Importance of Tracking COVID-19 Data from Official Sources for Short-Term Forecasting of Cases and Deaths

Naci Murat

Makale detayları

Importance of Tracking COVID-19 Data from Official Sources for Short-Term Forecasting of Cases and Deaths

Yazarlar:

Naci Murat

Yayıncı:

Kirsehir Ahi Evran University

Ana Başlıklar:

Klinik Tıp Bilimleri

Dergi:

Ahi Evran Tıp Dergisi Vol.7 Issue 1, pp.41-48

Belge Tipi:

Makale

Yayın Tarihi:

4/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001284398

pISSN:

2619-9203

Anahtar kelimeler:

Özet:

 Purpose: During the COVID-19 outbreak, governments, scientists, health workers, and numerous people worked on strategies or solutions for halting disease propagation. Unfortunately, the need for monitoring is steeply increasing, and restrictive actions are currently unavoidable. Due to the lack of epidemiological data and constantly changing numbers, constructing less error-prone predictive models and reliable mathematical models for the near future will help make better legal actions and prevention strategies. Materials and Methods: In this study, daily data from eleven countries between 21012020-02052020 and 21012020-17062020 were used to forecast the number of future COVID-19 events by using different forecasting models. Best fit models were chosen after analysis with ARIMA, Browns LES, and Holts LES models based on MAPE values. Results: The study showed the least error-prone best-fit models for short-term future predictions by analyzing two datasets and demonstrated that models changed after data updates among the selected countries. Investigation of the data from eleven countries, USA, Turkey, Brazil, and Russia analysis showed that updating data alters the model selection resulting in changes in the predictions. Conclusion: The results of this study indicate that using more than one statistical model has superiority over the current approaches, and fluctuations in the numbers should be considered when using the data to construct mathematical models and create future predictions for the management of the already complicated and exhausting COVID-19 pandemic. Thus, policies and restrictions against COVID-19 spread might be more successful after considering that adjusted predictions for providing more accurate results.

 Purpose: During the COVID-19 outbreak, governments, scientists, health workers, and numerous people worked on strategies or solutions for halting disease propagation. Unfortunately, the need for monitoring is steeply increasing, and restrictive actions are currently unavoidable. Due to the lack of epidemiological data and constantly changing numbers, constructing less error-prone predictive models and reliable mathematical models for the near future will help make better legal actions and prevention strategies. Materials and Methods: In this study, daily data from eleven countries between 21012020-02052020 and 21012020-17062020 were used to forecast the number of future COVID-19 events by using different forecasting models. Best fit models were chosen after analysis with ARIMA, Browns LES, and Holts LES models based on MAPE values. Results: The study showed the least error-prone best-fit models for short-term future predictions by analyzing two datasets and demonstrated that models changed after data updates among the selected countries. Investigation of the data from eleven countries, USA, Turkey, Brazil, and Russia analysis showed that updating data alters the model selection resulting in changes in the predictions. Conclusion: The results of this study indicate that using more than one statistical model has superiority over the current approaches, and fluctuations in the numbers should be considered when using the data to construct mathematical models and create future predictions for the management of the already complicated and exhausting COVID-19 pandemic. Thus, policies and restrictions against COVID-19 spread might be more successful after considering that adjusted predictions for providing more accurate results.

 Purpose: During the COVID-19 outbreak, governments, scientists, health workers, and numerous people worked on strategies or solutions for halting disease propagation. Unfortunately, the need for monitoring is steeply increasing, and restrictive actions are currently unavoidable. Due to the lack of epidemiological data and constantly changing numbers, constructing less error-prone predictive models and reliable mathematical models for the near future will help make better legal actions and prevention strategies. Materials and Methods: In this study, daily data from eleven countries between 21012020-02052020 and 21012020-17062020 were used to forecast the number of future COVID-19 events by using different forecasting models. Best fit models were chosen after analysis with ARIMA, Browns LES, and Holts LES models based on MAPE values. Results: The study showed the least error-prone best-fit models for short-term future predictions by analyzing two datasets and demonstrated that models changed after data updates among the selected countries. Investigation of the data from eleven countries, USA, Turkey, Brazil, and Russia analysis showed that updating data alters the model selection resulting in changes in the predictions. Conclusion: The results of this study indicate that using more than one statistical model has superiority over the current approaches, and fluctuations in the numbers should be considered when using the data to construct mathematical models and create future predictions for the management of the already complicated and exhausting COVID-19 pandemic. Thus, policies and restrictions against COVID-19 spread might be more successful after considering that adjusted predictions for providing more accurate results.

 Amaç: COVID-19 salgını sırasında hükümetler, bilim adamları, sağlık çalışanları ve çok sayıda insan, hastalığın yayılmasını durdurmak için stratejiler veya çözümler üzerinde çalışmıştır. Ne yazık ki artık vakaların izleme ihtiyacı hızla artmakta ve gerekli veya kısıtlayıcı önlemlerin alınması kaçınılmaz hale gelmektedir. Epidemiyolojik verilerin eksikliği ve sürekli değişen sayılar nedeniyle, daha az hataya açık tahmin modelleri ve yakın gelecek için güvenilir matematiksel modeller oluşturmak, daha iyi yasal eylemler ve önleme stratejilerinin harekete geçirilmesine yardımcı olacaktır. Araçlar ve Yöntem: Bu çalışmada, farklı tahmin modelleri kullanılarak gelecekteki COVID-19 olaylarının sayısını tahmin etmek için 01212020-02052020 ve 21012020-17062020 tarihleri arasında on bir ülkenin günlük vaka sayılarının verileri kullanılmıştır. MAPE değerlerine dayalı olarak Auto-Regressive Integrated Moving Average ARIMA, Browns linear exponential smoothing LES ve Holts LES modelleri ile mevcut sayıların analizinden sonra en uygun modeller seçilerek analizler yapılmıştır. Bulgular: Çalışmamız, iki veri setini analiz ederek kısa vadeli gelecek tahminleri için en az hataya en uygun modelleri ortaya çıkararak bu modellerin seçilen ülkeler arasında veri güncellemelerinden sonra değiştiğini göstermiştir. Verilerin analiz edilmesiyle onbir ülkenin içinde Amerika, Türkiye, Brezilya, Rusyanın verilerinin güncellenmesinin tahmin sonuçlarında değişikliklere neden olduğunu göstermiştir. Sonuç: Bu çalışmanın sonuçları, mevcut yaklaşımlarda birden fazla istatistiksel model kullanmanın üstünlüğü olduğunu ve halihazırda karmaşık ve yorucu olan COVID-19un yönetimi için matematiksel modeller oluşturmak ve geleceğe yönelik tahminler oluşturmak için verileri kullanırken sayılardaki dalgalanmaların dikkate alınması gerektiğini göstermektedir. Bu sayede, COVID-19 yayılımına karşı uygulanacak olan politikalar ve kısıtlamalar, daha doğru sonuçlar sağlamak için düzeltilmiş tahminler göz önüne alındığında daha başarılı olabilir.

Makale detayları

Importance of Tracking COVID-19 Data from Official Sources for Short-Term Forecasting of Cases and Deaths

Yazarlar:

Naci Murat

Yayıncı:

Kirsehir Ahi Evran University

Ana Başlıklar:

Klinik Tıp Bilimleri

Dergi:

Ahi Evran Tıp Dergisi Vol.7 Issue 1, pp.41-48

Belge Tipi:

Makale

Yayın Tarihi:

4/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001284398

pISSN:

2619-9203

COVID-19

ARIMA

Brown’s LES

Holt’s LES

forecasting

COVID-19

ARIMA

Brown’s LES

Holt’s LES

tahmin

Sayı

Makale detayları

Yazarlar: Naci Murat

Yayıncı: Kirsehir Ahi Evran University

Ana Başlıklar: Klinik Tıp Bilimleri

Dergi: Ahi Evran Tıp Dergisi Vol.7 Issue 1, pp.41-48

Belge Tipi: Makale

Yayın Tarihi: 4/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001284398

pISSN: 2619-9203

Sayı

Yazarlar:

Naci Murat

Yayıncı:

Kirsehir Ahi Evran University

Ana Başlıklar:

Klinik Tıp Bilimleri

Dergi:

Ahi Evran Tıp Dergisi Vol.7 Issue 1, pp.41-48

Belge Tipi:

Makale

Yayın Tarihi:

4/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001284398

pISSN:

2619-9203