Machine learning algorithms are commonly used for quickly and efficiently counting people from a crowd. Test-time adaptation methods for crowd counting adjust model parameters and employ additional data augmentation to better adapt the model to the specific conditions encountered during testing. The majority of current studies concentrate on unsupervised domain adaptation. These approaches commonly perform hundreds of epochs of training iterations, requiring a sizable number of unannotated data of every new target domain apart from annotated data of the source domain. Unlike these methods, we propose a meta-test-time adaptive crowd counting approach called CrowdTTA, which integrates the concept of test-time adaptation into the meta-learning framework and makes it easier for the counting model to adapt to the unknown test distributions. To facilitate the reliable supervision signal at the pixel level, we introduce uncertainty by inserting the dropout layer into the counting model. The uncertainty is then used to generate valuable pseudo labels, serving as effective supervisory signals for adapting the model. In the context of meta-learning, one image can be regarded as one task for crowd counting. In each iteration, our approach is a dual-level optimization process. In the inner update, we employ a self-supervised consistency loss function to optimize the model so as to simulate the parameters update process that occurs during the test phase. In the outer update, we authentically update the parameters based on the image with ground truth, improving the model\'s performance and making the pseudo labels more accurate in the next iteration. At test time, the input image is used for adapting the model before testing the image. In comparison to various supervised learning and domain adaptation methods, our results via extensive experiments on diverse datasets showcase the general adaptive capability of our approach across datasets with varying crowd densities and scales.

According to the main international guidelines, patients with obesity and psychiatric/psychological disorders who cannot be addressed to surgery are recommended to follow a nutritional approach and a psychological treatment. A total of 94 patients (T0) completed a battery of self-report measures: Symptom Checklist-90-Revised (SCL-90-R), Barratt Impulsiveness Scale-11 (BIS-11), Binge-Eating Scale (BES), Obesity-Related Well-Being Questionnaire-97 (ORWELL-97), and Minnesota Multiphasic Personality Inventory-2 (MMPI-2). Then, twelve sessions of a brief psychodynamic psychotherapy were delivered, which was followed by the participants completing the follow-up evaluation (T1). Two groups of patients were identified: Group 1 (n = 65), who fully completed the assessment in both T0 and T1; and Group 2-dropout (n = 29), who fulfilled the assessment only at T0 and not at T1. Machine learning models were implemented to investigate which variables were most associated with treatment failure. The classification tree model identified patients who were dropping out of treatment with an accuracy of about 80% by considering two variables: the MMPI-2 Correction (K) scale and the SCL-90-R Phobic Anxiety (PHOB) scale. Given the limited number of studies on this topic, the present results highlight the importance of considering the patient\'s level of adaptation and the social context in which they are integrated in treatment planning. Cautionary notes, implications, and future directions are discussed.

Background: Retention in treatment is crucial for the success of interventions targeting alcohol use disorder (AUD), which affects over 100 million people globally. Most previous studies have used classical statistical techniques to predict treatment dropout, and their results remain inconclusive. This study aimed to use novel machine learning tools to identify models that predict dropout with greater precision, enabling the development of better retention strategies for those at higher risk. Methods: A retrospective observational study of 39,030 (17.3% female) participants enrolled in outpatient-based treatment for alcohol use disorder in a state-wide public treatment network has been used. Participants were recruited between 1 January 2015 and 31 December 2019. We applied different machine learning algorithms to create models that allow one to predict the premature cessation of treatment (dropout). With the objective of increasing the explainability of those models with the best precision, considered as black-box models, explainability technique analyses were also applied. Results: Considering as the best models those obtained with one of the so-called black-box models (support vector classifier (SVC)), the results from the best model, from the explainability perspective, showed that the variables that showed greater explanatory capacity for treatment dropout are previous drug use as well as psychiatric comorbidity. Among these variables, those of having undergone previous opioid substitution treatment and receiving coordinated psychiatric care in mental health services showed the greatest capacity for predicting dropout. Conclusions: By using novel machine learning techniques on a large representative sample of patients enrolled in alcohol use disorder treatment, we have identified several machine learning models that help in predicting a higher risk of treatment dropout. Previous treatment for other substance use disorders (SUDs) and concurrent psychiatric comorbidity were the best predictors of dropout, and patients showing these characteristics may need more intensive or complementary interventions to benefit from treatment.

This study investigates the role of social capital within the university context in retaining working students. It specifically examines the effects of university social capital factors-such as teacher-student relationships, peer networks, and support services-on the dropout intentions of working students, emphasizing the mediating role of employability trust. Using a sample of 1902 working students from the Eurostudent VII survey, this study employed factor analysis techniques and structural equation modeling to derive its findings. The results indicated that university social capital significantly reduces dropout intentions among working students. Strong teacher-student relationships, satisfaction with support services, robust peer networks, and high employability trust positively influence this social capital. There is a statistically significant negative association between teacher-student relationships, peer networks, employability trust, and dropout intentions. Furthermore, the findings reveal that without enhancing students\' employability trust, the effectiveness of support services might be limited. These findings not only contribute to the discourse on student retention and the development of university social capital but also provide practical insights for higher education strategies aimed at supporting working students.

OBJECTIVE: A multidisciplinary approach to Inflammatory Bowel Disease (IBD) has recently demonstrated a positive impact in pediatric patients, reducing dropout rates and facilitating the transition to adult care. Our study aims to evaluate how this approach influences disease activity, dropout rates, and transition.
METHODS: We conducted a longitudinal observational study including all patients diagnosed with IBD during pediatric-adolescent age, with a minimum follow-up period of 12 months. For each patient, endpoints included therapeutic approach, need for surgery and transition features.
RESULTS: We included 19 patients: 13 with Ulcerative Colitis (UC) and 6 with Crohn\'s disease (CD). Most patients required multiple lines of therapy, with over 50% in both groups receiving biological drugs. Compliance was good, with a single dropout in each group (10, 5%). The need for surgery was significantly higher in the CD group compared to the UC group (16% vs. 7.7%, p < 0.01). Mean age at transition was significantly higher in the UC group compared to the CD group (19.2 ± 0.7 years SD vs. 18.3 ± 0.6 years SD, p < 0.05).
CONCLUSIONS: In our experience, the multidisciplinary approach to IBD in transition-age patients appears effective in achieving clinical remission, offering the potential to reduce therapeutic dropouts.

BACKGROUND: Dietary behaviors significantly influence health outcomes across populations. Unhealthy diets are linked to serious diseases and substantial economic burdens, contributing to approximately 11 million deaths and significant disability-adjusted life years annually. Digital dietary interventions offer accessible solutions to improve dietary behaviors. However, attrition, defined as participant dropout before intervention completion, is a major challenge, with rates as high as 75%-99%. High attrition compromises intervention validity and reliability and exacerbates health disparities, highlighting the need to understand and address its causes.
OBJECTIVE: This study systematically reviews the literature on attrition in digital dietary interventions to identify the underlying causes, propose potential solutions, and integrate these findings with behavior theory concepts to develop a comprehensive theoretical framework. This framework aims to elucidate the behavioral mechanisms behind attrition and guide the design and implementation of more effective digital dietary interventions, ultimately reducing attrition rates and mitigating health inequalities.
METHODS: We conducted a systematic review, meta-analysis, and thematic synthesis. A comprehensive search across 7 electronic databases (PubMed, MEDLINE, Embase, CENTRAL, Web of Science, CINAHL Plus, and Academic Search Complete) was performed for studies published between 2013 and 2023. Eligibility criteria included original research exploring attrition in digital dietary interventions. Data extraction focused on study characteristics, sample demographics, attrition rates, reasons for attrition, and potential solutions. We followed ENTREQ (Enhancing the Transparency in Reporting the Synthesis of Qualitative Research) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and used RStudio (Posit) for meta-analysis and NVivo for thematic synthesis.
RESULTS: Out of the 442 identified studies, 21 met the inclusion criteria. The meta-analysis showed mean attrition rates of 35% for control groups, 38% for intervention groups, and 40% for observational studies, with high heterogeneity (I²=94%-99%) indicating diverse influencing factors. Thematic synthesis identified 15 interconnected themes that align with behavior theory concepts. Based on these themes, the force-resource model was developed to explore the underlying causes of attrition and guide the design and implementation of future interventions from a behavior theory perspective.
CONCLUSIONS: High attrition rates are a significant issue in digital dietary interventions. The developed framework conceptualizes attrition through the interaction between the driving force system and the supporting resource system, providing a nuanced understanding of participant attrition, summarized as insufficient motivation and inadequate or poorly matched resources. It underscores the critical necessity for digital dietary interventions to balance motivational components with available resources dynamically. Key recommendations include user-friendly design, behavior-factor activation, literacy training, force-resource matching, social support, personalized adaptation, and dynamic follow-up. Expanding these strategies to a population level can enhance digital health equity. Further empirical validation of the framework is necessary, alongside the development of behavior theory-guided guidelines for digital dietary interventions.
BACKGROUND: PROSPERO CRD42024512902; https://tinyurl.com/3rjt2df9.

UNASSIGNED: Polycystic Ovary Syndrome (PCOS) is a medical condition that causes hormonal disorders in women in their childbearing years. The hormonal imbalance leads to a delayed or even absent menstrual cycle. Women with PCOS mainly suffer from extreme weight gain, facial hair growth, acne, hair loss, skin darkening, and irregular periods, leading to infertility in rare cases. Doctors usually examine ultrasound images and conclude the affected ovary but are incapable of deciding whether it is a normal cyst, PCOS, or cancer cyst manually.
UNASSIGNED: To have access to the high-risk crucial PCOS and to detect the condition and the treatment aimed at mitigating health hazards such as endometrial hyperplasia/cancer, infertility, pregnancy complications, and the long-term burden of chronic diseases such as cardiometabolic disorders linked with PCOS.
UNASSIGNED: The proposed Self-Defined Convolution Neural Network method (SD_CNN) is used to extract the features and machine learning models such as SVM, Random Forest, and Logistic Regression are used to classify PCOS images. The parameter tuning is done with lesser parameters in order to overcome over-fitting issues. The self-defined model predicts the occurrence of the cyst based on the analyzed features and classifies the class labels effectively.
UNASSIGNED: The Random Forest Classifier was found to be the most reliable and accurate among Support Vector Machine (SVM) and Logistic Regression (LR), with accuracy being 96.43%.
UNASSIGNED: The proposed model establishes better trade-off compared to various other approaches and works effectually for PCOS prediction.

UNASSIGNED: Psychotherapeutic failures involve situational, relational, and personal factors. Dropout refers to a patient\'s unilateral termination of treatment without the therapist\'s knowledge or approval. Premature termination occurs when therapy is discontinued before achieving a sufficient reduction in initial problems.
UNASSIGNED: This study explores the role of therapist\'s emotional response (countertransference), gender, psychotherapeutic orientation, and patient diagnosis in the context of psychotherapeutic failures.
UNASSIGNED: A mixed-method approach was used. Fifty-nine Italian psychotherapists, practicing mostly privately with at least 5 years of experience, were recruited through Italian professional internet websites. The Therapist Response Questionnaire and the Impasse Interview were administered to each psychotherapist. Each therapist was asked to reflect on their last dropout patient. Quantitative (MANOVA) and qualitative analyses (textual content analysis) were conducted with SPSS and T-LAB, respectively.
UNASSIGNED: The quantitative analyses revealed that the most frequent countertransference response was Helpless/Inadequate, with female therapists experiencing this more frequently than male therapists. The qualitative analyses identified two main factors explaining most of the variance in countertransference responses: Parental/Protective versus Hostile/Angry, and Positive/Satisfying versus Helpless/Inadequate, with Helpless/Inadequate central. Additionally, the qualitative analysis of treatment interruption methods revealed two factors explaining over 50% of the variance. Lack of communication was linked to negative themes, while mediated and direct communication were associated with positive terms. Direct communication was characterized as useful, while mediated communication was linked to dropout and attachment figures.
UNASSIGNED: Under pressure, psychotherapists\' anxiety levels increase, often managed ambivalently or avoidantly. These results suggest that awareness of psychotherapist emotional responses is important to limit psychotherapeutic failures. These findings offer valuable insights for clinical practice.

Visual predictive checks (VPC) are commonly used to evaluate pharmacometrics models. However their performance may be hampered if patients with worse outcomes drop out earlier, as often occurs in clinical trials, especially in oncology. While methods accounting for dropouts have appeared in literature, they vary in assumptions, flexibility, and performance, and the differences between them are not widely understood. This manuscript aims to elucidate which methods can be used to handle VPC with dropout and when, along with a more informative VPC approach using confidence intervals. Additionally, we propose constructing the confidence interval based on the observed data instead of the simulated data. The theoretical framework for incorporating dropout in VPCs is developed and applied to propose two approaches: full and conditional. The full approach is implemented using a parametric time-to-event model, while the conditional approach is implemented using both parametric and Cox proportional-hazard (CPH) models. The practical performances of these approaches are illustrated with an application to the tumor growth dynamics (TGD) modeling of data from two cancer clinical trials of nivolumab and docetaxel, where patients were followed until disease progression. The dataset consisted of 3504 tumor size measurements from 855 subjects, which were described by a TGD model. The dropout of subjects was described by a Weibull or CPH model. Simulated datasets were also used to further illustrate the properties of the VPC methods. The results showed that the more familiar full approach might not provide meaningful improvement for TGD model evaluation over the naive approach of not adjusting for dropout, and could be outperformed by the conditional approach using either the Weibull model or the Cox proportional hazard model. Overall, including confidence intervals in VPC should improve interpretation, the conditional approach was shown to be more generally applicable when dropout occurs, and the nonparametric approach could provide additional robustness.

BACKGROUND: The attrition rate of Chinese medical students is high. This study utilizes a nomogram technique to develop a predictive model for dropout intention among Chinese medical undergraduates based on 19 individual and work-related characteristics.
METHODS: A repeated cross-sectional study was conducted, enrolling 3536 medical undergraduates in T1 (August 2020-April 2021) and 969 participants in T2 (October 2022) through snowball sampling. Demographics (age, sex, study phase, income, relationship status, history of mental illness) and mental health factors (including depression, anxiety, stress, burnout, alcohol use disorder, sleepiness, quality of life, fatigue, history of suicidal attempts (SA), and somatic symptoms), as well as work-related variables (career choice regret and reasons, workplace violence experience, and overall satisfaction with the Chinese healthcare environment), were gathered via questionnaires. Data from T1 was split into a training cohort and an internal validation cohort, while T2 data served as an external validation cohort. The nomogram\'s performance was evaluated for discrimination, calibration, clinical applicability, and generalization using receiver operating characteristic curves (ROC), area under the curve (AUC), calibration curves, and decision curve analysis (DCA).
RESULTS: From 19 individual and work-related factors, five were identified as significant predictors for the construction of the nomogram: history of SA, career choice regret, experience of workplace violence, depressive symptoms, and burnout. The AUC values for the training, internal validation, and external validation cohorts were 0.762, 0.761, and 0.817, respectively. The nomogram demonstrated reliable prediction and discrimination, with adequate calibration and generalization across both the training and validation cohorts.
CONCLUSIONS: This nomogram exhibits reasonable accuracy in foreseeing dropout intentions among Chinese medical undergraduates. It could guide colleges, hospitals, and policymakers in pinpointing students at risk, thus informing targeted interventions. Addressing underlying factors such as depressive symptoms, burnout, career choice regret, and workplace violence may help reduce the attrition of medical undergraduates.
BACKGROUND: This is an observational study. There is no Clinical Trial Number associated with this manuscript.