Convolutional Neural Network-Based Automated Quality Assessment of OCT and OCT Angiography Image Maps in Individuals With Neurodegenerative Disease.

Purpose: To train and test convolutional neural networks (CNNs) to automate quality assessment of optical coherence tomography (OCT) and OCT angiography (OCTA) images in patients with neurodegenerative disease. Methods: Patients with neurodegenerative disease were enrolled in the Duke Eye Multimodal Imaging in Neurodegenerative Disease Study. Image inputs were ganglion cell-inner plexiform layer (GC-IPL) thickness maps and fovea-centered 6-mm × 6-mm OCTA scans of the superficial capillary plexus (SCP). Two trained graders manually labeled all images for quality (good versus poor). Interrater reliability (IRR) of manual quality assessment was calculated for a subset of each image type. Images were split into train, validation, and test sets in a 70%/15%/15% split. An AlexNet-based CNN was trained using these labels and evaluated with area under the receiver operating characteristic (AUC) and summaries of the confusion matrix. Results: A total of 1465 GC-IPL thickness maps (1217 good and 248 poor quality) and 2689 OCTA scans of the SCP (1797 good and 892 poor quality) served as model inputs. The IRR of quality assessment agreement by two graders was 97% and 90% for the GC-IPL maps and OCTA scans, respectively. The AlexNet-based CNNs trained to assess quality of the GC-IPL images and OCTA scans achieved AUCs of 0.990 and 0.832, respectively. Conclusions: CNNs can be trained to accurately differentiate good- from poor-quality GC-IPL thickness maps and OCTA scans of the macular SCP. Translational Relevance: Since good-quality retinal images are critical for the accurate assessment of microvasculature and structure, incorporating an automated image quality sorter may obviate the need for manual image review.

Behavioral health and treatment-seeking behaviors among deployed vs. non-deployed service members: How impactful is deployment on well-being?

Increasing attention has been dedicated to studying behavioral health of non-deployed military personnel. This investigation explored the impacts of a variety of sociodemographic and health factors on key behavioral health outcomes among active duty personnel. A secondary analysis was conducted using 2014 Defense Health Agency Health Related Behaviors Survey data (unweighted n = 45,762, weighted n = 1,251,606). Three logistic regression models investigated factors associated with reporting symptomatology consistent with depression, anxiety, and stress. We found that after adjusting for sociodemographic and other health variables (e.g., sleep), deployment was associated with stress but not anxiety or depression. Although deployed personnel were more likely to report increased levels of stress overall, few differences with respect to the sources of stressors were identified. While behavioral health screening and treatment needs may differ for non-deployed and deployed personnel, programs to support mental and physical well-being among all service members should be robustly promoted.

Teamwork Is Associated with Reduced Hospital Staff Burnout at Military Treatment Facilities: Findings from the 2019 Department of Defense Patient Safety Culture Survey.

BACKGROUND: A National Academy of Medicine report emphasizes the importance of creating positive work environments to address the negative effects of burnout on health care workers. The purpose of this investigation was to determine the scope of burnout among military hospital personnel and explore the relationship between teamwork, burnout, and patient safety culture. METHODS: A logistic regression analysis investigated the relationship between teamwork and burnout using the 2019 US Department of Defense Patient Safety Culture Survey data from 15,838 military hospital workers. Additional regressions investigated teamwork/burnout relationships among individual work areas and staff positions. RESULTS: About one third of respondents (34.4%) reported experiencing burnout. Work areas most likely to report burnout included many different/other work areas (43.4%), pharmacy (41.8%), and labor and delivery/obstetrics (41.8%). Staff positions most likely to report burnout included pharmacy/pharmacists (39.7%), assistants/technicians/therapists (38.1%), and nurses/nursing (37.6%). Analysis revealed an association between lower burnout and high teamwork, both within (odds ratio [OR] 0.54, 95% confidence interval [CI] 0.48-0.60) and across (OR 0.64, 95% CI 0.57-0.72) units. Within-unit teamwork was associated with reduced odds of burnout across almost all work areas and staff positions, with the greatest odds reduction among personnel working in emergency (OR 0.25, 95% CI 0.14-0.43), radiology (OR 0.41, 95% CI 0.20-0.83), and labor and delivery/obstetrics (OR 0.42, 95% CI 0.27-0.65); and physicians/medical staff (OR = 0.44, 95% CI: 0.28-0.69), other staff positions (OR 0.48, 95% CI 0.28-0.81), and assistants/technicians/therapists (OR 0.58, 95% CI 0.46-0.73). CONCLUSION: Effective teamwork may reduce burnout in hospital workers. This association between teamwork (particularly teamwork within units) and burnout was found in all work areas, even in those with the highest levels of self-reported workplace chaos. Greater adoption of workplace interventions focused on improving teamwork, such as TeamSTEPPS, is warranted.

A comparison of film and computer workstation measurements of degenerative spondylolisthesis: intraobserver and interobserver reliability.

STUDY DESIGN: A comparison of measurements of degenerative spondylolisthesis made on film and on computer workstations. OBJECTIVE: To determine whether the 2 methodologies are comparable in some of the parameters used to assess lumbar degenerative spondylolisthesis. SUMMARY OF BACKGROUND DATA: Digital radiology has been replacing analog radiographs. In scoliosis, several studies have shown that measurements made on digital and analog films are similar and that they are also similar to those made on computer workstations. Such work has not been done in spondylolisthesis. METHODS: Twenty-four cases of lumbar degenerative spondylolisthesis were identified from our clinic practice. Three observers measured anterior displacement, sagittal rotation, and lumbar lordosis on digital films using the same protractor and pencil. The same parameters were measured on the same studies at clinical workstations. All measurements were repeated 2 weeks later. A statistician determined the intra and interobserver reliability of the 2 measurement methods and the degree of agreement between the 2 methods. RESULTS: The differences between the first and second readings did reach statistical significance in some cases, but none of them were large enough to be clinically meaningful. The interclass correlation coefficients (ICCs) were >or=0.80 except for one (0.67). The difference among the 3 observers was similarly statistically significant in a few instances but not enough to influence clinical decisions and with good ICCs (0.67 and better). Similarly, the differences in the 2 methods were small, and ICCs ranged from 0.69 to 0.98. CONCLUSION: This study supports the use of computer workstation measurements in lumbar degenerative spondylolisthesis. The parameters used in this study were comparable, whether measured on film or at clinical workstations.