Search

Abstract Self-supervised learning methods for medical images primarily rely on the imaging modality during pretraining. Although such approaches deliver promising results, they do not take advantage of the associated patient or scan information collected within Electronic Health Records (EHR). This study aims to develop a multimodal pretraining approach for chest radiographs that considers EHR data incorporation as an additional modality that during training. We propose to incorporate EHR data during self-supervised pretraining with a Masked Siamese Network (MSN) to enhance the quality of chest radiograph representations. We investigate three types of EHR data, including demographic, scan metadata, and inpatient stay information. We evaluate the multimodal MSN on three publicly available chest X-ray datasets, MIMIC-CXR, CheXpert, and NIH-14, using two vision transformer (ViT) backbones, specifically ViT-Tiny and ViT-Small. In assessing the quality of the representations through linear evaluation, our proposed method demonstrates significant improvement compared to vanilla MSN and state-of-the-art self-supervised learning baselines. In particular, our proposed method achieves an improvement of of 2% in the Area Under the Receiver Operating Characteristic Curve (AUROC) compared to vanilla MSN and 5% to 8% compared to other baselines, including uni-modal ones. Furthermore, our findings reveal that demographic features provide the most significant performance improvement. Our work highlights the potential of EHR-enhanced self-supervised pretraining for medical imaging and opens opportunities for future research to address limitations in existing representation learning methods for other medical imaging modalities, such as neuro-, ophthalmic, and sonar imaging.

Indonesia is a tropical climate, hence building controlling air ventilation and humid condition have been a challenge to meet residents’ convenience. It is often energy usage that is majorly used to control indoor air climate circulation. The passive design has recently received increasing attention as an option to reduce energy consumption and abate carbon footprint by taking advantage of local climatic conditions of building features. This pilot study seeks to identify the relationships between real energy consumption data and building design data. A dwelling house located in Malang, Indonesia was selected as a sample building for the study which introduces a method to use real energy consumption data to calculate the extra energy use related to tropical indoor thermal conditions. The 24 h observation result was validated through interviews with residents, before analyzing with criteria of ideal climate conditions from the literature study. This study also presents relationships between the increase in mean daily energy consumption data and trends of humidity building design data. In conclusion, this present study establishes the starting point for exploring all features affecting the tropical climate benefits of passive design for building energy efficiency.

Abstract Unrecognized deterioration of COVID-19 patients can lead to high morbidity and mortality. Most existing deterioration prediction models require a large number of clinical information, typically collected in hospital settings, such as medical images or comprehensive laboratory tests. This is infeasible for telehealth solutions and highlights a gap in deterioration prediction models based on minimal data, which can be recorded at a large scale in any clinic, nursing home, or even at the patient’s home. In this study, we develop and compare two prognostic models that predict if a patient will experience deterioration in the forthcoming 3 to 24 h. The models sequentially process routine triadic vital signs: (a) oxygen saturation, (b) heart rate, and (c) temperature. These models are also provided with basic patient information, including sex, age, vaccination status, vaccination date, and status of obesity, hypertension, or diabetes. The difference between the two models is the way that the temporal dynamics of the vital signs are processed. Model #1 utilizes a temporally-dilated version of the Long-Short Term Memory model (LSTM) for temporal processes, and Model #2 utilizes a residual temporal convolutional network (TCN) for this purpose. We train and evaluate the models using data collected from 37,006 COVID-19 patients at NYU Langone Health in New York, USA. The convolution-based model outperforms the LSTM based model, achieving a high AUROC of 0.8844–0.9336 for 3 to 24 h deterioration prediction on a held-out test set. We also conduct occlusion experiments to evaluate the importance of each input feature, which reveals the significance of continuously monitoring the variation of the vital signs. Our results show the prospect for accurate deterioration forecast using a minimum feature set that can be relatively easily obtained using wearable devices and self-reported patient information.

COVID-19 is caused by a novel coronavirus (2019-nCoV), which was declared as a pandemic after it emerged in China 2019. A vast international effort has been conducted to prevent and treat COVID-19 due to its high transmissibility and severe morbidity and mortality rates, particularly in individuals with chronic co-morbidities. In addition, polymorphic variants increased the need for proper vaccination to overcome the infectivity of new variants that are emerging across the globe. Many treatment options have been proposed and more than 25 vaccines are in various stages of development; however, the infection peaks are oscillating periodically, which raises a significant question about the effectiveness of the prevention measures and the persistence of this pandemic disease. In this review, we are exploring the most recent knowledge and advances in the treatment and vaccination options as well as the new emerging variants of 2019-nCoV and the possible mitigation of one of the most aggressive pandemics in the last centuries.

An improved implicit direct-forcing immersed boundary method (DF-IBM) is presented for simulating incompressible flows around complex rigid structures undergoing arbitrary motion. The current approach harnesses the pressure implicit with splitting of operators algorithm to handle the fluid–solid system's dual constraints in a segregated manner. As a result, the divergence-free condition is preserved throughout the Eulerian domain, and the no-slip velocity boundary condition is exactly enforced on the immersed boundary. A new pressure Poisson equation (PPE) is derived, incorporating the boundary force where the no-slip condition is already met, enabling the use of fast iterative PPE solvers without modifications. The improvement involves integrating Lagrangian weight methods having better reciprocity over the IBM-related linear operators with the implicit formulation. An additional force initialization scheme is introduced to further boost the algorithm's performance. The method's accuracy, efficiency, and capability are verified through various stationary and moving immersed boundary cases. The results are validated against experimental and numerical data from the literature. The proposed improvements seamlessly integrate into existing incompressible fluid solvers with minimal adjustments to the original system equations, highlighting their ease of implementation. [ABSTRACT FROM AUTHOR]

The present study aims to analyze the effects of digital marketing and Electronic Word of Mouth (E-WOM) on brand image, then examine the effects of digital marketing and Electronic Word of Mouth on the decision to be an Islamic bank customer and analyze the effects of digital marketing and Electronic Word of Mouth on the decision to be an Islamic bank customer through brand image as a mediating variable. The research type used in the present study was quantitative, using primary data obtained by distributing questionnaires. By distributing questionnaires, 100 respondent data was found and analyzed using SPSS version 26. The sampling techniques used by the author were the snowball sampling technique and nonprobability sampling. The criteria for the research sample were Islamic bank customers and social media users. Because the size of the research population was unknown, the present study used Lemeshow’s formula. The research results showed that digital marketing had a significant effect on brand image, Electronic Word of Mouth had a considerable effect on brand image, and digital marketing significantly affected the decision to become an Islamic bank customer. In contrast, Electronic Word of Mouth did not significantly affect the decision to be an Islamic bank customer. Brand image positively and significantly affects the decision to become a customer.

Copyright of Jornal of Biotechnology Research Center is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Background Despite the extensive use of community-based participatory research (CBPR) in health-related projects, there is limited work on how CBPR processes result in outcomes, especially in household and ambient air pollution (HAAP) research. This study explores the reflections of key informants on factors that shape the implementation and outcomes of CBPR in HAAP projects. Methods We conducted semi-structured interviews with 13 key stakeholders, including academic researchers, non-governmental organisation administrators, a policymaker, and community members. All interviewees have experience in CBPR projects. Interviews were analysed using framework analysis, and findings were mapped to Wallerstein et al.’s CBPR conceptual model, which consists of four constructs: context, partnership processes, intervention and research, and outcomes. Results The findings are described under two main categories: ‘barriers to participation’ and ‘good practices for effective CBPR design and implementation’. Relevant sub-categories were barriers at the structural, research, community, and individual levels. Suggestions for good practices included respect, cultural humility, trust, effective communication, suitable and affordable interventions such as improved cookstoves, appropriate participatory research tools, and gratuity for the community’s time. Conclusion Key informants’ perspectives identified factors supported by the CBPR model to inform the design and implementation of the CBPR approach. The add-ons to some of the model’s factors, such as intra-community dynamics, give value to the informants’ knowledge to support community-research partnerships and improve outcomes in HAAP intervention projects. Addressing these factors at the design stage and reporting CBPR evaluation could deepen the understanding of community-research partnerships.