Creating symptom-based criteria for diagnostic testing: a case study based on a multivariate analysis of data collected during the first wave of the COVID-19 pandemic in New Zealand

Background Diagnostic testing using PCR is a fundamental component of COVID-19 pandemic control. Criteria for determining who should be tested by PCR vary between countries, and ultimately depend on resource constraints and public health objectives. Decisions are often based on sets of symptoms in individuals presenting to health services, as well as demographic variables, such as age, and travel history. The objective of this study was to determine the sensitivity and specificity of sets of symptoms used for triaging individuals for confirmatory testing, with the aim of optimising public health decision making under different scenarios. Methods Data from the first wave of COVID-19 in New Zealand were analysed; comprising 1153 PCR-confirmed and 4750 symptomatic PCR negative individuals. Data were analysed using Multiple Correspondence Analysis (MCA), automated search algorithms, Bayesian Latent Class Analysis, Decision Tree Analysis and Random Forest (RF) machine learning. Results Clinical criteria used to guide who should be tested by PCR were based on a set of mostly respiratory symptoms: a new or worsening cough, sore throat, shortness of breath, coryza, anosmia, with or without fever. This set has relatively high sensitivity (> 90%) but low specificity (< 10%), using PCR as a quasi-gold standard. In contrast, a group of mostly non-respiratory symptoms, including weakness, muscle pain, joint pain, headache, anosmia and ageusia, explained more variance in the MCA and were associated with higher specificity, at the cost of reduced sensitivity. Using RF models, the incorporation of 15 common symptoms, age, sex and prioritised ethnicity provided algorithms that were both sensitive and specific (> 85% for both) for predicting PCR outcomes. Conclusions If predominantly respiratory symptoms are used for test-triaging, a large proportion of the individuals being tested may not have COVID-19. This could overwhelm testing capacity and hinder attempts to trace and eliminate infection. Specificity can be increased using alternative rules based on sets of symptoms informed by multivariate analysis and automated search algorithms, albeit at the cost of sensitivity. Both sensitivity and specificity can be improved through machine learning algorithms, incorporating symptom and demographic data, and hence may provide an alternative approach to test-triaging that can be optimised according to prevailing conditions.

Safer prescribing and care for the elderly (SPACE): cluster randomised controlled trial in general practice

BackgroundSafer prescribing in general practice may help to decrease preventable adverse drug events (ADE) and related hospitalisations.AimTo test effect of SPACE on high-risk prescribing of non-steroidal anti-inflammatory drugs (NSAIDs) and/or antiplatelet medicines and related hospitalisations.Design & settingPragmatic cluster randomised controlled trial in general practice. Participants were patients at increased risk of ADEs from NSAIDs and/or antiplatelet medicines at baseline. SPACE comprises automated search to generate for each general practitioner (GP)a list of patients with high-risk prescribing; pharmacist outreach to provide education and one-on-one review of list with GP; and automated letter inviting patients to seek medication review with their GP.MethodPrimary outcome was difference in high-risk prescribing of NSAIDs and/or antiplatelet medicines at 6 months; secondary outcomes included high-risk prescribing for gastrointestinal, renal or cardiac ADEs separately; 12-month outcomes; and related ADE hospitalisations.ResultsWe recruited 39 practices with 205 GPs and 191,593 patients including 21,877 (11.4%) participants, 1,479 (6.8%) with high-risk prescribing. High-risk prescribing improved in both groups at 6 and 12 months compared with baseline. At 6 months, there was no significant difference between groups (OR: 0.99 (0.87, 1.13)) although SPACE improved more for gastrointestinal ADEs (0.81 (0.68, 0.96)). At 12 months, the control group improved more (OR: 1.29 (1.11, 1.49)). There was no significant difference for related hospitalisations.ConclusionFurther work is needed to identify scalable interventions that support safer prescribing in general practice. The use of automated search and feedback plus letter to patient warrants further exploration.

Method of automated search of unauthorized cryptocurrency mining in server operating system containers

It is known that with the growing popularity of blockchain and cryptocurrency technology, many people want to make money on it. As a result, hackers who use other people's resources for easy profit are becoming more active. There are many different tools available today to protect user’s personal computers from cryptojacking, but effective protection for server operating systems are still actual.This paper investigates the possibility of searching for unauthorized cryptocurrency mining processes by three parameters: search for suspicious processes by name, by binary signature and by connection to the mining pool.Based on the study, a method of automated search for unauthorized cryptocurrency mining in server OS containers was proposed, which consists of 5 main stages:1. Search for unauthorized cryptocurrency generation processes by process name.2. Search by binary signature.3. Search for a connection to a mining pool4. Detection of the process of unauthorized mining and stopping the container in which the mining process was detected.5. Notification of the system administrator about the detection of unauthorized cryptocurrency generation processes.It is worth noting that, unlike existing tools, the developed method searches for containers from the host virtual machine, so that there is no need to run a search in each of the containers, as it can be a large number of them and as a result reduce the load on the system.The block diagram of the application for the implementation of the proposed method was also described, as well as examples of stopping the container in which an unauthorized mining process was found and the corresponding message to the system administrator.In addition, a study of the speed of the proposed method was conducted. The results of the test showed a time of 2,585 seconds, which reflects the fast operation and the absence of additional overload on the system.

Automated Search Oriented to Key Recovery on Ciphers with Linear Key Schedule

Automatic modelling to search distinguishers with high probability covering as many rounds as possible, such as MILP, SAT/SMT, CP models, has become a very popular cryptanalysis topic today. In those models, the optimizing objective is usually the probability or the number of rounds of the distinguishers. If we want to recover the secret key for a round-reduced block cipher, there are usually two phases, i.e., finding an efficient distinguisher and performing key-recovery attack by extending several rounds before and after the distinguisher. The total number of attacked rounds is not only related to the chosen distinguisher, but also to the extended rounds before and after the distinguisher. In this paper, we try to combine the two phases in a uniform automatic model.Concretely, we apply this idea to automate the related-key rectangle attacks on SKINNY and ForkSkinny. We propose some new distinguishers with advantage to perform key-recovery attacks. Our key-recovery attacks on a few versions of round-reduced SKINNY and ForkSkinny cover 1 to 2 more rounds than the best previous attacks.

Searching for pneumothorax in x-ray images using autoencoded deep features

Fast diagnosis and treatment of pneumothorax, a collapsed or dropped lung, is crucial to avoid fatalities. Pneumothorax is typically detected on a chest X-ray image through visual inspection by experienced radiologists. However, the detection rate is quite low due to the complexity of visual inspection for small lung collapses. Therefore, there is an urgent need for automated detection systems to assist radiologists. Although deep learning classifiers generally deliver high accuracy levels in many applications, they may not be useful in clinical practice due to the lack of high-quality and representative labeled image sets. Alternatively, searching in the archive of past cases to find matching images may serve as a “virtual second opinion” through accessing the metadata of matched evidently diagnosed cases. To use image search as a triaging or diagnosis assistant, we must first tag all chest X-ray images with expressive identifiers, i.e., deep features. Then, given a query chest X-ray image, the majority vote among the top k retrieved images can provide a more explainable output. In this study, we searched in a repository with more than 550,000 chest X-ray images. We developed the Autoencoding Thorax Net (short AutoThorax -Net) for image search in chest radiographs. Experimental results show that image search based on AutoThorax -Net features can achieve high identification performance providing a path towards real-world deployment. We achieved 92% AUC accuracy for a semi-automated search in 194,608 images (pneumothorax and normal) and 82% AUC accuracy for fully automated search in 551,383 images (normal, pneumothorax and many other chest diseases).