Mapping the Heartbeat of America with ChatGPT-4: Unpacking the Interplay of Social Vulnerability, Digital Literacy, and Cardiovascular Mortality in County Residency Choices DOI Open Access
Mohammed M. Ali, Subi Gandhi, Samian Sulaiman

et al.

Journal of Personalized Medicine, Journal Year: 2023, Volume and Issue: 13(12), P. 1625 - 1625

Published: Nov. 21, 2023

Cardiovascular disease remains a leading cause of morbidity and mortality in the United States (US). Although high-quality data are accessible US for cardiovascular research, digital literacy (DL) has not been explored as potential factor influencing mortality, although Social Vulnerability Index (SVI) used previously variable predictive modeling. Utilizing large language model, ChatGPT4, we investigated variability CVD-specific that could be explained by DL SVI using regression We fitted two models to calculate crude adjusted CVD rates. Mortality ICD-10 codes were retrieved from CDC WONDER, geographic level was Department Agriculture. Both datasets merged Federal Information Processing Standards code. The initial exploration involved 1999 through 2020 (n = 65,791; 99.98% complete all Counties) (CCM). Age-adjusted (ACM) had 3118 rows; 99% Counties), with inclusion model (a composite internet access). By leveraging on advanced capabilities ChatGPT4 linear regression, successfully highlighted importance incorporating predicting mortality. Our findings imply just availability may sufficient without significant variables, such SVI, predict ACM. Further, our approach enable future researchers consider key variables study other health outcomes public-health importance, which inform clinical practices policies.

Language: Английский

Assessing and correcting neighborhood socioeconomic spatial sampling biases in citizen science mosquito data collection DOI Creative Commons
Álvaro Padilla‐Pozo, Frederic Bartumeus, Tomás Montalvo

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Sept. 28, 2024

Language: Английский

Citations

2
Flood risk assessment of coastal cities based on GCW_ISODATA and explainable artificial intelligence methods DOI

Yawen Zang,

Huimin Wang, Zhenzhen Liu

et al.

International Journal of Disaster Risk Reduction, Journal Year: 2024, Volume and Issue: unknown, P. 105025 - 105025

Published: Nov. 1, 2024

Language: Английский

Citations

2
Potential impacts of storm surge-induced flooding based on refined exposure estimation: a case study in Zhoushan island, China DOI Creative Commons

Bairu Chen,

Junyu He, Zhiguo He

et al.

Geomatics Natural Hazards and Risk, Journal Year: 2023, Volume and Issue: 14(1)

Published: July 7, 2023

Storm surge-induced flooding (SSIF) is a major hazard for coastal areas under intensified typhoons. Therefore, it essential to assess the potential impacts of SSIF (SSPIA). This study proposes multidisciplinary framework refined SSPIA using an ocean model and exposure estimation method. First, finite-volume (FVCOM) typhoon were developed validated. Then, five scenarios varying intensity defined combined with FVCOM identify inundation scenarios. Subsequently, machine learning was used obtain fine-scale gridded population gross domestic product (GDP) maps based on census geospatial data. Finally, we assessed magnitude affected GDP datasets. We selected Zhoushan Island as area implement this framework. Our assessment results show that lowest scenario (955 hPa) 2587 people 323.745 million CNY GDP, while highest (915 259,516 20,178.898 GDP. imperative effective mitigation adaptation measures address threat SSIF. will apply all flood-prone

Language: Английский

Citations

5
Social Justice in Urban–Rural Flood Exposure: A Case Study of Nanjing, China DOI Creative Commons
Yi Chen, Hui Liu,

Zhicong Ye

et al.

Land, Journal Year: 2022, Volume and Issue: 11(9), P. 1588 - 1588

Published: Sept. 16, 2022

The environmental justice research on urban–rural exposure to flooding is underdeveloped and few empirical studies have been conducted in China. This study addresses this gap by exploring the probabilities of floods (10-, 20-, 50-year) examining relationship between vulnerable groups Nanjing, an important central city Yangtze River. Statistical analysis based multivariable generalised estimating equation (GEE) models that describe sociodemographic disparities at census-tract level. results revealed (1) highly educated people urban centre are more likely live areas with high flood risk because abundance education resources, employment opportunities concentrated centre. (2) Natives suburban flood-prone due their favourable ecological environments near rivers lakes. (3) Women rural high-flood-risk zones most men migrant workers. These findings highlight urgent need develop mitigation strategies reduce exposure, especially districts proportions socially disadvantaged people. linkages be strengthened order exposure.

Language: Английский

Citations

7
Mapping the Heartbeat of America with ChatGPT-4: Unpacking the Interplay of Social Vulnerability, Digital Literacy, and Cardiovascular Mortality in County Residency Choices DOI Open Access
Mohammed M. Ali, Subi Gandhi, Samian Sulaiman

et al.

Journal of Personalized Medicine, Journal Year: 2023, Volume and Issue: 13(12), P. 1625 - 1625

Published: Nov. 21, 2023

Cardiovascular disease remains a leading cause of morbidity and mortality in the United States (US). Although high-quality data are accessible US for cardiovascular research, digital literacy (DL) has not been explored as potential factor influencing mortality, although Social Vulnerability Index (SVI) used previously variable predictive modeling. Utilizing large language model, ChatGPT4, we investigated variability CVD-specific that could be explained by DL SVI using regression We fitted two models to calculate crude adjusted CVD rates. Mortality ICD-10 codes were retrieved from CDC WONDER, geographic level was Department Agriculture. Both datasets merged Federal Information Processing Standards code. The initial exploration involved 1999 through 2020 (n = 65,791; 99.98% complete all Counties) (CCM). Age-adjusted (ACM) had 3118 rows; 99% Counties), with inclusion model (a composite internet access). By leveraging on advanced capabilities ChatGPT4 linear regression, successfully highlighted importance incorporating predicting mortality. Our findings imply just availability may sufficient without significant variables, such SVI, predict ACM. Further, our approach enable future researchers consider key variables study other health outcomes public-health importance, which inform clinical practices policies.

Language: Английский

Citations

4