Streamlining healthcare delivery for sex-trafficked adolescents.

Recent years have elucidated that trafficking in the pediatric population constitutes a broader pattern of child maltreatment. Given the inconsistent engagement with the medical system that trafficked youth can experience, there is growing advocacy promoting streamlined provision of specialized services. One innovative example includes the Adolescent Protection Collaborative (APC) launched at the Children's Hospital of Philadelphia in 2021. The APC was conceptualized to serve the overlapping populations of youth impacted by sex trafficking victimization and child welfare involvement. In an effort to consolidate care and address a range of needs across the biopsychosocial spectrum, the APC brought together a child abuse pediatrician, adolescent medicine physician, and social worker to provide coordinated, real-time care during each clinic visit. It is hoped that the APC may represent a novel approach to balancing the medico-legal aspects of trafficking aftercare with the youth-empowering features of adolescent medicine and social care.

Integrating Social Care Into a Specialized Medical Home for Sex-Trafficked Youth.

After a series of meetings between medical personnel and community stakeholders, the Children's Hospital of Philadelphia successfully launched the Adolescent Protection Collaborative in July 2021. This novel clinic created a specialized medical home for sex-trafficked youth. The clinic was staffed by a core team of child abuse pediatrics and adolescent medicine physicians and a social worker who provided coordinated evaluations and same-day services, followed by ongoing long-term care. The Adolescent Protection Collaborative model was built on interdisciplinary collaboration with the goal of consolidating medical services and reducing fragmentation of care. A Community Advisory Committee was formed and aided in linking interested youth with additional services. Healthcare navigation was facilitated through support of a clinic-specific social worker, and transportation barriers were largely eliminated through a grant-funded program. Pilot data from the initial 21 months of clinical operations revealed that 88% of 43 referred patients (ages ranging from 13-22 years with a mean of 16 years) attended a scheduled appointment with 55% returning for follow up. Most patients (68%) identified as Black. All (100%) had past or present involvement with child protective services. Fifty percent of referrals tested positive for a sexually transmitted infection with a total of 33 sexually transmitted infections diagnosed and treated. Patient-desired contraception was facilitated for approximately 67% of referrals. Social care needs, such as referrals for educational support, case management, housing and employment resources, and mental health linkages, were offered alongside standard medical services. The described clinic model demonstrates promise in meeting the unique healthcare needs of sex-trafficked youth.

A generalizable deep voxel-guided morphometry algorithm for the detection of subtle lesion dynamics in multiple sclerosis.

Introduction: Multiple sclerosis (MS) is a chronic neurological disorder characterized by the progressive loss of myelin and axonal structures in the central nervous system. Accurate detection and monitoring of MS-related changes in brain structures are crucial for disease management and treatment evaluation. We propose a deep learning algorithm for creating Voxel-Guided Morphometry (VGM) maps from longitudinal MRI brain volumes for analyzing MS disease activity. Our approach focuses on developing a generalizable model that can effectively be applied to unseen datasets. Methods: Longitudinal MS patient high-resolution 3D T1-weighted follow-up imaging from three different MRI systems were analyzed. We employed a 3D residual U-Net architecture with attention mechanisms. The U-Net serves as the backbone, enabling spatial feature extraction from MRI volumes. Attention mechanisms are integrated to enhance the model's ability to capture relevant information and highlight salient regions. Furthermore, we incorporate image normalization by histogram matching and resampling techniques to improve the networks' ability to generalize to unseen datasets from different MRI systems across imaging centers. This ensures robust performance across diverse data sources. Results: Numerous experiments were conducted using a dataset of 71 longitudinal MRI brain volumes of MS patients. Our approach demonstrated a significant improvement of 4.3% in mean absolute error (MAE) against the state-of-the-art (SOTA) method. Furthermore, the algorithm's generalizability was evaluated on two unseen datasets (n = 116) with an average improvement of 4.2% in MAE over the SOTA approach. Discussion: Results confirm that the proposed approach is fast and robust and has the potential for broader clinical applicability.

Streamlining Acute Abdominal Aortic Dissection Management-An AI-based CT Imaging Workflow.

Life-threatening acute aortic dissection (AD) demands timely diagnosis for effective intervention. To streamline intrahospital workflows, automated detection of AD in abdominal computed tomography (CT) scans seems useful to assist humans. We aimed at creating a robust convolutional neural network (CNN)-based pipeline capable of real-time screening for signs of abdominal AD in CT. In this retrospective study, abdominal CT data from AD patients presenting with AD and from non-AD patients were collected (n 195, AD cases 94, mean age 65.9 years, female ratio 35.8%). A CNN-based algorithm was developed with the goal of enabling a robust, automated, and highly sensitive detection of abdominal AD. Two sets from internal (n = 32, AD cases 16) and external sources (n = 1189, AD cases 100) were procured for validation. The abdominal region was extracted, followed by the automatic isolation of the aorta region of interest (ROI) and highlighting of the membrane via edge extraction, followed by classification of the aortic ROI as dissected/healthy. A fivefold cross-validation was employed on the internal set, and an ensemble of the 5 trained models was used to predict the internal and external validation set. Evaluation metrics included receiver operating characteristic curve (AUC) and balanced accuracy. The AUC, balanced accuracy, and sensitivity scores of the internal dataset were 0.932 (CI 0.891-0.963), 0.860, and 0.885, respectively. For the internal validation dataset, the AUC, balanced accuracy, and sensitivity scores were 0.887 (CI 0.732-0.988), 0.781, and 0.875, respectively. Furthermore, for the external validation dataset, AUC, balanced accuracy, and sensitivity scores were 0.993 (CI 0.918-0.994), 0.933, and 1.000, respectively. The proposed automated pipeline could assist humans in expediting acute aortic dissection management when integrated into clinical workflows.

Caring for Domestic Minor Sex Trafficking Patients: Recommendations for Identification, Interventions, and Resources.

Domestic minor sex trafficking has increasingly gained awareness as a social phenomenon that affects adolescent health and safety. Healthcare providers are uniquely positioned to identify and facilitate supportive interventions for adolescents at high risk or involved in trafficking. A growing literature base and clinical experience provide recommendations on how to identify, engage trafficked youth, and provide beneficial linkages with community resources. A coordinated, multidisciplinary, and trauma-informed response that fosters therapeutic alliances promoting agency, safety, and trust are key components of successful care for this vulnerable adolescent population.

Automated prognosis of renal function decline in ADPKD patients using deep learning.

An accurate prognosis of renal function decline in Autosomal Dominant Polycystic Kidney Disease (ADPKD) is crucial for early intervention. Current biomarkers used are height-adjusted total kidney volume (HtTKV), estimated glomerular filtration rate (eGFR), and patient age. However, manually measuring kidney volume is time-consuming and subject to observer variability. Additionally, incorporating automatically generated features from kidney MRI images, along with conventional biomarkers, can enhance prognostic improvement. To address these issues, we developed two deep-learning algorithms. Firstly, an automated kidney volume segmentation model accurately calculates HtTKV. Secondly, we utilize segmented kidney volumes, predicted HtTKV, age, and baseline eGFR to predict chronic kidney disease (CKD) stages >=3A, >=3B, and a 30% decline in eGFR after 8 years from the baseline visit. Our approach combines a convolutional neural network (CNN) and a multi-layer perceptron (MLP). Our study included 135 subjects and the AUC scores obtained were 0.96, 0.96, and 0.95 for CKD stages >=3A, >=3B, and a 30% decline in eGFR, respectively. Furthermore, our algorithm achieved a Pearson correlation coefficient of 0.81 between predicted and measured eGFR decline. We extended our approach to predict distinct CKD stages after eight years with an AUC of 0.97. The proposed approach has the potential to enhance monitoring and facilitate prognosis in ADPKD patients, even in the early disease stages.

A baby carrier fall leading to intracranial bleeding and multilayered retinal hemorrhages.

Significant intracranial and retinal hemorrhages are often seen in infants with abusive head trauma, although accidental injury and previously undiagnosed medical disorders are important considerations in the differential diagnosis. We present the case of an infant with confirmed accidental trauma sustained from an adult-worn baby carrier fall with superimposed head crush injury, which resulted in significant cranial, intracranial, and retinal findings.

Deep Learning-Based Total Kidney Volume Segmentation in Autosomal Dominant Polycystic Kidney Disease Using Attention, Cosine Loss, and Sharpness Aware Minimization.

Early detection of the autosomal dominant polycystic kidney disease (ADPKD) is crucial as it is one of the most common causes of end-stage renal disease (ESRD) and kidney failure. The total kidney volume (TKV) can be used as a biomarker to quantify disease progression. The TKV calculation requires accurate delineation of kidney volumes, which is usually performed manually by an expert physician. However, this is time-consuming and automated segmentation is warranted. Furthermore, the scarcity of large annotated datasets hinders the development of deep learning solutions. In this work, we address this problem by implementing three attention mechanisms into the U-Net to improve TKV estimation. Additionally, we implement a cosine loss function that works well on image classification tasks with small datasets. Lastly, we apply a technique called sharpness aware minimization (SAM) that helps improve the generalizability of networks. Our results show significant improvements (p-value < 0.05) over the reference kidney segmentation U-Net. We show that the attention mechanisms and/or the cosine loss with SAM can achieve a dice score (DSC) of 0.918, a mean symmetric surface distance (MSSD) of 1.20 mm with the mean TKV difference of −1.72%, and R2 of 0.96 while using only 100 MRI datasets for training and testing. Furthermore, we tested four ensembles and obtained improvements over the best individual network, achieving a DSC and MSSD of 0.922 and 1.09 mm, respectively.

Characterizing Multiple Perpetrator Sexual Assaults in the Adolescent Female Population.

STUDY OBJECTIVE: To determine whether differences exist between the acute presentations and post-assault needs of youth presenting to an emergency department (ED) following multiple perpetrator sexual assault (MPSA) compared with those presenting after single perpetrator sexual assault. METHODS: A retrospective cohort study of all female adolescents evaluated in an urban pediatric ED between 2014 and 2021 for acute sexual assault was conducted. Demographic characteristics and assault outcomes were assessed using bivariate analyses. RESULTS: Survivors of MPSA were not more likely than survivors of single perpetrator assaults to be diagnosed with an anal-genital injury or sexually transmitted infection but were more likely to re-present in the subsequent year for an emergent mental health concern (31% vs 11%, P = .001), including suicide attempt (6% vs 1%, P = .022). CONCLUSION: The high rate of subsequent ED visits for mental health concerns among female adolescent survivors of MPSA highlights the need for providing specialized support to this population.

Evaluation for Bleeding Disorders in Suspected Child Abuse.

Bruising or bleeding in a child can raise the concern for child abuse. Assessing whether the findings are the result of trauma and/or whether the child has a bleeding disorder is critical. Many bleeding disorders are rare, and not every child with bruising/bleeding that may raise a concern for abuse requires an evaluation for bleeding disorders. However, in some instances, bleeding disorders can present in a manner similar to child abuse. Bleeding disorders cannot be ruled out solely on the basis of patient and family history, no matter how extensive. The history and clinical evaluation can be used to determine the necessity of an evaluation for a possible bleeding disorder, and prevalence and known clinical presentations of individual bleeding disorders can be used to guide the extent of laboratory testing. This clinical report provides guidance to pediatricians and other clinicians regarding the evaluation for bleeding disorders when child abuse is suspected.

Impact of Cl Doping on Electrochemical Performance in Orthosilicate (Li2FeSiO4): A Density Functional Theory Supported Experimental Approach.

Safe and high-capacity cathode materials are a long quest for commercial lithium-ion battery development. Among various searched cathode materials, Li2FeSiO4 has taken the attention due to optimal working voltage, high elemental abundance, and low toxicity. However, as per our understanding and observation, the electrochemical performance of this material is significantly limited by the intrinsic low electronic conductivity and slow lithium-ion diffusion, which limits the practical capacity (a theoretical value of ∼330 mAh g-1). In this report, using first-principles density functional theory based approach, we demonstrate that chlorine doping on oxygen site can enhance the electronic conductivity of the electrode and concurrently improve the electrochemical performance. Experimentally, X-ray diffraction, X-ray photoelectron spectroscopy, and field-emission gun scanning electron microscopy elemental mapping confirms Cl doping in Li2-xFeSiO4-xClx/C (x ≤ 0.1), while electrochemical cycling performance demonstrated improved performance. The theoretical and experimental studies collectively predict that, via Cl doping, the lithium deinsertion voltage associated with the Fe2+/Fe3+ and Fe3+/Fe4+ redox couples can be reduced and electronic conductivity can be enhanced, which opens up the possibility of utilization of silicate-based cathode with carbonate-based commercial electrolyte. In view of potential and electronic conductivity benefits, our results indicate that Cl doping can be a promising low-cost method to improve the electrochemical performance of silicate-based cathode materials.