Continuous Data Research Articles

Analysis of multiple factors influencing the survival of patients with advanced gastric cancer.

The aim of this study was to investigate the main factors influencing the survival of patients with advanced gastric cancer. The clinicopathological data of 120 patients with advanced gastric cancer were analyzed retrospectively, and clinical and pathological data were collected. Tumor tissue staging and grading were re-evaluated, and 5-year overall survival was followed up. The classified data were described by percentages, and the continuous data were described by standard deviations or medians. Univariate analysis was performed using the χ2 test or rank-sum test, followed by Kaplan-Meier survival analysis to calculate the median survival time and 5-year cumulative survival. A multivariate Cox regression model was used to evaluate the independent risk factors affecting survival. The test level was α = 0.05. Patients were followed up for 0 to 60 months, the 5-year overall survival rate was 36.2%, and the median survival time was 53.0 ± 1.461 months. K-M and log-rank test results revealed that tumor location, degree of differentiation, depth of invasion, regional lymph node involvement, and postoperative tumor stage were correlated with a decreased 5-year survival rate (P < 0.05). A multivariate Cox risk regression model was used to analyze the degree of histological differentiation (HR = 1.441; 95% CI = 1.049-1.979; P = 0.024), regional lymph node (HR = 1.626; 95% CI = 1.160-2.279; P = 0.005), and pTNM stage (HR = 2.266; 95% CI = 1.335-3.847; P = 0.002), which are independent risk factors for poor survival. Tumor location (P = 0.191), invasion depth (P = 0.579) and tumor size (P = 0.324) were not found to be independent risk factors. The degree of tumor differentiation, regional lymph node metastasis and postoperative pathological stage were found to be independent risk factors for 5-year overall survival in patients with advanced gastric cancer. Standardized and reasonable lymph node dissection and accurate postoperative pathological staging were very important.

Leveraging Transfer Learning and U-Nets Method for Improved Gap Filling in Himawari Sea Surface Temperature Data Adjacent to Taiwan

Satellite sea surface temperature (SST) images are valuable for various oceanic applications, including climate monitoring, ocean modeling, and marine ecology. However, cloud cover often obscures SST signals, creating gaps in the data that reduce resolution and hinder spatiotemporal analysis, particularly in the waters near Taiwan. Thus, gap-filling methods are crucial for reconstructing missing SST values to provide continuous and consistent data. This study introduces a gap-filling approach using the Double U-Net, a deep neural network model, pretrained on a diverse dataset of Level-4 SST images. These gap-free products are generated by blending satellite observations with numerical models and in situ measurements. The Double U-Net model excels in capturing SST dynamics and detailed spatial patterns, offering sharper representations of ocean current-induced SST patterns than the interpolated outputs of Data Interpolating Empirical Orthogonal Functions (DINEOFs). Comparative analysis with buoy observations shows the Double U-Net model’s enhanced accuracy, with better correlation results and lower error values across most study areas. By analyzing SST at five key locations near Taiwan, the research highlights the Double U-Net’s potential for high-resolution SST reconstruction, thus enhancing our understanding of ocean temperature dynamics. Based on this method, we can combine more high-resolution satellite data in the future to improve the data-filling model and apply it to marine geographic information science.

DMLoc: Automatic Microseismic Locating Workflow Based on Deep Learning and Waveform Migration

Abstract During hydraulic fracturing, real-time acquisition of the spatiotemporal distribution of microseismic in the reservoir is essential in evaluating the risk of induced seismicity and optimizing injection parameters. By integrating deep learning with migration-based location methods, we develop an automatic microseismic locating workflow (named DMLoc). DMLoc applies deep learning to automate phase picking and leverage the phase arrival probability function generated by a convolutional network as the input for waveform migration. The proposed workflow is first applied to the continuous data of the Dawson-Septimus area. Compared with a reference catalog generated by the SeisComP3 software, our method automatically locates 57 additional seismic events (accounting for 43% of the events in the obtained catalog). We further evaluate the performance of DMLoc by applying it to a 35-day continuous microseismic dataset from the Tony Creek Dual Microseismic Experiment. The spatiotemporal distribution of our detected events is consistent with results reported in prior catalogs, demonstrating the effectiveness of our method. In contrast to using raw microseismic records for stacking, DMLoc addresses the issue of inaccurate locating caused by low signal-to-noise ratios and polarity changes. The use of GPUs has substantially accelerated the calculations and enabled DMLoc to output locating results in minutes. This fast and efficient metric could be easily extended to any microseismic monitoring scenario that requires (near) real-time locations and assists in site-based risk mitigation and industrial operation optimization.

An Efficient Water Quality Prediction and Assessment Method Based on the Improved Deep Belief Network—Long Short-Term Memory Model

The accuracy of water quality prediction and assessment has always been the focus of environmental departments. However, due to the high complexity of water systems, existing methods struggle to capture the future internal dynamic changes in water quality based on current data. In view of this, this paper proposes a data-driven approach to combine an improved deep belief network (DBN) and long short-term memory (LSTM) network model for water quality prediction and assessment, avoiding the complexity of constructing a model of the internal mechanism of water quality. Firstly, using Gaussian Restricted Boltzmann Machines (GRBMs) to construct a DBN, the model has a better ability to extract continuous data features compared to classical DBN. Secondly, the extracted time-series data features are input into the LSTM network to improve predicting accuracy. Finally, due to prediction errors, noise that randomly follows the Gaussian distribution is added to the assessment results based on the predicted values, and the probability of being at the current water quality level in the future is calculated through multiple evolutionary computations to complete the water quality assessment. Numerical experiments have shown that our proposed algorithm has a greater accuracy compared to classical algorithms in challenging scenarios.

Hidden Variable Models in Text Classification and Sentiment Analysis

In this paper, we are proposing extensions to the multinomial principal component analysis (MPCA) framework, which is a Dirichlet (Dir)-based model widely used in text document analysis. The MPCA is a discrete analogue to the standard PCA (it operates on continuous data using Gaussian distributions). With the extensive use of count data in modeling nowadays, the current limitations of the Dir prior (independent assumption within its components and very restricted covariance structure) tend to prevent efficient processing. As a result, we are proposing some alternatives with flexible priors such as generalized Dirichlet (GD) and Beta-Liouville (BL), leading to GDMPCA and BLMPCA models, respectively. Besides using these priors as they generalize the Dir, importantly, we also implement a deterministic method that uses variational Bayesian inference for the fast convergence of the proposed algorithms. Additionally, we use collapsed Gibbs sampling to estimate the model parameters, providing a computationally efficient method for inference. These two variational models offer higher flexibility while assigning each observation to a distinct cluster. We create several multitopic models and evaluate their strengths and weaknesses using real-world applications such as text classification and sentiment analysis.

Transient surrogate modeling of modally reduced structures with discontinuous loads and damping

AbstractIn this work, a surrogate model for structural, transient and discontinuously excited finite element method simulations is developed. This allows to reduce the computational effort of repeated calculations of identical models under different load cases. The architecture of the surrogate combines fully connected neural network layers with long short-term memory layers. For the reproduction of different damping ratios, a categorical variable is added to the continuous input data. Based on a recursive flow of the predicted data back to the input layer, long-term dependencies do not vanish due to short-input sequences. The system dimension is reduced by applying the model-order reduction technique for modal decomposition. The high accuracy of the surrogate and the reduction of computational costs are shown on an academic example of a cantilever beam and a real-world example of a robot. The advantages of our approach are illustrated in comparison with state-of-the-art surrogates for transient finite element analysis. By using the surrogate proposed in this study, oscillations due to discontinuous excitation of mechanical structures can be reproduced. For this purpose, only short-input sequences are necessary since the excitation of the oscillations does not have to be part of the input sequence during the whole duration of the oscillations. Due to the categorical variable for the damping ratio, the surrogate can account for the influence of different damping in parameter studies.

Estimating Forest Canopy Height based on GEDI Lidar Data and Multi-source Remote Sensing Images

Abstract. Estimating forest canopy height is crucial for assessing aboveground biomass and carbon sequestration. Light detection and ranging (lidar) is an important technology for its ability in capturing vertical structural information. However, due to instrument limitations and cost constraints, acquiring large-scale and continuous forest data solely through lidar is challenging. To compensate this, remote sensing images can be used to cover wide regions. Therefore, leveraging multi-source data for constructing canopy height models (CHMs) holds great promise in this field. The objective of this study is to evaluate and compare the contributions of multi-source remote sensing data and methods in estimating forest canopy height. In constructing the CHM, the commonly used random forest (RF) and fully convolutional network (FCN) are assessed. The canopy height obtained from GEDI was used as the reference data, and Landsat 8 and Sentinel-2 data were used for prediction. Multiple CHMs were constructed for the Dabie Mountains, Central China, in 2019 based on different data sources and methods, respectively, which are then comparatively analysed. The results showed that (1) the accuracy of the CHM using Sentinel-2 as input is marginally better than that using Landsat 8 based on RF, where the difference is insignificant; and (2) FCN is less accurate than RF despite domain-specific fine-tuning, although further improvement in accuracy is expected by weighing in more FCN models.

Leveraging relationships between species abundances to improve predictions and inform conservation

Abstract Many management and conservation contexts can benefit from understanding relationships between species abundances, which can be used to improve predictions of species occurrence and abundance. We present conditional prediction as a tool to capture information about species abundances via residual covariance between species. From a fitted joint species distribution model, this framework produces a species coefficient matrix that contains relationships between species abundances. The species coefficients allow co‐observed species to be treated as a second set of predictors supplementing covariates in the model to improve prediction. We use simulations to demonstrate the potential benefits and limitations of conditional prediction across data types and species covariance before applying conditional prediction to two management contexts with real data. Simulations demonstrate that conditional prediction provides the largest benefits to continuous data and when there is residual covariance between many species. In our first application, we show that conditioning on other species improves in‐sample and out‐of‐sample predictions of fish and invertebrate species, including Atlantic cod. In our second application, we show that the species coefficient matrix can be used to identify bird species at risk of nest parasitism by Brown‐headed Cowbirds. Synthesis and applications. We present guidelines for using conditional prediction, which can help understand relationships between species abundances, improve predictions and inform conservation in a variety of contexts.

Continuous data assimilation for the three dimensional primitive equations with magnetic field

In this paper, the problem of continuous data assimilation of three dimensional primitive equations with magnetic field in thin domain is studied. We establish the well-posedness of the assimilation system and prove that the H 2 -strong solution of the assimilation system converges exponentially to the reference solution in the sense of L 2 as t → ∞. We also study the sensitivity analysis of the assimilation system and prove that a sequence of solutions of the difference quotient equation converge to the unique solution of the formal sensitivity equation.

Effectiveness of Interventions for Changing More Than One Behavior at a Time to Manage Chronic Conditions: A Systematic Review and Meta-analysis

Abstract Background Health behaviors play a significant role in chronic disease management. Rather than being independent of one another, health behaviors often co-occur, suggesting that targeting more than one health behavior in an intervention has the potential to be more effective in promoting better health outcomes. Purpose We aimed to conduct a systematic review and meta-analysis of randomized trials of interventions that target more than one behavior to examine the effectiveness of multiple health behavior change interventions in patients with chronic conditions. Methods Five electronic databases (Web of Science, PubMed, CINAHL, EMBASE, and Cochrane) were systematically searched in November 2023, and studies included in previous reviews were also consulted. We included randomized trials of interventions aiming to change more than one health behavior in individuals with chronic conditions. Two independent reviewers screened and extracted data, and used Cochrane’s Risk of Bias 2 tool. Meta-analyses were conducted to estimate the effects of interventions on change in health behaviors. Results were presented as Cohen’s d for continuous data, and risk ratio for dichotomous data. Results Sixty-one studies were included spanning a range of chronic diseases: cardiovascular (k = 25), type 2 diabetes (k = 15), hypertension (k = 10), cancer (k = 7), one or more chronic conditions (k = 3), and multiple conditions (k = 1). Most interventions aimed to change more than one behavior simultaneously (rather than in sequence) and most targeted three particular behaviors at once: “physical activity, diet and smoking” (k = 20). Meta-analysis of 43 eligible studies showed for continuous data (k = 29) a small to substantial positive effect on behavior change for all health behaviors (d = 0.081–2.003) except for smoking (d = −0.019). For dichotomous data (k = 23) all analyses showed positive effects of targeting more than one behavior on all behaviors (RR = 1.026–2.247). Conclusions Targeting more than one behavior at a time is effective in chronic disease management and more research should be directed into developing the science of multiple behavior change.

A comprehensive AI model development framework for consistent Gleason grading

BackgroundArtificial Intelligence(AI)-based solutions for Gleason grading hold promise for pathologists, while image quality inconsistency, continuous data integration needs, and limited generalizability hinder their adoption and scalability.MethodsWe present a comprehensive digital pathology workflow for AI-assisted Gleason grading. It incorporates A!MagQC (image quality control), A!HistoClouds (cloud-based annotation), Pathologist-AI Interaction (PAI) for continuous model improvement, Trained on Akoya-scanned images only, the model utilizes color augmentation and image appearance migration to address scanner variations. We evaluate it on Whole Slide Images (WSI) from another five scanners and conduct validations with pathologists to assess AI efficacy and PAI.ResultsOur model achieves an average F1 score of 0.80 on annotations and 0.71 Quadratic Weighted Kappa on WSIs for Akoya-scanned images. Applying our generalization solution increases the average F1 score for Gleason pattern detection from 0.73 to 0.88 on images from other scanners. The model accelerates Gleason scoring time by 43% while maintaining accuracy. Additionally, PAI improve annotation efficiency by 2.5 times and led to further improvements in model performance.ConclusionsThis pipeline represents a notable advancement in AI-assisted Gleason grading for improved consistency, accuracy, and efficiency. Unlike previous methods limited by scanner specificity, our model achieves outstanding performance across diverse scanners. This improvement paves the way for its seamless integration into clinical workflows.

Comparing the effectiveness of full-vacuum and half-vacuum drainage in reducing seroma after modified radical mastectomy: a meta-analysis

Introduction Owing to limited outpatient support for drain management, delayed discharge after mastectomy is more prevalent in developing countries. Utilising half-vacuum (HV) suction drains for routine drainage after mastectomy could lead to a reduced incidence of seroma and a shorter hospital stay. This systematic review and meta-analysis compared the outcomes of HV against full-vacuum (FV) suction drains in patients who underwent modified radical mastectomy for breast cancer. Methods Differences between the two groups in length of hospital stay, total volume of drain effluent and incidence of seroma were assessed. RevMan 5.4 was used to calculate the odds ratio (OR) and relative risk (RR) for dichotomous data, and the mean difference (MD) for continuous data. Results Nine randomised controlled trials were included in this review. Using HV drains reduced both the mean length of hospital stay (MD: −2.30 days, 95% confidence interval [CI]: −4.10 to −0.49 days, I2=97%) and the mean total volume of effluent (MD: −132.61ml, 95% CI: −207.32ml to −57.91ml, I2=88%) compared with FV drains. However, there was no statistically significant difference in incidence of seroma between the two groups (RR: 0.67, 95% CI: 0.30 to 1.46, I2=65%). Likewise, there was no difference in rate of seroma occurrence on sensitivity analysis (OR: 1.29, 95% CI: 0.72 to 2.33, I2=74%). Conclusions There was no difference in the incidence of seroma between HV and FV suction drainage. Conversely, a reduction in the length of hospital stay and the total volume of drain effluent was observed for mastectomy patients with a HV drain.

The effect of intraoperative low-dose ketamine versus dexmedetomidine infusion on postoperative bowel recovery in patients undergoing gastrointestinal malignancy surgeries: Placebo-controlled, randomized trial

Abstract Background and Aims: No studies have compared the effects of ketamine and dexmedetomidine on bowel recovery. We evaluated the effects of intraoperative low-dose ketamine or dexmedetomidine infusion on postoperative bowel recovery in patients undergoing gastrointestinal (GI) malignancy surgeries. Material and Methods: This placebo-controlled, randomized study was carried out in 84 American Society of Anesthesiologists II patients, aged 18–70 years, of either gender, undergoing elective open GI malignancy surgeries. Patients received intraoperative infusion of ketamine @ 0.1 mg kg-1 h-1 (KET), dexmedetomidine @ 0.25 μg kg-1 h-1 (DEX), or normal saline (placebo). Primary outcome was the time to first flatus and/or stool. Secondary outcomes included time to extubation, total analgesic requirement, postoperative pain scores, time to feeds, duration of intensive care unit (ICU) and hospital stay, and the incidence of adverse events. Continuous data were analyzed by the one-way analysis of variance (ANOVA) or the Kruskal–Wallis test. Categorical data were analyzed by the Chi-square test or the Fisher’s exact test. Results: Median time to passage of flatus and/or stool was 3 [interquartile range (IQR) 2–3] days in the KET group, 2 [IQR 2–3] days in the DEX group, and 2 [IQR 2–3] days in the placebo group (P = 0.53 for placebo vs. KET, 0.81 for placebo vs. DEX, and 0.99 for KET vs. DEX). Pain scores and analgesic consumption were significantly less in the intervention groups versus placebo (P &lt; 0.001). No difference was seen in other secondary outcomes. Conclusion: Low-dose ketamine or dexmedetomidine did not result in early bowel recovery despite lower pain scores and opioid consumption in patients undergoing open GI malignancy surgeries. Key Message: What is known: Ketamine and dexmedetomidine may promote bowel recovery by improving analgesia and decreasing opioid usage.Main findings: This randomized controlled trial found no evidence of earlier bowel recovery with ketamine or dexmedetomidine versus placebo despite lower pain scores and analgesic consumption in the ketamine and dexmedetomidine groups.

Improving performance of defect detection by setting skewed tolerance and joint tolerances in crimp force monitor

AbstractA Crimp Force Monitor (CFM) detects defects by whether the crimp force curve of the force sensor exceeds the set tolerance, with the goal of low defect miss rate and false alarm rate. In this study, typical defects made by hand are crimped with an automatic crimping machine together with good products to obtain continuous data of the crimping force curves and to process the data. For the peak and area deviations of the crimp force curve, the good products show skew‐normal distribution, and the defective samples show outliers and different deviation intensities in the positive and negative directions. Furthermore, by manually intervening in the batch production of multiple groups of defects and comparing the defect miss rate and false alarm rate of CFM with different tolerance settings, the peak skewed tolerance, joint loose tolerance and joint skewed tolerance tree settings can meet a low defect miss rate and low false alarm rate at the same time. The group test results verify the skew‐normal distribution of crimping force curve deviation rate and the characteristics of deviation intensities, providing reference for the tolerance setting of CFM in automated terminal crimping production.

Carotid Body Tumor Excision with and without Carotid Artery Reconstruction: Equivalency of 30-Day Outcomes over 12 Years in the American College of Surgery National Surgical Quality Improvement Program (ACS-NSQIP) Database

Background: Carotid body tumors (CBTs) are rare benign tumors that arise from the chemoreceptor tissue located at the carotid bifurcation that require excision if symptomatic. Depending on the size and location of the tumor, the carotid artery may need to be repaired after resection. This study aims to assess whether CBT excision with artery resection had higher rates of 30-day postoperative outcomes compared with CBT excision without artery resection. Methods: This is a retrospective cohort study. Patients were identified in the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) registry from 2005 to 2017. They were divided into two groups, based on Current Procedural Terminology (CPT®) codes: group A had CBT excision without carotid artery excision (CPT code 60600) and group B with carotid artery excision (CPT code 60605). Patient demographic characteristics, co-morbidities, and 30-days postoperative outcomes were compared between the two groups. Categorical data were analyzed using Pearson’s X2 or Fisher exact tests and presented as proportions (percentages). Continuous data were analyzed using parametric or non-parametric tests as appropriate. Statistical significance was defined as p &lt; 0.05. Statistical analysis was performed using the SPSS statistical software package. Results: A total of 463 patients were identified, 410 (88.4%) in group A and 53 (11.4%) in group B. Overall, there were 291 (62.9%) women. A higher proportion of women underwent CBT excision only, compared to men (91.1% [265/291] vs. 84.3% [145/172], p &lt; 0.0001). Demographics and comorbidities were similar between groups. There was no significant difference in the 30-day postoperative outcomes. The reoperation rate was higher in group B (3.8% vs. 1.5%, p = 0.334), while the readmission rate was higher in group A (3.2% vs. 0% p = 0.269), and both were not significantly different. Overall morbidity and serious morbidity were higher in group B (7.5% vs. 5.9%, p = 0.626) and lower in group A (5.7% vs. 3.9%, p = 0.544), respectively, but were not significantly different. Operative time (mean, SD) was higher in group B (187 ± 107 vs. 138 ± 66 min, p &lt; 0.001). However, the median (IQR) of hospital length of stay (LOS) was similar (2 [1, 4] vs. 2 [1, 3] days, p = 0.134). Conclusions: Overall, no difference was noted in the 30-day postoperative outcome between the two surgical approaches of CBT. However, operative time was longer when artery resection was performed. Further research to determine the factors predicting the need for carotid artery resection among patient gender is needed.

Observation Of Ocean Wave Based On Binocular Vision In The Swash Zone Of Yazhou Bay

Due to climate change, extreme weather events frequently occur. This can increase the probability of typhoon, resulting in storm surge more frequently. Meanwhile, the severe movement of ocean wave is generated. Ocean wave on the coastal zone can results in retreat of the coastlines and erosion for the beach. The research on the ocean wave in storm surge process based on field observation is not only able to provide the basic data for the validation of numerical model of storm surges but also significant to prevent the loss of beaches resources in the extreme climate condition. The previous studies of swash zone using video technology concentrated on experimental scale (De Vries et al., 2011), and the research parameters mostly focused on bed and water level (Wanek et al., 2006), while there is a lack of the research of ocean wave parameters. The binocular vision observation system, which mainly consists of two cameras, has been a powerful technical support in acquiring 3D information of ocean wave. Compared with the measurement of manual, radar (Harry et al., 2018) and satellite remote, the binocular vision method is not only hardly affected by weather condition, but also can acquire the continuous image data. In addition, two cameras with high resolution can obtain high precision measurement results. This study aims at obtaining the wave height of the swash zone in storm surge process.

Measuring the effectiveness of hybrid diabetes care over 90 days through continuous data monitoring in type 2 diabetic patients

BackgroundDiabetes Mellitus, a global health challenge, affects 537 million individuals. Traditional management relies on periodic clinic visits, but technological advancements, including remote monitoring, offer transformative changes. Telemedicine enhances access, convenience, adherence, and glycemic control. Challenges include trust-building and limitations in face-to-face interactions. Integrating remote monitoring with in-person healthcare creates a hybrid approach. This study evaluates the impact on Type 2 Diabetes patients over 3 months.MethodsA retrospective case-control observational study. Inclusion criteria involved previous Type 2 Diabetes diagnosis and a minimum 3-month GluCare model period with two physical visits. Patients in the case group had in-clinic visits, bi-weekly app engagement, and monthly body weight readings. Control group had in-clinic visits only. Outcomes measured included HbA1c, lipid profile, CV risk, eGFR, urine Albumin/Creatinine Ratio, Uric Acid, and CRP.ResultsCase group showed significant HbA1c improvements (-2.19%), especially in higher baseline levels. Weight, BMI, LDL, total cholesterol, and CVD risk also improved. Controls showed smaller improvements. Higher digital interactions correlated with better outcomes. Patients with ≥11 interactions showed significant reductions in HbA1c (-2.38%) and weight (-6.00 kg).ConclusionThe GluCare.Health hybrid model demonstrates promising outcomes in Type 2 diabetes management. The integration of in-clinic consultations with continuous remote monitoring leads to substantial improvements in glycemic control and clinical parameters. The study highlights the importance of patient engagement in achieving positive outcomes, with higher digital interactions associated with greater reductions in HbA1c and weight. The hybrid approach proves more effective than digital-only interventions, emphasizing the need for comprehensive, end-to-end solutions in diabetes care.

Innova4Health: an integrated approach for prevention of recurrence and personalized treatment of Major Depressive Disorder

BackgroundMajor Depressive Disorder (MDD) is a prevalent mental health condition characterized by persistent low mood, cognitive and physical symptoms, anhedonia (loss of interest in activities), and suicidal ideation. The World Health Organization (WHO) predicts depression will become the leading cause of disability by 2030. While biological markers remain essential for understanding MDD's pathophysiology, recent advancements in social signal processing and environmental monitoring hold promise. Wearable technologies, including smartwatches and air purifiers with environmental sensors, can generate valuable digital biomarkers for depression assessment in real-world settings. Integrating these with existing physical, psychopathological, and other indices (autoimmune, inflammatory, neuroradiological) has the potential to improve MDD recurrence prevention strategies.MethodsThis prospective, randomized, interventional, and non-pharmacological integrated study aims to evaluate digital and environmental biomarkers in adolescents and young adults diagnosed with MDD who are currently taking medication. The study implements a sensor-integrated platform built around an open-source “Pothos” air purifier system. This platform is designed for scalability and integration with third-party devices. It accomplishes this through software interfaces, a dedicated app, sensor signal pre-processing, and an embedded deep learning AI system. The study will enroll two experimental groups (10 adolescents and 30 young adults each). Within each group, participants will be randomly allocated to Group A or Group B. Only Group B will receive the technological equipment (Pothos system and smartwatch) for collecting digital biomarkers. Blood and saliva samples will be collected at baseline (T0) and endpoint (T1) to assess inflammatory markers and cortisol levels.ResultsFollowing initial age-based stratification, the sample will undergo detailed classification at the 6-month follow-up based on remission status. Digital and environmental biomarker data will be analyzed to explore intricate relationships between these markers, depression symptoms, disease progression, and early signs of illness.ConclusionThis study seeks to validate an AI tool for enhancing early MDD clinical management, implement an AI solution for continuous data processing, and establish an AI infrastructure for managing healthcare Big Data. Integrating innovative psychophysical assessment tools into clinical practice holds significant promise for improving diagnostic accuracy and developing more specific digital devices for comprehensive mental health evaluation.

Digital Interventions to Understand and Mitigate Stress Response: Protocol for Process and Content Evaluation of a Cohort Study.

Staffing and resource shortages, especially during the COVID-19 pandemic, have increased stress levels among health care workers. Many health care workers have reported feeling unable to maintain the quality of care expected within their profession, which, at times, may lead to moral distress and moral injury. Currently, interventions for moral distress and moral injury are limited. This study has the following aims: (1) to characterize and reduce stress and moral distress related to decision-making in morally complex situations using a virtual reality (VR) scenario and a didactic intervention; (2) to identify features contributing to mental health outcomes using wearable, physiological, and self-reported questionnaire data; and (3) to create a personal digital phenotype profile that characterizes stress and moral distress at the individual level. This will be a single cohort, pre- and posttest study of 100 nursing professionals in Ontario, Canada. Participants will undergo a VR simulation that requires them to make morally complex decisions related to patient care, which will be administered before and after an educational video on techniques to mitigate distress. During the VR session, participants will complete questionnaires measuring their distress and moral distress, and physiological data (electrocardiogram, electrodermal activity, plethysmography, and respiration) will be collected to assess their stress response. In a subsequent 12-week follow-up period, participants will complete regular assessments measuring clinical outcomes, including distress, moral distress, anxiety, depression, and loneliness. A wearable device will also be used to collect continuous data for 2 weeks before, throughout, and for 12 weeks after the VR session. A pre-post comparison will be conducted to analyze the effects of the VR intervention, and machine learning will be used to create a personal digital phenotype profile for each participant using the physiological, wearable, and self-reported data. Finally, thematic analysis of post-VR debriefing sessions and exit interviews will examine reoccurring codes and overarching themes expressed across participants' experiences. The study was funded in 2022 and received research ethics board approval in April 2023. The study is ongoing. It is expected that the VR scenario will elicit stress and moral distress. Additionally, the didactic intervention is anticipated to improve understanding of and decrease feelings of stress and moral distress. Models of digital phenotypes developed and integrated with wearables could allow for the prediction of risk and the assessment of treatment responses in individuals experiencing moral distress in real-time and naturalistic contexts. This paradigm could also be used in other populations prone to moral distress and injury, such as military and public safety personnel. ClinicalTrials.gov NCT05923398; https://clinicaltrials.gov/study/NCT05923398. DERR1-10.2196/54180.

Transgender people in clinical trials of drugs and biologics: An analysis of ClinicalTrials.gov from 2007 to 2023.

Transgender people have unmet health needs related to chronic conditions such as dementia, osteoporosis and hypertension. Community-driven advocacy increased transgender representation in phase III trials for pharmacological prevention of HIV, but the extent to which drug trials for other conditions have included transgender people is unknown. We investigated the extent to which trials of drugs and biologics represented transgender people across therapeutic areas on ClinicalTrials.gov. Cross-sectional analysis of trials of drugs and biologics registered on ClinicalTrials.gov from 2007-2023. We included efficacy and effectiveness trials (phase II-IV) with transgender-related terms (e.g. 'transgend*'). We labelled trials as Inclusive or Exclusive of transgender people using the trial eligibility criteria. We compared trials (therapeutic area, trial design, enrolment), summarized trials registered from 2008 onward and characterized participant enrolment for Inclusive trials with primary trial publications. We summarized continuous data using median (range), categorical data using frequencies and percentages and compared trial characteristics using Fisher's exact test. Ninety-seven trials represented transgender people. Characteristics were similar between 85 Inclusive and 12 Exclusive trials. Among Inclusive trials, 58% focused on infectious diseases (e.g. treatment or prevention of HIV and COVID-19), 15% on mental health (e.g. post-traumatic stress disorder, substance use-related disorders), and the remainder focused on endocrine (9%), pain (5%), digestive system disorders (1%) and neoplasms (1%). Twenty (of 25) trials reported enrolment of transgender participants in primary trial publications or reported results. Transgender-inclusive trials have increased since 2008. Most trials focused on infectious diseases and mental health. Investigators should increase opportunities to include of transgender people in trials of drugs and biologics for chronic diseases.