Search Results (16,321)

Counting fetal movements is essential for assessing fetal health, but manually recording these movements can be challenging and inconvenient for pregnant women. This study presents a wearable device designed to detect fetal movements across various settings, both within and outside medical facilities. The device integrates accelerometer and gyroscope sensors with Internet of Things (IoT) technology to accurately differentiate between fetal and non-fetal movements. Data were collected from 35 pregnant women at Suranaree University of Technology (SUT) Hospital. This study evaluated ten signal extraction methods, six machine learning algorithms, and four feature selection techniques to enhance classification performance. The device utilized Particle Swarm Optimization (PSO) for feature selection and Extreme Gradient Boosting (XGB) with PSO hyper-tuning. It achieved a sensitivity of 90.00%, precision of 87.46%, and an F1-score of 88.56%, reflecting commendable results. The IoT-enabled technology facilitated continuous monitoring with an average latency of 423.6 ms. It ensured complete data integrity and successful transmission, with the capability to operate continuously for up to 48 h on a single charge. The findings substantiate the efficacy of the proposed approach in detecting fetal movements, thereby demonstrating a practical and valuable technology for fetal movement detection applications. Full article

Background: Nutritional support through oral nutritional supplements (ONSs) is important for patients. It leads to improved nutritional intake and better clinical and economic outcomes. Objectives: The problem that often accompanies the use of ONSs is their consumption below the optimal prescribed doses. One of the reasons for this is patient education on the importance of ONS intake. This study investigated hospitalized patients and focused on the impact that educational sources have on ONS intake. It also investigated patient compliance with the intake of the prescribed dose, and the time of initiation and discontinuation of ONS consumption. Methods: A qualitative survey using an anonymous questionnaire was conducted on 120 hospital patients across three locations in the Republic of Croatia: Varaždin General Hospital, the Special Hospital for Chronic Diseases in Novi Marof, and the hospital for lung diseases and tuberculosis in Klenovnik. Data were collected by independent nurses and analyzed using appropriate statistical tests, including Shapiro–Wilk, Levene, Mann–Whitney, and χ² tests. Results: There is a statistically significant difference between compliance with the intake at home and the source of information on how to consume ONSs (p = 0.003). There is also a statistically significant difference between compliance with intake at home and the initiation of ONS consumption (p = 0.000) with a key time of six months (half a year) when most of them give up. Conclusions: Only 47.95% complied with the recommended dose of ONS intake at home who received the information from a nurse, if we look at the information source. There is a clear need to change patient education by developing a standardized form and tools accessible to patients. After six months, most patients discontinue ONS consumption. Further research is necessary to determine whether a medical specialist is the reason for discontinuation, or whether discontinuation happened due to insufficient education on the importance of ONS intake. Full article

Introduction: Aortic valve disease (AVD) is an inflammatory, lipid infiltration and calcification disease that has been associated with changes in the conventional linear heart rate variability (HRV) indices showing a marked shift towards sympathetic predominance and a deterioration of the autonomic control. Objective: To explore the HRV dynamics in AVD patients through nonlinear methods by recurrence quantification analysis (RQA). Methods: In total, 127 subjects participated in a cross-sectional study categorized into three groups: healthy valve (HV), aortic valve sclerosis (AVSc), and aortic valve stenosis (AVS), as determined by echocardiographic assessment. HRV data were collected from five-minute ECG recordings at both a supine position and active standing. RQA indices were calculated using the Cross Recurrence Plot Toolbox. Results: In the supine position, patients with AVS exhibited larger determinism and trapping time than those with AVSc and HV. The analysis of these differences revealed that determinism and laminarity increased progressively from HV to AVS. In the same way, the magnitude of change (Δ) between positions decreased and presented the lowest values in AVS in most of the nonlinear indices. Conclusion: RQA indices of HRV in AVD patients indicate a rigidizing dynamic characterized by larger determinism and extended trapping times in fewer system states in relation to the severity of AVD. These findings establish a precedent for future perspective assessments for the implementation of these methods in medical software or devices. Full article

Background: Previous research has linked high coffee consumption to an increased risk of metabolic syndrome (MetS). This study aimed to assess the relationship between coffee consumption and MetS components among Saudi adults. Methods: A cross-sectional study was performed on adults who met at least three criteria for a MetS diagnosis. Data concerning demographics, lifestyle, sleeping patterns, medical health, anthropometric measurements, habitual coffee drinking, and lab levels for HDL-C, LDL-C, TC, TGs, HbA1c, and FBG were collected. Results: Of the 95 participants, 51% were women, 75.8% were >50 years old, 75.8% were obese, 62% were used to practicing physical activity, 74.5% never smoked, 56.4% slept < 7 h/day, and 89.5% were coffee consumers. Of these, 94.7% had high waist circumference, 63.2% had high BP, 47.4% had high FBG, 41.1% had low HDL, and 23.2% had high TGs. For coffee consumers, 37.6% drank a small cup, 34.5% drank coffee once daily, 89.4% drank Arabic coffee, and 75.3% added no additives. Conclusions: No significant association was found between coffee consumption patterns and any MetS component, with the exception of elevated TGs, which was strongly associated with coffee cup size and number of daily cups. Waist circumference and BMI had a strong positive correlation with coffee cup size, and there was a significant relationship between the number of daily cups, BMI, and TC. Further prospective studies are needed to establish a causal relationship. Full article

Integrating deep learning (DL) with the Internet of Medical Things (IoMT) is a paradigm shift in modern healthcare, offering enormous opportunities for patient care, diagnostics, and treatment. Implementing DL with IoMT has the potential to deliver better diagnosis, treatment, and patient management. However, the practical implementation has challenges, including data quality, privacy, interoperability, and limited computational resources. This survey article provides a conceptual IoMT framework for healthcare, synthesizes and identifies the state-of-the-art solutions that tackle the challenges of the current applications of DL, and analyzes existing limitations and potential future developments. Through an analysis of case studies and real-world implementations, this work provides insights into best practices and lessons learned, including the importance of robust data preprocessing, integration with legacy systems, and human-centric design. Finally, we outline future research directions, emphasizing the development of transparent, scalable, and privacy-preserving DL models to realize the full potential of IoMT in healthcare. This survey aims to serve as a foundational reference for researchers and practitioners seeking to navigate the challenges and harness the opportunities in this rapidly evolving field. Full article

Background: Infant brain tissue segmentation from MRI data is a critical task in medical imaging, particularly challenging due to the evolving nature of tissue contrasts in the early months of life. The difficulty increases as gray matter (GM) and white matter (WM) intensities converge, making accurate segmentation challenging. This study aims to develop an improved U-net-based model to enhance the precision of automatic segmentation of cerebro-spinal fluid (CSF), GM, and WM in 10 infant brain MRIs using the iSeg-2017 dataset. Methods: The proposed method utilizes a U-net architecture with (2+1)Dconvolutional layers and skip connections. Preprocessing includes intensity normalization using histogram alignment to standardize MRI data across different records. The model was trained on the iSeg-2017 dataset, which comprises T1-weighted and T2-weighted MRI data from ten infant subjects. Cross-validation was performed to evaluate the model’s segmentation performance. Results: The model achieved an average accuracy of 92.2%, improving on previous methods by 0.7%. Sensitivity, precision, and Dice similarity scores were used to evaluate the performance, showing high levels of accuracy across different tissue types. The model demonstrated a slight bias toward misclassifying GM and WM, indicating areas for potential improvement. Conclusions: The results suggest that the U-net architecture is highly effective in segmenting infant brain tissues from MRI data. Future work will explore enhancements such as attention mechanisms and dual-network processing for further improving segmentation accuracy. Full article

Breast reconstruction following mastectomy or sectorectomy significantly impacts the quality of life and psychological well-being of breast cancer patients. Since its inception in the 1950s, artificial intelligence (AI) has gradually entered the medical field, promising to transform surgical planning, intraoperative guidance, postoperative care, and medical research. This article examines AI applications in breast reconstruction, supported by recent studies. AI shows promise in enhancing imaging for tumor detection and surgical planning, improving microsurgical precision, predicting complications such as flap failure, and optimizing postoperative monitoring. However, challenges remain, including data quality, safety, algorithm transparency, and clinical integration. Despite these shortcomings, AI has the potential to revolutionize breast reconstruction by improving preoperative planning, surgical precision, operative efficiency, and patient outcomes. This review provides a foundation for further research as AI continues to evolve and clinical trials expand its applications, offering greater benefits to patients and healthcare providers. Full article

Background and Objectives: Cluster headaches (CHs) are one of the most painful primary headaches and negatively affect the lives of patients due to misdiagnosis. Family medicine (FM) and emergency medicine (EM) physicians are one of the most important steps in making the correct diagnosis and directing patients to headache specialists. In this study, the knowledge and management approaches of these two groups regarding CH were evaluated. Materials and Methods: Two online questionnaires were developed to gather the demographic data of physicians and to assess their knowledge about the characteristics, diagnosis, and treatment of CHs. Results: A total of 120 FM doctors and 98 EM doctors participated in this study. Answers about diagnostic criteria were similar in both groups. It was found that 70% of the participating physicians had concerns about misdiagnosing cluster headaches, and only 15% considered themselves sufficiently knowledgeable on the topic. Additionally, nearly half of the physicians were unaware that autonomic symptoms are mandatory for diagnosis and believed that NSAIDs are effective in treatment. Conclusions: In our study, for the first time, EM and FM physicians’ knowledge about the diagnosis and treatment of and professional competence in CHs was evaluated. It was found that the participants had knowledge about CHs but still considered themselves incompetent. For the correct and early diagnosis and for the proper management of CHs, EM and FM physicians, who can be called gatekeepers of CHs, need more medical education-based strategies. Full article

Background and Study Aim: Colonoscopy holds the highest volume of all endoscopic procedures, allowing for large colonoscopy databases to serve as valuable datasets for quality assurance. We aimed to build a comprehensive colonoscopy database for quality assurance and the training of future AIs. Materials and Methods: As part of a cluster-randomized controlled trial, a designated, onsite medical student was used to acquire procedural and patient-specific data, ensuring a high level of data integrity. The following data were thereby collected for all colonoscopies: full colonoscopy vides, colonoscope position (XYZ-coordinates), intraprocedural timestamps, pathological report, endoscopist description, endoscopist planning, and patient-reported discomfort. Results: A total of 1447 patients were included from the 1st of February 2022 to the 21st of November 2023; 1191 colonoscopies were registered as completed, 88 were stopped due to inadequate bowel cleansing, and 41 were stopped due to patient discomfort. Of the 1191 completed colonoscopies, 601 contained polypectomies (50.4%), and 590 did not (49.6%). Comparing colonoscopies with polypectomies to those without the withdrawal time (caecum to extubating the scope) was significantly longer for all parts of the colon (p values < 0.001), except the transverse colon (p value = 0.92). The database was used to train an AI, automatically and objectively evaluating bowel preparation. Conclusions: We established the most thorough database in colonoscopy with previously inaccessible information, indicating that the transverse colon differs from the other parts of the colon in terms of withdrawal time for procedures with polypectomies. To further explore these findings and reach the full potential of the database, an AI evaluating bowel preparation was developed. Several research partners have been identified to collaborate in the development of future AIs. Full article

Medical image segmentation is a challenging task due to limited annotated data, complex lesion boundaries, and the inherent variability in medical images. These challenges make accurate and robust segmentation crucial for clinical applications. In this study, we propose the Uncertainty-Driven Auxiliary Mean Teacher (UDAMT) model, a novel semi-supervised framework specifically designed for skin lesion segmentation. Our approach employs a dual-headed teacher–student architecture with an uncertainty-guided mechanism, enhancing feature learning and boundary precision. Extensive experiments on the ISIC 2016, ISIC 2017, and ISIC 2018 datasets demonstrate that UDAMT achieves significant improvements over state-of-the-art methods, with increases of 1.17 percentage points in the Dice coefficient and 1.31 percentage points in mean Intersection over Union (mIoU) under low-label settings (5% labeled data). Furthermore, UDAMT requires 12.9 M parameters, which is slightly higher than the baseline model (12.5 M) but significantly lower than MT (14.8 M) and UAMT (15.2 M). It also achieves an inference time of 25.7 ms per image, ensuring computational efficiency. Ablation studies validate the contributions of each component, and cross-dataset evaluations on the PH2 benchmark confirm robustness to small lesions. This work provides a scalable and efficient solution for semi-supervised medical image segmentation, balancing accuracy, efficiency, and clinical applicability. Full article

This study developed a novel domain-adaptive neural network framework, CNDAD—Net, for addressing the challenges of lung lesion detection in cross-domain medical image analysis. The proposed framework integrates domain adaptation techniques into a classical encoding–decoding structure to align feature distributions between source and target domains. Specifically, a “Generative Adversarial Network” GAN-based domain discriminator is utilized for the iterative refinement of feature representations to minimize cross-domain discrepancies and improve the generalization capability of the model. In addition, a novel Cross-Fusion Block (CFB) is proposed to implement multi-scale feature fusion that facilitates the deep integration of 2D, 3D, and domain-adapted features. The CFB achieves bidirectional feature flow across dimensions, thereby improving the model’s capability to detect diverse lesion morphologies while minimizing false positives and missed detections. For better detection, coarse-grained domain adaptation is implemented by MMD for further optimization. It integrates a module inspired by a CycleGAN for the process to generate high-resolution images on low-quality data. Using the Lung Nodule Analysis (LUNA16) dataset, the test was conducted and its experimental result was compared with that of previous standard methods such as Faster R-CNN and YOLO, yielding mAP 0.889, recall at 0.845 and the F1-score at 0.886. This work, with a novel CNDAD—Net model, lays down a solid and scalable framework for the precise detection of lung lesions, which is extremely critical for early diagnosis and treatment. The model has prospects and is capable of being extended in future to multimodal imaging data ad real-time diagnostic scenarios, and can help in further developing intelligent medical image analysis systems. Full article

Background/Objective: The prognostic value of specific hot-spot mutations within KRAS, NRAS, and BRAF genes in metastatic colorectal cancer (mCRC) genes remains debatable. This study explores whether certain KRAS, NRAS, and BRAF mutations are associated with the risk of all-cause mortality in mCRC. Methods: We retrospectively analyzed records of 494 patients with mCRC treated at the University of Texas Medical Branch between January 2016 and July 2023. Data on genetic mutations and clinicopathological features were collected for this analysis. We estimated survival probabilities and conducted multivariable Cox proportional hazards regression to evaluate the impact of specific mutations on all-cause mortality risk. Results: KRAS c.35G>T (p.Gly12Val) and c.34G>T (p.Gly12Cys) mutations were significantly associated with an increased risk of all-cause mortality in the overall mCRC population and the treated mCRC subgroup. KRAS c.38G>A (p.Gly13Asp) was significantly associated with an increased risk of all-cause mortality in the treated mCRC subgroup but BRAF c.1799T>A (p.Val600Glu) was significantly associated with an increased risk of all-cause mortality in the overall mCRC population. No significant association was observed between NRAS mutations and mortality risk in mCRC, possibly due to their lower frequency or different biological effects compared to KRAS and BRAF mutations. Conclusions: These findings suggest that specific KRAS [c.35G>T (p.Gly12Val), c.34G>T (p.Gly12Cys), and c.38G>A (p.Gly13Asp)] and BRAF c.1799T>A (p.Val600Glu) mutations may have prognostic value in mCRC. However, given the single-center study design and lack of direct therapeutic implications, larger multicenter studies are needed to substantiate these results and better define the clinical relevance of these mutations. Full article

Background/Objectives: Ultrasound (US) imaging plays a crucial role in the early detection and treatment of hepatocellular carcinoma (HCC). However, challenges such as speckle noise, low contrast, and diverse lesion morphology hinder its diagnostic accuracy. Methods: To address these issues, we propose CSM-FusionNet, a novel framework that integrates clustering, SoftMax-weighted Box Fusion (SM-WBF), and padding. Using raw US images from a leading hospital, Samsung Medical Center (SMC), we applied intensity adjustment, adaptive histogram equalization, low-pass, and high-pass filters to reduce noise and enhance resolution. Data augmentation generated ten images per one raw US image, allowing the training of 10 YOLOv8 networks. The [email protected] of each network was used as SoftMax-derived weights in SM-WBF. Threshold-lowered bounding boxes were clustered using Density-Based Spatial Clustering of Applications with Noise (DBSCAN), and outliers were managed within clusters. SM-WBF reduced redundant boxes, and padding enriched features, improving classification accuracy. Results: The accuracy improved from 82.48% to 97.58% with sensitivity reaching 100%. The framework increased lesion detection accuracy from 56.11% to 95.56% after clustering and SM-WBF. Conclusions: CSM-FusionNet demonstrates the potential to significantly improve diagnostic reliability in US-based lesion detection, aiding precise clinical decision-making. Full article

Background: The advent of biosimilars has revolutionized the management of conditions like rheumatoid arthritis by offering cost-effective alternatives to expensive biologics. Objectives: This study aims to compare the post-marketing safety profiles of biosimilars used in rheumatology with their respective reference products (RPs). Methods: Data were retrieved from EudraVigilance for biosimilars of adalimumab, etanercept, infliximab, and rituximab, and compared with their RPs. Our analysis focused on biosimilars authorized before 2021, using data from January 2021 to December 2023. We conducted a descriptive analysis of suspected adverse events, categorized using the Medical Dictionary for Regulatory Activities, and performed a comparative analysis using the reporting odds ratio to identify potential safety signals of disproportionate reporting. Results: We analyzed 75,327 reports, identifying 566,249 drug–event pairs. The results indicate that biosimilars have safety profiles largely comparable to their RPs. Female patients predominated in the reports, representing 69.4% of RPs and 56.9% of biosimilars. Notably, biosimilars demonstrated higher reporting rates for non-serious suspected adverse drug events (AEs), such as injection site pain, arthralgia, and fatigue. Specific AEs, including drug ineffectiveness and off-label use, were more frequent for infliximab and etanercept biosimilars, possibly reflecting real-world usage patterns and nocebo effects. Serious AEs, including malignancies and immunological reactions, were also noted, underscoring the necessity for ongoing monitoring. Conclusions: Our findings suggest that biosimilars are safe alternatives to RPs, contributing to significant healthcare cost savings in the EU. This study underscores the need for ongoing pharmacovigilance and long-term safety research to validate the clinical use of biosimilars in rheumatology. Full article

Background/Objectives: The aim of this study is to evaluate the long-term efficacy and safety of the MINIject supraciliary device in patients with medically uncontrolled primary open-angle glaucoma (POAG) with up to 2 years of follow-up. Methods: A retrospective study was conducted using electronic medical records. Patients with medically uncontrolled POAG were included. Patients were either phakic, receiving combined phacoemulsification and MINIject, or pseudophakic receiving standalone MINIject. They were followed up for 24 months postoperatively. The primary outcomes were intraocular pressure (IOP) and use of IOP-lowering medications at 24 months postoperatively. Other secondary outcomes included IOP and use of glaucoma medications at 6, 12, and 18 months, success defined as 6 ≤ IOP ≤ 18 mmHg without the use of medications (complete) or regardless of the use of medications (qualified), average change in visual field (VF) mean deviation (MD) from baseline to 24 months, and adverse events. Results: The study included 37 eyes of 37 consecutive glaucoma patients. Of these, 27 underwent combined phacoemulsification with MINIject implantation and 10 had standalone MINIject. The mean preoperative IOP was 17.95 ± 4.75 mmHg on 2.16 ± 1.12 glaucoma drops. At 24 months, the mean IOP was 14.58 ± 4.55 on 0.69 ± 0.98 medications (p = 0.002). No difference in IOP was noted between the combined and the standalone group, although the latter had a trend for more glaucoma drops. The qualified success and the complete success rates were 67.6% and 56.8%, respectively. Average VF mean deviation progression was 0.19 ± 1.19 dB. No sight threatening complications occurred. Conclusions: MINIject can be a safe and effective alternative to current glaucoma devices, offering significant reduction in IOP and medication use with a good safety profile. Longer term data are needed to confirm its prolonged safety. Full article