Hasil untuk "Pediatrics"

Leonie Dyck, Aiko Galetzka, Maximilian Noller et al.

Introduction: Socially assistive robots hold promise for enhancing therapeutic engagement in paediatric clinical settings. However, their successful implementation requires not only technical robustness but also context-sensitive, co-designed solutions. This paper presents Mobirobot, a socially assistive robot developed to support mobilisation in children recovering from trauma, fractures, or depressive disorders through personalised exercise programmes. Methods: An agile, human-centred development approach guided the iterative design of Mobirobot. Multidisciplinary clinical teams and end users were involved throughout the co-development process, which focused on early integration into real-world paediatric surgical and psychiatric settings. The robot, based on the NAO platform, features a simple setup, adaptable exercise routines with interactive guidance, motivational dialogue, and a graphical user interface (GUI) for monitoring and no-code system feedback. Results: Deployment in hospital environments enabled the identification of key design requirements and usability constraints. Stakeholder feedback led to refinements in interaction design, movement capabilities, and technical configuration. A feasibility study is currently underway to assess acceptance, usability, and perceived therapeutic benefit, with data collection including questionnaires, behavioural observations, and staff-patient interviews. Discussion: Mobirobot demonstrates how multiprofessional, stakeholder-led development can yield a socially assistive system suited for dynamic inpatient settings. Early-stage findings underscore the importance of contextual integration, robustness, and minimal-intrusion design. While challenges such as sensor limitations and patient recruitment remain, the platform offers a promising foundation for further research and clinical application.

Judith Massmann, Alexander Lichtenstein, Francisco M. López

Numerous visual impairments can be detected in red-eye reflex images from young children. The so-called Bruckner test is traditionally performed by ophthalmologists in clinical settings. Thanks to the recent technological advances in smartphones and artificial intelligence, it is now possible to recreate the Bruckner test using a mobile device. In this paper, we present a first study conducted during the development of KidsVisionCheck, a free application that can perform vision screening with a mobile device using red-eye reflex images. The underlying model relies on deep neural networks trained on children's pupil images collected and labeled by an ophthalmologist. With an accuracy of 90% on unseen test data, our model provides highly reliable performance without the necessity of specialist equipment. Furthermore, we can identify the optimal conditions for data collection, which can in turn be used to provide immediate feedback to the users. In summary, this work marks a first step toward accessible pediatric vision screenings and early intervention for vision abnormalities worldwide.

Suresh Babu Nettur, Shanthi Karpurapu, Unnati Nettur et al.

Pneumonia is a leading cause of illness and death in children, underscoring the need for early and accurate detection. In this study, we propose a novel lightweight ensemble model for detecting pneumonia in children using chest X-ray images. This ensemble model integrates two pre-trained convolutional neural networks (CNNs), MobileNetV2 and NASNetMobile, selected for their balance of computational efficiency and accuracy. These models were fine-tuned on a pediatric chest X-ray dataset and combined to enhance classification performance. Our proposed ensemble model achieved a classification accuracy of 98.63%, significantly outperforming individual models such as MobileNetV2 (97.10%) and NASNetMobile(96.25%) in terms of accuracy, precision, recall, and F1 score. Moreover, the ensemble model outperformed state-of-the-art architectures, including ResNet50, InceptionV3, and DenseNet201, while maintaining computational efficiency. The proposed lightweight ensemble model presents a highly effective and resource-efficient solution for pneumonia detection, making it particularly suitable for deployment in resource-constrained settings.

Anthony Hevia, Sanjana Chintalapati, Veronica Ka Wai Lai et al.

We present ROBOTO2, an open-source, web-based platform for large language model (LLM)-assisted risk of bias (ROB) assessment of clinical trials. ROBOTO2 streamlines the traditionally labor-intensive ROB v2 (ROB2) annotation process via an interactive interface that combines PDF parsing, retrieval-augmented LLM prompting, and human-in-the-loop review. Users can upload clinical trial reports, receive preliminary answers and supporting evidence for ROB2 signaling questions, and provide real-time feedback or corrections to system suggestions. ROBOTO2 is publicly available at https://roboto2.vercel.app/, with code and data released to foster reproducibility and adoption. We construct and release a dataset of 521 pediatric clinical trial reports (8954 signaling questions with 1202 evidence passages), annotated using both manually and LLM-assisted methods, serving as a benchmark and enabling future research. Using this dataset, we benchmark ROB2 performance for 4 LLMs and provide an analysis into current model capabilities and ongoing challenges in automating this critical aspect of systematic review.

Joshua Wolff Anderson, Shyam Visweswaran

Trustworthy machine learning in healthcare requires strong predictive performance, fairness, and explanations. While it is known that improving fairness can affect predictive performance, little is known about how fairness improvements influence explainability, an essential ingredient for clinical trust. Clinicians may hesitate to rely on a model whose explanations shift after fairness constraints are applied. In this study, we examine how enhancing fairness through bias mitigation techniques reshapes Shapley-based feature rankings. We quantify changes in feature importance rankings after applying fairness constraints across three datasets: pediatric urinary tract infection risk, direct anticoagulant bleeding risk, and recidivism risk. We also evaluate multiple model classes on the stability of Shapley-based rankings. We find that increasing model fairness across racial subgroups can significantly alter feature importance rankings, sometimes in different ways across groups. These results highlight the need to jointly consider accuracy, fairness, and explainability in model assessment rather than in isolation.

Marco Voegeli, Sonia Laguna, Heike Leutheuser et al.

The dead-in-bed syndrome describes the sudden and unexplained death of young individuals with Type 1 Diabetes (T1D) without prior long-term complications. One leading hypothesis attributes this phenomenon to nocturnal hypoglycemia (NH), a dangerous drop in blood glucose during sleep. This study aims to improve NH prediction in children with T1D by leveraging physiological data and machine learning (ML) techniques. We analyze an in-house dataset collected from 16 children with T1D, integrating physiological metrics from wearable sensors. We explore predictive performance through feature engineering, model selection, architectures, and oversampling. To address data limitations, we apply transfer learning from a publicly available adult dataset. Our results achieve an AUROC of 0.75 +- 0.21 on the in-house dataset, further improving to 0.78 +- 0.05 with transfer learning. This research moves beyond glucose-only predictions by incorporating physiological parameters, showcasing the potential of ML to enhance NH detection and improve clinical decision-making for pediatric diabetes management.

Alejandro Acosta-Rodríguez, Sandra A. Reza-López, César R. Aguilar-Torres et al.

ObjectiveExternal ear anomalies may lead to conductive hearing loss with significant childhood disability, psychological distress, anxiety, social avoidance, and behavioral problems. The aim of this study is to compile and review published literature on the frequency of isolated and non-isolated external ear anomalies, their associated factors, and associated malformations/deformations in non-isolated cases.MethodsWe conducted a systematic review in PubMed, Google Scholar, and Science Direct searching for any type of article (excluding reviews and meta-analyses) reporting isolated and non-isolated external ear anomalies in humans. Two authors extracted the information according to the main variables of interest according to PICO criteria. Details of studied population and main findings were also obtained (malformation type, unilateral or bilateral malformations and associated factors).ResultsTwenty-six studies met eligibility criteria to be included in this review. Anotia/microtia was the most reported malformation, more frequently found in males, mostly unilateral; being the right ear the most affected, and more frequent in Hispanic population. Associated factors for external ear anomalies included parental age, maternal education, multiple pregnancies, high maternal body mass index and diabetes, pregnancy, and perinatal complications (low birth weight, prematurity, threatened abortion, etc.), twining, and chemical/drug exposure. The most reported malformations and syndromes associated with congenital external ear defects included: skull/face anomalies, cleft lip/palate, congenital heart defects, musculoskeletal malformations of skull, face and jaw, Treacher-Collins, OAVS (oculo-auriculo-vertebral spectrum), and trisomy 18, 13 and 21.ConclusionCongenital external ear anomalies can occur isolated or associated with other malformations or syndromes. Environmental, socioeconomic, and cultural factors may partially explain the variation across populations for congenital external ear anomalies. Depending on their type and severity, they can lead to speech impediments and childhood disability, particularly in bilateral cases, highlighting the relevance of early detection and repair to avoid childhood disability.

Shashank Manjunath, Hau-Tieng Wu, Aarti Sathyanarayana

Sleep staging is a challenging task, typically manually performed by sleep technologists based on electroencephalogram and other biosignals of patients taken during overnight sleep studies. Recent work aims to leverage automated algorithms to perform sleep staging not based on electroencephalogram signals, but rather based on the airflow signals of subjects. Prior work uses ideas from topological data analysis (TDA), specifically Hermite function expansions of persistence curves (HEPC) to featurize airflow signals. However, finite order HEPC captures only partial information. In this work, we propose Fourier approximations of persistence curves (FAPC), and use this technique to perform sleep staging based on airflow signals. We analyze performance using an XGBoost model on 1155 pediatric sleep studies taken from the Nationwide Children's Hospital Sleep DataBank (NCHSDB), and find that FAPC methods provide complimentary information to HEPC methods alone, leading to a 4.9% increase in performance over baseline methods.

Shashank Manjunath, Aarti Sathyanarayana

In this work, we leverage machine learning techniques to identify potential biomarkers of oxygen desaturation during sleep exclusively from electroencephalogram (EEG) signals in pediatric patients with sleep apnea. Development of a machine learning technique which can successfully identify EEG signals from patients with sleep apnea as well as identify latent EEG signals which come from subjects who experience oxygen desaturations but do not themselves occur during oxygen desaturation events would provide a strong step towards developing a brain-based biomarker for sleep apnea in order to aid with easier diagnosis of this disease. We leverage a large corpus of data, and show that machine learning enables us to classify EEG signals as occurring during oxygen desaturations or not occurring during oxygen desaturations with an average 66.8% balanced accuracy. We furthermore investigate the ability of machine learning models to identify subjects who experience oxygen desaturations from EEG data that does not occur during oxygen desaturations. We conclude that there is a potential biomarker for oxygen desaturation in EEG data.

Jennifer J. Schnur, Angélica Garcia-Martínez, Patrick Soga et al.

We developed SaludConectaMX as a comprehensive system to track and understand the determinants of complications throughout chemotherapy treatment for children with cancer in Mexico. SaludConectaMX is unique in that it integrates patient clinical indicators with social determinants and caregiver mental health, forming a social-clinical perspective of the patient's evolving health trajectory. The system is composed of a web application (for hospital staff) and a mobile application (for family caregivers), providing the opportunity for cooperative patient monitoring in both hospital and home settings. This paper presents the system's preliminary design and usability evaluation results from a 1.5-year pilot study. Our findings indicate that while the hospital web app demonstrates high completion rates and user satisfaction, the family mobile app requires additional improvements for optimal accessibility; statistical and qualitative data analysis illuminate pathways for system improvement. Based on this evidence, we formalize suggestions for health system development in LMICs, which HCI researchers may leverage in future work.

Arnon Elizur, Shirel Rachel‐Jossefi, Marianna Rachmiel et al.

Abstract Background The effect of the amount of transient cow's milk formula (CMF) consumed during the first days of life on IgE‐cow's milk allergy (IgE‐CMA) is unknown. Methods A cohort of 58 patients with IgE‐CMA was identified from a large scale population‐based study of 13,019 infants followed from birth. A group of 116 infants matched for sex and breastfeeding only duration (beyond the nursery period), and another random group of 259 healthy infants were used as controls. Parents were interviewed and the infants' medical records were searched to assess CMF consumption in the nursery. Results While 96% of the mothers of the 174 infants (58 with Cow's milk allergy and 116 controls) reported on exclusive breastfeeding during the stay in the nursery, CMF consumption was documented in 96 (55%) of the infants. Of those, most (57; 59%) received one to three feedings, 20 (21%) received four to nine feedings, and 19 (20%) received ≥10 feedings. Fewer formula feeds (1–3) were significantly more common in the allergic group than ≥4 feeds (p = 0.0003) and no feeds at all (p = 0.02) compared to controls (n = 116). Of those exclusively breastfed in the nursery, 13/23 allergic infants (57%) introduced CMF at age 105–194 days (the period with highest‐risk for IgE‐CMA) compared to 33/98 (34%) from the random control group (n = 259) (p = 0.04). Conclusions Most infants end up receiving few CMF feeds in the nursery. Transient CMF in the nursery is associated with increased risk of IgE‐CMA.

Hao Yu, Anas M Khanshour, Aki Ushiki et al.

Adolescent idiopathic scoliosis (AIS) is a common and progressive spinal deformity in children that exhibits striking sexual dimorphism, with girls at more than fivefold greater risk of severe disease compared to boys. Despite its medical impact, the molecular mechanisms that drive AIS are largely unknown. We previously defined a female-specific AIS genetic risk locus in an enhancer near the PAX1 gene. Here, we sought to define the roles of PAX1 and newly identified AIS-associated genes in the developmental mechanism of AIS. In a genetic study of 10,519 individuals with AIS and 93,238 unaffected controls, significant association was identified with a variant in COL11A1 encoding collagen (α1) XI (rs3753841; NM_080629.2_c.4004C>T; p.(Pro1335Leu); p=7.07E–11, OR = 1.118). Using CRISPR mutagenesis we generated Pax1 knockout mice (Pax1-/-). In postnatal spines we found that PAX1 and collagen (α1) XI protein both localize within the intervertebral disc-vertebral junction region encompassing the growth plate, with less collagen (α1) XI detected in Pax1-/- spines compared to wild-type. By genetic targeting we found that wild-type Col11a1 expression in costal chondrocytes suppresses expression of Pax1 and of Mmp3, encoding the matrix metalloproteinase 3 enzyme implicated in matrix remodeling. However, the latter suppression was abrogated in the presence of the AIS-associated COL11A1P1335L mutant. Further, we found that either knockdown of the estrogen receptor gene Esr2 or tamoxifen treatment significantly altered Col11a1 and Mmp3 expression in chondrocytes. We propose a new molecular model of AIS pathogenesis wherein genetic variation and estrogen signaling increase disease susceptibility by altering a PAX1-COL11a1-MMP3 signaling axis in spinal chondrocytes.

Kameswara Bharadwaj Mantha, Ramanakumar Sankar, Lucy Fortson

Development of robust general purpose 3D segmentation frameworks using the latest deep learning techniques is one of the active topics in various bio-medical domains. In this work, we introduce Temporal Cubic PatchGAN (TCuP-GAN), a volume-to-volume translational model that marries the concepts of a generative feature learning framework with Convolutional Long Short-Term Memory Networks (LSTMs), for the task of 3D segmentation. We demonstrate the capabilities of our TCuP-GAN on the data from four segmentation challenges (Adult Glioma, Meningioma, Pediatric Tumors, and Sub-Saharan Africa subset) featured within the 2023 Brain Tumor Segmentation (BraTS) Challenge and quantify its performance using LesionWise Dice similarity and $95\%$ Hausdorff Distance metrics. We demonstrate the successful learning of our framework to predict robust multi-class segmentation masks across all the challenges. This benchmarking work serves as a stepping stone for future efforts towards applying TCuP-GAN on other multi-class tasks such as multi-organelle segmentation in electron microscopy imaging.

Toygar Tanyel, Serkan Ayvaz, Bilgin Keserci

The field of explainability in artificial intelligence (AI) has witnessed a growing number of studies and increasing scholarly interest. However, the lack of human-friendly and individual interpretations in explaining the outcomes of machine learning algorithms has significantly hindered the acceptance of these methods by clinicians in their research and clinical practice. To address this issue, our study uses counterfactual explanations to explore the applicability of "what if?" scenarios in medical research. Our aim is to expand our understanding of magnetic resonance imaging (MRI) features used for diagnosing pediatric posterior fossa brain tumors beyond existing boundaries. In our case study, the proposed concept provides a novel way to examine alternative decision-making scenarios that offer personalized and context-specific insights, enabling the validation of predictions and clarification of variations under diverse circumstances. Additionally, we explore the potential use of counterfactuals for data augmentation and evaluate their feasibility as an alternative approach in our medical research case. The results demonstrate the promising potential of using counterfactual explanations to improve AI-driven methods in clinical research.

Minh Hieu Phan, Zhibin Liao, Johan W. Verjans et al.

Medical image synthesis is a challenging task due to the scarcity of paired data. Several methods have applied CycleGAN to leverage unpaired data, but they often generate inaccurate mappings that shift the anatomy. This problem is further exacerbated when the images from the source and target modalities are heavily misaligned. Recently, current methods have aimed to address this issue by incorporating a supplementary segmentation network. Unfortunately, this strategy requires costly and time-consuming pixel-level annotations. To overcome this problem, this paper proposes MaskGAN, a novel and cost-effective framework that enforces structural consistency by utilizing automatically extracted coarse masks. Our approach employs a mask generator to outline anatomical structures and a content generator to synthesize CT contents that align with these structures. Extensive experiments demonstrate that MaskGAN outperforms state-of-the-art synthesis methods on a challenging pediatric dataset, where MR and CT scans are heavily misaligned due to rapid growth in children. Specifically, MaskGAN excels in preserving anatomical structures without the need for expert annotations. The code for this paper can be found at https://github.com/HieuPhan33/MaskGAN.

R. Brian Lowry, Tanya Bedard, Xin Grevers et al.

IntroductionCurrent published long-term provincial or territorial congenital anomaly data are lacking for Canada. We report on prevalence (per 1000 total births) and trends in 1997–2019, in Alberta, Canada, for selected congenital anomalies. Associated risk factors are also discussed. MethodsWe used data from the Alberta Congenital Anomalies Surveillance System (ACASS) to calculate the prevalence and perform chi-square linear trend analyses. ResultsFrom 1997 to 2019, the overall prevalence of neural tube defects was stable, at 0.74 per 1000 total births. The same was true for spina bifida (0.38), orofacial clefts (1.99), more severe CHDs (transposition of the great arteries, 0.38; tetralogy of Fallot, 0.33; and hypoplastic left heart syndrome, 0.32); and gastroschisis (0.38). Anencephaly, cleft palate and anorectal malformation significantly decreased with a prevalence of 0.23, 0.75 and 0.54 per 1000 total births, respectively. Significantly increasing trends were reported for anotia/microtia (0.24), limb reduction anomalies (0.73), omphalocele (0.36) and Down syndrome (2.21) and for hypospadias and undescended testes (4.68 and 5.29, respectively, per 1000 male births). ConclusionCongenital anomalies are an important public health concern with significant social and societal costs. Surveillance data gathered by ACASS for over 40 years can be used for planning and policy decisions and the evaluation of prevention strategies. Contributing genetic and environmental factors are discussed as is the need for continued surveillance and research.

Peter J. Lawrence, Simona Skripkauskaite, Adrienne Shum et al.

Abstract Background The COVID‐19 pandemic caused significant disruption to the lives of children and their families. Pre‐school children may have been particularly vulnerable to the effects of the pandemic, with the closure of childcare facilities, playgrounds, playcentres and parent and toddler groups limiting their opportunities for social interaction at a crucial stage of development. Additionally, for parents working from home, caring for pre‐school aged children who require high levels of support and care, was likely challenging. We conducted an intensive longitudinal, but not nationally representative, study to examine trajectories of pre‐schoolers’ mental symptoms in the United Kingdom during the first year of the COVID‐19 pandemic. Methods UK‐based parents and carers (n = 1520) of pre‐school‐aged children (2–4 years) completed monthly online surveys about their pre‐schoolers’ mental health between April 2020 and March 2021. The survey examined changes in children's emotional symptoms, conduct problems and hyperactivity/inattention. Results In our final mixed‐effects models, our predictors (fixed effects) accounted for 5% of the variance in each of conduct problems, emotional symptoms and hyperactivity/inattention symptoms scores, and the combined random and fixed effects accounted for between 64% and 73% of the variance. Pre‐schoolers’ emotional problems and hyperactivity/inattention symptoms declined from April through summer 2020 and then increased again during the autumn and winter 2020/2021 as lockdowns were re‐introduced. Pre‐schoolers who attended childcare showed greater decline in symptom severity than those who did not. Older children, compared to younger, showed greater lability of emotion symptom severity. Attending childcare predicted lower symptom severity across all three domains of conduct problems, emotional symptoms, and hyperactivity/inattention, while the opposite pattern was observed for children whose parent had a mental health problem. Conclusions Our findings reinforce the importance of examining pre‐schoolers’ mental health in the context of micro and macro‐level factors. Interventions focussing on family factors such as parent mental health, as well as continued provision of childcare, may have most potential to mitigate the impact of COVID‐19 on young children's mental health.

He Liu, Pei Liu, Ning Sun et al.

Background Hypospadias repair is a complex surgical procedure that involves correcting penile ventral curvature (VC) and performing urethroplasty. This study aims to evaluate the effectiveness of different strategies for VC correction and analyse the trends in hypospadias repair at a national centre in China.Methods Prospective data collection was conducted from 2019 to 2020 for patients undergoing hypospadias repair. The effectiveness of VC correction was assessed based on the degree of VC change with different strategies. Furthermore, the choice of surgical techniques for different types of hypospadias repair was analysed.Results A total of 434 patients were included, with a median preoperative VC degree of 50° (35°, 70°). All patients achieved a straight penis postoperatively, with 15.2% undergoing degloving, 28.6% undergoing degloving and dorsal plication (DP), 13.1% undergoing degloving and urethral plate transection (UPT), and 43.1% undergoing degloving, UPT and DP. Degloving alone was effective in correcting VC in 57.6% of patients with VC less than 30°. In our analysis, DP after UPT resulted in a higher degree of correction (25°) compared with DP after degloving alone (20°) (p<0.001). The study identified the current trends in hypospadias repair, with tubularised incised plate urethroplasty (TIP) being the most common technique used in distal hypospadias repair (70.6% of patients) and transverse preputial island flap urethroplasty (TPIFU) being preferred for proximal hypospadias repair (63.0%).Conclusions Degloving alone is effective for correcting VC less than 30°. The majority of patients in our centre underwent UPT, and DP after UPT yielded better results compared with DP after degloving alone. Distal hypospadias repair commonly used TIP, while TPIFU was favoured for proximal hypospadias repair.Trial registration number ChiCTR1900023055.

Yurong Du, Lei Liu, Weiliang Yan et al.

Abstract Exopolysaccharide (EPS) from Weissella cibaria has been devoted to the study of food industry. However, the anticancer activity of W. cibaria derived EPS has not yet been investigated. In this study, we obtained the EPS from W. cibaria D-2 isolated from the feces of healthy infants and found that D-2-EPS, a homopolysaccharide with porous web like structure, could effectively inhibit the proliferation, migration, invasion and induce cell cycle arrest in G0/G1 phase of colorectal cancer (CRC) cells. In HT-29 tumor xenografts, D-2-EPS significantly retarded tumor growth without obvious cytotoxicity to normal organs. Furthermore, we revealed that D-2-EPS promoted the apoptosis of CRC cells by increasing the levels of Fas, FasL and activating Caspase-8/Caspase-3, indicating that D-2-EPS might induce apoptosis through the extrinsic Fas/FasL pathway. Taken together, the D-2-EPS has the potential to be developed as a nutraceutical or drug to prevent and treat colorectal cancer.

Adam B Kashlak, Prachi Loliencar, Giseon Heo

The hidden Markov model (HMM) is a classic modeling tool with a wide swath of applications. Its inception considered observations restricted to a finite alphabet, but it was quickly extended to multivariate continuous distributions. In this article, we further extend the HMM from mixtures of normal distributions in $d$-dimensional Euclidean space to general Gaussian measure mixtures in locally convex topological spaces. The main innovation is the use of the Onsager-Machlup functional as a proxy for the probability density function in infinite dimensional spaces. This allows for choice of a Cameron-Martin space suitable for a given application. We demonstrate the versatility of this methodology by applying it to simulated diffusion processes such as Brownian and fractional Brownian sample paths as well as the Ornstein-Uhlenbeck process. Our methodology is applied to the identification of sleep states from overnight polysomnography time series data with the aim of diagnosing Obstructive Sleep Apnea in pediatric patients. It is also applied to a series of annual cumulative snowfall curves from 1940 to 1990 in the city of Edmonton, Alberta.