Alpha-1-antitrypsin-deficiency is associated with lower cardiovascular risk: an approach based on federated learning.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is an inflammatory multisystemic disease caused by environmental exposures and/or genetic factors. Inherited alpha-1-antitrypsin deficiency (AATD) is one of the best recognized genetic factors increasing the risk for an early onset COPD with emphysema. The aim of this study was to gain a better understanding of the associations between comorbidities and specific biomarkers in COPD patients with and without AATD to enable future investigations aimed, for example, at identifying risk factors or improving care. METHODS: We focused on cardiovascular comorbidities, blood high sensitivity troponin (hs-troponin) and lipid profiles in COPD patients with and without AATD. We used clinical data from six German University Medical Centres of the MIRACUM (Medical Informatics Initiative in Research and Medicine) consortium. The codes for the international classification of diseases (ICD) were used for COPD as a main diagnosis and for comorbidities and blood laboratory data were obtained. Data analyses were based on the DataSHIELD framework. RESULTS: Out of 112,852 visits complete information was available for 43,057 COPD patients. According to our findings, 746 patients with AATD (1.73%) showed significantly lower total blood cholesterol levels and less cardiovascular comorbidities than non-AATD COPD patients. Moreover, after adjusting for the confounder factors, such as age, gender, and nicotine abuse, we confirmed that hs-troponin is a suitable predictor of overall mortality in COPD patients. The comorbidities associated with AATD in the current study differ from other studies, which may reflect geographic and population-based differences as well as the heterogeneous characteristics of AATD. CONCLUSION: The concept of MIRACUM is suitable for the analysis of a large healthcare database. This study provided evidence that COPD patients with AATD have a lower cardiovascular risk and revealed that hs-troponin is a predictor for hospital mortality in individuals with COPD.

Rheuma-VOR study: optimising healthcare of rheumatic diseases by multiprofessional coordinating centres.

OBJECTIVES: Early diagnosis of inflammatory arthritis is critical to prevent joint damage and functional incapacities. However, the discrepancy between recommendations of early diagnosis and reality is remarkable. The Rheuma-VOR study aimed to improve the time to diagnosis of patients with early arthritis by coordinating cooperation between primary care physicians, specialists and patients in Germany. METHODS: This prospective non-randomised multicentre study involved 2340 primary care physicians, 72 rheumatologists, 4 university hospitals and 4 rheumatology centres in 4 German Federal States. The two coprimary endpoints (time to diagnosis and screening performance of primary care physicians) were evaluated for early versus late implementation phase. Additionally, time to diagnosis and secondary endpoints (decrease of disease activity, increase in quality of life and overall well-being, improvement of fatigue, depression, functional ability, and work ability, reduction in drug and medical costs and hospitalisation) were compared with a reference cohort of the German Rheumatism Research Centre (DRFZ) reflecting standard care. RESULTS: A total of 7049 patients were enrolled in the coordination centres and 1537 patients were diagnosed with a rheumatic disease and consented to further participation. A follow-up consultation after 1 year was realised in 592 patients. The time to diagnosis endpoint and the secondary endpoints were met. In addition, the calculation of cost-effectiveness shows that Rheuma-VOR has a dominant cost-benefit ratio compared with standard care. DISCUSSION: Rheuma-VOR has shown an improvement in rheumatological care, patient-reported outcome parameters and cost savings by coordinating the cooperation of primary care physicians, rheumatologists and patients, in a nationwide approach.

Convolutional neural network-based kidney volume estimation from low-dose unenhanced computed tomography scans.

PURPOSE: Kidney volume is important in the management of renal diseases. Unfortunately, the currently available, semi-automated kidney volume determination is time-consuming and prone to errors. Recent advances in its automation are promising but mostly require contrast-enhanced computed tomography (CT) scans. This study aimed at establishing an automated estimation of kidney volume in non-contrast, low-dose CT scans of patients with suspected urolithiasis. METHODS: The kidney segmentation process was automated with 2D Convolutional Neural Network (CNN) models trained on manually segmented 2D transverse images extracted from low-dose, unenhanced CT scans of 210 patients. The models' segmentation accuracy was assessed using Dice Similarity Coefficient (DSC), for the overlap with manually-generated masks on a set of images not used in the training. Next, the models were applied to 22 previously unseen cases to segment kidney regions. The volume of each kidney was calculated from the product of voxel number and their volume in each segmented mask. Kidney volume results were then validated against results semi-automatically obtained by radiologists. RESULTS: The CNN-enabled kidney volume estimation took a mean of 32 s for both kidneys in a CT scan with an average of 1026 slices. The DSC was 0.91 and 0.86 and for left and right kidneys, respectively. Inter-rater variability had consistencies of ICC = 0.89 (right), 0.92 (left), and absolute agreements of ICC = 0.89 (right), 0.93 (left) between the CNN-enabled and semi-automated volume estimations. CONCLUSION: In our work, we demonstrated that CNN-enabled kidney volume estimation is feasible and highly reproducible in low-dose, non-enhanced CT scans. Automatic segmentation can thereby quantitatively enhance radiological reports.

Implementation of a Learning Management System for Medical Students: A Case Study of Kilimanjaro Christian Medical University College.

This article was migrated. The article was marked as recommended. Learning Management Systems (LMS) are powerful tools for the organization and presentation of curricular learning materials, for monitoring of student and faculty members performance, and for overall quality control. However, there is limited evidence regarding the acceptance and performance of LMS in Africa. This manuscript describes the implementation, the outcomes, and the challenges of the first five years of a LMS at the Kilimanjaro Christian Medical University College (KCMUCo). The LMS has been fully adopted into KCMUCo curriculum and deployed to 1356 students. It has been demonstrated to enhance learning with strength of consensus measure of 84% for basic sciences and 78% for clinical classes. 80% of faculty members have been satisfied with the use of LMS. Electronic assessment has become an obligatory platform for theory examinations. LMS adoption may improve education outcomes at other medical schools in Tanzania and sub-Saharan Africa.

A systems approach to implementation of eLearning in medical education: five MEPI schools' journeys.

How should eLearning be implemented in resource-constrained settings? The introduction of eLearning at four African medical schools and one school of pharmacy, all part of the Medical Education Partnership Initiative (MEPI) eLearning Technical Working Group, highlighted the need for five factors essential for successful and sustainable implementation: institutional support; faculty engagement; student engagement; technical expertise; and infrastructure and support systems. All five MEPI schools reported strengthening technical expertise, infrastructure, and support systems; four schools indicated that they were also successful in developing student engagement; and three reported making good progress in building institutional support. Faculty engagement was the one core component that all five schools needed to enhance.

Modernizing and transforming medical education at the Kilimanjaro Christian Medical University College.

The Kilimanjaro Christian Medical University (KCMU) College and the Medical Education Partnership Initiative (MEPI) are addressing the crisis in Tanzanian health care manpower by modernizing the college's medical education with new tools and techniques. With a $10 million MEPI grant and the participation of its partner, Duke University, KCMU is harnessing the power of information technology (IT) to upgrade tools for students and faculty. Initiatives in eLearning have included bringing fiber-optic connectivity to the campus, offering campus-wide wireless access, opening student and faculty computer laboratories, and providing computer tablets to all incoming medical students. Beyond IT, the college is also offering wet laboratory instruction for hands-on diagnostic skills, team-based learning, and clinical skills workshops. In addition, modern teaching tools and techniques address the challenges posed by increasing numbers of students. To provide incentives for instructors, a performance-based compensation plan and teaching awards have been established. Also for faculty, IT tools and training have been made available, and a medical education course management system is now being widely employed. Student and faculty responses have been favorable, and the rapid uptake of these interventions by students, faculty, and the college's administration suggests that the KCMU College MEPI approach has addressed unmet needs. This enabling environment has transformed the culture of learning and teaching at KCMU College, where a path to sustainability is now being pursued.