Personalized cognitive training: Protocol for individual-level meta-analysis implementing machine learning methods

Classification Of MeMory InTerventions: Rationale and developmental process of the COMMIT tool

ABSTRACTOver the last decades, numerous memory interventions have been developed to mitigate memory decline in normal ageing. However, there is a large variability in the success of memory interventions, and it remains poorly understood which memory intervention programs are most effective and for whom. This is partially explained by the heterogeneity of memory intervention protocols across studies as well as often poor reporting of the study design. To facilitate a reporting framework that enables researchers to systemize the content and design of memory intervention paradigms, we developed the Classification Of MeMory InTerventions (COMMIT) tool using a 3-stage developmental process. Briefly, COMMIT was based on qualitative content analysis of already existing memory intervention studies published between April 1983 and July 2020, and iteratively validated by both internal and external expert panels. COMMIT provides an easily-applicable interactive tool that enables systematic description of memory intervention studies, together with instructions on how to use this classification tool. Our main goal is to provide a tool that enables the reporting and classification of memory interventions in a transparent, comprehensible, and complete manner, to ensure a better comparability between memory interventions, and, to ultimately contribute to the question which memory intervention shows the greatest benefits.

Cognitive training interventions for substance use disorders: what they really offer?

Cognitive training (CT) has emerged as a potential therapeutic approach for substance use disorders (SUD), aiming to restore cognitive impairments and potentially improve treatment outcomes. However, despite promising findings, the effectiveness of CT in real-life applications and its impact on SUD symptoms has remained unclear. This perspective article critically examines the existing evidence on CT for SUD and explores the challenges and gaps in implementing CT interventions. It emphasizes the need for clarity in expectations and decision-making from a public health standpoint, advocating for comprehensive studies that consider a broader range of SUD consequences and utilize measures that reflect patients' actual experiences.

Cognitive improvement in patients with major depressive disorder after personalised multi domain training in the CERT-D study

The CERT-D program offers a new treatment approach addressing disturbed cognitive and psychosocial functioning in major depressive disorder (MDD). The current analysis of a randomised controlled trial (RCT) comprises two objectives: Firstly, evaluating the program's efficacy of a personalised versus standard treatment and secondly, assessing the treatment's persistence longitudinally. Participants (N = 112) were randomised into a personalised or standard treatment group. Both groups received 8 weeks of cognitive training, followed by a three-month follow-up without additional training. The type of personalised training was determined by pre-treatment impairments in the domains of cognition, emotion-processing and social-cognition. Standard training addressed all three domains equivalent. Performance in these domains was assessed repeatedly during RCT and follow-up. Treatment comparisons during the RCT-period showed benefits of personalised versus standard treatment in certain aspects of social-cognition. Conversely, no benefits in the remaining domains were found, contradicting a general advantage of personalisation. Exploratory follow-up analysis on persistence of the program's effects indicated sustained intervention outcomes across the entire sample. A subsequent comparison of clinical outcomes between personalised versus standard treatment over a three-month follow-up period showed similar results. First evidence suggests that existing therapies for MDD could benefit from an adjunct administration of the CERT-D program.

Threats to Terrestrial Plants from Emerging Nanoplastics

Nanoplastics are ubiquitous in ecosystems and impact planetary health. However, our current understanding on the impacts of nanoplastics upon terrestrial plants is fragmented. The lack of systematic approaches to evaluating these impacts limits our ability to generalize from existing studies and perpetuates regulatory barriers. Here, we undertook a meta-analysis to quantify the overall strength of nanoplastic impacts upon terrestrial plants and developed a machine learning approach to predict adverse impacts and identify contributing features. We show that adverse impacts are primarily associated with toxicity metrics, followed by plant species, nanoplastic mass concentration and size, and exposure time and medium. These results highlight that the threats of nanoplastics depend on a diversity of reactions across molecular to ecosystem scales. These reactions are rooted in both the spatial and functional complexities of nanoplastics and, as such, are specific to both the plastic characteristics and environmental conditions. These findings demonstrate the utility of interrogating the diversity of toxicity data in the literature to update both risk assessments and evidence-based policy actions.

A Machine Learning Approach to Personalize Computerized Cognitive Training Interventions

Executive functions are a class of cognitive processes critical for purposeful goal-directed behavior. Cognitive training is the adequate stimulation of executive functions and has been extensively studied and applied for more than 20 years. However, there is still a lack of solid consensus in the scientific community about its potential to elicit consistent improvements in untrained domains. Individual differences are considered one of the most important factors of inconsistent reports on cognitive training benefits, as differences in cognitive functioning are both genetic and context-dependent, and might be affected by age and socioeconomic status. We here present a proof of concept based on the hypothesis that baseline individual differences among subjects would provide valuable information to predict the individual effectiveness of a cognitive training intervention. With a dataset from an investigation in which 73 6-year-olds trained their executive functions using an online software with a fixed protocol, freely available at www.matemarote.org.ar, we trained a support vector classifier that successfully predicted (average accuracy = 0.67, AUC = 0.707) whether a child would improve, or not, after the cognitive stimulation, using baseline individual differences as features. We also performed a permutation feature importance analysis that suggested that all features contribute equally to the model's performance. In the long term, this results might allow us to design better training strategies for those players who are less likely to benefit from the current training protocols in order to maximize the stimulation for each child.

Machine Learning-Based Behavioral Diagnostic Tools for Depression: Advances, Challenges, and Future Directions

The psychiatric diagnostic procedure is currently based on self-reports that are subject to personal biases. Therefore, the diagnostic process would benefit greatly from data-driven tools that can enhance accuracy and specificity. In recent years, many studies have achieved promising results in detecting and diagnosing depression based on machine learning (ML) analysis. Despite these favorable results in depression diagnosis, which are primarily based on ML analysis of neuroimaging data, most patients do not have access to neuroimaging tools. Hence, objective assessment tools are needed that can be easily integrated into the routine psychiatric diagnostic process. One solution is to use behavioral data, which can be easily collected while still maintaining objectivity. The current paper summarizes the main ML-based approaches that use behavioral data in diagnosing depression and other psychiatric disorders. We classified these studies into two main categories: (a) laboratory-based assessments and (b) data mining, the latter of which we further divided into two sub-groups: (i) social media usage and movement sensors data and (ii) demographic and clinical information. The paper discusses the advantages and challenges in this field and suggests future research directions and implementations. The paper's overarching aim is to serve as a first step in synthetizing existing knowledge about ML-based behavioral diagnosis studies in order to develop interventions and individually tailored treatments in the future.

Rethinking cognitive training: The moderating roles of emotional vulnerability and perceived cognitive impact of training in high worriers

Trait worry is a hallmark feature of anxiety and depression, interfering with attentional control and impairing cognitive performance. Previous research has shown the adaptive dual n-back training is effective in improving attentional control and reducing emotional vulnerability, but not for everyone. The current randomised controlled trial explored the role of baseline emotional vulnerability and perceived cognitive impact in training-related cognitive and emotional improvements in 60 high worriers randomly assigned to 10 sessions of the adaptive dual n-back training or non-adaptive 1-back training. Pre-training, post-training and one-month follow-up measures of cognitive performance were assessed using an emotional Flanker task, a cued task-switching task, and the MaRs-IB task. Self-report questionnaires assessed worry, anxiety, depression, somatisation, and self-efficacy, as well as participants' perceived cognitive impact of the training. Participants with higher levels of baseline emotional vulnerability presented the largest improvements in non-verbal reasoning and emotional vulnerability one month after the training, as well as the greatest perceived cognitive impact. Perceived cognitive impact was predicted by working memory improvement on the adaptive n-back training at high baseline levels of anxiety. These results suggest that the adaptive n-back training presents the greatest emotional and cognitive benefits for individuals experiencing severe levels of emotional vulnerability.