Hasil untuk "Therapeutics. Psychotherapy"

Mehrab Beikzadeh, Yasaman Asadollah Salmanpour, Ashima Suvarna et al.

Mental health disorders affect over 1 billion people worldwide, yet access to care remains limited by workforce shortages and cost constraints. While AI systems show therapeutic promise, current alignment approaches optimize objectives independently, failing to balance patient preferences with clinical safety. We survey 335 individuals with lived mental health experience to collect preference rankings across therapeutic dimensions, then develop a multi-objective alignment framework using direct preference optimization. We train reward models for six criteria -- empathy, safety, active listening, self-motivated change, trust/rapport, and patient autonomy -- and systematically compare multi-objective approaches against single-objective optimization, supervised fine-tuning, and parameter merging. Multi-objective DPO (MODPO) achieves superior balance (77.6% empathy, 62.6% safety) compared to single-objective optimization (93.6% empathy, 47.8% safety), and therapeutic criteria outperform general communication principles by 17.2%. Blinded clinician evaluation confirms MODPO is consistently preferred, with LLM-evaluator agreement comparable to inter-clinician reliability.

Anqi Li, Chenxiao Wang, Yu Lu et al.

Client perceptions of the therapeutic alliance are critical for counseling effectiveness. Accurately capturing these perceptions remains challenging, as traditional post-session questionnaires are burdensome and often delayed, while existing computational approaches produce coarse scores, lack interpretable rationales, and fail to model holistic session context. We present CARE, an LLM-based framework to automatically predict multi-dimensional alliance scores and generate interpretable rationales from counseling transcripts. Built on the CounselingWAI dataset and enriched with 9,516 expert-curated rationales, CARE is fine-tuned using rationale-augmented supervision with the LLaMA-3.1-8B-Instruct backbone. Experiments show that CARE outperforms leading LLMs and substantially reduces the gap between counselor evaluations and client-perceived alliance, achieving over 70% higher Pearson correlation with client ratings. Rationale-augmented supervision further improves predictive accuracy. CARE also produces high-quality, contextually grounded rationales, validated by both automatic and human evaluations. Applied to real-world Chinese online counseling sessions, CARE uncovers common alliance-building challenges, illustrates how interaction patterns shape alliance development, and provides actionable insights, demonstrating its potential as an AI-assisted tool for supporting mental health care.

Cintami Farmawati, Nadhifatuz Zulfa, Sitti Rahmah Marsidi

Post-traumatic social withdrawal is a common psychological impact experienced by natural disaster survivors and has the potential to hinder the recovery process. In the digital era, online religious-based support is an easily accessible alternative intervention and is considered capable of supporting the psychological adaptation process. This study aims to test the effectiveness of online religious coping intervention in reducing post-traumatic social withdrawal levels in landslide survivors in Batang Regency. The study used an experimental design with two groups: an experimental group that received the intervention and a control group without treatment. Measurements were conducted at the pretest and post-test stages. Data analysis used the Mann-Whitney U test to examine differences between groups. The results showed that the experimental group experienced a significantly greater reduction in post-traumatic social withdrawal (mean pretest = 49.00; post-test = 25.40) compared to the control group (mean pretest = 50.00; post-test = 45.20). Statistical tests showed a significant difference in post-test scores (p < 0.05), but not in pre-test scores. These findings indicate that online religious coping interventions are effective in reducing post-traumatic social withdrawal symptoms. This research contribution underscores the importance of a technology-based spiritual approach as an adaptive psychological recovery strategy, particularly in disaster contexts and in communities with religious ties. It also broadens understanding of the integration of religious values ​​into modern psychosocial interventions.

Yinzhou Wang, Yimeng Wang, Ye Xiao et al.

Recent advancements in large language models (LLMs) promise to expand mental health interventions by emulating therapeutic techniques, potentially easing barriers to care. Yet there is a lack of real-world empirical evidence evaluating the strengths and limitations of LLM-enabled psychotherapy interventions. In this work, we evaluate an LLM-powered chatbot, designed via prompt engineering to deliver cognitive restructuring (CR), with 19 users. Mental health professionals then examined the resulting conversation logs to uncover potential benefits and pitfalls. Our findings indicate that an LLM-based CR approach has the capability to adhere to core CR protocols, prompt Socratic questioning, and provide empathetic validation. However, issues of power imbalances, advice-giving, misunderstood cues, and excessive positivity reveal deeper challenges, including the potential to erode therapeutic rapport and ethical concerns. We also discuss design implications for leveraging LLMs in psychotherapy and underscore the importance of expert oversight to mitigate these concerns, which are critical steps toward safer, more effective AI-assisted interventions.

Xinchen Wan, Jinhua Liang, Huan Zhang

Existing digital mental wellness tools often overlook the nuanced emotional states underlying everyday challenges. For example, pre-sleep anxiety affects more than 1.5 billion people worldwide, yet current approaches remain largely static and "one-size-fits-all", failing to adapt to individual needs. In this work, we present EmoHeal, an end-to-end system that delivers personalized, three-stage supportive narratives. EmoHeal detects 27 fine-grained emotions from user text with a fine-tuned XLM-RoBERTa model, mapping them to musical parameters via a knowledge graph grounded in music therapy principles (GEMS, iso-principle). EmoHeal retrieves audiovisual content using the CLAMP3 model to guide users from their current state toward a calmer one ("match-guide-target"). A within-subjects study (N=40) demonstrated significant supportive effects, with participants reporting substantial mood improvement (M=4.12, p<0.001) and high perceived emotion recognition accuracy (M=4.05, p<0.001). A strong correlation between perceived accuracy and therapeutic outcome (r=0.72, p<0.001) validates our fine-grained approach. These findings establish the viability of theory-driven, emotion-aware digital wellness tools and provides a scalable AI blueprint for operationalizing music therapy principles.

Omer Faruk Durugol, Maximilian Rokuss, Yannick Kirchhoff et al.

Automated segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) from MRI is critical for clinical workflows but is hindered by poor tumor-tissue contrast and a scarcity of annotated data. This paper details our submission to the PANTHER challenge, addressing both diagnostic T1-weighted (Task 1) and therapeutic T2-weighted (Task 2) segmentation. Our approach is built upon the nnU-Net framework and leverages a deep, multi-stage cascaded pre-training strategy, starting from a general anatomical foundation model and sequentially fine-tuning on CT pancreatic lesion datasets and the target MRI modalities. Through extensive five-fold cross-validation, we systematically evaluated data augmentation schemes and training schedules. Our analysis revealed a critical trade-off, where aggressive data augmentation produced the highest volumetric accuracy, while default augmentations yielded superior boundary precision (achieving a state-of-the-art MASD of 5.46 mm and HD95 of 17.33 mm for Task 1). For our final submission, we exploited this finding by constructing custom, heterogeneous ensembles of specialist models, essentially creating a mix of experts. This metric-aware ensembling strategy proved highly effective, achieving a top cross-validation Tumor Dice score of 0.661 for Task 1 and 0.523 for Task 2. Our work presents a robust methodology for developing specialized, high-performance models in the context of limited data and complex medical imaging tasks (Team MIC-DKFZ).

Agnes Galih Chris Roseita, Susana Prapunoto, Sutarto Wijono

Pekerja wanita memiliki peran ganda yaitu sebagai anggota keluarga dan sebagai seorang professional. Hal tersebut menjadi tuntutan yang tidak mudah untuk diselesaikan karena terlalu banyak peran yang dijalankan. Oleh sebab itu, pekerja wanita dengan peran ganda membutuhkan penerapan budaya organisasi dan keseimbangan kehidupan kerja yang baik untuk mendorong peningkatan kinerja organisasi dan kinerja pada masing-masing individu. Penelitian ini bertujuan untuk mengetahui budaya organisasi dan keseimbangan kehidupan kerja secara simultan sebagai prediktor kinerja pada pekerja wanita. Populasi dan sampel pada penelitian ini berjumlah 111 responden yang merupakan pekerja wanita yang masih aktif bekerja. Teknik pengambilan sampel dilakukan dengan cara sampel jenuh. Pengumpulan data menggunakan skala psikologi yaitu skala Individual Work Performance Questionnaire (IWPQ), skala Organizational Culture Profile (OCP) dan skala Work Life Balance. Data yang digunakan adalah data primer yang dianalisis menggunakan uji regresi linier berganda. Hasil penelitian menunjukkan bahwa budaya organisasi dan keseimbangan kehidupan kerja secara simultan sebagai prediktor kinerja pada pe kerja wanita sebesar 31,3% sedangkan sisanya sebesar 68,7% dipengaruhi oleh variabel lain yang tidak diteliti.

K. Aafjes-van Doorn, Céline Kamsteeg, Jordan Bate et al.

Abstract Machine learning (ML) offers robust statistical and probabilistic techniques that can help to make sense of large amounts of data. This scoping review paper aims to broadly explore the nature of research activity using ML in the context of psychological talk therapies, highlighting the scope of current methods and considerations for clinical practice and directions for future research. Using a systematic search methodology, fifty-one studies were identified. A narrative synthesis indicates two types of studies, those who developed and tested an ML model (k=44), and those who reported on the feasibility of a particular treatment tool that uses an ML algorithm (k=7). Most model development studies used supervised learning techniques to classify or predict labeled treatment process or outcome data, whereas others used unsupervised techniques to identify clusters in the unlabeled patient or treatment data. Overall, the current applications of ML in psychotherapy research demonstrated a range of possible benefits for indications of treatment process, adherence, therapist skills and treatment response prediction, as well as ways to accelerate research through automated behavioral or linguistic process coding. Given the novelty and potential of this research field, these proof-of-concept studies are encouraging, however, do not necessarily translate to improved clinical practice (yet).

Palash Moon, Pushpak Bhattacharyya

The detection of depression through non-verbal cues has gained significant attention. Previous research predominantly centred on identifying depression within the confines of controlled laboratory environments, often with the supervision of psychologists or counsellors. Unfortunately, datasets generated in such controlled settings may struggle to account for individual behaviours in real-life situations. In response to this limitation, we present the Extended D-vlog dataset, encompassing a collection of 1, 261 YouTube vlogs. Additionally, the emergence of large language models (LLMs) like GPT3.5, and GPT4 has sparked interest in their potential they can act like mental health professionals. Yet, the readiness of these LLM models to be used in real-life settings is still a concern as they can give wrong responses that can harm the users. We introduce a virtual agent serving as an initial contact for mental health patients, offering Cognitive Behavioral Therapy (CBT)-based responses. It comprises two core functions: 1. Identifying depression in individuals, and 2. Delivering CBT-based therapeutic responses. Our Mistral model achieved impressive scores of 70.1% and 30.9% for distortion assessment and classification, along with a Bert score of 88.7%. Moreover, utilizing the TVLT model on our Multimodal Extended D-vlog Dataset yielded outstanding results, with an impressive F1-score of 67.8%

Ljubisa Bojic, Joerg Matthes, Agariadne Dwinggo Samala et al.

The emergence of the metaverse - envisioned as a hyperreal virtual universe enabling boundless human interaction - has the potential to revolutionize our conception of media. This transformation could alter society as we know it. This paper identifies addictive features of social media, including immersion, interactivity, real-time access, and personalization. These features are examined within the context of virtual reality through a literature review and content analysis, aimed at exploring the potential consequences of metaverse development. From an initial pool of 193,218 documents, a refined selection of N = 44 relevant papers formed the basis of our qualitative analysis. About half of the analyzed papers indicate that these features contribute to VR addiction. Interestingly, the same features that contribute to addictive behaviors can also be harnessed for positive therapeutic interventions of VR, particularly in treating addictions and managing mental health conditions. This duality, observed in the other half of the papers, emphasizes the complex role of VR technologies, suggesting that they can serve as a substitute for other addictions. This phenomenon is placed into the historical context of evolving media technologies that increasingly mimic reality. The complex interplay of factors contributing to addiction necessitates the development of algorithmic solutions that actively curate diverse offerings, rather than promoting a closed loop of like-minded views. Traditional models of addiction should be adapted to address these unique challenges. Finally, the discussion turned to the implications of these findings for a society where the metaverse is widely accepted as a mainstream technology.

Yijun Chen, Xiaochu Zhang, Rei Akaishi

Abstract Smartphones have become an integral part of modern life, raising concerns about their impact on mental health, especially among young people. However, previous studies yielded inconsistent results, possibly due to neglecting the possibility of interactions between offline and online communications. To explore potential interactions among different communication modes (online vs. offline) and communication types (private vs. public), we adopted the experience sampling method to track 418 Japanese individuals over 21 days and analyzed the data using multilevel models and psychometric network models. The findings revealed that digital use has only small direct effects on happiness and loneliness, especially through public (one-to-many) online communication. The increased digital use reduced offline communication time, indirectly influencing loneliness to a large degree. Overall, this study highlights the indirect effects of decreased face-to-face communication and the significant role of one-to-many online communication, which may explain a part of the diverse findings on this issue.

Shabina Rana, Nayab Iftikhar

Objective: To determine the effectiveness of ten therapeutic exercises on the patients of Oro-pharyngeal Dysphagia (OD) clinically diagnosed with one structural disorder (Head and neck cancer; HNC) and two neurological disorders (Traumatic Brain Injury; TBI and Cerebral Vascular Accidents; CVA). Methodology: The Quasi experimental study (pretest-posttest design) was conducted, gathering a sample of 75 patients with mild to moderate Oro-pharyngeal Dysphagia (OD) severity through purposive sampling technique from Govt. and private hospitals without no age and geneder limits. The patients with neurological diseases, nasogastric (NG) tube and tracheostomy were excluded. Two screening test (a) Glassgow Coma Scale (GCS) and (b) The Repetitive Saliva Swallowing Test (RSST) were used to investigate patient’s consciousness and voluntarily swallow, respectively. To quantify the effectiveness of therapeutic manual, The Eating Assessment Tool (EAT-10) was employed as baseline (pre-test and post-test). Therapeutic protocol was received by the patients twice a week for six weeks in the clinical setting and post test was administered on patients’ follow-ups and some through online calls. Results: Using SPSS version 26, Shapiro-Wilk test demonstrated normality in the data distribution showing kurtosis (+10, -10) and skewness (+3, -3) values falling within their ranges. Consequently, parametric tests: One-way between-subject ANOVA was employed to compare the statistical significant mean difference between the groups (HNC, TBI, CVA) on EAT-10 score measuring the effect of therapeutic exercises manual for OD. Paired sample t-test was run to investigate the mean difference of EAT-10 scores within subjects before and after the implication of therapeutic exercises manual. One-way between-subject ANOVA identified a significant mean difference of EAT-10 score between three groups F (2, 72) = 17.64, p< .05, with large effect size (η2= .970). Paired sample t-test results indicated a significant mean difference (t= 80.884, df= 74, p< .005, one-tailed) with large effect size (d = .82) within the subjects before and after the intervention. Conclusion: So, findings addressed a large improvement in Oro-Pharyngeal Dysphagia after the implementation of therapeutic exercises manual.

Karen M. Doyle, Barbara Hannigan

Research suggests pervasive disparities in mental health diagnoses, levels of care and treatment outcomes for Black or Multi-ethnic service users compared to white service users. This study explores the mental health implications of being racialised and subsequent experiences of psychological services. Studies show that increased race related stressors over time increase the likelihood a person will experience psychological distress. Research also suggests that the personal biases of mental health service providers may impact their competencies and success rate when working with Black and Multi-ethnic clients. In this study, semi-structured interviews were conducted with 10 Black or Multi-ethnic participants who had recently engaged in psychological therapy in Ireland. Data were analysed using the Generic Descriptive Interpretive Qualitative Research Analysis (GDI-QR) approach (Elliott & Timulak, 2021). All participants shared lived experiences of negative mental health implications of being racialised. These were expressed as feelings of not belonging, experiences of racism or discrimination, feeling silenced by cultural and social stigma, and feeling inequitably burdened compared to their white peers. Participants typically reported barriers to access as conflicting values between cultures, previous negative experiences, waitlists, lack of previous knowledge of mental health, and inadequate services for Black service users. Barriers to engagement were mismanagement of racial dynamics and a perceived lack of attunement between service provider and client. Conversely, participants also spoke of growth promoting therapy experiences that strengthened the therapeutic bond. Suggestions for change include adjustment to practice and training for psychologists, in addition to suggestions that could increase accessibility to services for Black and Multi-ethnic service users.

W. Tschacher, Deborah Meier

Abstract Objective: In this proof-of-principle study, a convenience sample of 55 dyadic psychotherapy sessions conducted by one therapist was analyzed. This study aimed at exploring physiological synchrony in naturalistic psychotherapy sessions and the association of such synchrony with self-report ratings. Methods: The electrocardiograms and respiration behavior of both therapist and client were monitored simultaneously. Four clients were included, and session outcome was documented by session reports in two clients. From electrocardiograms, heart rate and heart rate variability were derived in consecutive 15-second intervals throughout sessions. Entire sessions (average duration, 51 min) were assessed for physiological synchrony of therapist’s and client’s respiration, electrocardiogram, heart rate, and heart rate variability. Two methods of synchrony computation were applied to the time series: windowed cross-correlation and correlation of local slopes (concordance). Both methods included surrogate controls using segment-wise shuffling. Results: Significant synchrony of three measures, but not of electrocardiograms, was present in this dataset. In regression models, we found associations between synchronies and alliance ratings, and further self-report variables. Conclusions: Results support the existence of physiological synchrony in this collection of psychotherapy sessions, which speaks for the sympathetic and parasympathetic coupling between this therapist and her clients and its link with ratings of the therapy process. The feasibility of deriving signatures of synchrony of physiological signals with the described methodology was corroborated. The findings now await generalization by further research.

J. Rosendahl, Cameron T Alldredge, G. Burlingame et al.

This article reviews group psychotherapy research published within the past 30 years, predominantly focusing on outcomes of group treatments for patients with various mental disorders. Additionally, meta-analyses on the efficacy of group treatments for patients with cancer or chronic pain are summarized. Results strongly support the use of group therapy and demonstrate outcomes equivalent to those of individual psychotherapy. The research also appears to emphasize the effect of feedback on outcomes in group treatments and an association between treatment outcomes and group cohesion and alliance. Other promising developments in the field of group therapy are discussed.

M. Karver, Alessandro S. De Nadai, Maureen F Monahan et al.

In the youth treatment literature, the alliance has been defined and measured as a consensual or collaborative bond. In this article, we review varied definitions of the alliance, enumerate its frequent measures, and present clinical examples. We provide a meta-analytic review on the relation between the therapeutic alliance and treatment outcome in child and adolescent psychotherapy. In particular, this review only includes prospective studies of youth therapy that used an explicit measure of alliance. The meta-analysis of 28 studies revealed a weighted random effect size of r = .19 (k = 28, N = 2419, p < .01, 95% confidence interval [.13, .25]), which is a small to medium effect (equivalent to d = 0.39) consistent with the adult alliance literature and with prior youth meta-analyses. Given that a medium-large amount of heterogeneity was observed in effect sizes (I2 = 64.19%), theory- and method-based moderators were examined. Multiple moderators of the alliance–outcome association were found, including diagnosis class, type of therapy, study design (randomized controlled trials [RCT] vs. nonrandomized trials [non-RCT]), and treatment setting (inpatient vs. outpatient). Research limitations, patient contributions, and diversity considerations follow. The article concludes with research-informed practices for building and maintaining the therapeutic alliance with youth.

Nayla Munawar, Khansa Ahsan, K. Muhammad et al.

Schizophrenia is a chronic, heterogeneous neurodevelopmental disorder that has complex symptoms and uncertain etiology. Mounting evidence indicates the involvement of genetics and epigenetic disturbances, alteration in gut microbiome, immune system abnormalities, and environmental influence in the disease, but a single root cause and mechanism involved has yet to be conclusively determined. Consequently, the identification of diagnostic markers and the development of psychotic drugs for the treatment of schizophrenia faces a high failure rate. This article surveys the etiology of schizophrenia with a particular focus on gut microbiota regulation and the microbial signaling system that correlates with the brain through the vagus nerve, enteric nervous system, immune system, and production of postbiotics. Gut microbially produced molecules may lay the groundwork for further investigations into the role of gut microbiota dysbiosis and the pathophysiology of schizophrenia. Current treatment of schizophrenia is limited to psychotherapy and antipsychotic drugs that have significant side effects. Therefore, alternative therapeutic options merit exploration. The use of psychobiotics alone or in combination with antipsychotics may promote the development of novel therapeutic strategies. In view of the individual gut microbiome structure and personalized response to antipsychotic drugs, a tailored and targeted manipulation of gut microbial diversity naturally by novel prebiotics (non-digestible fiber) may be a successful alternative therapeutic for the treatment of schizophrenia patients.

Anna Fang, Wenjie Yang, Raj Sanjay Shah et al.

Online mental health support communities have grown in recent years for providing accessible mental and emotional health support through volunteer counselors. Despite millions of people participating in chat support on these platforms, the clinical effectiveness of these communities on mental health symptoms remains unknown. Furthermore, although volunteers receive some training based on established therapeutic skills studied in face-to-face environments such as active listening and motivational interviewing, it remains understudied how the usage of these skills in this online context affects people's mental health status. In our work, we collaborate with one of the largest online peer support platforms and use both natural language processing and machine learning techniques to measure how one-on-one support chats affect depression and anxiety symptoms. We measure how the techniques and characteristics of support providers, such as using affirmation, empathy, and past experience on the platform, affect support-seekers' mental health changes. We find that online peer support chats improve both depression and anxiety symptoms with a statistically significant but relatively small effect size. Additionally, support providers' techniques such as emphasizing the autonomy of the client lead to better mental health outcomes. However, we also found that some behaviors (e.g. persuading) are actually harmful to depression and anxiety outcomes. Our work provides key understanding for mental health care in the online setting and designing training systems for online support providers.

Tianlai Chen, Madeleine Dumas, Rio Watson et al.

Target proteins that lack accessible binding pockets and conformational stability have posed increasing challenges for drug development. Induced proximity strategies, such as PROTACs and molecular glues, have thus gained attention as pharmacological alternatives, but still require small molecule docking at binding pockets for targeted protein degradation. The computational design of protein-based binders presents unique opportunities to access "undruggable" targets, but have often relied on stable 3D structures or structure-influenced latent spaces for effective binder generation. In this work, we introduce PepMLM, a target sequence-conditioned generator of de novo linear peptide binders. By employing a novel span masking strategy that uniquely positions cognate peptide sequences at the C-terminus of target protein sequences, PepMLM fine-tunes the state-of-the-art ESM-2 pLM to fully reconstruct the binder region, achieving low perplexities matching or improving upon validated peptide-protein sequence pairs. After successful in silico benchmarking with AlphaFold-Multimer, outperforming RFDiffusion on structured targets, we experimentally verify PepMLM's efficacy via fusion of model-derived peptides to E3 ubiquitin ligase domains, demonstrating endogenous degradation of emergent viral phosphoproteins and Huntington's disease-driving proteins. In total, PepMLM enables the generative design of candidate binders to any target protein, without the requirement of target structure, empowering downstream therapeutic applications.

Put'ri Modu, Arthur Huwae

PMO stands for porn, masturbation, & orgasm. Many individuals, especially adolescents, have begun to take up sexual pleasure via social media. Reputable studies have noted that individuals who experience sexual experimentation on social media have diverse dynamics and various indications of factors. This study aims to describe the experiences of individuals who have done PMO. Two participants participated through snowball sampling. Data was collected based on semi-structured interviews with the participants. Data analysis was carried out phenomenologically descriptively to see the substance of the PMO experience in the form of themes. This research study obtained 8 PMO themes, including self-limitation, self-control, exploratory behavior, idle curiosity, insecurity, escape coping, fetish, and addiction. The interest of this research is how it can be an effort to will sexual self-disclosure in a more positive way to build self-development.