Search

The COVID-19 global pandemic has significantly impacted every aspect of life all over the world. The United States is reported to have suffered more than 20% of the global casualties from this pandemic. It is imperative to investigate the growth dynamics of the disease in the US based on varying geographical and governmental factors that best manifest itself in each State of the Country. This paper utilizes a hybrid machine learning and continuum deformation-based approach for analyzing the stability and growth rate of the pandemic. To this end, principal stress values of the pandemic continuum body are obtained using Mohr's Circle method and overlapping, moving windows of data are analysed successively. This helps in finding the correlations between the growth rate and Governments' action/Public's reaction. Government actions include "state of emergency", "shelter at place", and "phase declarations". We also consider the vaccination rate milestones, which shows us the coordinated Governments' action/Public's reaction. Finally, a number of recommendations are made to the Governments and people for better management of future pandemics. [ABSTRACT FROM AUTHOR]

Homozygous familial hypercholesterolemia (HoFH) is an underdiagnosed and undertreated ultra-rare disease. We utilized claims data from the Komodo Healthcare Map database to develop a machine-learning model to identify potential HoFH patients. We tokenized patients enrolled in MyRARE (patient support program for those prescribed evinacumab-dgnb in the United States) and linked them with their Komodo claims. A true positive HoFH cohort (n = 331) was formed by including patients from MyRARE and patients with prescriptions for evinacumab-dgnb or lomitapide. The negative cohort (n = 1423) comprised patients with or at risk for cardiovascular disease. We divided the cohort into an 80% training and 20% testing set. Overall, 10,616 candidate features were investigated; 87 were selected due to clinical relevance and importance on prediction performance. Different machine-learning algorithms were explored, with fast interpretable greedy-tree sums selected as the final machine-learning tool. This selection was based on its satisfactory performance and its easily interpretable nature. The model identified four useful features and yielded precision (positive predicted value) of 0.98, recall (sensitivity) of 0.88, area under the receiver operating characteristic curve of 0.98, and accuracy of 0.97. The model performed well in identifying HoFH patients in the testing set, providing a useful tool to facilitate HoFH screening and diagnosis via healthcare claims data. [ABSTRACT FROM AUTHOR]

Electric vehicles (EVs) have been introduced as an alternative to gasoline and diesel cars to reduce greenhouse gas emissions, optimize fossil fuel use, and protect the environment. Predicting EV sales is momentous for stakeholders, including car manufacturers, policymakers, and fuel suppliers. The data used in the modeling process significantly affects the prediction model's quality. This research's primary dataset contains monthly sales and registrations of 357 new vehicles in the United States of America from 2014 to 2020. In addition to this data, several web crawlers were used to gather the required information. Vehicles sale were predicted using long short-term memory (LSTM) and Convolutional LSTM (ConvLSTM) models. To enhance LSTM performance, the hybrid model with a new structure called "Hybrid LSTM with two-dimensional Attention and Residual network" has been proposed. Also, all three models are built as Automated Machine Learning models to improve the modeling process. The proposed hybrid model performs better than the other models based on the same evaluation units, including Mean Absolute Percentage Error, Normalized Root Mean Square Error, R-square, slope, and intercept of fitted linear regressions. The proposed hybrid model has been able to predict the share of EVs with an acceptable Mean Absolute Error of 3.5%. [ABSTRACT FROM AUTHOR]

Travel patterns and mobility affect the spread of infectious diseases like COVID-19. However, we do not know to what extent local vs. visitor mobility affects the growth in the number of cases. This study evaluates the impact of state-level local vs. visitor mobility in understanding the growth with respect to the number of cases for COVID spread in the United States between March 1, 2020, and December 31, 2020. Two metrics, namely local and visitor transmission risk, were extracted from mobility data to capture the transmission potential of COVID-19 through mobility. A combination of the three factors: the current number of cases, local transmission risk, and the visitor transmission risk, are used to model the future number of cases using various machine learning models. The factors that contribute to better forecast performance are the ones that impact the number of cases. The statistical significance of the forecasts is also evaluated using the Diebold–Mariano test. Finally, the performance of models is compared for three waves across all 50 states. The results show that visitor mobility significantly impacts the case growth by improving the prediction accuracy by 33.78%. We also observe that the impact of visitor mobility is more pronounced during the first peak, i.e., March–June 2020. [ABSTRACT FROM AUTHOR]

Breast adenocarcinoma is the most common of all cancers that occur in women. According to the United States of America survey, more than 282,000 breast cancer patients are registered each year; most of them are women. Detection of cancer at its early stage saves many lives. Each cell contains the genetic code in the form of gene sequences. Changes in the gene sequences may lead to cancer. Replication and/or recombination in the gene base sometimes lead to a permanent change in the nucleotide sequence of the genome, called a mutation. Cancer driver mutations can lead to cancer. The proposed study develops a framework for the early detection of breast adenocarcinoma using machine learning techniques. Every gene has a specific sequence of nucleotides. A total of 99 genes are identified in various studies whose mutations can lead to breast adenocarcinoma. This study uses the dataset taken from 4127 human samples, including men and women from more than 12 cohorts. A total of 6170 mutations in gene sequences are used in this study. Decision Tree, Random Forest, and Gaussian Naïve Bayes are applied to these gene sequences using three evaluation methods: independent set testing, self-consistency testing, and tenfold cross-validation testing. Evaluation metrics such as accuracy, specificity, sensitivity, and Mathew's correlation coefficient are calculated. The decision tree algorithm obtains the best accuracy of 99% for each evaluation method. [ABSTRACT FROM AUTHOR]

Foliar fungicide usage in soybeans in the north-central United States increased steadily over the past two decades. An agronomically-interpretable machine learning framework was used to understand the importance of foliar fungicides relative to other factors associated with realized soybean yields, as reported by growers surveyed from 2014 to 2016. A database of 2738 spatially referenced fields (of which 30% had been sprayed with foliar fungicides) was fit to a random forest model explaining soybean yield. Latitude (a proxy for unmeasured agronomic factors) and sowing date were the two most important factors associated with yield. Foliar fungicides ranked 7th out of 20 factors in terms of relative importance. Pairwise interactions between latitude, sowing date and foliar fungicide use indicated more yield benefit to using foliar fungicides in late-planted fields and in lower latitudes. There was a greater yield response to foliar fungicides in higher-yield environments, but less than a 100 kg/ha yield penalty for not using foliar fungicides in such environments. Except in a few production environments, yield gains due to foliar fungicides sufficiently offset the associated costs of the intervention when soybean prices are near-to-above average but do not negate the importance of disease scouting and fungicide resistance management. [ABSTRACT FROM AUTHOR]

The need for improved models that can accurately predict COVID-19 dynamics is vital to managing the pandemic and its consequences. We use machine learning techniques to design an adaptive learner that, based on epidemiological data available at any given time, produces a model that accurately forecasts the number of reported COVID-19 deaths and cases in the United States, up to 10 weeks into the future with a mean absolute percentage error of 9%. In addition to being the most accurate long-range COVID predictor so far developed, it captures the observed periodicity in daily reported numbers. Its effectiveness is based on three design features: (1) producing different model parameters to predict the number of COVID deaths (and cases) from each time and for a given number of weeks into the future, (2) systematically searching over the available covariates and their historical values to find an effective combination, and (3) training the model using "last-fold partitioning", where each proposed model is validated on only the last instance of the training dataset, rather than being cross-validated. Assessments against many other published COVID predictors show that this predictor is 19–48% more accurate. [ABSTRACT FROM AUTHOR]

According to a recent study, around 99% of hospitals across the US now use electronic health record systems (EHRs). One of the most common types of EHR is the unstructured textual data, and unlocking hidden details from this data is critical for improving current medical practices and research endeavors. However, these textual data contain sensitive information, which could compromise our privacy. Therefore, medical textual data cannot be released publicly without undergoing any privacy-protective measures. De-identification is a process of detecting and removing all sensitive information present in EHRs, and it is a necessary step towards privacy-preserving EHR data sharing. Over the last decade, there have been several proposals to de-identify textual data using manual, rule-based, and machine learning methods. In this article, we propose new methods to de-identify textual data based on the self-attention mechanism and stacked Recurrent Neural Network. To the best of our knowledge, we are the first to employ these techniques. Experimental results on three different datasets show that our model performs better than all state-of-the-art mechanism irrespective of the dataset. Additionally, our proposed method is significantly faster than the existing techniques. Finally, we introduced three utility metrics to judge the quality of the de-identified data. [ABSTRACT FROM AUTHOR]