Bubble entropy has established its own place in the research community, representing a new and promising definition of entropy. Based on the work required to order a vector in an embedding space of dimension m, Bubble entropy gives a physical interpretation of what the metric actually computes. In this work, Bubble entropy is evaluated based on its ability to classify RR time series, the time series most commonly considered for entropy-based analysis in the field of biomedical engineering. For this purpose, it is compared with three other definitions of entropy: the most widely used Sample entropy and Approximate entropy, the most relative to Bubble entropy, and also the widely used Permutation entropy. Signals from healthy individuals, in sinus rhythm, are compared with signals from cardiac patients, and machine learning methods are applied to calculate the classification accuracy that each method can achieve. The classifiers chosen are k-Nearest Neighbors, Support Vector Machine, Logistic Regression, and Gaussian Naive Bayes. Feature evaluation methods are also employed to serve as additional measures of effectiveness. Bubble entropy generally manages to achieve better results than Sample entropy, Approximate entropy and Permutation entropy, both in terms of classification accuracy and feature ranking.

This brief research report explored the relationships between hikikomori symptom severity (extreme social withdrawal), basic psychological needs of Competence, Autonomy, and Relatedness, and perceived parental bonding in Italian adults experiencing social isolation. Participants (N = 33; Mage = 27.83, SD = 7.46; 42.9% women) were individuals recruited online who scored above the high-risk cutoff for hikikomori on the Hikikomori Questionnaire-25 (HQ-25). They completed the Basic Psychological Need Satisfaction and Frustration Scale (BPNSFS) and the Parental Bonding Instrument (PBI). Competence Frustration accounted for substantial variability in hikikomori symptom severity in this high-risk sample, explaining approximately 31% of the variance. Regarding perceived parental bonding, maternal Care was positively associated with Autonomy Satisfaction and negatively with Competence Frustration, whereas maternal Control was positively related to frustration of all three needs. Paternal Care was negatively related to Autonomy and Competence Frustration, while paternal Control was positively associated with Relatedness Frustration. Over 30% of participants perceived maternal bonding as Affectionless Control and paternal bonding as either Affectionless Control or Neglectful. No gender differences emerged. Findings suggest that Competence Frustration may represent a key psychological correlate of hikikomori symptom severity in this high-risk group. Moreover, distinct maternal and paternal patterns of perceived Care and Control were associated with need frustration and satisfaction, as well as with the hikikomori dimension of perceived lack of Emotional Support. Study limitations include small sample size, cross-sectional design, reliance on self-report measures, and potential selection bias toward help-seeking individuals. Replication in larger longitudinal samples is warranted to confirm these preliminary results.

PurposeThis article evaluates the impact of the Compass Program over the last six years, with a focus on access to mental health services in Northern British Columbia (BC) and Indigenous communities within the region.MethodsCompass program data from September 2018 to April 2024 were analyzed. Demographic and clinical characteristics were compared between Northern and other BC regions. Quantitative variables were summarized using descriptive statistics.FindingsNorthern BC accounts for 21.4% of total Compass encounters. Indigenous youth in this region are particularly underserved, and community providers are more likely to request specialized virtual consultations at Compass than other regions. Anxiety was the most common presenting concern across all regions. Northern BC represented 46% of all Indigenous consultations and showed a steady increase in Indigenous-related calls-from 18% in 2018 to 41% in 2024. Among direct consults in Northern BC, 55% involved Indigenous patients and medication questions were the most common reasons for calling.ConclusionsThe study highlights the distinct mental health challenges in Northern BC compared to other regions of the province, suggesting the unique socioeconomic and geographical factors contributing to different mental health issues. Further research should be done to explore the impact of specialized child and youth mental health and substance use provider-to-provider consultations in other similarly underserved areas in Canada. The Compass program at BC Children's Hospital provides a model that tries to navigate mental health disparities of Northern BC, where there is high demand for mental health services. Clinical trials registry number: H23-03251-A001.

Bubble entropy is a recently proposed entropy metric. Having certain advantages over popular definitions, bubble entropy finds its place in the research community map. It belongs to the family of entropy estimators which embed the signal into an m-dimensional space. Two are the main drawbacks for which those methods are criticized: the high computational cost and the dependence on parameters. Bubble entropy can be an answer to both, since computation can be performed in linear time and the dependence on parameters can be considered minimal in many practical situations. Popular entropy definitions, which are built over an embedding of the signal, mainly rely on two parameters: the size of the embedding space m and a tolerance r, which set a threshold over the distance between two points in the m-dimensional space to be considered similar. Bubble entropy totally eliminates the necessity to define a threshold distance, while it largely decouples the entropy estimation from the selection of the actual size of the embedding space in stationary conditions. Bubble entropy is compared to popular entropy definitions on theoretical and experimental basis. Theoretical analyses reveal significant advantages. Experimental analyses, comparing congestive heart failure patients and controls subjects, show that bubble entropy outperforms other popular, well established, entropy estimators in discriminating those two groups. Furthermore, machine learning-based feature ranking and experiments show that bubble entropy serves as a valuable source of features for AI decision-support algorithms.

Over the past decades, digital innovation has profoundly transformed pediatric care, promoting more integrated, personalized, and continuous models of assistance across hospital, community, and home settings. This contribution explores the impact of three key technological domains: telemedicine, virtual and augmented reality, and artificial intelligence. Telemedicine has expanded access to healthcare services, improved monitoring of chronic conditions, and strengthened communication between healthcare professionals and families. Its rapid development during the COVID-19 pandemic demonstrated its value in ensuring continuity of care and supporting vulnerable pediatric populations. Virtual and augmented reality offer new possibilities in surgical planning, medical training, rehabilitation, and psychological support, helping reduce anxiety and pain during procedures while enhancing understanding of clinical pathways. Artificial intelligence enables the analysis of large volumes of clinical and behavioral data, supporting early diagnosis, predictive modeling, and personalized clinical decision-making. Despite these opportunities, the integration of emerging technologies into pediatric practice requires careful attention to ethical, organizational, and educational issues, including data security, equitable access, and professional training. Overall, digital technologies are reshaping pediatrics toward more accessible, efficient, family-centered care.

The omnipolar mapping technology (OT) was introduced to overcome the sensitivity of bipolar recordings to catheter orientation and relies on electrodes arranged in regular geometries, such as squares or triangles. Recent studies demonstrated that OT can be applied without the need for specialized catheter geometries. However, whether OT can be effectively applied in sequential mapping without specialized catheter designs remains an open question. In this study, we proposed a variant of OT which could be applied in sequential mapping. A key challenge of this approach is that the electrical field has to be reconstructed from multiple wavefronts recorded across different beats rather than from a single wave as in standard OT, with electrodes arbitrarily positioned. Despite OT was found sufficiently tolerant to the spatial variability of the electrodes, the temporal variability may play an important role. Therefore, to test the efficacy of the algorithm, we investigated the impact of physiological inter-beat variability on the proposed algorithm, with a particular focus on changes in conduction velocity (CV). We performed multiple two-dimensional planar wave simulations with CV values spanning physiological ranges to emulate multiple atrial beats. For each simulation, two bipolar signals were randomly sampled within a circular region of radius 5 mm around a fixed reference point and used to apply OT. Three experimental conditions were considered: i) all bipolar signals were generated from a wavefront with fixed maximum CV, ii) all bipolar signals originated from a single wavefront with a randomly selected CV per simulation, and iii) each bipolar signal originated from a wavefront with an independently selected random CV. Results showed that sequential OT consistently outperformed standard bipolar mapping across all experimental conditions for the characterization of the voltage, exhibiting higher median values (e.g., 5.04 vs 4.62 in Experiment 1 and 4.18 vs 3.68 in Experiment 3). Wavefront direction estimation remained accurate in all cases, with a maximum error of 0, (−3.05,, 3.25)° in Experiment 3. CV estimation of both standard and sequential OT showed a systematic positive bias in Experiment 1 (median 0.99 vs reference 0.9 m/s) and increased variability in Experiments 2 and 3. Sequential OT improved voltage estimation compared with conventional bipolar mapping and enabled reliable wavefront direction assessment. Although the promising results, some limitations persisted, such as a positive bias in CV estimation and incomplete recovery of the reference voltage.

With the development of deep learning (DL)-based methods, automated atrial fibrillation (AF) detection from electrocardiograms (ECGs) has recently gained much attention. Although the performance of DL has been encouraging, the susceptibility of DL models to overfitting would benefit from the exploration of uncertainty quantification (UQ) to ensure safe integration into clinical practice. However, there has been limited exploration of UQ methods in the context of DL models for AF detection using Holter ECG recordings, and a comprehensive comparison of various UQ techniques remains absent. This study addressed this gap by introducing a benchmark study wherein 11 distinct UQ methods were rigorously evaluated and compared across three public Holter repositories: IRIDIA-AF, Long-Term AF, and MIT-BIH AF datasets. A residual DL model was used for the UQ methods, which is one of the most common architectures in this domain for its ability to capture complex patterns within ECG data. The findings revealed that batch-ensemble (BE) and packed-ensemble (PE) outperformed other UQ methods concerning both performance, as quantified by sensitivity, specificity and expected calibration error, and computational efficiency. In addition, when we implemented reject inference to discard ECG segments where the model confidence was not sufficiently high, BE and PE still showed to reject the least number of samples, while retaining the highest detection performance.

This letter presents a robust framework based on penalized least-squares optimization (PLSO) with e1-norm regular-ization, specifically designed for the development and implementation of bandpass filters (BPFs). By integrating the sparsity-inducing properties of e1-norm regularization with the frequency selectivity inherent in conventional BPFs, this approach yields an adaptive filter capable of dynamically adjusting its parameters accordingto the characteristics of the input signal. This adaptability enables the filter to accurately capture variations in frequency bands while preserving edges and boundaries between them

BACKGROUND:There is a lack of mental health and substance use providers for youth in BC, particularly in rural and remote areas. To address these gaps, Canada's first child psychiatry access program, BC Children's Hospital Compass Program, was developed in 2018 to support providers across the province in providing evidence-based mental health and substance use care to youth under 25. This article describes the program's first five years and provides an overview of its creation, utilization, and clinical uses. METHODS:Quantitative data collected by the Compass Program from September 2018 through September 2023 were analyzed. Participation and utilization of the service by providers in the province were analyzed and descriptive statistics, including means with standard deviations for quantitative variables have been used to describe demographic and other medical factors related to participants. FINDINGS:A total of 2336 new providers have been enrolled since Compass' inception. Number of clinical calls into Compass remained steady over the five-year period with an average of 1085 individual providers served per year. Service use is highest in Vancouver Coastal Region (27.3%), followed by Northern Health (21.4%), Interior (15.7%), Vancouver Island (14.5%), and Fraser (13.4%), and Yukon (0.3%). General practitioners make up over a third of all encounters (34.6%), followed closely by pediatrician encounters making up 27.5% of total encounters from 2018-2023. These two provider types comprise over 60% of all encounters over the 5-year timespan. Encounters with other provider types were less common, with the third most common encounter being Child and Youth Mental Health (CYMH) clinicians, totalling 8.6% of total encounters. 37.6% of encounters were for male patients and 42.9% for female patients with 6.8% reporting "Other" genders and 12.7% declining to answer. Medication concerns are the most common reason for accessing Compass, regardless of gender. Therapy questions, resource coordination issues, and diagnostic clarification followed in frequency, comprising a similar amount of consults. Compass consultations have the potential to benefit three groups of people: the specific patient being consulted on, the provider requesting the consultation, as well as the provider's colleagues who might benefit from peer consultation. CONCLUSIONS:Capacity building is important given Compass receives calls from rural and remote areas where there are no psychiatrists or child psychiatrists where general practitioners and clinicians regularly work with patients along the entire spectrum of mental health and substance use disorders.

Major depressive disorder (MDD) affects approximately 4.4% of the global population. Its prevalence is increasing among adolescents and has led to the psychosocial condition known as hikikomori. MDD is typically assessed by self-report questionnaires, which, although informative, are subject to evaluator bias and subjectivity. To address these limitations, recent studies have explored machine learning (ML) for automated MDD detection. Among the input data used, speech signals stand out due to their low cost and minimal intrusiveness. However, many speech-based approaches lack integration with cognitive behavioral therapy (CBT) and adherence to evidence-based, patient-centered care—often aiming to replace rather than support clinical monitoring. In this context, we propose ML models to assess MDD in hikikomori patients using speech data from a real-world clinical trial. The trial is conducted in Italy, supervised by physicians, and comprises an eight-session CBT plan that is clinical evidence-based and follows patient-centered practices. Patients’ speech is recorded during therapy, and the Mel-Frequency Cepstral Coefficients (MFCCs) and wav2vec 2.0 embedding are extracted to train the models. The results show that the Multi-Layer Perceptron (MLP) predicted depression outcomes with a Root Mean Squared Error (RMSE) of 0.064 using only MFCCs from the first session, suggesting that early-session speech may be valuable for outcome prediction. When considering the entire CBT treatment (i.e., all sessions), the MLP achieved an RMSE of 0.063 using MFCCs and a lower RMSE of 0.057 with wav2vec 2.0, indicating approximately a 9.5% performance improvement. To aid the interpretability of the treatment outcomes, a binary task was conducted, where Logistic Regression (LR) achieved 70% recall in predicting depression improvement among young adults using wav2vec 2.0. These findings position speech as a valuable predictive tool in clinical informatics, potentially supporting clinicians in anticipating treatment response.

ObjectiveUnderstanding differences in outpatient care before and after mental health hospitalization for adolescents from diverse backgrounds is critical to ensuring effective and responsive care. The objective of the current study was to examine outpatient mental health care in the two years before and 30 days after a mental health hospitalization for adolescents from immigrant, refugee and non-immigrant backgrounds.MethodThis retrospective, population-based cohort study, conducted in British Columbia (BC), Canada, analyzed linked health service utilization data (practitioner billings, hospitalizations) and migration records to track outpatient care before and after mental health hospitalization. The study included adolescents (ages 10-18) with an unscheduled/urgent mental health hospitalization between January 1, 2008 and December 31, 2016 (n = 5,314) from a cohort of adolescents in 10 of the largest school districts in BC (between 1996 and 2016). The main analyses examined outpatient mental health visits (e.g., general practitioner/psychiatrist) (i) in the two years before hospitalization and (ii) in the 30 days after discharge. Sub-analyses focused on outpatient visits with psychiatrists.ResultsOverall, 30.4% had no outpatient mental health visit in the two years before hospitalization and 45.1% had none in the 30 days following discharge. First-generation immigrants and refugees and second-generation immigrant adolescents were significantly less likely than non-immigrants to have had an outpatient mental health visit in the two years before mental health hospitalization (aOR1st_gen_immg = 0.79, 95% CI, 0.63 to 0.98; aOR2nd_gen_immg = 0.75, 95% CI, 0.61 to 0.93; aOR1st_gen_ref = 0.40, 95% CI, 0.26 to 0.64). Second-generation immigrant adolescents were significantly more likely than non-immigrants to have had any outpatient mental health visit in the 30 days following hospitalization (aOR2nd_gen_immg = 1.34, 95% CI, 1.09 to 1.65).ConclusionsResults suggest outpatient care before and after mental health hospitalizations is limited for many adolescents in BC and differed by migration background. Implications for meeting standards of care are discussed.Plain Language Summary TitleMental health-related care from a doctor/psychiatrist before and after mental health hospitalization for adolescents from immigrant, refugee, and non-immigrant backgrounds in British Columbia.

Background Detecting subtle patterns of atrial fibrillation (AF) and irregularities in Holter recordings is intricate and unscalable if done manually. Artificial intelligence-based techniques can be beneficial. In fact, with the rapid advancement of AI, deep learning (DL) demonstrated the capability to identify AF from ECGs with significant performance. However, further development and validation on larger cohorts is still needed. Purpose The main purpose of this study was to develop a Residual-attention DL model by considering a large cohort of 2‑lead Holter recordings. Methods We developed a residual DL model by collecting a large dataset of 661 Holter recordings, which was labeled manually by an expert cardiologist. The DL model leveraged attention mechanisms, allowing it to capture long-range dependencies and intricate temporal relationships crucial for identifying subtle patterns indicative of AF. Results Experimental results demonstrated that our model achieved a sensitivity (detection of AF) of Se=0.928 and a specificity of Sp=0.915, with an AUC-ROC of AUC=0.967 on our dataset. Additionally, when evaluated with an external test dataset, specifically IRIDIA-AF, our DL model obtained Se=0.942, Sp=0.932, and AUC=0.965. Finally, when compared under similar experimental conditions with other state-of-the-art models, our DL model achieved slightly better performance overall. Conclusion The Residual-attention DL model we proposed offers a promising solution for AF detection. The validation on external datasets contributes to its potential for deployment in clinical settings, providing clinicians with a valuable decision support system.