Using artificial intelligence to improve public health: a narrative review

Frontiers in Public Health, Journal Year: 2023, Volume and Issue: 11

Published: Oct. 26, 2023

Artificial intelligence (AI) is a rapidly evolving tool revolutionizing many aspects of healthcare. AI has been predominantly employed in medicine and healthcare administration. However, public health, the widespread employment only began recently, with advent COVID-19. This review examines advances health potential challenges that lie ahead. Some ways aided delivery are via spatial modeling, risk prediction, misinformation control, surveillance, disease forecasting, pandemic/epidemic diagnosis. implementation not universal due to factors including limited infrastructure, lack technical understanding, data paucity, ethical/privacy issues.

Language: Английский

---

Geosocial Media’s Early Warning Capabilities Across US County-Level Political Clusters: Observational Study

JMIR Infodemiology, Journal Year: 2025, Volume and Issue: 5, P. e58539 - e58539

Published: Jan. 30, 2025

Background The novel coronavirus disease (COVID-19) sparked significant health concerns worldwide, prompting policy makers and care experts to implement nonpharmaceutical public interventions, such as stay-at-home orders mask mandates, slow the spread of virus. While these interventions proved essential in controlling transmission, they also caused substantial economic societal costs should therefore be used strategically, particularly when activity is on rise. In this context, geosocial media posts (posts with an explicit georeference) have been shown provide a promising tool for anticipating moments potential crises. However, previous studies early warning capabilities data largely constrained by coarse spatial resolutions or short temporal scopes, limited understanding how local political beliefs may influence capabilities. Objective This study aimed assess epidemiological COVID-19 vary over time across US counties differing beliefs. Methods We classified into 3 clusters, democrat, republican, swing counties, based voting from last 6 federal election cycles. we analyzed consecutive waves (February 2020-April 2022). specifically examined lag between signals surges cases, measuring both number days which preceded cases (temporal lag) correlation their respective series. Results differed clusters waves. On average, 21 republican compared 14.6 democrat 24.2 counties. general, were preceding 5 out all clusters. observed decrease that Furthermore, decline signal strength impact trending topics presented challenges reliability signals. Conclusions provides valuable insights strengths limitations tool, highlighting can change county-level Thus, findings indicate future systems might benefit accounting addition, declining role need assessed research.

Language: Английский

---

Artificial intelligence empowering public health education: prospects and challenges

Frontiers in Public Health, Journal Year: 2024, Volume and Issue: 12

Published: July 3, 2024

Artificial Intelligence (AI) is revolutionizing public health education through its capacity for intricate analysis of large-scale datasets and the tailored dissemination health-related information interventions. This article conducts a profound exploration into integration AI within health, accentuating scientific foundations, prospective progress, practical application scenarios. It underscores transformative potential in crafting individualized educational programs, developing sophisticated behavioral models, informing creation policies. The manuscript strives to thoroughly evaluate extant landscape applications scrutinizing critical challenges such as propensity data bias imperative safeguarding privacy. By dissecting these issues, contributes conversation on how can be harnessed responsibly effectively, ensuring that both ethically grounded equitable. paper's significance multifold: it aims provide blueprint policy formulation, offer actionable insights authorities, catalyze progression interventions toward increasingly precise approaches. Ultimately, this research anticipates fostering an environment where not only augments but also does so with steadfast commitment principles justice inclusivity, thereby elevating standard reach initiatives globally.

Language: Английский

---

Clustering-Based Joint Topic-Sentiment Modeling of Social Media Data: A Neural Networks Approach

Information, Journal Year: 2024, Volume and Issue: 15(4), P. 200 - 200

Published: April 4, 2024

With the vast amount of social media posts available online, topic modeling and sentiment analysis have become central methods to better understand analyze online behavior opinion. However, semantic rarely been combined for joint topic-sentiment which yields topics associated with sentiments. Recent breakthroughs in natural language processing also not leveraged so far. Inspired by these advancements, this paper presents a novel framework short texts based on pre-trained models clustering approach. The method leverages techniques from dimensionality reduction multiple algorithms were considered. All configurations experimentally compared against existing an independent sequential baseline. Our produced clusters quality scores up 0.23 while best score among previous approaches was 0.12. classification accuracy increased 0.35 0.72 uniformity sentiments within reached 0.9 contrast baseline 0.56. presented approach can benefit various research areas such as disaster management where provide practical useful information.

Language: Английский

---

An epidemiological modeling framework to inform institutional-level response to infectious disease outbreaks: a Covid-19 case study

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

Published: March 27, 2024

Abstract Institutions have an enhanced ability to implement tailored mitigation measures during infectious disease outbreaks. However, macro-level predictive models are inefficient for guiding institutional decision-making due uncertainty in local-level model input parameters. We present institutional-level modeling toolkit used inform prediction, resource procurement and allocation, policy implementation at Clemson University throughout the Covid-19 pandemic. Through incorporating real-time estimation of surveillance epidemiological based on data, we argue this approach helps minimize uncertainties parameters presented broader literature increases prediction accuracy. demonstrate through case studies other university settings Omicron BA.1 BA.4/BA.5 variant surges. The our easily adaptable future health emergencies. This methodological has potential improve public response increasing capability institutions make data-informed decisions that better prioritize safety their communities while minimizing operational disruptions.

Language: Английский

---

Internet-based Surveillance Systems and Infectious Diseases Prediction: An Updated Review of the Last 10 Years and Lessons from the COVID-19 Pandemic

Journal of Epidemiology and Global Health, Journal Year: 2024, Volume and Issue: 14(3), P. 645 - 657

Published: Aug. 14, 2024

Abstract The last decade has seen major advances and growth in internet-based surveillance for infectious diseases through advanced computational capacity, growing adoption of smart devices, increased availability Artificial Intelligence (AI), alongside environmental pressures including climate land use change contributing to threat spread pandemics emerging diseases. With the increasing burden COVID-19 pandemic, need developing novel technologies integrating data approaches improving disease is greater than ever. In this systematic review, we searched scientific literature research on or digital influenza, dengue fever from 2013 2023. We have provided an overview recent (EID), describing changes landscape, with recommendations future directed at public health policymakers, healthcare providers, government departments enhance traditional detecting, monitoring, reporting, responding dengue, COVID-19.

Language: Английский

---

A Binary Prototype for Time-Series Surveillance and Intervention

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 5, 2025

Abstract Despite much research on early detection of anomalies from surveillance data, a systematic framework for appropriately acting these signals is lacking. We addressed this gap by formulating hidden Markov-style model time-series surveillance, where the system state, observed and decision rule are all binary. incur delayed cost, c , whenever abnormal no action taken, or an immediate k with action, < . If costs too high, then detrimental, intervention should never occur. sufficiently low, always Only when intermediate low beneficial. Our equations provide assessing which approach may apply under range scenarios and, if warranted, facilitate methodical classification strategies. thus offers conceptual basis designing real-world public health systems.

Language: Английский

---

An explainable GeoAI approach for the multimodal analysis of urban human dynamics: a case study for the COVID-19 pandemic in Rio de Janeiro

Computational Urban Science, Journal Year: 2025, Volume and Issue: 5(1)

Published: March 3, 2025

The recent COVID-19 pandemic has underscored the need for effective public health interventions during infectious disease outbreaks. Understanding spatiotemporal dynamics of urban human behaviour is essential such responses. Crowd-sourced geo-data can be a valuable data source this understanding. However, previous research often struggles with complexity and heterogeneity data, facing challenges in utilisation multiple modalities explainability. To address these challenges, we present novel approach to identify rank multimodal time series features derived from mobile phone geo-social media based on their association infection rates municipality Rio de Janeiro. Our analysis spans April 6, 2020, August 31, 2021, integrates 59 features. We introduce feature selection algorithm Chatterjee's Xi measure dependence relevant an Área Programática da Saúde (health area) city-wide level. then compare predictive power selected against those identified by traditional methods. Additionally, contextualise information correlating scores model error 15 socio-demographic variables as ethnic distribution social development. results show that activity related COVID-19, tourism leisure activities was associated most strongly rates, indicated high up 0.88. Mobility consistently yielded low intermediate scores, maximum being 0.47. resulted better or equivalent performance when compared At health-area level, local generally selection. Finally, observed factors proportion Indigenous population development correlated both mobility health- leisure-related semantic topics media. findings demonstrate value integrating localised city-level epidemiological offer method effectively identifying them. In broader context GeoAI, our provides framework ranking features, allowing concrete insights prior building, enabling more transparency making predictions.

Language: Английский

---

The generative revolution: AI foundation models in geospatial health—applications, challenges and future research

International Journal of Health Geographics, Journal Year: 2025, Volume and Issue: 24(1)

Published: April 2, 2025

Language: Английский

---

Czech Anti-Covid Rules Evaluation

Lecture notes in electrical engineering, Journal Year: 2025, Volume and Issue: unknown, P. 537 - 546

Published: Jan. 1, 2025

Language: Английский

---