Search Results (837)

Background: Healthcare systems worldwide are increasingly burdened by rising costs, growing patient demand, and limited resources. In this context, cost-effectiveness analysis (CEA) plays a vital role in evaluating the clinical value of medical interventions relative to their costs. Despite the lack of evidence supporting their necessity, routine post-removal chest X-rays for central venous catheters (CVCs) are still performed in some hospitals due to persistent misconceptions about their benefits. This study seeks to address these misconceptions by examining the costs of routine imaging through a cost analysis of complication detection rates in a large inpatient cohort, with the aim of highlighting the inefficiencies of this practice and promoting evidence-based approaches. Methods: A retrospective cohort analysis was performed across four university hospitals in Salzburg, Austria, including 984 CVC removals conducted between 2012 and 2021. Comparisons were made between X-rays after primary catheter insertion and post-removal X-rays to isolate complications specifically associated with CVC removal. A simple cost-per-outcome analysis, a subtype of CEA, was chosen to determine the cost per complication detected. The approach incorporated activity-based costing, adjusted to 2024 price levels via the Austrian Consumer Price Index (CPI), to capture real-world resource utilization. Results: Complications related to CVC removal were identified in five cases (0.5%), including one catheter rupture due to self-removal, two failed removals, one hemothorax, and one case of intrathoracic bleeding. Of these, three complications were detected on X-rays, including a retained catheter fragment, signs of intrathoracic bleeding, and a hemothorax. Additionally, one asymptomatic patient had a likely incidental finding of a small pneumothorax, which required no intervention. The cost of routine X-rays was calculated at EUR 38.20 per X-ray, resulting in a total expenditure of EUR 37,588.80 for 984 X-rays. This corresponds to EUR 7517.76 per detected complication (n = 4). The odds of detecting a complication on an X-ray were 193 times higher in symptomatic patients than in asymptomatic patients (p < 0.001). Conclusions: This study confirms that complications following CVC removal are rare with only five detected cases. Routine imaging did not improve clinical decision-making, as complications were significantly more likely to be identified in symptomatic patients through clinical evaluation alone. Given the high financial cost (EUR 37,588.80 for 984 X-rays, EUR 7517.76 per detected complication), routine post-removal X-rays are unnecessary in asymptomatic patients and should be reserved for symptomatic cases based on clinical judgment. Adopting a symptom-based imaging approach would reduce unnecessary healthcare costs, minimize patient radiation exposure, and optimize resource allocation in high-volume procedures such as CVC removal. Full article

Background: Machine learning methods for clinical assistance require a large number of annotations from trained experts to achieve optimal performance. Previous work in natural language processing has shown that it is possible to automatically extract annotations from the free-text reports associated with chest X-rays. Methods: This study investigated techniques to extract 49 labels in a hierarchical tree structure from chest X-ray reports written in Danish. The labels were extracted from approximately 550,000 reports by performing multi-class, multi-label classification using a method based on pattern-matching rules, a classic approach in the literature for solving this task. The performance of this method was compared to that of open-source large language models that were pre-trained on Danish data and fine-tuned for classification. Results: Methods developed for English were also applicable to Danish and achieved similar performance (a weighted F1 score of 0.778 on 49 findings). A small set of expert annotations was sufficient to achieve competitive results, even with an unbalanced dataset. Conclusions: Natural language processing techniques provide a promising alternative to human expert annotation when annotations of chest X-ray reports are needed. Large language models can outperform traditional pattern-matching methods. Full article

Background/Objectives: Remote dielectric sensing (ReDS) is a recently developed, noninvasive, electromagnetic energy-based technology designed to quantify pulmonary congestion without requiring expert techniques in adult patients with heart failure. However, its applicability in pediatric patients remains unknown. Methods: ReDS values and chest X-rays were simultaneously obtained from pediatric patients with a history of Fontan surgery at an outpatient clinic. The Congestion Severity Index (CSI) was calculated from chest X-rays to analyze its correlation with ReDS values. Results: A total of 21 pediatric patients (median age: 17 years; median height: 152.7 cm; median weight: 48.6 kg; 12 male patients) were included. ReDS values were successfully measured in all participants without any measurement failure. A mild correlation was observed between ReDS values and CSIs (r = 0.47, p = 0.030). In patients with ReDS values exceeding 35% (N = 11), a stronger correlation was noted between ReDS values and CSIs (r = 0.61, p = 0.046). In patients with ReDS values ≤ 35% (N = 10), ReDS values exhibited a wide distribution (25% to 35%) despite low CSI values. Conclusions: The ReDS system demonstrates potential as a feasible technology for the noninvasive quantification of pulmonary congestion in pediatric patients, irrespective of the severity of congestion. Notably, the ReDS system may have the potential to identify subclinical pulmonary congestion in pediatric patients with heart failure. Full article

Background: Pakistan is classified as a high-burden country for tuberculosis, and the prescription of antibiotics and fluoroquinolones complicates the detection and treatment of the disease. The existing literature primarily relies on knowledge questionnaires and prescription analyses, which focus on healthcare providers’ knowledge rather than their actual clinical practices. Therefore, this study aimed to evaluate the quality of tuberculosis care using standardized patients. Materials and Methods: We conducted a cross-sectional study, recruiting consenting private healthcare practitioners in four cities in Punjab, Pakistan. Standardized patients were engaged from the general public to simulate four cases: two suspected tuberculosis cases (Case 1 and 2), one confirmed tuberculosis case (Case 3), and one suspected multidrug-resistant tuberculosis case (Case 4). The optimal management in Cases 1 and 2 was referral for sputum testing, chest X-ray, or referral to a public facility for directly observed treatment short-courses without dispensing antibiotics, fluoroquinolones, and steroids. In Case 3, treatment with four anti-TB medications was expected, while Case 4 should have prompted a drug-susceptibility test. Descriptive statistics using SPSS version 23 were employed to analyze disparities in referrals, ideal case management, antibiotic use, steroid administration, and the number of medications prescribed. Results: From July 2022 to May 2023, 3321 standardized cases were presented to private healthcare practitioners. Overall, 39.4% of tuberculosis cases were managed optimally, with Case 3 showing the highest rate (56.7%) and Case 4 showing the lowest (19.8%). City-specific analysis revealed that Rawalpindi had the highest management rate (55.8%), while Sialkot had the lowest (30.6%). Antibiotics were most frequently prescribed in Case 1 and least prescribed in Case 4, with a similar pattern for fluoroquinolones. Anti-TB medications were also prescribed in naïve and suspected tuberculosis cases (8.3% in Case 1 and 10.8% in Case 2). Conclusions: The quality of tuberculosis management in actual practice is suboptimal among healthcare providers in Pakistan. Furthermore, the over-prescription of antibiotics, fluoroquinolones, and anti-TB drugs presents a significant risk for the development of drug-resistant tuberculosis. Full article

Over the past decade, deep learning techniques, particularly neural networks, have become essential in medical imaging for tasks like image detection, classification, and segmentation. These methods have greatly enhanced diagnostic accuracy, enabling quicker identification and more effective treatments. In chest X-ray analysis, however, challenges remain in accurately segmenting and classifying organs such as the lungs, heart, diaphragm, sternum, and clavicles, as well as detecting abnormalities in the thoracic cavity. Despite progress, these issues highlight the need for improved approaches to overcome segmentation difficulties and enhance diagnostic reliability. In this context, we propose a novel architecture named CXR-Seg, tailored for semantic segmentation of lungs from chest X-ray images. The proposed network mainly consists of four components, including a pre-trained EfficientNet as an encoder to extract feature encodings, a spatial enhancement module embedded in the skip connection to promote the adjacent feature fusion, a transformer attention module at the bottleneck layer, and a multi-scale feature fusion block at the decoder. The performance of the proposed CRX-Seg was evaluated on four publicly available datasets (MC, Darwin, and Shenzhen for chest X-rays, and TCIA for brain flair segmentation from MRI images). The proposed method achieved a Jaccard index, Dice coefficient, accuracy, sensitivity, and specificity of 95.63%, 97.76%, 98.77%, 98.00%, and 99.05%on MC; 91.66%, 95.62%, 96.35%, 95.53%, and 96.94% on V7 Darwin COVID-19; and 92.97%, 96.32%, 96.69%, 96.01%, and 97.40% on the Shenzhen Tuberculosis CXR Dataset, respectively. Conclusively, the proposed network offers improved performance in comparison with state-of-the-art methods, and better generalization for the semantic segmentation of lungs from chest X-ray images. Full article

Pediatric pneumonia remains a significant global health issue, particularly in low- and middle-income countries, where it contributes substantially to mortality in children under five. This study introduces a deep learning model for pediatric pneumonia diagnosis from chest X-rays that surpasses the performance of state-of-the-art methods reported in the recent literature. Using a DenseNet201 architecture with a Mish activation function and multi-scale convolutions, the model was trained on a dataset of 5856 chest X-ray images, achieving high performance: 0.9642 accuracy, 0.9580 precision, 0.9506 sensitivity, 0.9542 F1 score, and 0.9507 specificity. These results demonstrate a significant advancement in diagnostic precision and efficiency within this domain. By achieving the highest accuracy and F1 score compared to other recent work using the same dataset, our approach offers a tangible improvement for resource-constrained environments where access to specialists and sophisticated equipment is limited. While the need for high-quality datasets and adequate computational resources remains a general consideration for deep learning applications, our model’s demonstrably superior performance establishes a new benchmark and offers the delivery of more timely and precise diagnoses, with the potential to significantly enhance patient outcomes. Full article

Pneumonia is a deadly disease affecting millions worldwide, caused by microorganisms and environmental factors. It leads to lung fluid build-up, making breathing difficult, and is a leading cause of death. Early detection and treatment are crucial for preventing severe outcomes. Chest X-rays are commonly used for diagnoses due to their accessibility and low costs; however, detecting pneumonia through X-rays is challenging. Automated methods are needed, and machine learning can solve complex computer vision problems in medical imaging. This research develops a robust machine learning model for the early detection of pneumonia using chest X-rays, leveraging advanced image processing techniques and deep learning algorithms that accurately identify pneumonia patterns, enabling prompt diagnosis and treatment. The research develops a CNN model from the ground up and a ResNet-50 pretrained model This study uses the RSNA pneumonia detection challenge original dataset comprising 26,684 chest array images collected from unique patients (56% male, 44% females) to build a machine learning model for the early detection of pneumonia. The data are made up of pneumonia (31.6%) and non-pneumonia (68.8%), providing an effective foundation for the model training and evaluation. A reduced size of the dataset was used to examine the impact of data size and both versions were tested with and without the use of augmentation. The models were compared with existing works, the model’s effectiveness in detecting pneumonia was compared with one another, and the impact of augmentation and the dataset size on the performance of the models was examined. The overall best accuracy achieved was that of the CNN model from scratch, with no augmentation, an accuracy of 0.79, a precision of 0.76, a recall of 0.73, and an F1 score of 0.74. However, the pretrained model, with lower overall accuracy, was found to be more generalizable. Full article

Background: Chest X-rays are among the most frequently used imaging tests in medical practice. We aimed to assess the prognostic value of the cardio–thoracic ratio (CTR) and transverse cardiac diameter (TCD) and compare them with novel chest X-ray parameters used in screening for cardiac enlargement. Methods: CTR, TCD, and five other non-standard new radiographic indexes, including basic spherical index (BSI), assessing changes in cardiac silhouette in chest radiographs in posterior–anterior projection were related to increased left ventricular end-diastolic volume (LVEDV) and left ventricular hypertrophy (LVH) assessed in cardiac magnetic resonance imaging (CMR). Results: TCD, CTR, and BSI were the best predictors of both LVH and increased LVEDV diagnosed in CMR. The best sensitivity, along with good specificity in LVH prediction, defined as left ventricular mass/body surface area (BSA) > 72 g/m² in men or >55 g/m² in women, was observed when TCD and BSI parameters were used jointly (69.2%, 95% confidence interval [CI]: 52.4–83.0% and 80.0%, 95% CI: 51.9–95.7%, respectively). In the prediction of cardiac enlargement defined as LVEDV/BSA > 117 mL/m² in men or >101 mL/m² in women, BSI > 137.5 had the best sensitivity and specificity (85.0%, 95% CI: 62.1–96.8% and 82.4%, 95% CI: 65.5–93.2%, respectively). Conclusions: TCD may be valuable in the assessment of patients suspected of having cardiac enlargement. CTR and BSI serve as complementary tools for a more precise approach. TCD appears particularly useful for the prediction of LVH, while BSI demonstrates greater utility as an indicator of increased LVEDV. Full article

The right internal jugular line (RIJL) is a type of central venous catheter (CVC) inserted into the right internal jugular vein to deliver medications and monitor vital functions in ICU patients. The placement of RIJL is routinely checked by a clinician in a chest X-ray (CXR) image to ensure its proper function and patient safety. To reduce the workload of clinicians, deep learning-based automated detection algorithms have been developed to detect CVCs in CXRs. Although RIJL is the most widely used type of CVCs, there is a paucity of investigations focused on its accurate segmentation and tip localization. In this study, we propose a deep learning system that integrates an anatomical landmark segmentation, an RIJL segmentation network, and a postprocessing function to segment the RIJL course and detect the tip with accuracy and precision. We utilized the nnU-Net framework to configure the segmentation network. The entire system was implemented on the SimpleMind Cognitive AI platform, enabling the integration of anatomical knowledge and spatial reasoning to model relationships between objects within the image. Specifically, the trachea was used as an anatomical landmark to extract a subregion in a CXR image that is most relevant to the RIJL. The subregions were used to generate cropped images, which were used to train the segmentation network. The segmentation results were recovered to original dimensions, and the most inferior point’s coordinates in each image were defined as the tip. With guidance from the anatomical landmark and customized postprocessing, the proposed method achieved improved segmentation and tip localization compared to the baseline segmentation network: the mean average symmetric surface distance (ASSD) was decreased from 2.72 to 1.41 mm, and the mean tip distance was reduced from 11.27 to 8.29 mm. Full article

(1) Background: In children, bacterial pneumonia is the most common cause of parapneumonic pleural effusions which can eventually lead to pleural empyema. Treatment is varied and is a combination of antibiotic therapy, chest tube drainage, fibrinolytics and video-assisted thoracoscopic surgery (VATS). Postoperative complications of the latter include pneumothoraces and bronchopleural fistula (BPF). The aim of this study is to investigate the incidence and duration of pneumothoraces during the perioperative period and follow-up (FU) to elucidate their progression following video-assisted thoracoscopic surgery (VATS) to start to create an evidence-based standardized FU protocol. (2) Methods: This retrospective study included all patients who underwent VATS for pleural empyema between January 2013–May 2023 at the University Medical Center Hamburg-Eppendorf (UKE) and the Hamburg Children’s Hospital Altona (AKK). (3) Results: We identified 47 patients with pleural empyema who underwent VATS. A proportion of 43% of patients were found to have a pneumothorax with 55% of those being unresolved at discharge. At the end of FU, 27% of those had a “pneumothorax ex vacuo”. No surgical interventions were needed. (4) Conclusions: The majority of pneumothoraces after VATS in pediatric patients can be managed conservatively. In the context of follow-up care, it is recommended that X-ray examinations should be used sparingly, while sonographic follow-up examinations should be conducted more frequently. If the pneumothorax persists, further thoracoscopy for resection of the visceral pleura and treatment of bronchopleural fistula may be the next step in treatment. Full article

Pneumonia remains a significant cause of morbidity and mortality among pediatric patients worldwide. Accurate and timely diagnosis is crucial for effective treatment and improved patient outcomes. Traditionally, pneumonia diagnosis has relied on a combination of clinical evaluation and radiologists’ interpretation of chest X-rays. However, this process is time-consuming and prone to inconsistencies in diagnosis. The integration of advanced technologies such as Convolutional Neural Networks (CNNs) into medical diagnostics offers a potential to enhance the accuracy and efficiency. In this study, we conduct a comprehensive evaluation of various activation functions within CNNs for pediatric pneumonia classification using a dataset of 5856 chest X-ray images. The novel Mish activation function was compared with Swish and ReLU, demonstrating superior performance in terms of accuracy, precision, recall, and F1-score in all cases. Notably, InceptionResNetV2 combined with Mish activation function achieved the highest overall performance with an accuracy of 97.61%. Although the dataset used may not fully represent the diversity of real-world clinical cases, this research provides valuable insights into the influence of activation functions on CNN performance in medical image analysis, laying a foundation for future automated pneumonia diagnostic systems. Full article

Background: Endotracheal tube (ETT) placement is crucial for neonates with respiratory failure. Ultrasonography (US) has emerged as a valuable tool to detect ETT positioning, competing with traditional methods. Nurses, being front-line caregivers, can perform basic ultrasound examinations. This study aimed to assess whether a nurse inexperienced in US could identify the correct ETT position in neonates after a brief ultrasound training. Methods: This study included intubated neonates hospitalized in a NICU with a postmenstrual age of under 45 weeks. A NICU nurse, following a short ultrasound training, measured the distance of the ETT tip to the right pulmonary artery and aortic arch. Chest X-rays (CXRs) confirmed the ETT position. The neonates’ ages, genders, weights, and examination times were recorded. Results: This study involved 67 neonates, including 40 (59.7%) males, with 39 (58.2%) weighing below 1500 g. The median time for correct ETT placement confirmation by CXR was 12.6 min, while US-assisted ETT recognition took 6 min initially and 5.1 min at the end of the training, which was a significant difference. No major differences were found in US distance based on the neonate’s weight and age. Gender marginally influenced US distance (β = −0.089, p = 0.056). Conclusions: The NICU nurse responded well to ultrasound training, showing results comparable with CXR. Further studies with more patients and additional studied factors are needed to fully assess US’s reliability in determining ETT positioning. Full article

Background: The global burden of respiratory diseases such as influenza, tuberculosis, and viral pneumonia necessitates rapid, accurate diagnostic tools to improve healthcare responses. Current methods, including RT-PCR and chest radiography, face limitations in accuracy, speed, accessibility, and cost-effectiveness, especially in resource-constrained settings, often delaying treatment and increasing transmission. Methods: This study introduces an Enhanced Multi-Model Deep Learning (EMDL) approach to address these challenges. EMDL integrates an ensemble of five pre-trained deep learning models (VGG-16, VGG-19, ResNet, AlexNet, and GoogleNet) with advanced image preprocessing (histogram equalization and contrast enhancement) and a novel multi-stage feature selection and optimization pipeline (PCA, SelectKBest, Binary Particle Swarm Optimization (BPSO), and Binary Grey Wolf Optimization (BGWO)). Results: Evaluated on two independent chest X-ray datasets, EMDL achieved high accuracy in the multiclass classification of influenza, pneumonia, and tuberculosis. The combined image enhancement and feature optimization strategies significantly improved diagnostic precision and model robustness. Conclusions: The EMDL framework provides a scalable and efficient solution for accurate and accessible pulmonary disease diagnosis, potentially improving treatment efficacy and patient outcomes, particularly in resource-limited settings. Full article

Background: Lung cancer remains one of the leading causes of cancer-related deaths worldwide. Artificial intelligence (AI) holds significant potential roles in enhancing the detection of lung nodules through chest X-ray (CXR), enabling earlier diagnosis and improved outcomes. Methods: Papers were identified through a comprehensive search of the Web of Science (WOS), Scopus, and Ovid Medline databases for publications dated between 2020 and 2024. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, 34 studies that met the inclusion criteria were selected for quality assessment and data extraction. Results: AI demonstrated sensitivity rates of 56.4–95.7% and specificities of 71.9–97.5%, with the area under the receiver operating characteristic (AUROC) values between 0.89 and 0.99, compared to radiologists’ mean area under the curve (AUC) of 0.81. AI performed better with larger nodules (>2 cm) and solid nodules, showing higher AUC values for calcified (0.71) compared to non-calcified nodules (0.55). Performance was lower in hilar areas (30%) and lower lung fields (43.8%). A combined AI-radiologist approach improved overall detection rates, particularly benefiting less experienced readers; however, AI showed limitations in detecting ground-glass opacities (GGOs). Conclusions: AI shows promise as a supplementary tool for radiologists in lung nodule detection. However, the variability in AI results across studies highlights the need for standardized assessment methods and diverse datasets for model training. Future studies should focus on developing more precise and applicable algorithms while evaluating the effectiveness and cost-efficiency of AI in lung cancer screening interventions. Full article

Background: Cocaine has been shown to cause cytotoxic neuronal damage, which has been implicated in cases of leukoencephalopathy. We present a case of cocaine-induced toxic encephalopathy resulting in predominant lesions to the gray matter on magnetic resonance imaging (MRI). Case Presentation: A 70-year-old female presented acutely with confusion, agitation, and disorientation. She was markedly hypertensive with other vital signs within normal range. On presentation to the emergency department, she was uncooperative and had an unsteady gait but showed no focal neurological deficits. Her lab work was positive for elevated cardiac troponins, elevated D-dimer, and a urine drug screen positive only for cocaine. Head computed tomography (CT) showed no hemorrhage and head CT angiogram showed no abnormalities and no significant vascular stenosis. Chest X-ray and CT showed diffuse ground glass opacities compatible with atypical pneumonia. Antibiotics were initiated to treat the pneumonia and antihypertensives were administered to manage her blood pressure. She was also given IV thiamine. Brain MRI showed restricted diffusion involving bilateral hippocampi, thalami, putamen, caudate, and right occipital lobe, findings suspicious for cytotoxic edema. After acute stabilization, the patient demonstrated profound anterograde and retrograde amnesia, which improved gradually over days to weeks. She was eventually discharged to a skilled nursing facility. Conclusion: To our knowledge, this is the first reported case of profound amnesia secondary to cocaine-induced toxic encephalopathy with bilateral hippocampal involvement. These symptoms correlate with the implicated neuroanatomical structures. This case demonstrates that cocaine may be implicated in toxic encephalopathy affecting the brain’s gray matter and highlights a unique presentation of these findings. Full article