Classification algorithms analysis for brain–computer interface in drug craving therapy

A zero precision loss framework for EEG channel selection: enhancing efficiency and maintaining interpretability

The brain-computer interface (BCI) systems based on motor imagery typically rely on a large number of electrode channels to acquire information. The rational selection of electroencephalography (EEG) channel combinations is crucial for optimizing computational efficiency and enhancing practical applicability. However, evaluating all potential channel combinations individually is impractical. This study aims to explore a strategy for quickly achieving a balance between maximizing channel reduction and minimizing precision loss. To this end, we developed a spatio-temporal attention perception network named STAPNet. Based on the channel contributions adaptively generated by its subnetwork, we propose an extended step bi-directional search strategy that includes variable ratio channel selection (VRCS) and strided greedy channel selection (SGCS), designed to enhance global search capabilities and accelerate the optimization process. Experimental results show that on the High Gamma and BCI Competition IV 2a public datasets, the framework respectively achieved average maximum accuracies of 91.47% and 84.17%. Under conditions of zero precision loss, the average number of channels was reduced by a maximum of 87.5%. Additionally, to investigate the impact of neural information loss due to channel reduction on the interpretation of complex brain functions, we employed a heatmap visualization algorithm to verify the universal importance and complete symmetry of the selected optimal channel combination across multiple datasets. This is consistent with the brain's cooperative mechanism when processing tasks involving both the left and right hands.

Time-frequency analysis of speech signal using Chirplet transform for automatic diagnosis of Parkinson's disease

Parkinson's disease (PD) is the second most prevalent neurodegenerative disorder in the world after Alzheimer's disease. Early diagnosing PD is challenging as it evolved slowly, and its symptoms eventuate gradually. Recent studies have demonstrated that changes in speech may be utilized as an excellent biomarker for the early diagnosis of PD. In this study, we have proposed a Chirplet transform (CT) based novel approach for diagnosing PD using speech signals. We employed CT to get the time-frequency matrix (TFM) of each speech recording, and we extracted time-frequency based entropy (TFE) features from the TFM. The statistical analysis demonstrates that the TFE features reflect the changes in speech that occurs in the speech due to PD, hence can be used for classifying the PD and healthy control (HC) individuals. The effectiveness of the proposed framework is validated using the vowels and words from the PC-GITA database. The genetic algorithm is utilized to select the optimum features subset, while a support vector machine (SVM), decision tree (DT), K-Nearest Neighbor (KNN), and Naïve Bayes (NB) classifiers are employed for classification. The TFE features outperform the breathiness and Mel frequency cepstral coefficients (MFCC) features. The SVM classifier is most effective compared to other machine-learning classifiers. The highest classification accuracy rates of 98% and 99% are achieved using the vowel /a/ and word /atleta/, respectively. The results reveal that the proposed CT-based entropy features effectively diagnose PD using the speech of a person.

Italian University Students' Resilience during the COVID-19 Lockdown-A Structural Equation Model about the Relationship between Resilience, Emotion Regulation and Well-Being

Over the past two years, the consequences of the severe restrictions imposed by the rapid spread of COVID-19 among the global population have been a central focus of scientific research. The pandemic has been a singular and unexpected event that found people unprepared and vulnerable in responding to its emergence, resulting in substantial psychological distress. Scientific evidence has highlighted that adolescents and emerging adults have been among those populations at greatest risk of adverse psychological outcomes, even in the long term. In particular, more than one-third of young adults reported high levels of loneliness, and nearly half of 18- to 24-year-olds felt lonely during the pandemic, experiencing both psychological and emotional distress. The lockdown, the consequent suspension of face-to-face academic activities and the severe restriction of social life have disrupted the daily routines of students already involved in coping with developmental tasks related to identity formation and the relational experience. Under such conditions, emotions and emotional regulation skills are crucial in adapting behavior to reach academic goals and face mounting levels of distress. Therefore, several studies have investigated resilience mechanisms and coping strategies of emerging adults during the pandemic. The present study focuses on university students and explores the impact of resilience and emotional regulation on adverse psychological outcomes related to persistent distress conditions associated with the COVID-19 pandemic. Students were administered a self-report assessment battery through an online platform at the beginning (T0) and the end of the lockdown (T1). A structural equation model (SEM) was used to explore the relationship between resilience, emotional regulation difficulties and psychological distress (depression, anxiety and stress). The findings indicate that psychological resilience and emotion regulation are protective factors that buffer the extent of possible distress resulting from an adverse condition such as the COVID-19 pandemic.

Polysubstance Use Patterns among Outpatients Undergoing Substance Use Disorder Treatment: A Latent Class Analysis

Substance Use Disorders (SUDs) pose significant challenges to both individuals and society at large. The primary focus of existing research with clinical SUD populations has been on individual substances, but research is required to better understand the profiles of individuals who use different substances simultaneously. The purpose of the current study was, therefore, to identify patterns of use among subjects (n = 1025) who reported using multiple substances by adopting a Latent Class Analysis (LCA) methodology. The Addiction Severity Index (ASI-lite) was included as a measure of substance misuse, we performed LCA to identify patterns of substance use through the administration of the ASI-Lite. Responses were collected from the following substances: alcohol, cannabis/cannabinoids, opioids and heroin, and cocaine. Results identified two latent classes: (1) alcohol use dominant, and (2) poly-abuser use dominants. Class 1 represented 60.0% of the sample and refers to individuals with the dominant use of alcohol, of those a higher proportion (47%) reported low-frequency use (1 to 7 days per month) and 26% reported a frequency of use of 24 to 30 days per month. Furthermore, 18% used alcohol in combination with cocaine. Class 2 represents 40.0% of the sample. This class is characterized by low-frequency and high-frequency users of several substances. The results obtained highlight the importance of deepening the study of the concomitant use of substances in individuals with SUDs to better understand the health risk of the combined use of two or more substances.

Dealing with Loved Ones' Addiction: Development of an App to Cope with Caregivers' Stress

Caregivers remain the primary source of attachment, nurturing, and socialization for human beings in our current society. Family caregivers provide 11 to 100 h of care per week to their loved ones, including emotional and social support, assistance with transportation, home care, and so on. However, caregivers find the workload challenging due to fatigue, burnout, depression, anxiety, and sleep disturbances, and sometimes also from an excessive burden. Caregiver burden and stress ultimately negatively affect family members and caregivers. The caregiver is then at risk of developing deleterious physical, psychological, social, and emotional problems such as mood and anxiety disorders. Mobile health applications (mHealth applications) can be a solution to help family caregivers care for their loved ones and also for themselves. In this study, we present the development of an mHealth application for caregivers of persons with substance use and tested its usability. We used a user-centered design and intervention (UCDI) approach to develop the app by conducting a focus group with parents of individuals with addiction problems. Four key themes were identified during the focus group: (i) information section, (ii) self-care section, (iii) how-to: stress-reduction section, and (iv) chat section. The final app was developed with the software vendor and divided into several sections that were useful for managing psychological problems (such as stress or anxiety), informing about addiction and behavioral dependency problems, and helping users find a professional or services nearby. An analysis of the results of a usability test related to the app administered to a subsample of the focus group showed that the app provided ease of use, usefulness, and satisfaction.

Decoding Emotion in Drug Abusers: Evidence for Face and Body Emotion Recognition and for Disgust Emotion

Background: Different drugs damage the frontal cortices, particularly the prefrontal areas involved in both emotional and cognitive functions, with a consequence of decoding emotion deficits for people with substance abuse. The present study aimed to explore the cognitive impairments in drug abusers through facial, body and disgust emotion recognition, expanding the investigation of emotions processing, measuring accuracy and response velocity. Methods: We enrolled 13 addicted to cocaine and 12 alcohol patients attending treatment services in Italy, comparing them with 33 matched controls. Facial emotion and body posture recognition tasks, a disgust rating task and the Barrat Impulsivity Scale were included in the experimental assessment. Results: We found that emotional processes are differently influenced by cocaine and alcohol, suggesting that these substances impact diverse cerebral systems. Conclusions: Drug abusers seem to be less accurate on elaboration of facial, body and disgust emotions. Considering that the participants were not cognitively impaired, our data support the hypothesis that emotional impairments emerge independently from the damage of cognitive functions.

Digital Help for Substance Users (SU): A Systematic Review

The estimated number of Substance Users (SU) globally has currently reached a very high number and is still increasing. This aspect necessitates appropriate interventions for prevention and specific treatments. The literature shows that digital treatments can be useful in the context of health services and substance abuse. This systematic review focuses mainly on research on the effectiveness of digital treatments for SU. Data sources included studies found on PsycINFO, PubMed, SCOPUS, and WebOfScience (WOS) database searches. The following keywords were used: TITLE (digital OR computer OR software OR tablet OR app OR videogame OR seriousgame OR virtualreality) AND ABSTRACT((mental AND health) AND (addiction OR dependence OR substance OR drug)). We focused on peer-reviewed articles published from 2010 through 2021 using PRISMA guidelines. A total of 18 studies met the inclusion criteria (i.e., type of intervention, efficacy in terms of misuse of substances and scored outcomes from questionnaire or toxicology tests, study methodology). The studies included investigations of specific digital treatments for SU of various kinds of drugs. The interventions were administered using personal computers, smartphones, or, in a few cases, tablets. Most of the interventions focused on the cognitive behavior therapy (CBT) model and/or on the use strategies, tips, or feedback. A minority provided information or training programs. The current review shows that digital treatments and interventions are effective in reducing the frequency of use, augmenting abstinence, or reducing the gravity of dependence for most of the studies at post-treatment. However, due to the heterogeneity of the variables (i.e., substance type, digital tool used, and treatment administered), there was a reduced generalizability of the results. This review highlights the need to continue the research in this field, and above all, to create effective digital protocols.

Development of the motivation to use substance questionnaire

BACKGROUND

The use of a substance is always accompanied by a motivation that pushes the subject to use and abuse the substance. This work reports the validation data of the MUS (Motivation to Use Substance), which measures and evaluates the motivation to use substances based on the dimension of resistance, confidence, pleasure, and relaxation.

METHODS

The validation process involved 605 subjects belonging to a clinical sample of patients who used substances. The sample was divided into two groups: on the first, consisting of 342 subjects, an exploratory analysis was carried out, and on the second, consisting of 263 subjects, a confirmatory analysis was carried out. For concurrent and convergent validation, the SCL-90 test (Symptom Check List-90) was administered for the measurement of addiction-related psychiatric symptoms, and the ASI (Addiction Severity Index) test was administered for the measurement of the severity of the addiction.

RESULTS AND CONCLUSIONS

The MUS was found to be a robust test of construct validity, convergent, and concurrent. The results highlight gender and age differences for some of the MUS scales. Ultimately, MUS can be considered an excellent tool for structuring treatment programs for addiction services.