Distance learning in academic health education

Distance learning is an apparent alternative to traditional methods in education of health care professionals. Non-interactive distance learning, interactive courses and virtual learning environments exist as three different generations in distance learning, each with unique methodologies, strengths and potential. Different methodologies have been recommended for distance learning, varying from a didactic approach to a problem-based learning procedure. Accreditation, teamwork and personal contact between the tutors and the students during a course provided by distance learning are recommended as motivating factors in order to enhance the effectiveness of the learning. Numerous assessment methods for distance learning courses have been proposed. However, few studies report adequate tests for the effectiveness of the distance-learning environment. Available information indicates that distance learning may significantly decrease the cost of academic health education at all levels. Furthermore, such courses can provide education to students and professionals not accessible by traditional methods. Distance learning applications still lack the support of a solid theoretical framework and are only evaluated to a limited extent. Cases reported so far tend to present enthusiastic results, while more carefully-controlled studies suggest a cautious attitude towards distance learning. There is a vital need for research evidence to identify the factors of importance and variables involved in distance learning. The effectiveness of distance learning courses, especially in relation to traditional teaching methods, must therefore be further investigated.     

From the Cover: Exploiting olfactory learning in alien rats to protect birds’ eggs

Predators must ignore unhelpful background “noise” within information-rich environments and focus on useful cues of prey activity to forage efficiently. Learning to disregard unrewarding cues should happen quickly, weakening future interest in the cue. Prey odor, which is rapidly investigated by predators, may be particularly appropriate for testing whether consistently unrewarded cues are ignored, and whether such behavior can be exploited to benefit prey. Using wild free-ranging populations of black rats, Rattus rattus, an alien predator of global concern, we tested whether the application of bird-nesting odors before the introduction of artificial nests (odor preexposure), enhanced the survival of birds eggs (prey) compared with areas where prey and nesting odors were introduced concurrently. In areas where predators had encountered prey odor before prey being available, the subsequently introduced eggs showed 62% greater survival than in areas where prey and odor were introduced together. We suggest that black rats preexposed to prey odor learned to ignore the unrewarding cue, leading to a significant improvement in prey survival that held for the 7-d monitoring period. Exploiting rapid learning that underpins foraging decisions by manipulating sensory contexts offers a nonlethal, but effective approach to reducing undesirable predatory impacts. Techniques based on olfactory preexposure may provide prey with protection during critical periods of vulnerability, such as immediately following a prey reintroduction. These results also highlight the potential benefits to species conservation to be gained from a greater understanding of the cognitive mechanisms driving alien predator behavior within ecological contexts.     

Automated detection and classification of diabetes disease based on Bangladesh demographic and health survey data, 2011 using machine learning approach

Background and aimsDiabetes has been recognized as a continuing health challenge for the twenty-first century, both in developed and developing countries including Bangladesh. The main objective of this study is to use machine learning (ML) based classifiers for automated detection and classification of diabetes.MethodsThe diabetes dataset have taken from Bangladesh demographic and health survey, 2011 data having 1569 respondents are 127 diabetes. Two statistical tests as independent t for continuous and chi-square for categorical variables are used to determine the risk factors of diabetes. Six ML-based classifiers as support vector machine, random forest, linear discriminant analysis, logistic regression, k-nearest neighborhood, bagged classification and regression tree (Bagged CART) have been adopted to predict and classify of diabetes.ResultsOur findings show that 11 factors out of 15 factors are significantly associated with diabetes. Bagged CART provides the highest accuracy and area under the curve of 94.3% and 0.600.ConclusionsBagged CART anticipates a very supportive computational resource for classification of diabetes and it would be very helpful to the doctors for making a decision to control diabetes disease in Bangladesh.     

Identification and Quantification of Cardiovascular Structures From CCTA: An End-to-End,Rapid, Pixel-Wise,Deep-Learning Method

ObjectivesThis study designed and evaluated an end-to-end deep learning solution for cardiac segmentation and quantification.BackgroundSegmentation of cardiac structures from coronary computed tomography angiography (CCTA) images is laborious. We designed an end-to-end deep-learning solution.MethodsScans were obtained from multicenter registries of 166 patients who underwent clinically indicated CCTA. Left ventricular volume (LVV) and right ventricular volume (RVV), left atrial volume (LAV) and right atrial volume (RAV), and left ventricular myocardial mass (LVM) were manually annotated as ground truth. A U-Net−inspired, deep-learning model was trained, validated, and tested in a 70:20:10 split.ResultsMean age was 61.1 ± 8.4 years, and 49% were women. A combined overall median Dice score of 0.9246 (interquartile range: 0.8870 to 0.9475) was achieved. The median Dice scores for LVV, RVV, LAV, RAV, and LVM were 0.938 (interquartile range: 0.887 to 0.958), 0.927 (interquartile range: 0.916 to 0.946), 0.934 (interquartile range: 0.899 to 0.950), 0.915 (interquartile range: 0.890 to 0.920), and 0.920 (interquartile range: 0.811 to 0.944), respectively. Model prediction correlated and agreed well with manual annotation for LVV (r = 0.98), RVV (r = 0.97), LAV (r = 0.78), RAV (r = 0.97), and LVM (r = 0.94) (p < 0.05 for all). Mean difference and limits of agreement for LVV, RVV, LAV, RAV, and LVM were 1.20 ml (95% CI: −7.12 to 9.51), −0.78 ml (95% CI: −10.08 to 8.52), −3.75 ml (95% CI: −21.53 to 14.03), 0.97 ml (95% CI: −6.14 to 8.09), and 6.41 g (95% CI: −8.71 to 21.52), respectively.ConclusionsA deep-learning model rapidly segmented and quantified cardiac structures. This was done with high accuracy on a pixel level, with good agreement with manual annotation, facilitating its expansion into areas of research and clinical import.     

A Boosted Ensemble Algorithm for Determination of Plaque Stability in High-Risk Patients on Coronary CTA

ObjectivesThis study sought to identify culprit lesion (CL) precursors among acute coronary syndrome (ACS) patients based on qualitative and quantitative computed tomography–based plaque characteristics.BackgroundCoronary computed tomography angiography (CTA) has been validated for patient-level prediction of ACS. However, the applicability of coronary CTA to CL assessment is not known.MethodsUtilizing the ICONIC (Incident COroNary Syndromes Identified by Computed Tomography) study, a nested case-control study of 468 patients with baseline coronary CTA, the study included ACS patients with invasive coronary angiography–adjudicated CLs that could be aligned to CL precursors on baseline coronary CTA. Separate blinded core laboratories adjudicated CLs and performed atherosclerotic plaque evaluation. Thereafter, the study used a boosted ensemble algorithm (XGBoost) to develop a predictive model of CLs. Data were randomly split into a training set (80%) and a test set (20%). The area under the receiver-operating characteristic curve of this model was compared with that of diameter stenosis (model 1), high-risk plaque features (model 2), and lesion-level features of CL precursors from the ICONIC study (model 3). Thereafter, the machine learning (ML) model was applied to 234 non-ACS patients with 864 lesions to determine model performance for CL exclusion.ResultsCL precursors were identified by both coronary angiography and baseline coronary CTA in 124 of 234 (53.0%) patients, with a total of 582 lesions (containing 124 CLs) included in the analysis. The ML model demonstrated significantly higher area under the receiver-operating characteristic curve for discriminating CL precursors (0.774; 95% confidence interval [CI]: 0.758 to 0.790) compared with model 1 (0.599; 95% CI: 0.599 to 0.599; p < 0.01), model 2 (0.532; 95% CI: 0.501 to 0.563; p < 0.01), and model 3 (0.672; 95% CI: 0.662 to 0.682; p < 0.01). When applied to the non-ACS cohort, the ML model had a specificity of 89.3% for excluding CLs.ConclusionsIn a high-risk cohort, a boosted ensemble algorithm can be used to predict CL from non-CL precursors on coronary CTA.     

Myocardial Infarction Associates With a Distinct Pericoronary Adipose Tissue Radiomic Phenotype: A Prospective Case-Control Study

ObjectivesThis study sought to determine whether coronary computed tomography angiography (CCTA)-based radiomic analysis of pericoronary adipose tissue (PCAT) could distinguish patients with acute myocardial infarction (MI) from patients with stable or no coronary artery disease (CAD).BackgroundImaging of PCAT with CCTA enables detection of coronary inflammation. Radiomics involves extracting quantitative features from medical images to create big data and identify novel imaging biomarkers.MethodsIn a prospective case-control study, 60 patients with acute MI underwent CCTA within 48 h of admission, before invasive angiography. These subjects were matched to patients with stable CAD (n = 60) and controls with no CAD (n = 60) by age, sex, risk factors, medications, and CT tube voltage. PCAT was segmented around the proximal right coronary artery (RCA) in all patients and around culprit and nonculprit lesions in patients with MI. PCAT segmentations were analyzed using Radiomics Image Analysis software.ResultsOf 1,103 calculated radiomic parameters, 20.3% differed significantly between MI patients and controls, and 16.5% differed between patients with MI and stable CAD (critical p < 0.0006); whereas none differed between patients with stable CAD and controls. On cluster analysis, the most significant radiomic parameters were texture or geometry based. At 6 months post-MI, there was no significant change in the PCAT radiomic profile around the proximal RCA or nonculprit lesions. Using machine learning (XGBoost), a model integrating clinical features (risk factors, serum lipids, high-sensitivity C-reactive protein), PCAT attenuation, and radiomic parameters provided superior discrimination of acute MI (area under the receiver operator characteristic curve [AUC]: 0.87) compared with a model with clinical features and PCAT attenuation (AUC: 0.77; p = 0.001) or clinical features alone (AUC: 0.76; p < 0.001).ConclusionsPatients with acute MI have a distinct PCAT radiomic phenotype compared with patients with stable or no CAD. Using machine learning, a radiomics-based model outperforms a PCAT attenuation-based model in accurately identifying patients with MI.     

不同扫描仪构建的结直肠癌全切片数字病理图像中人工标注迁移的研究

目的研究结直肠癌人工智能病理诊断模型构建过程中,病理医师对数字切片癌组织的人工标注在不同扫描仪构建的全切片图像（WSI）中准确迁移的方法。 方法在本研究中,我们提出了一种基于图像配准的标注迁移方法,在来自不同扫描仪的WSI之间建立仿射映射。通过多分辨率最小化两个WSI缩略图之间的互信息来估计最佳仿射映射参数,以避免和改变扫描仪特定特性的影响,减少计算时间。我们使用了181张结直肠癌病理切片,使用两个品牌的扫描仪获得相应的WSI,对上述标注迁移方法进行测试。 结果181张HE切片的扫描结果表明,同一张切片由不同扫描仪构建的WSI在颜色、位置、大小等属性上都有不同的表现。使用我们提出的标注迁移方法,其中179张图像的人工标注成功地在不同扫描仪构建的WSI中迁移,其中125对使用单个CPU核心的计算时间不到1分钟。 结论我们提出了一种快速、准确的全自动的标注迁移方法,用于在不同扫描仪构建的WSI之间传递人工标注。在准备深度学习训练数据过程中,既可以避免病理医师对新图像的重新标注,也可以避免病理医师之间在标注上的差异。     

Emerging use of artificial intelligence in inflammatory bowel disease

Inflammatory bowel disease (IBD) is a complex, immune-mediated gastrointestinal disorder with ill-defined etiology, multifaceted diagnostic criteria, and unpredictable treatment response. Innovations in IBD diagnostics, including developments in genomic sequencing and molecular analytics, have generated tremendous interest in leveraging these large data platforms into clinically meaningful tools. Artificial intelligence, through machine learning facilitates the interpretation of large arrays of data, and may provide insight to improving IBD outcomes. While potential applications of machine learning models are vast, further research is needed to generate standardized models that can be adapted to target IBD populations.