A Highly Reliable Convolutional Neural Network Based Soft Tissue Sarcoma Metastasis Detection from Chest X-ray Images: A Retrospective Cohort Study

[Optimising Processes in a Severe Burn Intensive Care Unit through the Implementation of a Digital Management System]

BACKGROUND

The treatment of severely burned patients is demanding and necessitates specialised centres capable of providing adequate therapy over several months. The establishment of digital management systems in intensive care units signifies a substantial advancement in modern healthcare. Introducing such a system in a specialised intensive care unit for severe burn patients presents opportunities for optimisation but also potential obstacles. This study aims to provide insights into the perception of change from the perspective of staff and discuss the implementation of digital systems in the field of intensive care medicine.

METHODS

After a selective sample was established, the impacts of the digital management system were examined across various categories. The data collected through a questionnaire and brief interviews were evaluated in terms of average values within each category, with interpretations taking into account characteristics such as professional group and work experience.

RESULTS

Overall, the digital management system is considered suitable for use in the intensive care unit for severe burn patients by both medical and nursing staff. The continuous monitoring of vital parameters and the reduction of errors in medication administration are highlighted as positive aspects. However, negative points include the inferior documentation of burn wounds and specialised documentation for burn patients.

CONCLUSION

In due consideration of various factors such as experience, team size, and patient clientele, which impact the usability of the program, some aspects in need of improvement were identified. In summary, however, it can be said that there was a positive and favourable consensus regarding the introduction of such a system in the intensive care unit. Additionally, it can be concluded that the system is described as significantly more effective for a general surgical intensive care unit than for a specialised intensive care unit, e. g. an intensive care unit for severe burn patients.

3D modular bioceramic scaffolds for the investigation of the interaction between osteosarcoma cells and MSCs

Recent advances in bone tissue engineering have shown promise for bone repair post osteosarcoma excision. However, conflicting research on mesenchymal stem cells (MSCs) has raised concerns about their potential to either promote or inhibit tumor cell proliferation. It is necessary to thoroughly understand the interactions between MSCs and tumor cells. Most previous studies only focused on the interactions between cells within the tumor tissues. It has been challenging to develop an in vitro model of osteosarcoma excision sites replicating the complexity of the bone microenvironment and cell distribution. In this work, we designed and fabricated modular bioceramic scaffolds to assemble into a co-culture model. Because of the bone-like composition and mechanical property, tricalcium phosphate bioceramic could mimic the bone microenvironment and recapitulate the cell-extracellular matrix interaction. Moreover, the properties for easy assembly enabled the modular units to mimic the spatial distribution of cells in the osteosarcoma excision site. Under this co-culture model, MSCs showed a noticeable tumor-stimulating effect with a potential risk of tumor recurrence. In addition, tumor cells also could inhibit the osteogenic ability of MSCs. To undermine the stimulating effects of MSCs on tumor cells, we present the methods of pre-differentiated MSCs, which had lower expression of IL-8 and higher expression of osteogenic proteins. Both in vitro and in vivo studies confirm that pre-differentiated MSCs could maintain high osteogenic capacity without promoting tumor growth, offering a promising approach for MSCs' application in bone regeneration. Overall, 3D modular scaffolds provide a valuable tool for constructing hard tissue in vitro models. STATEMENT OF SIGNIFICANCE: Bone tissue engineering using mesenchymal stem cells (MSCs) and biomaterials has shown promise for bone repair post osteosarcoma excision. However, conflicting researches on MSCs have raised concerns about their potential to either promote or inhibit tumor cell proliferation. It remains challenges to develop in vitro models to investigate cell interactions, especially of osteosarcoma with high hardness and special composition of bone tissue. In this work, modular bioceramic scaffolds were fabricated and assembled to co-culture models. The interactions between MSCs and MG-63 were manifested as tumor-stimulating and osteogenesis-inhibiting, which means potential risk of tumor recurrence. To undermine the stimulating effect, pre-differentiation method was proposed to maintain high osteogenic capacity without tumor-stimulating, offering a promising approach for MSCs' application in bone regeneration.

Implementation of a Machine Learning Approach Evaluating Risk Factors for Complications after Single-Stage Augmentation Mastopexy

BACKGROUND

Single-stage mastopexy augmentation is a much-debated intervention due to its complexity and the associated relatively high complication rates. This study aimed to reevaluate the risk factors for these complications using a novel approach based on artificial intelligence and to demonstrate its possible limitations.

PATIENTS AND METHODS

Complete datasets of patients who underwent single-staged augmentation mastopexy during 2014-2023 at one institution by a single surgeon were collected retrospectively. These were subsequently processed and analyzed by CART, RF and XGBoost algorithms.

RESULTS

A total of 342 patients were included in the study, of which 43 (12.57%) reported surgery-associated complications, whereby capsular contracture (n = 19) was the most common. BMI represented the most important variable for the development of complications (FIS = 0.44 in CART). 2.9% of the patients expressed the desire for implant change in the course, with absence of any complications. A statistically significant correlation between smoking and the desire for implant change (p < 0.001) was revealed.

CONCLUSION

The importance of implementing artificial intelligence into clinical research could be underpinned by this study, as risk variables can be reclassified based on factors previously considered less or even irrelevant. Thereby we encountered limitations using ML approaches. Further studies will be needed to investigate the association between smoking, BMI and the current implant size with the desire for implant change without any complications. Moreover, we could show that the procedure can be performed safely without high risk of developing major complications.

LEVEL OF EVIDENCE IV

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.

Improvement of Predictive Scores in Burn Medicine through Different Machine Learning Approaches

The mortality of severely burned patients can be predicted by multiple scores which have been created over the last decades. As the treatment of burn injuries and intensive care management have improved immensely over the last years, former prediction scores seem to be losing accuracy in predicting survival. Therefore, various modifications of existing scores have been established and innovative scores have been introduced. In this study, we used data from the German Burn Registry and analyzed them regarding patient mortality using different methods of machine learning. We used Classification and Regression Trees (CARTs), random forests, XGBoost, and logistic regression regarding predictive features for patient mortality. Analyzing the data of 1401 patients via machine learning, the factors of full-thickness burns, patient's age, and total burned surface area could be identified as the most important features regarding the prediction of patient mortality following burn trauma. Although the different methods identified similar aspects, application of machine learning shows that more data are necessary for a valid analysis. In the future, the usage of machine learning can contribute to the development of an innovative and precise predictive score in burn medicine and even to further interpretations of relevant data regarding different forms of outcome from the German Burn registry.

Deep learning-based system development for black pine bast scale detection

The prevention of the loss of agricultural resources caused by pests is an important issue. Advances are being made in technologies, but current farm management methods and equipment have not yet met the level required for precise pest control, and most rely on manual management by professional workers. Hence, a pest detection system based on deep learning was developed for the automatic pest density measurement. In the proposed system, an image capture device for pheromone traps was developed to solve nonuniform shooting distance and the reflection of the outer vinyl of the trap while capturing the images. Since the black pine bast scale pest is small, pheromone traps are captured as several subimages and they are used for training the deep learning model. Finally, they are integrated by an image stitching algorithm to form an entire trap image. These processes are managed with the developed smartphone application. The deep learning model detects the pests in the image. The experimental results indicate that the model achieves an F1 score of 0.90 and mAP of 94.7% and suggest that a deep learning model based on object detection can be used for quick and automatic detection of pests attracted to pheromone traps.