Secure Dengue Epidemic Prediction System: Healthcare Perspective

Aldaej, Abdulaziz; Ahanger, Tariq Ahamed; Uddin, Mohammed Yousuf; Ullah, Imdad

doi:10.32604/cmc.2022.027487

Cited by 2 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using autocorrelation (ACF) and partial autocorrelation functions, auto-regressive and shifting average constituents are chosen after seasonality and stationary recognition. The ARIMA examines opposite goals in the lack of seasonality in the time series data [ 16 ] where the “forecast R package” is used in this current study, and Equation (2) is presented below [ 17 ]: Vt = α + φ1V (t−1) + … +φpV (t− p ) + θ 1e (t−1) + … +θqe (t − q) + Wt …”

Section: Methodsmentioning

confidence: 99%

Correlation of Dengue and Meteorological Factors in Bangladesh: A Public Health Concern

Islam

Hasan

Tiwari

et al. 2023

IJERPH

View full text Add to dashboard Cite

Dengue virus (DENV) is an enveloped, single-stranded RNA virus, a member of the Flaviviridae family (which causes Dengue fever), and an arthropod-transmitted human viral infection. Bangladesh is well known for having some of Asia’s most vulnerable Dengue outbreaks, with climate change, its location, and it’s dense population serving as the main contributors. For speculation about DENV outbreak characteristics, it is crucial to determine how meteorological factors correlate with the number of cases. This study used five time series models to observe the trend and forecast Dengue cases. Current data-based research has also applied four statistical models to test the relationship between Dengue-positive cases and meteorological parameters. Datasets were used from NASA for meteorological parameters, and daily DENV cases were obtained from the Directorate General of Health Service (DGHS) open-access websites. During the study period, the mean of DENV cases was 882.26 ± 3993.18, ranging between a minimum of 0 to a maximum of 52,636 daily confirmed cases. The Spearman’s rank correlation coefficient between climatic variables and Dengue incidence indicated that no substantial relationship exists between daily Dengue cases and wind speed, temperature, and surface pressure (Spearman’s rho; r = −0.007, p > 0.05; r = 0.085, p > 0.05; and r = −0.086, p > 0.05, respectively). Still, a significant relationship exists between daily Dengue cases and dew point, relative humidity, and rainfall (r = 0.158, p < 0.05; r = 0.175, p < 0.05; and r = 0.138, p < 0.05, respectively). Using the ARIMAX and GA models, the relationship for Dengue cases with wind speed is −666.50 [95% CI: −1711.86 to 378.86] and −953.05 [−2403.46 to 497.36], respectively. A similar negative relation between Dengue cases and wind speed was also determined in the GLM model (IRR = 0.98). Dew point and surface pressure also represented a negative correlation in both ARIMAX and GA models, respectively, but the GLM model showed a positive association. Additionally, temperature and relative humidity showed a positive correlation with Dengue cases (105.71 and 57.39, respectively, in the ARIMAX, 633.86, and 200.03 in the GA model). In contrast, both temperature and relative humidity showed negative relation with Dengue cases in the GLM model. In the Poisson regression model, windspeed has a substantial significant negative connection with Dengue cases in all seasons. Temperature and rainfall are significantly and positively associated with Dengue cases in all seasons. The association between meteorological factors and recent outbreak data is the first study where we are aware of the use of maximum time series models in Bangladesh. Taking comprehensive measures against DENV outbreaks in the future can be possible through these findings, which can help fellow researchers and policymakers.

show abstract

Section: Methodsmentioning

confidence: 99%

Correlation of Dengue and Meteorological Factors in Bangladesh: A Public Health Concern

Islam

Hasan

Tiwari

et al. 2023

IJERPH

View full text Add to dashboard Cite

show abstract

Artificial Intelligence used in Pharmaceutical and Healthcare Industry: A Review

Sourajyoti Goswami,

Mohit Kumar Singh

2023

IJARSCT

View full text Add to dashboard Cite

The pharmaceutical and healthcare sectors have transformed thanks to AI, which has sped up innovation and efficiency in many areas. By anticipating prospective medication candidates and modeling their interactions with biological systems, AI quickens the procedure for finding and creating novel medications. Through tailored treatment, early illness diagnosis, and increased diagnostic precision, AI-driven data analysis improves patient care. Robotic surgery technologies driven by AI increase operation accuracy. Predictive analytics reduces medicine shortages and waste in the pharmaceutical supply chain. AI is essential in medication safety monitoring because it can spot possible problems. Virtual health assistants powered by AI offer round-the-clock assistance and information, while chatbots simplify arranging appointments and making medical questions. However, data privacy, legal compliance, and ethical issues still need to be addressed. The increasing convergence of AI and these industries has enormous potential to transform healthcare delivery and pharmaceutical innovation

show abstract

Secure Dengue Epidemic Prediction System: Healthcare Perspective

Cited by 2 publications

References 41 publications

Correlation of Dengue and Meteorological Factors in Bangladesh: A Public Health Concern

Correlation of Dengue and Meteorological Factors in Bangladesh: A Public Health Concern

Artificial Intelligence used in Pharmaceutical and Healthcare Industry: A Review

Contact Info

Product

Resources

About