Search

The evaluation of tumor follow-up according to RECIST 1.1 has become essential in clinical practice given its role in therapeutic decision making. At the same time, radiologists are facing an increase in activity while facing a shortage. Radiographic technologists could contribute to the follow-up of these measures, but no studies have evaluated their ability to perform them. Ninety breast cancer patients were performed three CT follow-ups between September 2017 and August 2021. 270 follow-up treatment CT scans were analyzed including 445 target lesions. The rate of agreement of classifications RECIST 1.1 between five technologists and radiologists yielded moderate (k value between 0.47 and 0.52) and substantial (k value = 0.62 and k = 0.67) agreement values. 112 CT were classified as progressive disease (PD) by the radiologists, and 414 new lesions were identified. The analysis showed a percentage of strict agreement of progressive disease classification between reader-technologists and radiologists ranging from substantial to almost perfect agreement (range 73–97%). Analysis of intra-observer agreement was strong at almost perfect (k > 0.78) for 3 technologists. These results are encouraging regarding the ability of selected technologists to perform measurements according to RECIST 1.1 criteria by CT scan with good identification of disease progression. [ABSTRACT FROM AUTHOR]

Scoring sleep stages from biological signals is an essential but labor-intensive inspection for sleep diagnosis. The existing automated scoring methods have achieved high accuracy but are not widely applied in clinical practice. In our understanding, the existing methods have failed to establish the trust of sleep experts (e.g., physicians and clinical technologists) due to a lack of ability to explain the evidences/clues for scoring. In this study, we developed a deep-learning-based scoring model with a reasoning mechanism called class activation mapping (CAM) to solve this problem. This mechanism explicitly shows which portions of the signals support our model's sleep stage decision, and we verified that these portions overlap with the "characteristic waves," which are evidences/clues used in the manual scoring process. In exchange for the acquisition of explainability, employing CAM makes it difficult to follow some scoring rules. Although we concerned the negative effect of CAM on the scoring accuracy, we have found that the impact is limited. The evaluation experiment shows that the proposed model achieved a scoring accuracy of 86.9 % . It is superior to those of some existing methods and the inter-rater reliability among the sleep experts. These results suggest that Sleep-CAM achieved both explainability and required scoring accuracy for practical usage. [ABSTRACT FROM AUTHOR]

Amid accelerating threats to species and ecosystems, technology advancements to monitor, protect, and conserve biodiversity have taken on increased importance. While most innovations stem from adaptation of off-the-shelf devices, these tools can fail to meet the specialized needs of conservation and research or lack the support to scale beyond a single site. Despite calls from the conservation community for its importance, a shift to bottom-up innovation driven by conservation professionals remains limited. We surveyed practitioners, academic researchers, and technologists to understand the factors contributing to or inhibiting engagement in the collaborative process of technology development and adoption for field use and identify emerging technology needs. High cost was the main barrier to technology use across occupations, while development of new technologies faced barriers of cost and partner communication. Automated processing of data streams was the largest emerging need, and respondents focused mainly on applications for individual-level monitoring and automated image processing. Cross-discipline collaborations and expanded funding networks that encourage cyclical development and continued technical support are needed to address current limitations and meet the growing need for conservation technologies. [ABSTRACT FROM AUTHOR]

We aim to prospectively investigate, in a large and heterogeneous population, the electroencephalogram (EEG)-reading performances of EEG technologists. A total of 8 EEG technologists and 5 certified neurophysiologists independently analyzed 20-min EEG recordings. Interrater agreement (IRA) for predefined EEG pattern identification between EEG technologists and neurophysiologits was assessed using percentage of agreement (PA) and Gwet-AC1. Among 1528 EEG recordings, the PA [95% confidence interval] and interrater agreement (IRA, AC1) values were as follows: status epilepticus (SE) and seizures, 97% [96–98%], AC1 kappa = 0.97; interictal epileptiform discharges, 78% [76–80%], AC1 = 0.63; and conclusion dichotomized as "normal" versus "pathological", 83.6% [82–86%], AC1 = 0.71. EEG technologists identified SE and seizures with 99% [98–99%] negative predictive value, whereas the positive predictive values (PPVs) were 48% [34–62%] and 35% [20–53%], respectively. The PPV for normal EEGs was 72% [68–76%]. SE and seizure detection were impaired in poorly cooperating patients (SE and seizures; p < 0.001), intubated and older patients (SE; p < 0.001), and confirmed epilepsy patients (seizures; p = 0.004). EEG technologists identified ictal features with few false negatives but high false positives, and identified normal EEGs with good PPV. The absence of ictal features reported by EEG technologists can be reassuring; however, EEG traces should be reviewed by neurophysiologists before taking action. [ABSTRACT FROM AUTHOR]