AI technologies have revolutionized various sectors, and healthcare is no exception. AI algorithms, including Machine Learning (ML) and Deep Learning (DL), can analyze vast amounts of medical data, identify patterns, and make informed decisions that would otherwise require extensive manual analysis [2]. In healthcare, AI is already applied to disease diagnosis, treatment planning, and predictive analytics tasks. For instance, AI-based tools like IBM Watson health use advanced Natural Language Processing (NLP) to extract valuable insights from unstructured patient data and help physicians make more accurate decisions. Moreover, AI enables predictive modeling, allowing healthcare providers to anticipate patient needs and manage resources more efficiently, thus contributing to smarter healthcare systems.

The IoT can revolutionize healthcare by enabling real-time monitoring and continuous patient care. IoT-based devices such as wearable sensors, smart implants, and connected medical equipment facilitate the seamless collection of patient data. When integrated into a centralized system, this data gives healthcare professionals a holistic view of a patient's health, allowing for timely interventions and personalized treatment plans. IoT devices improve patient monitoring and reduce hospital readmissions, as continuous remote monitoring helps in the early detection of complications. For example, smart wearable devices can track vital signs such as heart rate, oxygen levels, and blood pressure, alerting healthcare providers to potential issues before they become critical.

Despite having access to more advanced medical technologies, urban areas often suffer from healthcare disparities. Population density in cities leads to overcrowded hospitals, long waiting times, and a shortage of healthcare professionals. Additionally, urban populations often experience a higher prevalence of chronic conditions such as diabetes, cardiovascular diseases, and respiratory disorders due to lifestyle factors and environmental conditions. The increasing burden on healthcare systems in cities necessitates a shift toward more efficient, scalable, and responsive solutions. Traditional healthcare systems, which are often reactive, fail to meet the growing needs of urban populations. To mitigate these challenges, a more proactive approach that leverages AI and IoT can play a crucial role in the future of urban healthcare systems.

AI and IoT are complementary technologies that can significantly enhance the effectiveness of smart healthcare solutions. While IoT devices gather large amounts of patient data, AI algorithms can process and analyze this data to generate actionable insights. This synergy between AI and IoT enables the creation of real-time health monitoring systems capable of diagnosing and treating conditions more effectively than conventional methods. For example, a patient with a chronic illness can use wearable IoT devices that continuously track their health metrics. AI algorithms can analyze the data collected to detect anomalies, which are then communicated to healthcare providers for immediate action. This proactive healthcare approach ensures timely interventions, reducing the likelihood of severe health outcomes.

In a smart city, services are delivered to resolve the issues faced by residential surroundings [2]. The practical systems consist of hospital services and health monitoring services. The concept of remote sensing is commonly used in healthcare monitoring services and has many research applications [3]. Core to the smart city healthcare system is a Patient Record Management Center (PRMC) that helps collect, manage, and preserve patients' electronic Fig. 1. Basic elements of an IoT-enabled smart city healthcare system. Electronic Health Records (EHRs) [4].

Remote sensing plays a crucial role in healthcare monitoring services within smart cities. Veenis and Brugts [3] noted that remote sensing involves using sensors placed on or near the patient to monitor physiological signals like heart rate, blood pressure, glucose levels, and more. These sensors communicate with central healthcare systems, allowing for continuous, real-time tracking of patients' health status without requiring them to visit a hospital or clinic. Remote sensing also enables early detection of potential health issues, improving preventive care and reducing emergency admissions.

In addition to wearable health devices, remote sensing monitors environmental factors that may impact public health, such as air quality, noise pollution, and urban heat islands. This data is essential for urban healthcare planning and predicting public health risks in densely populated areas. Remote sensing technologies have been applied in various healthcare applications, including managing chronic conditions like cardiovascular diseases and diabetes, which are prevalent in urban populations.

In summary, integrating IoT, remote sensing, and centralized EHR systems forms the backbone of smart city healthcare solutions. These technologies enable continuous health monitoring, better resource management, and personalized care, making healthcare services more responsive and efficient in urban areas. By leveraging data from remote sensing and wearable devices, healthcare providers can monitor patient health in real-time and make informed decisions that improve patient outcomes. Centralized patient data management through the PRMC ensures patient records are always accessible, contributing to better care coordination and long-term health management.

Sensors, monitoring, and control are required to make healthcare cities smarter. These sensors' feedback values help healthcare providers conduct monitoring and control through automation. These sensors' feedback values help healthcare providers monitor and control through automation. The IoT, wireless sensor networks, DL, and other technologies can be used successfully to accomplish these goals [5]. Smart cities can quickly meet people's healthcare needs by accessing real-time information. Healthcare providers can make quick decisions that yield positive results. IoTs, AI, and computing technology have changed the face of healthcare [6]. Sensors such as smartwatches can be implanted or worn on the body's surface. Connections are made to healthcare providers through gateways and wireless networks with data transmitted [7]. The implanted sensors, such as electrochemical glucose sensors, help monitor and control diabetes [8]. Patients also self-manage and personalize their diabetes using AI devices.

Sensors can transmit data to smartphones, and patients with DM can use these systems to monitor their blood glucose levels [9]. Several other advanced sensors control sleep apnea, rheumatoid, cranial pressure, and heart arrhythmias [10]. The main limitations of these devices are in operations and management. The people in charge may not have the required education or forget to charge the devices. This makes adopting Zero Effects Technologies (ZETs) essential to free the user from the tasks needed to operate and manage the sensor devices [6]. Remote sensing helps monitor various diseases, such as cardiovascular diseases and dementia. Behavioral monitoring is an essential process in treating such disease categories.

According to one estimate, 47 million people were affected by dementia in 2017, and this number is projected to increase to 132 million by 2050 [8]. Advanced remote sensing systems, with assistance from the IoT and AI, would ease the monitoring and control needed to treat these diseases effectively.

The health monitoring service is a system that obtains information from the medical sensors attached to the patient's body and the smart device of the custodian. The Health Monitoring Server (HMS) serves as the controller; it delivers an Individualized Healthcare Plan (IHP) in real-time through an analysis of the current health situation and historical records [11]. It also generates signal notifications, warnings, and exceptions during periods involving critical situations. The smart service's essential elements include health monitoring service for evaluation and oversight, hospital service for procuring health problem identification, and instant reaction. At the same time, the PRMC deals with storing and utilizing information. The health monitoring system serves the IHP in real-time. The hospital system permits medical specialists to make inferences on the patient's health status concerning the documented report delivered by HMS and the past health records obtained from the PRMC, where all personal records are kept.

The PRMC is a central storehouse in which all the health records and data of patients and the prevailing health conditions in patients' digital health records are kept [11]. It also delivers the necessary information-carrying headers of constraints and protocols to other systems connected to it. The health monitoring service also has local storage. This storage holds the patient's medical history and health records as the main requirement for a simplified technology architecture for smart healthcare service.

The Patient Central Electronic Health Record (PC-EHR) is versatile storage that embodies patients' past health records and detailed information, such as name, address, phone number, etc.

AI has increasingly been recognized as a transformative tool for improving healthcare outcomes. According to [12], AI technologies, especially ML and DL, have demonstrated exceptional capabilities in diagnosing diseases, interpreting medical images, and even predicting patient outcomes. These algorithms analyze vast datasets, identify patterns, and enable physicians to make data-driven decisions, leading to better diagnostic accuracy and reduced human error in clinical settings. For instance, Jiang and Chen [13] found that AI-powered systems could diagnose skin cancer with accuracy comparable to that of board-certified dermatologists, suggesting that AI could play a pivotal role in early disease detection.

Beyond diagnostics, AI's role in predictive analytics has gained traction in urban healthcare. Shickel et al. [15] highlight that AI-based predictive models can be used to forecast disease outbreaks in densely populated urban areas by analyzing environmental and social determinants of health. These models allow healthcare providers to anticipate patient needs, optimize resource allocation, and implement preventive measures more effectively. However, several studies, including those by [15], emphasize that while AI can significantly enhance decision-making processes, its efficacy is contingent on the quality and diversity of the data used in training models. Many AI applications in healthcare are still hindered by biased datasets, which can lead to unequal health outcomes across different demographic groups.

IoT technology has introduced new avenues for continuous health monitoring and remote patient management, particularly in urban settings where access to healthcare facilities may be constrained by distance or overcrowding. Research by [16] illustrates that wearable IoT devices, such as smartwatches and biosensors, can monitor vital signs (e.g., heart rate, blood pressure, glucose levels) in real-time, enabling early detection of health anomalies and reduce the likelihood of acute medical events. Using such IoT devices is especially beneficial for managing chronic diseases, such as diabetes and cardiovascular conditions, which are prevalent in urban populations due to lifestyle and environmental factors [17].

Furthermore, IoT has proven valuable in enhancing hospital resource management. According to [18], IoT-based systems can monitor medical equipment usage, bed availability, and inventory levels, improving operational efficiency in urban hospitals. These systems have been instrumental in minimizing resource wastage and ensuring that critical medical supplies are available when needed. Similarly, [19] found that IoT-enabled smart healthcare systems, when integrated with cloud computing, can securely transmit patient data to healthcare providers in real-time, facilitating timely medical interventions. However, they also noted that the scalability and interoperability of IoT devices remain significant challenges, particularly in urban settings with diverse healthcare infrastructure.

The synergy between AI and IoT has been the subject of growing interest due to its potential to enhance healthcare systems through real-time, data-driven solutions. Patel et al. [20] posit that combining AI's data-processing power with IoT's real-time data collection capabilities can significantly improve healthcare delivery. For example, AI can analyze data collected from IoT devices to predict disease progression and recommend personalized treatment plans, reducing hospital readmissions and improving patient outcomes. Similarly, Kaur et al. [21] highlight that AI-IoT integration enables remote health monitoring systems that are particularly valuable for elderly patients and those with chronic conditions, allowing them to receive continuous care without frequent hospital visits.

Research by [22] points to the successful implementation of AI-IoT-based systems in smart cities, where healthcare is integrated with other urban services such as transportation and emergency management. AI algorithms can predict and manage health crises in these cities, such as pandemics or disease outbreaks, by analyzing data from IoT devices distributed across urban areas. This has been exemplified during the COVID-19 pandemic, where AI-IoT systems were used to monitor the spread of the virus, manage hospital resources, and track patient recovery rates [23].

Despite these advancements, integrating AI and IoT into healthcare is challenging. One of the major concerns is data security and privacy, as highlighted by [24]. The massive volumes of sensitive health data generated by IoT devices are vulnerable to cyberattacks, which can compromise patient confidentiality and safety. Data breaches not only threaten individual privacy but can also erode public trust in smart healthcare systems. Furthermore, the issue of interoperability between different IoT devices and AI platforms remains unresolved. As [25] pointed out, the lack of standardized protocols for communication between devices from other manufacturers can lead to fragmented systems that are difficult to scale.

While AI and IoT offer numerous benefits to urban healthcare systems, several challenges remain. First, the cost of implementing AI and IoT solutions is a significant barrier, especially in low and middle-income urban areas where healthcare infrastructure is already underfunded. According to [26], the initial investment required to install IoT devices, data storage systems, and AI-based analytics tools can be prohibitively high for many healthcare providers. This raises concerns about the equity of access to smart healthcare technologies, as wealthier urban areas may benefit disproportionately from these innovations compared to less affluent regions.

Second, ethical concerns related to the use of AI in healthcare are becoming more prominent. Jobin et al. [27] argue that AI-based systems could reinforce existing biases in healthcare delivery if not adequately regulated. For instance, AI models trained on biased data may lead to discriminatory practices, especially in urban areas with diverse populations. Ensuring that AI systems are transparent, explainable, and fair is essential to avoid exacerbating health disparities.

Lastly, the technological infrastructure required to support AI and IoT integration remains a significant challenge, particularly in older urban areas with outdated healthcare facilities. As [28] point out, upgrading existing infrastructure to accommodate these technologies may require substantial financial and logistical investments, which may be beyond the reach of many cities.