Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and these models are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models need to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak as an alternative to susceptible–infected–recovered (SIR) and susceptible-exposed-infectious-removed (SEIR) models. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP; and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior across nations, this study suggests machine learning as an effective tool to model the outbreak. This paper provides an initial benchmarking to demonstrate the potential of machine learning for future research. This paper further suggests that a genuine novelty in outbreak prediction can be realized by integrating machine learning and SEIR models.

This paper provides a comprehensive state-of-the-art investigation of the recent advances in data science in emerging economic applications. The analysis is performed on the novel data science methods in four individual classes of deep learning models, hybrid deep learning models, hybrid machine learning, and ensemble models. Application domains include a broad and diverse range of economics research from the stock market, marketing, and e-commerce to corporate banking and cryptocurrency. Prisma method, a systematic literature review methodology, is used to ensure the quality of the survey. The findings reveal that the trends follow the advancement of hybrid models, which outperform other learning algorithms. It is further expected that the trends will converge toward the evolution of sophisticated hybrid deep learning models.

Background and Objectives Declines in stroke admission, IV thrombolysis (IVT), and mechanical thrombectomy volumes were reported during the first wave of the COVID-19 pandemic. There is a paucity of data on the longer-term effect of the pandemic on stroke volumes over the course of a year and through the second wave of the pandemic. We sought to measure the effect of the COVID-19 pandemic on the volumes of stroke admissions, intracranial hemorrhage (ICH), IVT, and mechanical thrombectomy over a 1-year period at the onset of the pandemic (March 1, 2020, to February 28, 2021) compared with the immediately preceding year (March 1, 2019, to February 29, 2020). Methods We conducted a longitudinal retrospective study across 6 continents, 56 countries, and 275 stroke centers. We collected volume data for COVID-19 admissions and 4 stroke metrics: ischemic stroke admissions, ICH admissions, IVT treatments, and mechanical thrombectomy procedures. Diagnoses were identified by their ICD-10 codes or classifications in stroke databases. Results There were 148,895 stroke admissions in the 1 year immediately before compared with 138,453 admissions during the 1-year pandemic, representing a 7% decline (95% CI [95% CI 7.1–6.9]; p < 0.0001). ICH volumes declined from 29,585 to 28,156 (4.8% [5.1–4.6]; p < 0.0001) and IVT volume from 24,584 to 23,077 (6.1% [6.4–5.8]; p < 0.0001). Larger declines were observed at high-volume compared with low-volume centers (all p < 0.0001). There was no significant change in mechanical thrombectomy volumes (0.7% [0.6–0.9]; p = 0.49). Stroke was diagnosed in 1.3% [1.31–1.38] of 406,792 COVID-19 hospitalizations. SARS-CoV-2 infection was present in 2.9% ([2.82–2.97], 5,656/195,539) of all stroke hospitalizations. Discussion There was a global decline and shift to lower-volume centers of stroke admission volumes, ICH volumes, and IVT volumes during the 1st year of the COVID-19 pandemic compared with the prior year. Mechanical thrombectomy volumes were preserved. These results suggest preservation in the stroke care of higher severity of disease through the first pandemic year. Trial Registration Information This study is registered under NCT04934020.

To meet the requirements imposed by the time-dependency of acute stroke therapies, it is necessary 1) to initiate structural and cultural changes in the breadth of stroke-ready hospitals and 2) to find new ways to train the personnel treating patients with acute stroke. We aimed to implement and validate a composite intervention of a stroke team algorithm and simulation-based stroke team training as an effective quality initiative in our regional interdisciplinary neurovascular network consisting of 7 stroke units. We recorded door-to-needle times of all consecutive stroke patients receiving thrombolysis at seven stroke units for 3 months before and after a 2 month intervention which included setting up a team-based stroke workflow at each stroke unit, a train-the-trainer seminar for stroke team simulation training and a stroke team simulation training session at each hospital as well as a recommendation to take up regular stroke team trainings. The intervention reduced the network-wide median door-to-needle time by 12 minutes from 43,0 (IQR 29,8–60,0, n = 122) to 31,0 (IQR 24,0–42,0, n = 112) minutes (p < 0.001) and substantially increased the share of patients receiving thrombolysis within 30 minutes of hospital arrival from 41.5% to 59.6% (p < 0.001). Stroke team training participants stated a significant increase in knowledge on the topic of acute stroke care and in the perception of patient safety. The overall course concept was regarded as highly useful by most participants from different professional backgrounds. The composite intervention of a binding team-based algorithm and stroke team simulation training showed to be well-transferable in our regional stroke network. We provide suggestions and materials for similar campaigns in other stroke networks.

Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models needs to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak.

Number theory is an area of mathematics not unknown to students majoring in mathematics teaching. As early as in junior high, they may encounter basic number theory concepts such as prime numbers, multiples, divisors, or even the fundamental theorem of arithmetic—the proof of which, however, will only be included in the university curriculum of mathematics teacher students. When teaching number theory, in addition to inspiring and motivating students, it is important to have them ask the right questions. Proofs are important, but so is the proper formulation of mathematical conjectures, not to mention intuitions regarding mathematical properties and relationships. These processes are facilitated by the software used, developed to visualize functions related to number theory. Our study aims to assess the relevance of visualization in the teaching and understanding of certain arithmetic functions among mathematics teacher students. Furthermore, we aim to investigate the practical usability of our visualization software, relying on student feedback. According to our results, students found the software useful, as it helped them to discover previously unknown relationships in the examined arithmetic functions. We may conclude our software fills a niche, with student feedback indicating its usefulness.