the changes in the original scRNA-seq dataset. Benchmarking comparisons across nine scRNA-seq datasets show that DREAM outperforms four state-of-the-art methods on average. Moreover, we prove that DREAM can accurately capture the expression dynamics of human preimplantation embryonic development. DREAM is implemented in Python, freely available via the GitHub website, https://github.com/Crystal-JJ/DREAM.

Continuous Risk Score Predicts Waitlist & Post-Transplant Outcomes in Hepatocellular Carcinoma Despite Exception Changes.

BACKGROUND AND AIMS: Continuous risk stratification of candidates and urgency-based prioritization have been utilized for liver transplantation (LT) in non-hepatocellular carcinoma (HCC) patients in the United States. Instead, for HCC patients, a dichotomous criterion with exception points is still used. This study evaluated the utility of the hazard associated with LT for HCC (HALT-HCC), an oncological continuous risk score, to stratify waitlist dropout and post-LT outcomes. METHODS: A competing risk model was developed and validated using the UNOS database (2012-2021) through multiple policy changes. The primary outcome was to assess the discrimination ability of waitlist dropouts and LT outcomes. The study focused on the HALT-HCC score, compared to other HCC risk scores. RESULTS: Among 23,858 candidates, 14,646 (59.9%) underwent LT and 5,196 (21.8%) dropped out of the waitlist. Higher HALT-HCC scores correlated with increased dropout incidence and lower predicted five-year overall survival after LT. HALT-HCC demonstrated the highest AUC values for predicting dropout at various intervals post-listing (0.68 at six months, 0.66 at one year), with excellent calibration (R2=0.95 at six months, 0.88 at one year). Its accuracy remained stable across policy periods and locoregional therapy applications. CONCLUSIONS: This study highlights the predictive capability of the continuous oncological risk score to forecast waitlist dropout and post-LT outcomes in HCC patients, independent of policy changes. The study advocates integrating continuous scoring systems like HALT-HCC in liver allocation decisions, balancing urgency, organ utility, and survival benefit.

A Bayesian semiparametric approach for inference on the population partly conditional mean from longitudinal data with dropout.

Studies of memory trajectories using longitudinal data often result in highly nonrepresentative samples due to selective study enrollment and attrition. An additional bias comes from practice effects that result in improved or maintained performance due to familiarity with test content or context. These challenges may bias study findings and severely distort the ability to generalize to the target population. In this study, we propose an approach for estimating the finite population mean of a longitudinal outcome conditioning on being alive at a specific time point. We develop a flexible Bayesian semiparametric predictive estimator for population inference when longitudinal auxiliary information is known for the target population. We evaluate the sensitivity of the results to untestable assumptions and further compare our approach to other methods used for population inference in a simulation study. The proposed approach is motivated by 15-year longitudinal data from the Betula longitudinal cohort study. We apply our approach to estimate lifespan trajectories in episodic memory, with the aim to generalize findings to a target population.

Geographical distance predicts psychiatric treatment retention for Hispanic women with comorbid major depression and breast cancer.

PURPOSE: Depression is among the most common comorbid psychiatric disorders of patients with breast cancer. Depression decreases patient quality of life and, if untreated, can adversely affect cancer treatment. We sought to identify treatment barriers for women with breast cancer receiving psychotherapy for depression. Findings may help policy makers and researchers determine funding and design of future studies involving this population, especially in communities with high rates of health disparities. METHODS: We used data from a randomized trial for women with breast cancer and current DSM-IV non-psychotic unipolar major depressive disorder (MDD). Patients were randomly assigned to 12 weeks of one of three psychotherapies and attrition was assessed by whether subjects completed 12 weekly treatment sessions. We used descriptive analyses and logistic regression to identify treatment barriers. R shiny was used to determine study patient residences. RESULTS: Of 134 randomized patients, 84 (62.7%) were Hispanic. Fifty-nine patients (44%) either did not start or dropped out of treatment, 49 (83.1%) of them being Hispanic. Being a Hispanic woman, less educated, and geographically distant from treatment significantly predicted attrition. Single Hispanic mothers had significantly higher attrition risk than married and/or childless women. CONCLUSION: Identifying barriers to treatment is important to improve treatment adherence for patients with concurrent diagnoses of breast cancer and MDD, especially for traditionally underserved minorities. Additional support such as affordable tele-medicine, multi-language assistance, financial aid for transportation and child-care, and allocation of more funds to address some identified barriers deserve consideration to improve treatment adherence and outcomes.

Are dropout imputation methods for scRNA-seq effective for scATAC-seq data?

The tremendous progress of single-cell sequencing technology has given researchers the opportunity to study cell development and differentiation processes at single-cell resolution. Assay of Transposase-Accessible Chromatin by deep sequencing (ATAC-seq) was proposed for genome-wide analysis of chromatin accessibility. Due to technical limitations or other reasons, dropout events are almost a common occurrence for extremely sparse single-cell ATAC-seq data, leading to confusion in downstream analysis (such as clustering). Although considerable progress has been made in the estimation of scRNA-seq data, there is currently no specific method for the inference of dropout events in single-cell ATAC-seq data. In this paper, we select several state-of-the-art scRNA-seq imputation methods (including MAGIC, SAVER, scImpute, deepImpute, PRIME, bayNorm and knn-smoothing) in recent years to infer dropout peaks in scATAC-seq data, and perform a systematic evaluation of these methods through several downstream analyses. Specifically, we benchmarked these methods in terms of correlation with meta-cell, clustering, subpopulations distance analysis, imputation performance for corruption datasets, identification of TF motifs and computation time. The experimental results indicated that most of the imputed peaks increased the correlation with the reference meta-cell, while the performance of different methods on different datasets varied greatly in different downstream analyses, thus should be used with caution. In general, MAGIC performed better than the other methods most consistently across all assessments. Our source code is freely available at https://github.com/yueyueliu/scATAC-master.

The neglected emotional drawbacks of the prioritization of embryos to transfer.

In recent years, increasing efforts have been made to develop advanced techniques that could predict the potential of implantation of each single embryo and prioritize the transfer of those at higher chance. The most promising include non-invasive preimplantation genetic testing for aneuploidy and artificial intelligence-based algorithms using time lapse images. The psychological effect of these add-ons is neglected. One could speculate that embarking on another transfer after one or more failures with the prospect of receiving an embryo of lower potential may be distressing for the couple. In addition, the symbolic and mental representation of an embryo with 'lower capacity to implant' is currently unknown but could affect couples' choices and wellbeing. These emotional responses may also undermine adherence to the programme and, ultimately, its real effectiveness. Future trials aimed at evaluating the validity of prioritization procedures must also consider the emotional burden on the couples.

A Bayesian convolutional neural network-based generalized linear model.

Convolutional neural networks (CNNs) provide flexible function approximations for a wide variety of applications when the input variables are in the form of images or spatial data. Although CNNs often outperform traditional statistical models in prediction accuracy, statistical inference, such as estimating the effects of covariates and quantifying the prediction uncertainty, is not trivial due to the highly complicated model structure and overparameterization. To address this challenge, we propose a new Bayesian approach by embedding CNNs within the generalized linear models (GLMs) framework. We use extracted nodes from the last hidden layer of CNN with Monte Carlo (MC) dropout as informative covariates in GLM. This improves accuracy in prediction and regression coefficient inference, allowing for the interpretation of coefficients and uncertainty quantification. By fitting ensemble GLMs across multiple realizations from MC dropout, we can account for uncertainties in extracting the features. We apply our methods to biological and epidemiological problems, which have both high-dimensional correlated inputs and vector covariates. Specifically, we consider malaria incidence data, brain tumor image data, and fMRI data. By extracting information from correlated inputs, the proposed method can provide an interpretable Bayesian analysis. The algorithm can be broadly applicable to image regressions or correlated data analysis by enabling accurate Bayesian inference quickly.

Adherence to Online Interventions for Family Caregivers of People With Dementia: A Meta-Analysis and Systematic Review.

OBJECTIVE: Online interventions hold promise in supporting the well-being of family caregivers and enhancing the quality of care they provide for individuals with long-term or chronic conditions. However, dropout rates from support programs among specific groups of caregivers, such as caregivers of people with dementia, pose a challenge. Focused reviews are needed to provide more accurate insights and estimates in this specific research area. METHODS: A meta-analysis of dropout rates from available online interventions for family caregivers of people with dementia was conducted to assess treatment acceptability. A systematic search yielded 18 studies involving 1,215 caregivers. RESULTS: The overall pooled dropout rate was 18.4%, with notable heterogeneity indicating varied intervention adherence. Interventions incorporating human contact, interactive features, and personalization strategies for specific types and stages of dementia predicted significantly lower dropout rates. Methodological assessment revealed variability in study quality. CONCLUSION: Findings support the effectiveness of social support, personalization strategies, and co-design in enhancing intervention adherence among dementia family caregivers. Further research is needed to explore factors influencing dropout rates and conduct robust trials to refine the implementation of future interventions.

School-based physical activity interventions: which intervention characteristics are associated with participation and retention? A meta-analysis.

OBJECTIVE: Many school-based intervention studies are conducted to increase students' physical activity (PA). Recruitment and retention problems potentially impact the robustness of RCT findings. We conducted a meta-analysis to summarize recruitment and retention rates in long-term secondary school-based PA intervention studies and examined associated participant and intervention characteristics. METHODS: Web of Science, Pubmed, Medline, and PsychInfo were searched until March 20th 2023. We included studies on secondary school-based PA interventions ≥12 weeks, aimed at typically developing adolescents. We abstracted number of schools and students invited, randomized, and participating at follow-up to calculate pooled recruitment and retention rates; participant and intervention characteristics were abstracted to execute subgroup or meta-regression analyses. RESULTS: Recruitment rates were 51% for invited schools and 80% for invited students, the retention for schools was almost 100% and for students 91%. Interventions with fixed and flexible components, executed in Asia and South America, and from later publication years had higher student recruitment rates. Students' retention rates were lower for interventions which had flexible components, were theory/model-based, used an accelerometer, had a longer intervention duration, and included more females. CONCLUSION: Recruitment and retention rates in school-based PA interventions are high. Some participant and intervention characteristics influence these rates: flexibility of the intervention, theory/model-based intervention, accelerometer use, intervention duration, continent, and number of females. Researchers should consider these characteristics in intervention development to achieve optimal balance between intervention effectiveness, recruitment, and retention.

On finding natural antibiotics based on TCM formulae.

CONTEXT: Novel kinds of antibiotics are needed to combat the emergence of antibacterial resistance. Natural products (NPs) have shown potential as antibiotic candidates. Current experimental methods are not yet capable of exploring the massive, redundant, and noise-involved chemical space of NPs. In silico approaches are needed to select NPs as antibiotic candidates. OBJECTIVE: This study screens out NPs with antibacterial efficacy guided by both TCM and modern medicine and constructed a dataset aiming to serve the new antibiotic design. METHOD: A knowledge-based network is proposed in this study involving NPs, herbs, the concepts of TCM, and the treatment protocols (or etiologies) of infectious in modern medicine. Using this network, the NPs candidates are screened out and compose the dataset. Feature selection of machine learning approaches is conducted to evaluate the constructed dataset and statistically validate the im- portance of all NPs candidates for different antibiotics by a classification task. RESULTS: The extensive experiments prove the constructed dataset reaches a convincing classification performance with a 0.9421 weighted accuracy, 0.9324 recall, and 0.9409 precision. The further visu- alizations of sample importance prove the comprehensive evaluation for model interpretation based on medical value considerations.

Dropout From Exercise Interventions in Adults With Fibromyalgia: A Systematic Review and Meta-analysis.

OBJECTIVE: To meta-analyze the prevalence and predictors of dropout rates among adults with fibromyalgia participating in exercise randomized controlled trials (RCTs). DATA SOURCES: Two authors searched Embase, CINAHL, PsycARTICLES, and Medline up to 01/21/2023. STUDY SELECTION: We included RCTs of exercise interventions in people with fibromyalgia that reported dropout rates. DATA EXTRACTION: Dropout rates from exercise and control conditions and exerciser/participant, provider, and design/implementation related predictors. DATA SYNTHESIS: A random effects meta-analysis and meta-regression were conducted. In total, 89 RCTs involving 122 exercise arms in 3.702 people with fibromyalgia were included. The trim-and-fill-adjusted prevalence of dropout across all RCTs was 19.2% (95% CI=16.9%-21.8%), which is comparable with the dropout observed in control conditions with the trim-and-fill-adjusted odds ratio being 0.31 (95% CI=0.92-1.86, P=.44). Body mass index (R2=0.16, P=.03) and higher effect of illness (R2=0.20, P=.02) predicted higher dropout. The lowest dropout was observed in exergaming, compared with other exercise types (P=.014), and in lower-intensity exercises, compared with high intensity exercise (P=.03). No differences in dropout were observed for the frequency or duration of the exercise intervention. Continuous supervision by an exercise expert (eg, physiotherapist) resulted in the lowest dropout rates (P<.001). CONCLUSIONS: Exercise dropout in RCTs is comparable with control conditions, suggesting that exercise is a feasible and accepted treatment modality; however, interventions are ideally supervised by an expert (eg, physiotherapist) to minimize the risk of dropout. Experts should consider a high BMI and the effect of the illness as risk factors for dropout.

Dropout From Exercise Interventions in Adults With Knee or Hip Osteoarthritis: A Systematic Review and Meta-analysis.

OBJECTIVE: To investigate the prevalence and moderators of dropout rates among adults with knee or hip osteoarthritis participating in exercise randomized controlled trials (RCTs). DATA SOURCES: Two authors searched Embase, CINAHL, PsycARTICLES, and PubMed up to 01/09/2023. STUDY SELECTION: We included RCTs of exercise interventions in people with knee or hip osteoarthritis that reported dropout rates. DATA EXTRACTION: Dropout rates from exercise and control conditions and exerciser/participant, provider, and design/implementation related moderators. DATA SYNTHESIS: In total, 209 RCTs involving 277 exercise arms in 13,102 participants were included (mean age at study level=64 years; median prevalence of men participants=26.8%). The trim-and-fill-adjusted prevalence of dropout across all RCTs was 17.5% (95% CI=16.7%-18.2%), which is comparable with dropout observed in control conditions (trim-and-fill-adjusted odds ratio=0.89; 95% CI=0.71-1.12, P=.37). Higher prevalence of antidepressant use at study-level predicted higher dropout (R2=0.75, P=.002, N RCTs=6, n exercisers=412). Supervision by an exercise professional was associated with lower dropout rates, with a trim-and-fill-adjusted rate of 13.2% (95% CI=11.7%-14.9%) compared with 20.8% without supervision (95% CI=18.3%-23.5%) (P<.001). CONCLUSIONS: Dropout rates for exercise in RCTs are comparable with control conditions, suggesting that exercise is a generally well-accepted intervention. However, interventions should be supervised by an exercise professional, such as a physiotherapist or exercise physiologist, to further minimize the risk of dropout. Health professionals should consider participants' use of antidepressants as a risk factor for dropout from exercise.

Predicting adolescents' continuation in club sports: A prospective cohort study of the importance of personal and contextual motivational factors in five sports in Denmark.

PURPOSE: The purpose of this prospective cohort study was to investigate the influence of types of motivation, basic psychological needs satisfaction and of a coach-created motivational climate on continued participation in youth sports across types of sport, competitive levels, ages, and gender. METHODS: Participants were 7110 adolescent (age 12-20 years) members of leisure time club organized in basketball, handball, football, badminton, and gymnastics in Denmark. Motivational regulation was measured with BRSQ-6, basic psychological needs satisfaction and frustration were measured with PNSS-S, and coach-created climate was measured with the EDMCQ-C. The participants' continuation or dropout was measured at the beginning of the following season with a short electronic questionnaire. RESULTS: Intrinsic motivation, identified behavior regulation, experiences of competence, relatedness, and autonomy, as well as a coach-created empowering motivational climate, were associated with continuation both in the sport and in the club the following season across different sports, genders, age groups, and competitive levels. Introjected and external behavior regulation, frustrations with the need to experience competence, relatedness, and autonomy, as well as a disempowering coach-created climate, were associated with dropout. CONCLUSION: In Danish youth sports, autonomous motivation, satisfaction of basic psychological needs, and an empowering coach-created motivational climate have a positive impact on the continuation of the sport and the club the following season. In contrast, controlled types of motivation, needs frustration, and a disempowering coach-created climate are associated with dropout. This is the case at both elite and recreational levels, for boys and girls, adolescents, and youth.

Rate and reasons for peritoneal dialysis dropout following haemodialysis to peritoneal dialysis switch: a systematic review and meta-analysis.

BACKGROUND: Patient experiences and survival outcomes can be influenced by the circumstances related to dialysis initiation and subsequent modality choices. This systematic review and meta-analysis aimed to explore the rate and reasons for peritoneal dialysis (PD) dropout following haemodialysis (HD) to PD switch. METHOD: This systematic review conducted searches in four databases, including Medline, PubMed, Embase, and Cochrane. The protocol was registered on PROSPERO (study ID: CRD42023405718). Outcomes included factors leading to the switch from HD to PD, the rate and reasons for PD dropout and mortality difference in two groups (PD first group versus HD to PD group). The Critical Appraisal Skills Programme (CASP) checklist and the GRADE tool were used to assess quality. RESULTS: 4971 papers were detected, and 13 studies were included. On meta-analysis, there was no statistically significant difference in PD dropout in the PD first group (OR: 0.81; 95%CI: 0.61, 1.09; I2 = 83%; P = 0.16), however, there was a statistically significant reduction in the rate of mortality (OR: 0.48; 95%CI: 0.25, 0.92; I2 = 73%; P = 0.03) compared to the HD to PD group. The primary reasons for HD to PD switch, included vascular access failure, patient preference, social issues, and cardiovascular disease. Causes for PD dropout differed between the two groups, but inadequate dialysis and peritonitis were the main reasons for PD dropout in both groups. CONCLUSION: Compared to the PD first group, a previous HD history may not impact PD dropout rates for patients, but it could impact mortality in the HD to PD group. The reasons for PD dropout differed between the two groups, with no statistical differences. Psychosocial reasons for PD dropout are valuable to further research. Additionally, establishing a consensus on the definition of PD dropout is crucial for future studies.

Modeling the Therapeutic Process of Patients with Cocaine Use Disorders: A Guide for Predicting Readmission.

INTRODUCTION: Patients with cocaine use disorders have very high readmission rates. Our aim was to model the relationships between attributes of patients with cocaine use disorder at the beginning of treatment, therapeutic process indicators of time in treatment or proportion of appointments attended, and treatment outcomes, including outcomes at discharge and non-readmissions posttreatment as indicators of therapeutic success. METHOD: A retrospective observational design was used with 10,298 cocaine use disorder patients. Electronic health records were used for statistical analysis of the data. Randomized subsample 1 (n = 5,150) was used for exploratory analysis and subsample 2 (n = 5,148) for modeling relationships between the variables. RESULTS: Patients attributes at intake (e.g., legal services as the source of referral) were of limited significance in explaining time in treatment, proportion of appointments attended, and treatment outcomes. Time in treatment and proportion of appointments attended emerged as significant factors in explaining outcomes at discharge. However, readmissions were primarily explained by time in treatment and outcomes at discharge, although referrals to addiction centers by health services also appeared to be relevant for explaining readmission. DISCUSSION/CONCLUSION: Our study has shown that maintaining a sufficient appointment attendance rate and remaining in treatment for a longer duration are critical therapeutic process indicators for explaining outcomes at the point of discharge and therapeutic success, as indicated by a reduced likelihood of readmissions. Patients who remained in treatment for an extended period were found to have a reduced risk of future readmissions. In addition, our study highlights the importance of maintaining a satisfactory appointment attendance rate to attain successful short- and medium-term therapeutic discharge outcomes. These guidelines could help to increase the efficiency of patient treatment and alleviate the suffering of both patients and their families.

Refitting contact lens dropouts into a modern daily disposable contact lens.

PURPOSE: To determine the number of previous contact lens (CL) wearers who could be comfortably refitted into delefilcon A (DAILIES TOTAL1®) CLs. METHODS: This was a 6-month, three-visit study that recruited subjects who discontinued CLs within the past 2 years because of discomfort or dryness symptoms. Subjects were required to have Standard Patient Evaluation of Eye Dryness (SPEED) questionnaire scores ≤3 and to be able to wear spherical study CLs. Subjects were asked to complete a ±50 comfort visual analogue scale (VAS) at 1 month and a Likert questionnaire after 1 and 6 months of CL wear to understand the subjects' CL experience. RESULTS: All 60 subjects who were fitted with the study CLs were still wearing them after 1 month, while one subject had dropped out by 6 months. Subjects had a median (interquartile range) age of 24.0 (7.0) years (71.7% female). They reported a median VAS score of 44.0 (8.0) units at the 1-month visit, with all reporting a comfortable score. At the 1-month/6-month visits, 98.3%/93.2%, 86.5%/78.0% and 93.2%/91.5% of subjects responded that they were very satisfied or satisfied with their vision, their end-of-day CL comfort and overall CL comfort, respectively. The same subjects responded that they were very likely or likely to continue to wear the study CLs at 1 (89.6%) and 6 months (80.7%) and to recommend the study CLs to a friend at 1 (98.3%) and 6 months (93.2%). CONCLUSIONS: The results suggest that when encountering a CL dropout, a practitioner could educate a patient about trying an alternative CL and consider delefilcon A lenses as an option.

Efficacy and Acceptance of Cognitive Behavioral Therapy in Adults with Chronic Fatigue Syndrome: A Meta-analysis.

BACKGROUND: The systematic aggregation of research on cognitive behavioral therapy (CBT) in chronic fatigue syndrome (CFS) needs an update. Although meta-analyses evaluating interventions typically focus on symptom reduction, they should also consider indicators of treatment acceptability, e.g., drop-out rates. METHODS: Randomized controlled trials (RCTs) investigating CBT in adults with CFS compared to inactive and non-specific control groups were included. First, efficacy was examined, considering fatigue, depression, anxiety, and perceived health. Secondly, drop-out rates through different trial stages were analyzed: Non-completion of all mandatory sessions, drop-out (primary study definition), treatment refusal (non-starters), and average of sessions completed. RESULT: We included 15 RCTs with 2015 participants. CBT was more effective than controls in fatigue (g = -0.52, 95%CI -0.69 to -0.35), perceived health, depression, and anxiety at post-treatment. At long-term follow-up the effects were maintained for fatigue and anxiety. Rates of non-completion (22%, 95%CI 3-71), drop-out (15%, 95%CI 9-25), and treatment refusal (7%, 95%CI 3-15) were relatively low, with a high average proportion of sessions completed. Total time of therapy moderated the effect on fatigue, while the number of sessions moderated the effect on perceived health. Fatigue severity influenced adherence. CONCLUSION: The results indicate that CBT for CFS is effective in reducing fatigue, fatigue related impairment, and severity of depression and anxiety. Conclusions on efficacy at follow-ups are still limited. However, adherence is high in CBT. The results may help to inform clinical practice. Future research should focus on examining the maintenance of effects, while also emphasizing the importance of treatment acceptance.

Interpersonal sensitivity predicts slower change and less change in anxiety symptoms in cognitive behavioural therapy.

OBJECTIVES: Patients in cognitive behavioural therapy (CBT) who are high in interpersonal sensitivity may have difficulty fully engaging in treatment because therapy sessions require intimate interpersonal interactions that are especially uncomfortable for these individuals. The current study tests the hypotheses that patients who are high in interpersonal sensitivity benefit less from CBT for symptoms of depression and anxiety, show a slower rate of change in those symptoms, and are more likely to drop out of treatment. METHODS: Participants were 832 outpatients who received naturalistic CBT. We assessed interpersonal sensitivity before treatment began and depression and anxiety symptoms at every therapy session. We assessed early, premature, and uncollaborative termination after treatment ended. We constructed multilevel linear regression models and logistic regression models to assess the effects of baseline interpersonal sensitivity on the treatment outcome, the slope of change in depression and anxiety symptoms, and each type of dropout. RESULTS: Higher baseline interpersonal sensitivity was associated with a slower rate of change and less overall change in anxiety but not depressive symptoms. Baseline interpersonal sensitivity was not a predictor of dropout. CONCLUSIONS: Interpersonal sensitivity at baseline predicts less change and a slower rate of change in anxiety symptoms. Early detection of elevated interpersonal sensitivity can help therapists take action to address these barriers to successful treatment and help scientists build decision support tools that accurately predict the trajectory of change in anxiety symptoms for these patients.

Attrition in Conversational Agent-Delivered Mental Health Interventions: Systematic Review and Meta-Analysis.

BACKGROUND: Conversational agents (CAs) or chatbots are computer programs that mimic human conversation. They have the potential to improve access to mental health interventions through automated, scalable, and personalized delivery of psychotherapeutic content. However, digital health interventions, including those delivered by CAs, often have high attrition rates. Identifying the factors associated with attrition is critical to improving future clinical trials. OBJECTIVE: This review aims to estimate the overall and differential rates of attrition in CA-delivered mental health interventions (CA interventions), evaluate the impact of study design and intervention-related aspects on attrition, and describe study design features aimed at reducing or mitigating study attrition. METHODS: We searched PubMed, Embase (Ovid), PsycINFO (Ovid), Cochrane Central Register of Controlled Trials, and Web of Science, and conducted a gray literature search on Google Scholar in June 2022. We included randomized controlled trials that compared CA interventions against control groups and excluded studies that lasted for 1 session only and used Wizard of Oz interventions. We also assessed the risk of bias in the included studies using the Cochrane Risk of Bias Tool 2.0. Random-effects proportional meta-analysis was applied to calculate the pooled dropout rates in the intervention groups. Random-effects meta-analysis was used to compare the attrition rate in the intervention groups with that in the control groups. We used a narrative review to summarize the findings. RESULTS: The systematic search retrieved 4566 records from peer-reviewed databases and citation searches, of which 41 (0.90%) randomized controlled trials met the inclusion criteria. The meta-analytic overall attrition rate in the intervention group was 21.84% (95% CI 16.74%-27.36%; I2=94%). Short-term studies that lasted ≤8 weeks showed a lower attrition rate (18.05%, 95% CI 9.91%- 27.76%; I2=94.6%) than long-term studies that lasted >8 weeks (26.59%, 95% CI 20.09%-33.63%; I2=93.89%). Intervention group participants were more likely to attrit than control group participants for short-term (log odds ratio 1.22, 95% CI 0.99-1.50; I2=21.89%) and long-term studies (log odds ratio 1.33, 95% CI 1.08-1.65; I2=49.43%). Intervention-related characteristics associated with higher attrition include stand-alone CA interventions without human support, not having a symptom tracker feature, no visual representation of the CA, and comparing CA interventions with waitlist controls. No participant-level factor reliably predicted attrition. CONCLUSIONS: Our results indicated that approximately one-fifth of the participants will drop out from CA interventions in short-term studies. High heterogeneities made it difficult to generalize the findings. Our results suggested that future CA interventions should adopt a blended design with human support, use symptom tracking, compare CA intervention groups against active controls rather than waitlist controls, and include a visual representation of the CA to reduce the attrition rate. TRIAL REGISTRATION: PROSPERO International Prospective Register of Systematic Reviews CRD42022341415; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022341415.