RESUMO
INTRODUCTION: Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are critical for improving patients' outcomes, as over 40% of patients with EC are diagnosed after metastasis. Recent advances in machine learning (ML) techniques, particularly in computer vision, have demonstrated promising applications in medical image processing, assisting clinicians in making more accurate and faster diagnostic decisions. Given the significance of early detection of EC, this systematic review aims to summarize and discuss the current state of research on ML-based methods for the early detection of EC. METHODS: We conducted a comprehensive systematic search of five databases (PubMed, Scopus, Web of Science, Wiley, and IEEE) using search terms such as "ML", "Deep Learning (DL (", "Neural Networks (NN)", "Esophagus", "EC" and "Early Detection". After applying inclusion and exclusion criteria, 31 articles were retained for full review. RESULTS: The results of this review highlight the potential of ML-based methods in the early detection of EC. The average accuracy of the reviewed methods in the analysis of endoscopic and computed tomography (CT (images of the esophagus was over 89%, indicating a high impact on early detection of EC. Additionally, the highest percentage of clinical images used in the early detection of EC with the use of ML was related to white light imaging (WLI) images. Among all ML techniques, methods based on convolutional neural networks (CNN) achieved higher accuracy and sensitivity in the early detection of EC compared to other methods. CONCLUSION: Our findings suggest that ML methods may improve accuracy in the early detection of EC, potentially supporting radiologists, endoscopists, and pathologists in diagnosis and treatment planning. However, the current literature is limited, and more studies are needed to investigate the clinical applications of these methods in early detection of EC. Furthermore, many studies suffer from class imbalance and biases, highlighting the need for validation of detection algorithms across organizations in longitudinal studies.
Assuntos
Aprendizado Profundo , Neoplasias Esofágicas , Humanos , Detecção Precoce de Câncer , Aprendizado de Máquina , Redes Neurais de Computação , Neoplasias Esofágicas/diagnóstico por imagemRESUMO
INTRODUCTION: Spaceflight has detrimental effects on human health, imposing significant and unique risks to crewmembers due to physiological adaptations, exposure to physical and psychological stressors, and limited capabilities to provide medical care. Previous research has proposed and evaluated several strategies to support and mitigate the risks related to astronauts' health and medical exploration capabilities. Among these, extended reality (XR) technologies, including augmented reality (AR), virtual reality (VR), and mixed reality (MR) have increasingly been adopted for training, real-time clinical, and operational support in both terrestrial and aerospace settings, and only a few studies have reported research results on the applications of XR technologies for improving space health. This study aims to systematically review the scientific literature that has explored the application of XR technologies in the space health field. We also discuss the methodological and design characteristics of the existing studies in this realm, informing future research and development efforts on applying XR technologies to improve space health and enhance crew safety and performance.Ebnali M, Paladugu P, Miccile C, Park SH, Burian B, Yule S, Dias RD. Extended reality applications for space health. Aerosp Med Hum Perform. 2023; 94(3):122-130.
Assuntos
Voo Espacial , Realidade Virtual , Humanos , Astronautas , Estresse PsicológicoRESUMO
The cardiac operating room (OR) is a high-risk, high-stakes environment inserted into a complex socio-technical healthcare system. During cardiopulmonary bypass (CPB), the most critical phase of cardiac surgery, the perfusionist has a crucial role within the interprofessional OR team, being responsible for optimizing patient perfusion while coordinating other tasks with the surgeon, anesthesiologist, and nurses. The aim of this study was to investigate objective digital biomarkers of perfusionists' workload and stress derived from heart rate variability (HRV) metrics captured via a wearable physiological sensor in a real cardiac OR. We explored the relationships between several HRV parameters and validated self-report measures of surgical task workload (SURG-TLX) and acute stress (STAI-SF), as well as surgical processes and outcome measures. We found that the frequency-domain HRV parameter HF relative power - FFT (%) presented the strongest association with task workload (correlation coefficient: -0.491, p-value: 0.003). We also found that the time-domain HRV parameter RMSSD (ms) presented the strongest correlation with perfusionists' acute stress (correlation coefficient: -0.489, p-value: 0.005). A few workload and stress biomarkers were also associated with bypass time and patient length of stay in the hospital. The findings from this study will inform future research regarding which HRV-based biomarkers are best suited for the development of cognitive support systems capable of monitoring surgical workload and stress in real time.
RESUMO
Several studies have reported low adherence and high resistance from clinicians to adopt digital health technologies into clinical practice, particularly the use of computer-based clinical decision support systems. Poor usability and lack of integration with the clinical workflow have been identified as primary issues. Few guidelines exist on how to analyze the collected data associated with the usability of digital health technologies. In this study, we aimed to develop a coding framework for the systematic evaluation of users' feedback generated during focus groups and interview sessions with clinicians, underpinned by fundamental usability principles and design components. This codebook also included a coding category to capture the user's clinical role associated with each specific piece of feedback, providing a better understanding of role-specific challenges and perspectives, as well as the level of shared understanding across the multiple clinical roles. Furthermore, a voting system was created to quantitatively inform modifications of the digital system based on usability data. As a use case, we applied this method to an electronic cognitive aid designed to improve coordination and communication in the cardiac operating room, showing that this framework is feasible and useful not only to better understand suboptimal usability aspects, but also to recommend relevant modifications in the design and development of the system from different perspectives, including clinical, technical, and usability teams. The framework described herein may be applied in other highly complex clinical settings, in which digital health systems may play an important role in improving patient care and enhancing patient safety.
RESUMO
Research in aviation and driving has highlighted the importance of training as an effective approach to reduce the costs associated with the supervisory role of the human in automated systems. However, only a few studies have investigated the effect of training on highly automated driving. Moreover, available interactive trainings are mostly based on automated driving simulators and the application of immersive technology such as Virtual Reality (VR) as a low-cost training solution has not been widely adopted. In this study, we developed three types of familiarization tours (low-fidelity VR, high-fidelity VR, and video) to train first-time users of highly automated cars. Then, the effectiveness of these tours was investigated on automation trust and driving performance in several critical and non-critical transition tasks in four groups: control, video, low-fidelity VR, and high-fidelity VR. The results revealed the positive impact of the tours on trust and transition performance at the first time of measurement. Takeover quality only improved when practices were presented in high-fidelity VR. After three times of exposure to transition requests, trust and transition performance of all groups converged to those of the high-fidelity VR group, demonstrating that: a) experiencing takeover transition during the training may reduce costs associated with first critical takeover request in highly automated driving, b) the VR tour with high level of interaction fidelity was superior to other training methods, and c) untrained and less-trained drivers learned about automation after a few trials. Knowledge resulting from this research could help develop cost-effective solutions for automated driving training in dealerships and car rental centers.
Assuntos
Realidade Virtual , Automação , Automóveis , Análise Custo-Benefício , Humanos , ConfiançaRESUMO
BACKGROUND: Using in-vehicle audio technologies such as audio systems and voice messages is regarded as a common secondary task. Such tasks, known as the sources of non-visual distraction, affect the driving performance. Given the elderly drivers' cognitive limitations, driving can be even more challenging to drivers. The current study examined how listening to economic news, as a cognitively demanding secondary task, affects elderly subjects' driving performance and whether their comprehension accuracy is associated with these effects. METHODS: Participants of the study (N=22) drove in a real condition with and without listening to economic news. Measurements included driving performance (speed control, forward crash risk, and lateral lane position) and task performance (comprehension accuracy). RESULTS: The mean driving speed, duration of driving in unsafe zones and numbers of overtaking decreased significantly when drivers were engaged in the dual-task condition. Moreover, the cognitive secondary task led to a higher speed variability. Our results demonstrate that there was not a significant relationship between the lane changes and the activity of listening to economic news. However, a meaningful difference was observed between general comprehension and deep comprehension on the one hand and driving performance on the other. Another aspect of our study concerning the drivers' ages and their comprehension revealed a significant relationship between age above 75 and comprehension level. Drivers aging 75 and older showed a lower level of deep comprehension. CONCLUSION: Our study demonstrates that elderly drivers compensated driving performance with safety margin adoption while they were cognitively engaged. In this condition, however, maintaining speed proved more demanding for drivers aging 75 and older.