-
Scientific Reports Jul 2024The protocol predefined aim of this study is to assess sustained effects of the OptiTrain trial on several health outcomes, 5 years after the baseline assessment. The... (Randomized Controlled Trial)
Randomized Controlled Trial
The protocol predefined aim of this study is to assess sustained effects of the OptiTrain trial on several health outcomes, 5 years after the baseline assessment. The OptiTrain study was a prospective, randomised controlled trial with 240 patients with breast cancer undergoing adjuvant chemotherapy that compared the effects of 16 weeks of two exercise programs, RT-HIIT and AT-HIIT, with usual care (UC). After a 5-year follow-up, eligible participants were evaluated for the primary outcome of cancer-related fatigue (CRF) and secondary outcomes including quality of life, symptoms, muscle strength, cardiorespiratory fitness, body mass, physical activity, and sedentary behavior. Statistical analysis was conducted using linear mixed models adjusted for baseline values. Tumour profile and menopausal status were additionally adjusted for CRF. Mean differences (MD), 95% confidence intervals (CIs), and standardized effect sizes (ES) were reported. At the 5-year follow-up, there were no statistically significant differences in total CRF between the intervention groups and the UC group. RT-HIIT reported significantly reduced pain sensitivity at the gluteus MD = 79.00 (95% CI 10.17, 147.83, ES = 0.55) compared to UC. Clinically meaningful differences for an increase in cognitive CRF and cardiorespiratory fitness were observed for the AT-HIIT versus UC group, and for lower limb strength for the RT-HIIT versus UC group, albeit without statistical significance. Engaging in targeted exercise during adjuvant chemotherapy for breast cancer provides short-term benefits in reducing fatigue and maintaining physical function. However, our 5-year follow-up indicates that these effects are limited in the long term. This underscores the need to support breast cancer survivors maintain their PA levels throughout their survivorship journey.
Topics: Humans; Breast Neoplasms; Female; Middle Aged; Follow-Up Studies; Quality of Life; High-Intensity Interval Training; Fatigue; Resistance Training; Cardiorespiratory Fitness; Prospective Studies; Muscle Strength; Adult; Chemotherapy, Adjuvant; Exercise; Aged
PubMed: 38961182
DOI: 10.1038/s41598-024-65436-z -
Scientific Reports Jul 2024Machine learning (ML)-driven diagnosis systems are particularly relevant in pediatrics given the well-documented impact of early-life health conditions on later-life...
Machine learning (ML)-driven diagnosis systems are particularly relevant in pediatrics given the well-documented impact of early-life health conditions on later-life outcomes. Yet, early identification of diseases and their subsequent impact on length of hospital stay for this age group has so far remained uncharacterized, likely because access to relevant health data is severely limited. Thanks to a confidential data use agreement with the California Department of Health Care Access and Information, we introduce Ped-BERT: a state-of-the-art deep learning model that accurately predicts the likelihood of 100+ conditions and the length of stay in a pediatric patient's next medical visit. We link mother-specific pre- and postnatal period health information to pediatric patient hospital discharge and emergency room visits. Our data set comprises 513.9K mother-baby pairs and contains medical diagnosis codes, length of stay, as well as temporal and spatial pediatric patient characteristics, such as age and residency zip code at the time of visit. Following the popular bidirectional encoder representations from the transformers (BERT) approach, we pre-train Ped-BERT via the masked language modeling objective to learn embedding features for the diagnosis codes contained in our data. We then continue to fine-tune our model to accurately predict primary diagnosis outcomes and length of stay for a pediatric patient's next visit, given the history of previous visits and, optionally, the mother's pre- and postnatal health information. We find that Ped-BERT generally outperforms contemporary and state-of-the-art classifiers when trained with minimum features. We also find that incorporating mother health attributes leads to significant improvements in model performance overall and across all patient subgroups in our data. Our most successful Ped-BERT model configuration achieves an area under the receiver operator curve (ROC AUC) of 0.927 and an average precision score (APS) of 0.408 for the diagnosis prediction task, and a ROC AUC of 0.855 and APS of 0.815 for the length of hospital stay task. Further, we examine Ped-BERT's fairness by determining whether prediction errors are evenly distributed across various subgroups of mother-baby demographics and health characteristics, or if certain subgroups exhibit a higher susceptibility to prediction errors.
Topics: Humans; Female; Child Health; Infant; Child, Preschool; Maternal Health; Child; Early Diagnosis; Length of Stay; Infant, Newborn; Male; Deep Learning; Machine Learning
PubMed: 38961161
DOI: 10.1038/s41598-024-65449-8 -
Scientific Reports Jul 2024Understanding the exact pathophysiological mechanisms underlying the involvement of triggering receptor expressed on myeloid cells 2 (TREM2) related microglia activation...
Understanding the exact pathophysiological mechanisms underlying the involvement of triggering receptor expressed on myeloid cells 2 (TREM2) related microglia activation is crucial for the development of clinical trials targeting microglia activation at different stages of Alzheimer's disease (AD). Given the contradictory findings in the literature, it is imperative to investigate the longitudinal alterations in cerebrospinal fluid (CSF) soluble TREM2 (sTREM2) levels as a marker for microglia activation, and its potential association with AD biomarkers, in order to address the current knowledge gap. In this study, we aimed to assess the longitudinal changes in CSF sTREM2 levels within the framework of the A/T/N classification system for AD biomarkers and to explore potential associations with AD pathological features, including the presence of amyloid-beta (Aβ) plaques and tau aggregates. The baseline and longitudinal (any available follow-up visit) CSF sTREM2 levels and processed tau-PET and Aβ-PET data of 1001 subjects were recruited from the ADNI database. The participants were classified into four groups based on the A/T/N framework: A+ /TN+ , A+ /TN- , A- /TN+ , and A- /TN- . Linear regression analyses were conducted to assess the relationship between CSF sTREM2 with cognitive performance, tau and Aβ-PET adjusting for age, gender, education, and APOE ε4 status. Based on our analysis there was a significant difference in baseline and rate of change of CSF sTREM2 between ATN groups. While there was no association between baseline CSF sTREM2 and cognitive performance (ADNI-mem), we found that the rate of change of CSF sTREM2 is significantly associated with cognitive performance in the entire cohort but not the ATN groups. We found that the baseline CSF sTREM2 is significantly associated with baseline tau-PET and Aβ-PET rate of change only in the A+ /TN+ group. A significant association was found between the rate of change of CSF sTREM2 and the tau- and Aβ-PET rate of change only in the A+ /TN- group. Our study suggests that the TREM2-related microglia activation and their relations with AD markers and cognitive performance vary the in presence or absence of Aβ and tau pathology. Furthermore, our findings revealed that a faster increase in the level of CSF sTREM2 might attenuate future Aβ plaque formation and tau aggregate accumulation only in the presence of Aβ pathology.
Topics: Humans; Alzheimer Disease; Receptors, Immunologic; Membrane Glycoproteins; Biomarkers; Female; Male; Aged; Longitudinal Studies; tau Proteins; Neuroimaging; Aged, 80 and over; Amyloid beta-Peptides; Positron-Emission Tomography; Plaque, Amyloid; Microglia
PubMed: 38961148
DOI: 10.1038/s41598-024-66211-w -
Scientific Reports Jul 2024This study was performed to segment the urinary system as the basis for diagnosing urinary system diseases on non-contrast computed tomography (CT). This study was...
This study was performed to segment the urinary system as the basis for diagnosing urinary system diseases on non-contrast computed tomography (CT). This study was conducted with images obtained between January 2016 and December 2020. During the study period, non-contrast abdominopelvic CT scans of patients and diagnosed and treated with urinary stones at the emergency departments of two institutions were collected. Region of interest extraction was first performed, and urinary system segmentation was performed using a modified U-Net. Thereafter, fivefold cross-validation was performed to evaluate the robustness of the model performance. In fivefold cross-validation results of the segmentation of the urinary system, the average dice coefficient was 0.8673, and the dice coefficients for each class (kidney, ureter, and urinary bladder) were 0.9651, 0.7172, and 0.9196, respectively. In the test dataset, the average dice coefficient of best performing model in fivefold cross validation for whole urinary system was 0.8623, and the dice coefficients for each class (kidney, ureter, and urinary bladder) were 0.9613, 0.7225, and 0.9032, respectively. The segmentation of the urinary system using the modified U-Net proposed in this study could be the basis for the detection of kidney, ureter, and urinary bladder lesions, such as stones and tumours, through machine learning.
Topics: Humans; Tomography, X-Ray Computed; Urinary Bladder; Ureter; Kidney; Female; Male; Middle Aged; Adult; Aged; Image Processing, Computer-Assisted; Neural Networks, Computer
PubMed: 38961140
DOI: 10.1038/s41598-024-66045-6 -
Scientific Reports Jul 2024Human activity recognition has a wide range of applications in various fields, such as video surveillance, virtual reality and human-computer intelligent interaction. It...
Human activity recognition has a wide range of applications in various fields, such as video surveillance, virtual reality and human-computer intelligent interaction. It has emerged as a significant research area in computer vision. GCN (Graph Convolutional networks) have recently been widely used in these fields and have made great performance. However, there are still some challenges including over-smoothing problem caused by stack graph convolutions and deficient semantics correlation to capture the large movements between time sequences. Vision Transformer (ViT) is utilized in many 2D and 3D image fields and has surprised results. In our work, we propose a novel human activity recognition method based on ViT (HAR-ViT). We integrate enhanced AGCL (eAGCL) in 2s-AGCN to ViT to make it process spatio-temporal data (3D skeleton) and make full use of spatial features. The position encoder module orders the non-sequenced information while the transformer encoder efficiently compresses sequence data features to enhance calculation speed. Human activity recognition is accomplished through multi-layer perceptron (MLP) classifier. Experimental results demonstrate that the proposed method achieves SOTA performance on three extensively used datasets, NTU RGB+D 60, NTU RGB+D 120 and Kinetics-Skeleton 400.
Topics: Humans; Human Activities; Neural Networks, Computer; Algorithms; Pattern Recognition, Automated; Image Processing, Computer-Assisted; Imaging, Three-Dimensional
PubMed: 38961136
DOI: 10.1038/s41598-024-65850-3 -
Scientific Reports Jul 2024Alzheimer's disease (AD), the predominant form of dementia, is a growing global challenge, emphasizing the urgent need for accurate and early diagnosis. Current clinical...
Alzheimer's disease (AD), the predominant form of dementia, is a growing global challenge, emphasizing the urgent need for accurate and early diagnosis. Current clinical diagnoses rely on radiologist expert interpretation, which is prone to human error. Deep learning has thus far shown promise for early AD diagnosis. However, existing methods often overlook focal structural atrophy critical for enhanced understanding of the cerebral cortex neurodegeneration. This paper proposes a deep learning framework that includes a novel structure-focused neurodegeneration CNN architecture named SNeurodCNN and an image brightness enhancement preprocessor using gamma correction. The SNeurodCNN architecture takes as input the focal structural atrophy features resulting from segmentation of brain structures captured through magnetic resonance imaging (MRI). As a result, the architecture considers only necessary CNN components, which comprises of two downsampling convolutional blocks and two fully connected layers, for achieving the desired classification task, and utilises regularisation techniques to regularise learnable parameters. Leveraging mid-sagittal and para-sagittal brain image viewpoints from the Alzheimer's disease neuroimaging initiative (ADNI) dataset, our framework demonstrated exceptional performance. The para-sagittal viewpoint achieved 97.8% accuracy, 97.0% specificity, and 98.5% sensitivity, while the mid-sagittal viewpoint offered deeper insights with 98.1% accuracy, 97.2% specificity, and 99.0% sensitivity. Model analysis revealed the ability of SNeurodCNN to capture the structural dynamics of mild cognitive impairment (MCI) and AD in the frontal lobe, occipital lobe, cerebellum, temporal, and parietal lobe, suggesting its potential as a brain structural change digi-biomarker for early AD diagnosis. This work can be reproduced using code we made available on GitHub.
Topics: Alzheimer Disease; Humans; Magnetic Resonance Imaging; Neural Networks, Computer; Deep Learning; Neuroimaging; Brain; Image Processing, Computer-Assisted
PubMed: 38961114
DOI: 10.1038/s41598-024-60611-8 -
Scientific Reports Jul 2024Imbalances in electrolyte concentrations can have severe consequences, but accurate and accessible measurements could improve patient outcomes. The current measurement...
Imbalances in electrolyte concentrations can have severe consequences, but accurate and accessible measurements could improve patient outcomes. The current measurement method based on blood tests is accurate but invasive and time-consuming and is often unavailable for example in remote locations or an ambulance setting. In this paper, we explore the use of deep neural networks (DNNs) for regression tasks to accurately predict continuous electrolyte concentrations from electrocardiograms (ECGs), a quick and widely adopted tool. We analyze our DNN models on a novel dataset of over 290,000 ECGs across four major electrolytes and compare their performance with traditional machine learning models. For improved understanding, we also study the full spectrum from continuous predictions to a binary classification of extreme concentration levels. Finally, we investigate probabilistic regression approaches and explore uncertainty estimates for enhanced clinical usefulness. Our results show that DNNs outperform traditional models but model performance varies significantly across different electrolytes. While discretization leads to good classification performance, it does not address the original problem of continuous concentration level prediction. Probabilistic regression has practical potential, but our uncertainty estimates are not perfectly calibrated. Our study is therefore a first step towards developing an accurate and reliable ECG-based method for electrolyte concentration level prediction-a method with high potential impact within multiple clinical scenarios.
Topics: Electrocardiography; Humans; Electrolytes; Neural Networks, Computer; Regression Analysis; Machine Learning
PubMed: 38961109
DOI: 10.1038/s41598-024-65223-w -
Scientific Reports Jul 2024The forced turnout has a perceived risk of development of hallux valgus (HV) in ballet dancers. We determined how the forced turnout affects the sagittal mobility of the...
The forced turnout has a perceived risk of development of hallux valgus (HV) in ballet dancers. We determined how the forced turnout affects the sagittal mobility of the first tarsometatarsal (TMT) joint, which is one of the pathogenic factors of HV development. Seventeen female ballet dancers (body mass index: 18.2 ± 1.8 kg/m) were included and performed demi-plié in control, functional turnout, and forced turnout conditions. Ultrasound imaging synchronized with a three-dimensional motion analysis system was used for measuring the vertical locations of the first metatarsal and medial cuneiform (MC) to evaluate the first TMT joint mobility. Plantar displacement of MC and the first TMT joint mobility in the forced turnout were the greatest among the 3 conditions. Multiple regression analysis indicated that the greater extent of the forcing angle might increase the displacement of MC and the first TMT joint mobility. Evaluating the sagittal mobility of the first TMT joint in the forced turnout can assist in understanding the association between inappropriate techniques including the forced turnout and HV development in ballet dancers. Since the excessive mobility of the first TMT joint is a factor in HV development, the acquirement of adequate active turnout may have the potential to prevent HV development in ballet dancers.
Topics: Humans; Female; Dancing; Young Adult; Range of Motion, Articular; Hallux Valgus; Adult; Metatarsal Bones; Biomechanical Phenomena; Ultrasonography
PubMed: 38961097
DOI: 10.1038/s41598-024-64304-0 -
Scientific Reports Jul 2024Characteristics of chronic obstructive pulmonary disease (COPD) patients with superoptimal peak inspiratory flow rates (PIFR) has not been thoroughly investigated. This...
Characteristics of chronic obstructive pulmonary disease (COPD) patients with superoptimal peak inspiratory flow rates (PIFR) has not been thoroughly investigated. This study aimed to compare the characteristics between COPD patients with superoptimal PIFR and those with optimal and sub-optimal PIFR. PIFR was measured using In-Check DIAL G16 and categorized into sub-optimal (PIFR lower than that required by the patient's device), optimal, and superoptimal (peak PIFR ≥ 90 L/min). Considering COPD patients with sub-optimal PIFR as the reference group, analyses were performed to identify PIFR-related factors. Subgroup analysis was performed according to the forced expiratory volume in 1 s (FEV) % of the predicted value (%pred). Among 444 post-bronchodilator-confirmed COPD patients from seven tertiary hospitals in South Korea, 98, 223, and 123 were classified into the sub-optimal, optimal, and superoptimal PIFR groups, respectively. The superoptimal PIFR group were younger, had an increased proportion of males, a higher body mass index, lowest number of comorbidities and less frequent exacerbation in the previous year, as well as the highest forced vital capacity %pred. The adjusted odds ratio for frequent exacerbation in the previous year was lower in the superoptimal PIFR group than in the sub-optimal PIFR group and was more pronounced in patients with an FEV%pred of < 70%. COPD patients with superoptimal PIFR have clinical characteristics different from those patients with the sub-optimal and optimal PIFR. Having a high inspiratory flow may be a favorable trait in COPD.
Topics: Humans; Pulmonary Disease, Chronic Obstructive; Male; Female; Aged; Middle Aged; Forced Expiratory Volume; Inhalation; Republic of Korea; Vital Capacity
PubMed: 38961087
DOI: 10.1038/s41598-024-65085-2 -
Scientific Reports Jul 2024Early detection of the adenocarcinoma cancer in colon tissue by means of explainable deep learning, by classifying histological images and providing visual...
Early detection of the adenocarcinoma cancer in colon tissue by means of explainable deep learning, by classifying histological images and providing visual explainability on model prediction. Considering that in recent years, deep learning techniques have emerged as powerful techniques in medical image analysis, offering unprecedented accuracy and efficiency, in this paper we propose a method to automatically detect the presence of cancerous cells in colon tissue images. Various deep learning architectures are considered, with the aim of considering the best one in terms of quantitative and qualitative results. As a matter of fact, we consider qualitative results by taking into account the so-called prediction explainability, by providing a way to highlight on the tissue images the areas that from the model point of view are related to the presence of colon cancer. The experimental analysis, performed on 10,000 colon issue images, showed the effectiveness of the proposed method by obtaining an accuracy equal to 0.99. The experimental analysis shows that the proposed method can be successfully exploited for colon cancer detection and localisation from tissue images.
Topics: Deep Learning; Humans; Colonic Neoplasms; Image Processing, Computer-Assisted; Early Detection of Cancer; Adenocarcinoma
PubMed: 38961080
DOI: 10.1038/s41598-024-63659-8