Which Priorities Should Guide Design of Online Health Professions Capability-Based Curricula?

Inquiry-based learning instructional design methods support online health professions capability-based curricula. This article proposes which instructional design priorities should guide development of inclusive, accessible online curricula and learning experiences.

AutoML accurately predicts endovascular mechanical thrombectomy in acute large vessel ischemic stroke.

Background and objective: Automated machine learning or autoML has been widely deployed in various industries. However, their adoption in healthcare, especially in clinical settings is constrained due to a lack of clear understanding and explainability. The aim of this study is to utilize autoML for the prediction of functional outcomes in patients who underwent mechanical thrombectomy and compare it with traditional ML models with a focus on the explainability of the trained models. Methods: A total of 156 patients of acute ischemic stroke with Large Vessel Occlusion (LVO) who underwent mechanical thrombectomy within 24 h of stroke onset were included in the study. A total of 34 treatment variables including clinical, demographic, imaging, and procedure-related data were extracted. Various conventional machine learning models such as decision tree classifier, logistic regression, random forest, kNN, and SVM as well as various autoML models such as AutoGluon, MLJAR, Auto-Sklearn, TPOT, and H2O were used to predict the modified Rankin score (mRS) at the time of patient discharge and 3 months follow-up. The sensitivity, specificity, accuracy, and AUC for traditional ML and autoML models were compared. Results: The autoML models outperformed the traditional ML models. For the prediction of mRS at discharge, the highest testing accuracy obtained by traditional ML models for the decision tree classifier was 74.11%, whereas for autoML which was obtained through AutoGluon, it showed an accuracy of 88.23%. Similarly, for mRS at 3 months, the highest testing accuracy of traditional ML was that of the SVM classifier at 76.5%, whereas that of autoML was 85.18% obtained through MLJAR. The 24-h ASPECTS score was the most important predictor for mRS at discharge whereas for prediction of mRS at 3 months, the most important factor was mRS at discharge. Conclusion: Automated machine learning models based on multiple treatment variables can predict the functional outcome in patients more accurately than traditional ML models. The ease of clinical coding and deployment can assist clinicians in the critical decision-making process. We have developed a demo application which can be accessed at https://mrs-score-calculator.onrender.com/.

Design and analysis of DDoS mitigating network architecture.

Distributed Denial of Service (DDoS) attacks have emerged as the top security threat with the rise of e-commerce in recent years. Volumetric attacks are the most common DDoS attacks that aim to overwhelm the victim's bandwidth. The current mitigation methods use reactive filtering techniques that are not magical and straightforward solutions. In this paper, we propose a network architecture based on the capability to address the threat of DDoS attacks. Physically Unclonable Functions (PUFs) have emerged as a promising solution in security. Motivated by the capability approach, we put forward a network architecture where the routers use Transient Effect Ring Oscillator PUF to generate and verify capabilities. This novel hardware-based solution, to address the problem, has reduced the computational overhead of capability generation. Additionally, the destination has complete control over the incoming traffic in the proposed architecture, resulting in uninterrupted communication with the legitimate clients regardless of the attacker traffic. The large-scale simulation on an open-source Network Simulator (NS-3) has shown that the proposed architecture efficiently mitigates DDoS attacks to a large extend. With our proposed architecture, the throughput was hardly affected when attacker traffic was varied from 10 to 80%.

Crossover based technique for data augmentation.

BACKGROUND AND OBJECTIVE: Medical image classification problems are frequently constrained by the availability of datasets. "Data augmentation" has come as a data enhancement and data enrichment solution to the challenge of limited data. Traditionally data augmentation techniques are based on linear and label preserving transformations; however, recent works have demonstrated that even non-linear, non-label preserving techniques can be unexpectedly effective. This paper proposes a non-linear data augmentation technique for the medical domain and explores its results. METHODS: This paper introduces "Crossover technique", a new data augmentation technique for Convolutional Neural Networks in Medical Image Classification problems. Our technique synthesizes a pair of samples by applying two-point crossover on the already available training dataset. By this technique, we create N new samples from N training samples. The proposed crossover based data augmentation technique, although non-label preserving, has performed significantly better in terms of increased accuracy and reduced loss for all the tested datasets over varied architectures. RESULTS: The proposed method was tested on three publicly available medical datasets with various network architectures. For the mini-MIAS database of mammograms, our method improved the accuracy by 1.47%, achieving 80.15% using VGG-16 architecture. Our method works fine for both gray-scale as well as RGB images, as on the PH2 database for Skin Cancer, it improved the accuracy by 3.57%, achieving 85.71% using VGG-19 architecture. In addition, our technique improved accuracy on the brain tumor dataset by 0.40%, achieving 97.97% using VGG-16 architecture. CONCLUSION: The proposed novel crossover technique for training the Convolutional Neural Network (CNN) is painless to implement by applying two-point crossover on two images to form new images. The method would go a long way in tackling the challenges of limited datasets and problems of class imbalances in medical image analysis. Our code is available at https://github.com/rishiraj-cs/Crossover-augmentation.

Detection of alcoholism using EEG signals and a CNN-LSTM-ATTN network.

Alcoholism is a serious disorder that poses a problem for modern society, but the detection of alcoholism has no widely accepted standard tests or procedures. If alcoholism goes undetected at its early stages, it can create havoc in the patient's life. An electroencephalography (EEG) is a method used to measure the brain's electrical activity and can detect alcoholism. EEG signals are complex and multi-channel and thus can be difficult to interpret manually. Several previous works have tried to classify a subject as alcoholic or control (non-alcoholic) based on EEG signals. Such works have mainly used machine learning or statistical techniques along with handcrafted features such as entropy, correlation dimension, Hurst exponent. With the growth in computational power and data volume worldwide, deep learning models have recently been gaining momentum in various fields. However, only a few studies are available on the application of deep learning models for the classification of alcoholism using EEG signals. This paper proposes a deep learning architecture that uses a combination of fast Fourier transform (FFT), a convolution neural network (CNN), long short-term memory (LSTM), and a recently proposed attention mechanism for extracting Spatio-temporal features from multi-channel EEG signals. The proposed architecture can classify a subject as an alcoholic or control with a high degree of accuracy by analyzing EEG signals of that subject and can be used for automating alcoholism detection. The analytical results using the proposed architecture show a 98.83% accuracy, making it better than most state-of-the-art algorithms.