Prediction of the effective reproduction number of COVID-19 in Greece. A machine learning approach using Google mobility data.

This paper demonstrates how a short-term prediction of the effective reproduction number (Rt) of COVID-19 in regions of Greece is achieved based on online mobility data. Various machine learning methods are applied to predict Rt and attribute importance analysis is performed to reveal the most important variables that affect the accurate prediction of Rt. Work and Park categories are identified as the most important mobility features when compared to the other attributes, with values of 0.25 and 0.24, respectively. Our results are based on an ensemble of diverse Rt methodologies to provide non-precautious and non-indulgent predictions. Random Forest algorithm achieved the highest R2 (0.8 approximately), Pearson’s and Spearman’s correlation values close to 0.9, outperforming in all metrics the other models. The model demonstrates robust results and the methodology overall represents a promising approach towards COVID-19 outbreak prediction. This paper can help health-related authorities when deciding on non-nosocomial interventions to prevent the spread of COVID-19.

Download Full-text

Evaluating Apple Inc Mobility Trend Data Related to the COVID-19 Outbreak in Japan: Statistical Analysis

JMIR Public Health and Surveillance ◽

10.2196/20335 ◽

2021 ◽

Vol 7 (2) ◽

pp. e20335

Author(s):

Junko Kurita ◽

Yoshiyuki Sugishita ◽

Tamie Sugawara ◽

Yasushi Ohkusa

Keyword(s):

Statistical Analysis ◽

Local Governments ◽

Critical Level ◽

Polynomial Function ◽

Reproduction Number ◽

Herd Immunity ◽

Short Term ◽

Mobility Data ◽

Trend Data ◽

Short Term Prediction

Background In Japan, as a countermeasure against the COVID-19 outbreak, both the national and local governments issued voluntary restrictions against going out from residences at the end of March 2020 in preference to the lockdowns instituted in European and North American countries. The effect of such measures can be studied with mobility data, such as data which is generated by counting the number of requests made to Apple Maps for directions in select countries/regions, sub-regions, and cities. Objective We investigate the associations of mobility data provided by Apple Inc and an estimate an an effective reproduction number R(t). Methods We regressed R(t) on a polynomial function of daily Apple data, estimated using the whole period, and analyzed subperiods delimited by March 10, 2020. Results In the estimation results, R(t) was 1.72 when voluntary restrictions against going out ceased and mobility reverted to a normal level. However, the critical level of reducing R(t) to <1 was obtained at 89.3% of normal mobility. Conclusions We demonstrated that Apple mobility data are useful for short-term prediction of R(t). The results indicate that the number of trips should decrease by 10% until herd immunity is achieved and that higher voluntary restrictions against going out might not be necessary for avoiding a re-emergence of the outbreak.

Download Full-text

Short-term prediction of traffic state, statistical approach versus machine learning approach

Scientia Iranica ◽

10.24200/sci.2021.57906.5469 ◽

2021 ◽

Vol 0 (0) ◽

pp. 0-0

Author(s):

Arash Rasaizadi ◽

Elahe Sherafat ◽

Seyedehsan Seyedabrishami

Keyword(s):

Machine Learning ◽

Statistical Approach ◽

Learning Approach ◽

Short Term ◽

Traffic State ◽

Term Prediction ◽

Machine Learning Approach ◽

Short Term Prediction

Download Full-text

Short-term Prediction of Lightning in Southern Africa using Autoregressive Machine Learning Techniques

2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS) ◽

10.1109/iemtronics52119.2021.9422493 ◽

2021 ◽

Author(s):

Yaseen Essa ◽

Hugh G.P. Hunt ◽

Ritesh Ajoodha

Keyword(s):

Machine Learning ◽

Southern Africa ◽

Machine Learning Techniques ◽

Short Term ◽

Term Prediction ◽

Learning Techniques ◽

Short Term Prediction

Download Full-text

Short-Term Prediction of COVID-19 Cases Using Machine Learning Models

Applied Sciences ◽

10.3390/app11094266 ◽

2021 ◽

Vol 11 (9) ◽

pp. 4266

Author(s):

Md. Shahriare Satu ◽

Koushik Chandra Howlader ◽

Mufti Mahmud ◽

M. Shamim Kaiser ◽

Sheikh Mohammad Shariful Islam ◽

...

Keyword(s):

Machine Learning ◽

Web Application ◽

Learning Models ◽

Short Term ◽

Infected People ◽

Infected Case ◽

First Case ◽

Novel Coronavirus ◽

Short Term Prediction ◽

Machine Learning Models

The first case in Bangladesh of the novel coronavirus disease (COVID-19) was reported on 8 March 2020, with the number of confirmed cases rapidly rising to over 175,000 by July 2020. In the absence of effective treatment, an essential tool of health policy is the modeling and forecasting of the progress of the pandemic. We, therefore, developed a cloud-based machine learning short-term forecasting model for Bangladesh, in which several regression-based machine learning models were applied to infected case data to estimate the number of COVID-19-infected people over the following seven days. This approach can accurately forecast the number of infected cases daily by training the prior 25 days sample data recorded on our web application. The outcomes of these efforts could aid the development and assessment of prevention strategies and identify factors that most affect the spread of COVID-19 infection in Bangladesh.

Download Full-text

A Machine Learning Approach to Short-Term Traffic Flow Prediction: A Case Study of Interstate 64 in Missouri

2018 IEEE International Smart Cities Conference (ISC2) ◽

10.1109/isc2.2018.8656924 ◽

2018 ◽

Cited By ~ 3

Author(s):

Osama Mohammed ◽

Jalil Kianfar

Keyword(s):

Machine Learning ◽

Traffic Flow ◽

Learning Approach ◽

Short Term ◽

Traffic Flow Prediction ◽

Flow Prediction ◽

Machine Learning Approach

Download Full-text

A machine learning approach to predicting short-term mortality risk in patients starting chemotherapy

10.1101/204081 ◽

2017 ◽

Cited By ~ 2

Author(s):

Aymen A. Elfiky ◽

Maximilian J. Pany ◽

Ravi B. Parikh ◽

Ziad Obermeyer

Keyword(s):

Machine Learning ◽

Mortality Risk ◽

Palliative Chemotherapy ◽

Learning Algorithm ◽

Cancer Center ◽

Short Term ◽

Machine Learning Model ◽

Machine Learning Approach ◽

Short Term Mortality ◽

And Performance

ABSTRACTBackgroundCancer patients who die soon after starting chemotherapy incur costs of treatment without benefits. Accurately predicting mortality risk from chemotherapy is important, but few patient data-driven tools exist. We sought to create and validate a machine learning model predicting mortality for patients starting new chemotherapy.MethodsWe obtained electronic health records for patients treated at a large cancer center (26,946 patients; 51,774 new regimens) over 2004-14, linked to Social Security data for date of death. The model was derived using 2004-11 data, and performance measured on non-overlapping 2012-14 data.Findings30-day mortality from chemotherapy start was 2.1%. Common cancers included breast (21.1%), colorectal (19.3%), and lung (18.0%). Model predictions were accurate for all patients (AUC 0.94). Predictions for patients starting palliative chemotherapy (46.6% of regimens), for whom prognosis is particularly important, remained highly accurate (AUC 0.92). To illustrate model discrimination, we ranked patients initiating palliative chemotherapy by model-predicted mortality risk, and calculated observed mortality by risk decile. 30-day mortality in the highest-risk decile was 22.6%; in the lowest-risk decile, no patients died. Predictions remained accurate across all primary cancers, stages, and chemotherapies—even for clinical trial regimens that first appeared in years after the model was trained (AUC 0.94). The model also performed well for prediction of 180-day mortality (AUC 0.87; mortality 74.8% in the highest risk decile vs. 0.2% in the lowest). Predictions were more accurate than data from randomized trials of individual chemotherapies, or SEER estimates.InterpretationA machine learning algorithm accurately predicted short-term mortality in patients starting chemotherapy using EHR data. Further research is necessary to determine generalizability and the feasibility of applying this algorithm in clinical settings.

Download Full-text