Forecast Number of Covid-19 Cases Worldwide

Completed

• Conditions: Covid-19
• Interventions: Other: Model Building; Other: Model validation

• Registration Number: NCT04460274
• Lead Sponsor: Turkish Ministry of Health Izmir Teaching Hospital

Brief Summary

Coronavirus disease-19 (Covid-19) had an unprecedented effect on both nations and health systems. Time series modeling using Auto-Regressive Integrated Moving Averages (ARIMA) models have been used to forecast variables extensively mainly in statistics and econometrics. The investigators aimed to predict the total number of cases for Covid-19 using ARIMA models of time-series analysis.

Detailed Description

Coronavirus Disease 19 (Covid-19) is an infectious disease initially defined in December 2019 before becoming pandemic. Respiratory disease is the main form of disease causing acute respiratory distress as the main cause of death.

Increased number of cases worldwide had put an enormous load on public health resulting lockdowns, quarantines and curfews. Predicting number of cases is hard as the increment of cases between communities differ.

Time series had been used in different fields of science to predict, such as signal processing, mathematical finance, weather prediction. In medicine, time series analysis were used in number of admitted patients to hospitals. Aim of this study is to predict the total number of Covid-19 cases worldwide using time series anaylsis.

Study Timeline

• Study Start: 2019-12-31
• Primary Completion: 2020-06-15
• Study Completion: 2020-06-20
• Status Verified: 2020-07
• Study First Submitted: 2020-07-03
• Study First Submitted QC: 2020-07-03
• Last Update Submitted: 2020-07-06
• Study First Posted: 2020-07-07
• Last Update Posted: 2020-07-08

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 7882471

Inclusion Criteria

• Confirmed case of Covid-19

Exclusion Criteria

• Cases not reported

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Model Building	Model Building	Number of Covid-19 cases from December 31, 2019 to June 1, 2020 were used to build ARIMA model using Hyndman-Khandakar algorithm.
Model Validation	Model validation	Number of Covid-19 cases from June 2, 2020 to June 15, 2020 were used to forecast cases using the ARIMA model

Primary Outcome Measures

Name	Time	Method
Number of Confirmed cases of Covid-19	December 31, 2019 to June 15, 2020

Trial Locations

Locations (1)

Republic of Turkey, Health Sciences University, Izmir Bozyaka Education and Training Hospital; 🇹🇷 İzmir, Turkey