notesum.ai

Published at November 14

Artificial Intelligence for Infectious Disease Prediction and Prevention: A Comprehensive Review

cs.AI

q-bio.PE

Released Date: November 14, 2024

Authors: Selestine Melchane¹, Youssef Elmir², Farid Kacimi³, Larbi Boubchir⁴

Aff.: ¹Laboratoire LITAN, École supérieure en Sciences et Technologies de l'Informatique et du Numérique, Amizour 06300, Bejaia, Algérie; LIASD research Lab., University of Paris 8, France; ²Laboratoire LITAN, École supérieure en Sciences et Technologies de l'Informatique et du Numérique, Amizour 06300, Bejaia, Algérie; SGRE-Lab, Bechar, Algeria; ³Laboratoire LITAN, École supérieure en Sciences et Technologies de l'Informatique et du Numérique, Amizour 06300, Bejaia, Algérie; Laboratoire LIMED, Faculté des Sciences Exactes, Université de Bejaia, Algeria; ⁴LIASD research Lab., University of Paris 8, France

Arxiv: http://arxiv.org/abs/2411.10486v1

Ref	Title	Evaluation Metrics
Ref	Title	Dataset	Method	MAE (%)	MSE (%)	RMSE (%)
[9] (2020)	COVID-19 in Bangladesh: a deeper outlook into the forecast with prediction of upcoming per day cases using time series
		Confirmed	LSTM			65.83
			RFR			184.21
			SVR			166.15
		Death	LSTM			2.95
			RFR			3.28
			SVR			4.73
		Recovery	LSTM			163.21
			RFR			170.15
			SVR			215.08
[10] (2023)	Improved LSTM-based deep learning model for COVID-19 prediction using optimized approach
		Epidemiological data	LSTM	0.01962	0.00102
			GRU	0.00679	0.02788
			Bi-LSTM	0.00623	0.25110
			Dense-LSTM	0.00763	0.00016
[11] (2023)	Global analysis and prediction scenario of infectious outbreaks by recurrent dynamic model and machine learning models: A case study on COVID-19
		daily COVID-19 reports and global geographical distributions : Trained data	GRNN			0.03
			RBF			0.006
			LSTM			0.25
			MLP			0.005
			ANFIS			0.005
		daily COVID-19 reports and global geographical distributions : Tested data	GRNN			0.06
			RBF			0.011
			LSTM			0.02
			MLP			0.02
			ANFIS			0.01
[12] (2023)	A new RNN based machine learning model to forecast COVID-19 incidence, enhanced by the use of mobility data from the bike-sharing service in Madrid
[12] (2023)		weekly COVID-19 case counts per district in Madrid and the number of bike rides recorded by the city’s bike-sharing service, BiciMAD	LSTM-based RNN			0.0205