Artificial Intelligence and Public Health in new Era

Posted on by admin

ACHAIKI IATRIKI | 2025; 44(1):7–11

Editorial

Athanasia Palaiologou, Rafail Fokas, Apostolos Vantarakis

Department of Public Health, Medical School, University of Patras, Greece

Received: 14 Aug 2024; Accepted: 17 Sep 2024

Corresponding author: Apostolos Vantarakis, Tel.: +30 6945336243, E-mail: avanta@upatras.gr

Key words: Artificial intelligence, disease surveillance, prediction, risk analysis, personalized medicine, ethical frameworks, decision – making systems, healthcare management, resource optimization, telemedicine

 

INTRODUCTION

Artificial Intelligence (AI) has emerged as an effective and innovative technology in various and different sectors, including public health. It has rapidly been transformed into a tool revolutionizing numerous aspects of public health playing a significant role in it, mostly with its applications, benefits, several prospects but also with many challenges [1]. In this editorial, we explore the opportunities AI has predominantly offered in public health and healthcare administration and its future impact on disease prediction, epidemiology and healthcare quality (Table 1). Despite its capabilities in the healthcare domain, AI’s evolvement in public health systems also poses various ethical and technical challenges that will be considerably addressed. In recent years, the focus of AI in public health has been expanded mostly because of its potential, regarding big data processing, recognizing patterns and making predictive analysis [1]. Therefore, using AI may result in the enhancement of disease surveillance, efficient health interventions and the optimization of healthcare delivery.

Disease Surveillance and Prediction

Disease surveillance is a major component of AI in public health, offering the potential improvement of our ability to predict the spread of infectious diseases enabling the health care officials to take preventive mechanisms with the appropriate public health measures. In parallel, AI plays a significant role in the limitation of disease outbreaks before they occur contributing to an efficient disease surveillance system in public health [2].

More specifically, machine learning algorithms which consist of a branch of artificial intelligence enable AI to imitate the way that humans learn, improving its accuracy in time. Those algorithms can analyse big datasets from various sources including electronic health records (EHRs), databases on a global scale and social media targeting not only the prediction of disease outbreaks but also the ability to monitor ongoing threats. For instance, AI and Machine Learning (ML) were adequately applied to COVID-19 issues, including the identification and evaluation of clinical and social factors linked with the risk of COVID-19 cases and deaths, the advancement of spatial risk maps and eventually, the development of vaccination approaches [3].

The implications in epidemiology are to predict the future spread of diseases accurately. Especially, traditional methods related to statistical techniques are not sufficient enough and struggle to evolve patterns and capture complex information. AI, particularly machine learning algorithms, address the issue by identifying hidden relationships and detecting health related trends, thus producing more accurate predictions. They aim to provide early warnings and strategies for mitigating disease outbreaks. A considerable advancement is related to Google AI, which has developed a model that can predict the number of COVID-19 cases in each region up to two weeks in advance [4].

Personalized Medicine and Health Interventions

AI may analyze individual health data to provide healthcare recommendations promoting personalized medicine. In public health, this involves personalized interventions focused on disease prevention and health promotion at the population level. It aims to benefit personalized medicine by providing medical treatment to individuals based on factors like genetic profiles, lifestyles or environment.

Simultaneously, AI can contribute to the development of genetic analysis by processing genomic data to identify individuals at high risk of developing certain conditions. More specifically, the evaluation of vast amounts of genomic data gives the healthcare providers the opportunity to suggest measures regarding the prevention of the given situation. It can also efficiently contribute to early therapeutic protocols, especially when the aim is the management of chronic diseases [5]. An important application of AI in health intervention procedures are AI-tools applied in oncology which can analyze genetic tumors and can help to identify the best possible treatment plan on patients based on their genetic profiles.

Furthermore, AI plays an important role in enhancing the treatment precision by predicting how patients respond to various therapies. Based on the genetic profile of a specific individual, AI strengthens the possibility of predicting how this patient will respond to a particular drug. This fact is very beneficial for the options that are given to healthcare providers to select the most effective treatment, reducing multiple errors associated with the quest of the right treatment strategy [6].

Medical Diagnostics

Medical diagnostics evaluates medical conditions based on symptoms, medical history data, and test results. The main scope of medical diagnostics is the determination of the cause of a medical problem and provide an accurate diagnosis that benefits the patient, ensuring the correct treatment is administered.. AI plays a significant role in medical diagnostics, contributing to improvements to the prediction precision, accuracy and efficiency of the diagnostic procedures. AI algorithms can be utilized to analyse medical images and offer the opportunity for healthcare providers to effectively identify diseases as soon as massive amounts of patient data, demographic information, medical history data, and laboratory test results are being assessed. This is an important advantage considering the help healthcare providers can be provided to make more accurate decisions about patient care [7]. Especially, utilizing multiple data sources, a more complete understanding of a patient’s health can be succeeded as well as a more elaborating view regarding the causes of their symptoms. It is highly unlikely for misdiagnosis to occur by combining several and various data sources with the accuracy of diagnosis as a major result [7].

Health Systems and Resource Management

The optimization of healthcare delivery utilizing AI strategies can play a major role in improving resource allocation and management. Taking into consideration the needs in public health, this translates to more effective use of limited resources, such as hospital beds, medical supplies, and healthcare providers [8,9]. AI models give the possibility of the prediction of demands in healthcare services, aiming to supply public health personnel to allocate resources efficiently. At the same time, AI-driven decision support systems contribute to clinical decision-making resulting timely to appropriate patient care.

It is important that AI can be used in resource-poor settings as soon as AI systems can be utilized to benefit health programmes in various ways. AI has already played a major part in predicting, modelling and ceasing the spread of disease in epidemic situations worldwide, including in resource-poor settings. For instance, research has been made, leading to a ML tool for the identification of weather and land patterns linked with dengue fever transmission in Manila. That specific machine learning algorithm has learnt how to adjust its model to make predictions regarding dengue cases with high accuracy [10].

Prospects and Recommendations

One important perspective of AI in public health is related to its integration with other technologies. The evolvement of AI in the public health domain can strongly be associated with other imminent technologies, such as the Internet of Things (IOT) and big data analytics. Merging these technologies can effectively improve the capabilities of AI systems, enabling more comprehensive, secure and accurate public health interventions [11]. As an example,  the IOT can offer real-time health data to AI systems, improving disease monitoring and intervention procedures.

Moreover, another asset of AI in public health is the empowerment of ethical and regulatory frameworks. This is a recommendation which can be established with the development of specific and relevant guidelines for the ethical use of AI, setting the seal on the fact that sensitive data privacy and bias in AI algorithms are being secured [12]. Similarly, regulatory agencies are obliged to adapt to the challenges introduced by AI, providing supervision for the secure and adequate use of AI systems.

In addition, developing an adequate workforce is significant for the beneficial implementation of AI in public health sectors. This is a strategy that involves training healthcare professionals working in AI technologies as well as partnerships between governments, universities and the private sector which can introduce and support knowledge innovation, resulting in the adoption of AI in public health [13,14].

Considering the great significance of AI in the domain of public health, it is understood that it improves healthcare accessibility. In many parts of the world, one of the challenges public health faces is the lack of remote and automated healthcare services. This obstacle can be buried with the development of telemedicine platforms powered by AI which can diagnose and recommend treatments for common health cases by minimising the need of in-person visits to healthcare facilities, mostly in rural areas where medical services are sometimes scarce [15].

Limitations and Challenges

One of the primary challenges of integrating AI into public health are ethical matters related to data privacy. The requirement of AI systems to have access to a huge volume of personal health data, does how the data is gathered, stored, and utilized quite sensitive [16]. It is a matter of paramount importance to secure that AI systems are transparent and accountable regarding the individuals’ privacy.

Another limitation posed using AI in public health is the bias in AI algorithms. Specifically, AI algorithms are being used beneficially if the data they are trained on are accurate. In other words, considering the training data is biased, the AI system will also be biased, affecting negatively the patient outcomes and leading to unequal and untrustworthy results [17]. Google has developed a Testing with Concept Activation Vectors (TCAV) programme in which test decision-making algorithms are being used to reduce bias and gender discrimination [18]. As an example, to this issue is the fact that an AI model which is trained on data from a white population, it may not perform as well when applied to non-white patients.

The role of AI in public health systems introduces technical and logistical oppositions. More especially AI systems require significant computing analysis, massive data storage and skilled individuals to develop and maintain. Also, merging AI systems with existing health frameworks can be complex, rendering investment and coordination crucial [9].

AI in public health plays an important role in the addressing of regulatory and legal issues. As soon as current healthcare regulations are failing to present the challenges posed by AI, such as liability and accuracy for AI-driven decisions, the development of a regulatory base that assures the efficient utilization of AI in public health is excessively significant [19]. One important implication of facing such limitations is the procedure of training the application which may incorporate existing values and biases. Also, AI in healthcare can clash with data protection legislation, which in many situations requires only the collection of data associated with the purpose which is being examined [20].

CONCLUSION

Artificial intelligence promises a plethora of great and massive opportunities for public health, introducing new tools, approaches and strategies regarding disease surveillance, epidemiology, personalized medicine, and health systems management. Particularly, looking ahead, AI is set to evolve and expand even further if advances in AI technology will enable more accurate and sophisticated interventions. As follows it can play a major role in addressing global health challenges like climate change health impacts and it can help identify efficient strategies to combat such issues and improve population health on a global scale. All in all, AI promises great advances in public health from predicting disease outbreaks and generally improving healthcare to enhancing operational procedures. Considering the limitations concerning the ethical principles, it can be assumed that artificial intelligence can become a powerful ally in the quest for a healthier world.

Conflict of interest: The authors declare that there are no conflicts of interest associated with the publication of this editorial. The research was conducted independently, and the findings and opinions expressed herein are those of the authors alone. No financial or personal relationships with other people or organizations that could inappropriately influence (bias) the content of this publication have been identified.

Declaration of funding sources: None to declare.

Author contributions: AP, Literature review, Writing – Original Draft, Supervision; RF, Writing – Review & Editing; AP, Conceptualization, Supervision, – Review & Editing

REFERENCES
  1. Olawade DB, Wada OJ, David-Olawade AC, Kunonga E, Abaire O, Ling J. Using artificial intelligence to improve public health: a narrative review. Fron Public Health. 2023; 11:1196397.
  2. Zhao AP, Li S, Cao Z, Hu PJH, Wang J, Xiang Y, et al. AI for science: Predicting infectious diseases. JSSR. 2024; 5(2):130–46.
  3. Payedimarri AB, Concina D, Portinale L, Canonico M, Seys D, Vanhaecht K, et al. Prediction models for public health containment measures on covid-19 using artificial intelligence and machine learning: A systematic review.
    Int J Environ Res Public Health. 2021; 18(9):4499.
  4. Chakraborty C, Bhattacharya M, Pal S, Lee SS. From machine learning to deep learning: Advances of the recent data-driven paradigm shift in medicine and healthcare. Curr Res Biotechnol. 2024; 7:100164.
  5. Raparthi M. Deep Learning for Personalized medicine-Enhancing precision health with AI. JST. 2020; 1(1):82-90.
  6. Johnson KB, Wei WQ, Weeraratne D, Frisse ME, Misulis K, Rhee K, et al. Precision Medicine, AI, and the Future of Personalized Health Care. Clin Transl Sci. 2020;14(1):86–93.
  7. Al-Antari MA. Artificial Intelligence for Medical Diagnostics—Existing and Future AI Technology. Diagnostics. 2023; 13(4):688.
  8. Anesi GL, Kerlin MP. The impact of resource limitations on care delivery and outcomes: routine variation, the coronavirus disease 2019 pandemic, and persistent shortage. Curr Opin Crit Care. 2021;27(5):513–9.
  9. Maleki Varnosfaderani S, Forouzanfar M. The Role of AI in Hospitals and Clinics: Transforming Healthcare in the 21st Century. Bioengineering. 2024; 11(4):337.
  10. Cossy-Gantner A, Germann S, Schwalbe NR, Wahl B. Artificial intelligence (AI) and global health: How can AI contribute to health in resource-poor settings? BMJ Glob Health. 2018;3(4):e000798.
  11. Gouiza N, Jebari H, Reklaoui K, Essaâdi A. Integration of iot-enabled technologies and artificial intelligence in diverse domains: recent advancements and future trends. JATIT. 2024;102(5):1975-2029.
  12. Díaz-Rodríguez N, Del Ser J, Coeckelbergh M, López de Prado M, Herrera-Viedma E, Herrera F. Connecting the dots in trustworthy Artificial Intelligence: From AI principles, ethics, and key requirements to responsible AI systems and regulation. Information Fusion. 2023; 99:101896.
  13. Francisca Chibugo Udegbe, Ogochukwu Roseline Ebulue, Charles Chukwudalu Ebulue, Chukwunonso Sylvester Ekesiobi. The role of Artificial Intelligence in healthcare: A systematic review of applications and challenges. Int Medi Sci Res J. 2024;4(4):500–8.
  14. Morandini S, Fraboni F, De Angelis M, Puzzo G, Giusino D, Pietrantoni L. The impact of artificial intelligence on workers’ skills: Upskilling and Reskilling in organisations. Inf Sci. 2023; 26:39–68.
  15. Bekbolatova M, Mayer J, Ong CW, Toma M. Transformative Potential of AI in Healthcare: Definitions, Applications, and Navigating the Ethical Landscape and Public Perspectives. Healthcare. 2024; 12(2):125.
  16. Al-Hwsali A, Alsaadi B, Abdi N, Khatab S, Alzubaidi M, Solaiman B, et al. Scoping Review: Legal and Ethical Principles of Artificial Intelligence in Public Health. Stud Health Technol Inform. 2023; 305:640-3.
  17. Arora A, Alderman JE, Palmer J, Ganapathi S, Laws E, McCradden MD, et al. The value of standards for health datasets in artificial intelligence-based applications. Nat Med. 2023; 29(11):2929–38.
  18. Dr. Varsha P.S. How can we manage biases in artificial intelligence systems – A systematic literature review. Int J Inf Manag Data Insights. 2023;3(1):1-9.
  19. Mennella C, Maniscalco U, De Pietro G, Esposito M. Ethical and regulatory challenges of AI technologies in healthcare: A narrative review. Heliyon. 2024;10(4):e26297.
  20. McKee M, Wouters OJ. The Challenges of Regulating Artificial Intelligence in Healthcare Comment on “Clinical Decision Support and New Regulatory Frameworks for Medical Devices: Are We Ready for It? -A Viewpoint Paper.” Int J Health Policy Manag. 2023;12(1):7261.