Machine Learning Algorithms are Superior to Conventional Regression Models in Predicting Risk Stratification of COVID-19 Patients

AbstractIncreasing understanding of human genome variability allows for better use of the predictive potential of DNA. An obvious direct application is the prediction of the physical phenotypes. Significant success has been achieved, especially in predicting pigmentation characteristics, but the inference of some phenotypes is still challenging. In search of further improvements in predicting human eye colour, we conducted whole-exome (enriched in regulome) sequencing of 150 Polish samples to discover new markers. For this, we adopted quantitative characterization of eye colour phenotypes using high-resolution photographic images of the iris in combination with DIAT software analysis. An independent set of 849 samples was used for subsequent predictive modelling. Newly identified candidates and 114 additional literature-based selected SNPs, previously associated with pigmentation, and advanced machine learning algorithms were used. Whole-exome sequencing analysis found 27 previously unreported candidate SNP markers for eye colour. The highest overall prediction accuracies were achieved with LASSO-regularized and BIC-based selected regression models. A new candidate variant, rs2253104, located in the ARFIP2 gene and identified with the HyperLasso method, revealed predictive potential and was included in the best-performing regression models. Advanced machine learning approaches showed a significant increase in sensitivity of intermediate eye colour prediction (up to 39%) compared to 0% obtained for the original IrisPlex model. We identified a new potential predictor of eye colour and evaluated several widely used advanced machine learning algorithms in predictive analysis of this trait. Our results provide useful hints for developing future predictive models for eye colour in forensic and anthropological studies.

Download Full-text

Non-Invasive Risk Stratification of Hypertension: A Systematic Comparison of Machine Learning Algorithms

Journal of Sensor and Actuator Networks ◽

10.3390/jsan9030034 ◽

2020 ◽

Vol 9 (3) ◽

pp. 34

Author(s):

Giovanna Sannino ◽

Ivanoe De Falco ◽

Giuseppe De Pietro

Keyword(s):

Machine Learning ◽

Blood Pressure ◽

Risk Stratification ◽

Learning Algorithms ◽

Circulatory System ◽

Machine Learning Algorithms ◽

Learning Mechanisms ◽

Data Set ◽

Non Invasive ◽

Blood Pressure Estimation

One of the most important physiological parameters of the cardiovascular circulatory system is Blood Pressure. Several diseases are related to long-term abnormal blood pressure, i.e., hypertension; therefore, the early detection and assessment of this condition are crucial. The identification of hypertension, and, even more the evaluation of its risk stratification, by using wearable monitoring devices are now more realistic thanks to the advancements in Internet of Things, the improvements of digital sensors that are becoming more and more miniaturized, and the development of new signal processing and machine learning algorithms. In this scenario, a suitable biomedical signal is represented by the PhotoPlethysmoGraphy (PPG) signal. It can be acquired by using a simple, cheap, and wearable device, and can be used to evaluate several aspects of the cardiovascular system, e.g., the detection of abnormal heart rate, respiration rate, blood pressure, oxygen saturation, and so on. In this paper, we take into account the Cuff-Less Blood Pressure Estimation Data Set that contains, among others, PPG signals coming from a set of subjects, as well as the Blood Pressure values of the latter that is the hypertension level. Our aim is to investigate whether or not machine learning methods applied to these PPG signals can provide better results for the non-invasive classification and evaluation of subjects’ hypertension levels. To this aim, we have availed ourselves of a wide set of machine learning algorithms, based on different learning mechanisms, and have compared their results in terms of the effectiveness of the classification obtained.

Download Full-text

Functional Outcome Prediction in Ischemic Stroke: A Comparison of Machine Learning Algorithms and Regression Models

Frontiers in Neurology ◽

10.3389/fneur.2020.00889 ◽

2020 ◽

Vol 11 ◽

Author(s):

Shakiru A. Alaka ◽

Bijoy K. Menon ◽

Anita Brobbey ◽

Tyler Williamson ◽

Mayank Goyal ◽

...

Keyword(s):

Machine Learning ◽

Ischemic Stroke ◽

Functional Outcome ◽

Regression Models ◽

Outcome Prediction ◽

Learning Algorithms ◽

Machine Learning Algorithms

Download Full-text

Risk stratification of indeterminate thyroid nodules using ultrasound and machine learning algorithms

Clinical Endocrinology ◽

10.1111/cen.14612 ◽

2021 ◽

Author(s):

Matti Lauren Gild ◽

Mico Chan ◽

Jay Gajera ◽

Brett Lurie ◽

Ziba Gandomkar ◽

...

Keyword(s):

Machine Learning ◽

Risk Stratification ◽

Thyroid Nodules ◽

Learning Algorithms ◽

Machine Learning Algorithms

Download Full-text

Prediction of Air Pollution in Smart Cities Using Machine Learning Techniques

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.39241 ◽

2021 ◽

Vol 9 (12) ◽

pp. 273-277

Author(s):

Mrs. Gowri G

Keyword(s):

Machine Learning ◽

Air Pollution ◽

Predictive Model ◽

Regression Models ◽

Smart Cities ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Series Data ◽

Temporal Data ◽

Spatio Temporal

Abstract: Air-pollution is one of the main threats for developed societies. According to the World Health Organization (WHO), pollution is the main cause of deaths among children aged under five years. Smart cities are called to play a decisive role to increase such pollution in real-time. The increase in air pollution due to fossil fuel consumption as well as its ill effects on the climate has made air pollution forecasting an important research area in today’s times. Deployment of the Internet of things (IoT) based sensors has considerably changed the dynamics of predicting air quality. prediction of spatio-temporal data has been one of the major challenges in creating a good predictive model. There are many different approaches which have been used to create an accurate predictive model. Primitive predictive machine learning algorithms like simple linear regression have failed to produce accurate results primarily due to lack of computing power but also due to lack of optimization techniques. A recent development in deep learning as well as improvements in computing resources has increased the accuracy of predicting time series data. However, with large spatio-temporal data sets spanning over years. Employing regression models on the entire data can cause per date predictions to be corrupted. In this work, we look at dealing with pre-processing the times series. However, pre-processing involves a similarity measure, we explore the use of Dynamic Time Warping (DTW). K-means is then used to classify the spatio-temporal pollution data over a period of 16 years from 2000 to 2016. Here Mean Absolute error (MAE) and Root Mean Square Error (RMSE) have been used as evaluation criteria for the comparison of regression models. Keywords: Spatio-temporal data, Primitive predictive machine learning algorithms, regression models

Download Full-text

Machine learning algorithms performed no better than regression models for prognostication in traumatic brain injury

Journal of Clinical Epidemiology ◽

10.1016/j.jclinepi.2020.03.005 ◽

2020 ◽

Vol 122 ◽

pp. 95-107 ◽

Cited By ~ 2

Author(s):

Benjamin Y. Gravesteijn ◽

Daan Nieboer ◽

Ari Ercole ◽

Hester F. Lingsma ◽

David Nelson ◽

...

Keyword(s):

Machine Learning ◽

Traumatic Brain Injury ◽

Brain Injury ◽

Regression Models ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Better Than

Download Full-text

Clinical Classifiers to Identify Ascending Aortic Dilatation in Patients With Bicuspid Versus Tricuspid Aortic Valves

10.21203/rs.3.rs-957446/v1 ◽

2021 ◽

Author(s):

Bamba Gaye ◽

Maxime Vignac ◽

Jesper R. Gådin ◽

Magalie Ladouceur ◽

Kenneth Caidahl ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Aortic Valve ◽

Regression Models ◽

Prediction Models ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Multidimensional Data ◽

Aortic Dilatation ◽

Logistic Regression Models

Abstract Objective: We aimed to develop clinical classifiers to identify prevalent ascending aortic dilatation in patients with BAV and tricuspid aortic valve (TAV). Methods: This study included BAV (n=543) and TAV (n=491) patients with aortic valve disease and/or ascending aortic dilatation but devoid of coronary artery disease undergoing cardiothoracic surgery. We applied machine learning algorithms and classic logistic regression models, using multiple variable selection methodologies to identify predictors of high risk of ascending aortic dilatation (ascending aorta with a diameter above 40 mm). Analyses included comprehensive multidimensional data (i.e., valve morphology, clinical data, family history of cardiovascular diseases, prevalent diseases, demographic, lifestyle and medication). Results: BAV patients were younger (60.4±12.4 years) than TAV patients (70.4±9.1 years), and had a higher frequency of aortic dilatation (45.3% vs. 28.9% for BAV and TAV, respectively. P<0.001). The aneurysm prediction models showed mean AUC values above 0.8 for TAV patients, with the absence of aortic stenosis being the main predictor, followed by diabetes and high sensitivity C-Reactive Protein. Using the same clinical measures in BAV patients our prediction model resulted in AUC values between 0.5-0.55, not useful for prediction of aortic dilatation. The classification results were consistent for all machine learning algorithms and classic logistic regression models. Conclusions: Cardiovascular risk profiles appear to be more predictive of aortopathy in TAV patients than in patients with BAV. This adds evidence to the fact that BAV- and TAV-associated aortopathy involve different pathways to aneurysm formation and highlights the need for specific aneurysm preventions in these patients. Further, our results highlight that machine learning approaches do not outperform classical prediction methods in addressing complex interactions and non-linear relations between variables.

Download Full-text

Bitcoin Price Prediction using SVM and ARIMA Model

International Journal of Advanced Research in Science, Communication and Technology ◽

10.48175/ijarsct-1486 ◽

2021 ◽

pp. 1094-1096

Author(s):

Gausiya Momin ◽

Trupti Ingle ◽

Vaishnavi Mirajkar ◽

A. A. Magar

Keyword(s):

Machine Learning ◽

Regression Models ◽

Mean Squared Error ◽

Learning Algorithms ◽

Arima Model ◽

Machine Learning Algorithms ◽

Price Prediction ◽

Squared Error ◽

Minute Interval ◽

The Mean

Bitcoin is the most profitable in the cryptocurrency market. However, the prices of Bitcoin have highly fluctuated which makes them very difficult to predict. This research aims to discover the most efficient accuracy model to predict Bitcoin prices from various machine learning algorithms. Using one-minute interval trading data on the exchange website name is bit stamp from January 1, 2012, to January 8, 2018, some different regression models with sci-kit- learn and Keras libraries had experimented. The best results showed that the Mean Squared Error (MSE) was as low as 0.00002 and the R-Square (R2) was as high as 99.2 Percentage.

Download Full-text