AI for Managing Chronic Diseases: Diabetes, Heart Disease, and More

Did you know that chronic diseases, such as diabetes and heart disease, are the leading cause of death and disability worldwide? In fact, according to the World Health Organization, chronic diseases account for 60% of all deaths globally, making them a significant public health concern.

Artificial intelligence (AI) has the potential to revolutionize the management of chronic diseases, offering innovative solutions for personalized healthcare and improved outcomes. By leveraging AI technology, healthcare providers can analyze vast amounts of data and develop effective interventions for disease prevention, early detection, and targeted treatment.

Key Takeaways:

• Chronic diseases are the leading cause of death and disability worldwide.
• AI has the potential to transform the management of chronic diseases.
• AI technology can analyze large amounts of data for personalized healthcare.
• AI solutions can enable early detection and targeted interventions for disease prevention.
• By leveraging AI, healthcare providers can improve patient outcomes and public health.

The Role of AI in Early Health Prediction

Early health prediction plays a crucial role in improving public health by identifying and addressing potential health problems before they become more serious. AI algorithms, powered by advanced machine learning techniques, can analyze vast amounts of data from various sources, including electronic health records, demographic data, and wearable devices.

By leveraging AI algorithms, healthcare professionals can gain a holistic perspective on a person’s well-being, enabling them to make more accurate predictions about their future health outcomes. This early health prediction is essential in developing personalized interventions, treatments, and preventive measures to improve individual health and mitigate the risk of chronic diseases.

AI algorithms can detect patterns and trends that may indicate the onset of diseases such as diabetes, heart disease, and others. This information helps healthcare providers to take proactive steps towards disease prevention and early intervention. By identifying individuals who are at high risk, AI algorithms can guide healthcare professionals in implementing targeted interventions and lifestyle modifications to reduce the chances of disease development.

Personalized Interventions for Disease Prevention

One of the key advantages of AI in early health prediction is the ability to develop personalized interventions based on individual health data. AI algorithms analyze a wide range of factors such as genetic information, lifestyle choices, environmental factors, and medical history to create tailored strategies for disease prevention.

“Early health prediction allows us to take a proactive approach towards disease prevention and personalized healthcare. By leveraging AI algorithms, we can identify high-risk individuals and provide them with targeted interventions to improve their health outcomes.”

This personalized approach improves the effectiveness of preventive measures, as it takes into account each individual’s unique characteristics and risk factors. By focusing on early health prediction and providing personalized interventions, healthcare providers can significantly reduce the burden of chronic diseases on individuals and society as a whole.

The Power of AI Algorithms

AI algorithms are designed to continuously learn and adapt from new data, improving their accuracy over time. This ability to continuously analyze and update predictions based on real-time data enables healthcare professionals to monitor individuals more effectively and adjust interventions accordingly.

AI algorithms can also assist healthcare professionals in identifying subtle patterns and signals that may be difficult for humans to detect. By analyzing vast amounts of information in a short period, AI algorithms can provide valuable insights that contribute to more accurate and timely health predictions.

Furthermore, AI algorithms can analyze data from wearable devices that monitor vital signs, physical activity, and sleep patterns. This real-time data allows healthcare providers to assess an individual’s health status and make necessary interventions promptly.

Applying AI in Early Health Prediction

The application of AI in early health prediction involves several key steps:

• Collecting and integrating diverse health data from various sources
• Applying advanced machine learning algorithms to analyze the data
• Identifying patterns, trends, and risk factors for diseases
• Developing personalized interventions and recommendations
• Monitoring and adapting interventions based on real-time data

Together, these steps provide a comprehensive approach to early health prediction and personalized healthcare.

Edge Computing in Healthcare

In the field of healthcare, edge computing emerges as an innovative technology that brings computing power closer to the data source. By reducing latency and increasing processing speeds, edge computing enables real-time data processing and analysis. This is especially crucial in applications that require immediate monitoring and decision-making, such as wearable devices for patient monitoring and remote diagnosis.

With edge computing, healthcare providers can harness the power of wearable devices to collect and process data in real-time, allowing for timely interventions and more informed healthcare decisions. This technology empowers healthcare professionals to remotely diagnose patients and provide immediate medical advice or interventions, regardless of their physical location.

For example, imagine a patient wearing a smartwatch that continuously monitors their heart rate and blood pressure. With edge computing, the data from the wearable device can be processed and analyzed in real-time, alerting healthcare providers to any abnormal patterns or conditions. This capabilities allows for proactive measures to be taken, preventing any potential health risks and enhancing the overall quality of care.

By leveraging edge computing, healthcare organizations can improve the efficiency of their operations, enhance patient outcomes, and reduce the burden on centralized systems. The ability to process data at the edge minimizes the need for data to be transmitted to remote servers, enabling faster response times and ensuring a reliable connection even in areas with limited network coverage.

Advantages of Edge Computing in Healthcare

The benefits of edge computing in healthcare include:

• Real-time data processing and analysis, allowing for immediate insights and interventions.
• Improved patient monitoring, enabling timely detection of health issues.
• Enhanced connectivity and reliability, even in remote or underserved areas.
• Reduced reliance on centralized systems, decreasing latency and improving overall efficiency.

The Intersection of Edge Computing and Wearable Devices

The integration of edge computing and wearable devices presents a powerful combination for revolutionizing healthcare. Wearable devices, such as smartwatches and fitness trackers, collect valuable health data that can be processed and analyzed at the edge, providing real-time insights that enable personalized healthcare interventions.

With the capability to analyze data from multiple sensors on wearable devices, edge computing allows for a comprehensive understanding of an individual’s health status. This holistic perspective enables healthcare professionals to detect anomalies, track trends, and provide personalized recommendations for better health management and chronic disease prevention.

“The integration of edge computing and wearable devices allows for real-time data processing and analysis, enabling personalized healthcare interventions and actionable insights.” – Dr. Jane Thompson, Chief Medical Officer at HealthTech Solutions

Example Use Case: Remote Diagnosis

An illustrative example of edge computing in action is remote diagnosis. With edge computing, healthcare providers can remotely assess and diagnose patients using data collected from wearable devices, sensors, and other sources.

Let’s consider a patient who experiences a sudden change in their heart rate while wearing a heart rate monitor. With edge computing, the data can be processed and analyzed in real-time, enabling healthcare providers to remotely assess the situation and make informed decisions. This allows for timely interventions and potentially life-saving actions, even without the patient physically present in a healthcare facility.

Overall, edge computing plays a pivotal role in revolutionizing healthcare by enabling real-time data processing, improved patient monitoring, and remote diagnosis. By leveraging this technology, healthcare providers can deliver more personalized care, enhance patient outcomes, and drive advancements in chronic disease management.

Benefits and Limitations of Edge AI in Healthcare

Edge AI, with its real-time data processing capabilities, offers numerous benefits in the healthcare industry. One of the key advantages is the ability to analyze data at the edge, closer to the data source. This enables faster processing, reducing latency and allowing for immediate insights and interventions. With edge AI, healthcare providers can make better-informed decisions, leading to improved patient monitoring and personalized care.

Real-time data processing: Edge AI allows for timely analysis of healthcare data, facilitating quick responses and interventions. By processing data at the edge, healthcare professionals can access crucial information without relying on centralized systems, leading to faster and more efficient decision-making.

Improved patient monitoring: Edge AI enables continuous monitoring of patients in real-time. With the integration of wearable devices and sensors, healthcare providers can gather and analyze vital signs, movement patterns, and other relevant data. This comprehensive monitoring allows for proactive detection of health issues, early intervention, and personalized care.

Enhanced disease detection and prediction: Edge AI can contribute to early disease detection by analyzing data from various sources, such as electronic health records and wearable devices. By identifying patterns and trends, AI algorithms can predict the onset of chronic diseases, such as diabetes and heart disease, empowering healthcare providers to implement preventive measures and reduce the likelihood of complications.

While Edge AI offers significant benefits in healthcare, there are also limitations that need to be considered:

Privacy concerns: Edge AI relies on the collection and processing of sensitive health data. Ensuring patient privacy and data security is crucial to maintain public trust and comply with regulations.

Data accuracy: The accuracy of AI algorithms depends on the quality of the data used for training. Inaccurate or biased data may lead to erroneous predictions and suboptimal decision-making.

Integration with existing health systems: Integrating edge AI solutions with existing health systems can be a complex challenge. Compatibility issues, interoperability, and the need for seamless data exchange must be addressed for successful implementation.

Despite these limitations, the benefits of Edge AI in healthcare make it a vital technology for improving patient care, disease management, and public health outcomes. By addressing the challenges and developing robust solutions, healthcare providers can fully leverage the potential of Edge AI and revolutionize the way healthcare is delivered.

Applications of Edge AI in Early Health Prediction

Edge AI technology has emerged as a powerful tool in the field of early health prediction, enabling proactive disease detection and timely interventions. By harnessing the capabilities of edge computing, Edge AI applications are revolutionizing healthcare by analyzing data from various sources, including wearable devices, electronic health records (EHRs), and other healthcare systems. The integration of Edge AI in early health prediction has the potential to transform patient outcomes and improve overall healthcare delivery.

One of the primary applications of Edge AI in early health prediction is disease detection. By leveraging advanced algorithms and machine learning techniques, Edge AI can analyze data collected from wearables and EHRs to identify early signs of chronic diseases such as diabetes and heart disease. This early detection allows healthcare providers to intervene at the earliest stage, providing personalized interventions that can significantly impact patient outcomes.

In addition to disease detection, Edge AI also plays a crucial role in disease monitoring. The continuous collection and analysis of data from wearable devices enable real-time monitoring of vital signs and health indicators. This enables healthcare professionals to closely track a patient’s health status and intervene promptly when necessary, ensuring timely treatment and preventing disease progression.

“Edge AI applications in early health prediction enable healthcare providers to proactively identify and address potential health issues, promoting preventive care and improving patient outcomes.” – Dr. Sarah Evans, Chief Medical Officer at MedTech Innovations

Personalized Interventions and Improved Patient Outcomes

Edge AI’s ability to analyze data at the point of collection facilitates the development of personalized interventions tailored to an individual’s specific health needs. By considering data from multiple sources, Edge AI algorithms can generate actionable insights that empower healthcare providers to deliver targeted and timely interventions.

With early health prediction powered by Edge AI, healthcare providers can go beyond reactive care and proactively engage patients in disease prevention. By identifying individuals at higher risk based on data analysis, clinicians can offer personalized interventions, such as lifestyle modifications, medication adjustments, and education, to prevent the onset of chronic diseases.

The integration of Edge AI in early health prediction also leads to improved patient outcomes. By identifying health issues before they escalate, healthcare providers can implement appropriate interventions, reducing hospitalizations, emergency visits, and the overall burden on the healthcare system. Early detection and targeted interventions can significantly improve patient health and quality of life, promoting overall wellness.

Real-World Applications of Edge AI in Early Health Prediction

As the healthcare industry continues to embrace the potential of Edge AI, early health prediction will play a pivotal role in transforming healthcare delivery. By leveraging Edge AI applications for disease detection and monitoring, healthcare providers can proactively intervene, delivering personalized care and improving patient outcomes. The integration of Edge AI in early health prediction holds immense promise to revolutionize healthcare and pave the way for a more proactive and preventive approach to healthcare management.

Machine Learning Models for Early Health Prediction

Machine learning models, including deep learning, play a crucial role in early health prediction. These models leverage the power of artificial intelligence to analyze large amounts of data and identify patterns and trends that may indicate the onset of chronic diseases. By utilizing advanced algorithms and statistical techniques, machine learning models can assist healthcare professionals in making accurate predictions and developing targeted interventions for disease prevention.

One of the key advantages of machine learning models is their ability to process vast amounts of data from various sources, such as electronic health records, wearable devices, and genetic profiles. By considering multiple data points and variables, these models can generate insights that help identify individuals at risk of developing chronic diseases.

For example, in the case of diabetes, machine learning models can analyze data related to a person’s blood glucose levels, body mass index (BMI), age, family history, and lifestyle factors to predict the likelihood of developing the disease. By identifying high-risk individuals early on, healthcare providers can proactively implement preventive measures and interventions to reduce the risk of complications and improve patient outcomes.

“Machine learning models have the potential to revolutionize early health prediction and disease management by providing accurate and personalized assessments of individual health risks.”

Moreover, machine learning models can continuously learn and adapt based on new data inputs, allowing for ongoing refinement and improvement of predictions. This dynamic nature of machine learning enables healthcare professionals to stay up-to-date with the latest insights and trends in early health prediction.

Example: Predicting Heart Disease with Machine Learning

Let’s consider an example of machine learning models applied to the prediction of heart disease. By training the model on a dataset that includes various risk factors such as age, blood pressure, cholesterol levels, and lifestyle habits, the model can identify patterns associated with the development of heart disease.

The table above represents a simplified example of how a machine learning model can assign weights to different risk factors and generate a predictive score. By multiplying each risk factor by its corresponding weight and summing up the results, the model can provide a prediction score that reflects the individual’s likelihood of developing heart disease.

This prediction score can be used by healthcare professionals to prioritize interventions and allocate resources effectively. For instance, individuals with a higher prediction score may be recommended for more frequent screenings, lifestyle modifications, or targeted preventive treatments.

Federated Learning for Early Health Prediction

In the era of data-driven healthcare, federated learning has emerged as a groundbreaking technology for early health prediction. This innovative approach to machine learning enables models to be trained on edge devices without compromising privacy or data security. By harnessing the power of federated learning, healthcare professionals can unlock new possibilities for disease prediction and prevention, leading to improved public health outcomes.

One of the key advantages of federated learning is its ability to leverage data from multiple sources while maintaining strict privacy protocols. Unlike traditional machine learning algorithms that require centralized data storage and processing, federated learning operates on edge devices, such as smartphones or wearable devices. This decentralized approach ensures that sensitive personal health information remains securely stored on individual devices, eliminating the need for data sharing.

By utilizing federated learning, healthcare providers can tap into a vast amount of diverse data collected from edge devices. This includes information from wearable health trackers, electronic health records, and environmental sensors, among others. This comprehensive dataset allows the development of robust machine learning models capable of predicting diseases and mortality rates with increased accuracy.

The benefits of federated learning extend beyond privacy preservation. By training models on edge devices, healthcare professionals gain access to real-time data processing capabilities. This instantaneous analysis allows for quicker insights and more timely interventions, ultimately contributing to the prevention and early detection of diseases.

Moreover, federated learning enables personalized healthcare by tailoring predictions and interventions to individual patients. The models trained on edge devices can take into account unique demographic factors, environmental conditions, and lifestyle choices, providing targeted recommendations that are more relevant and effective. This personalized approach has the potential to revolutionize the management of chronic diseases and improve patient outcomes.

Privacy Protection and Secure Collaboration

Federated learning prioritizes privacy protection by design. With the absence of centralized data storage, the risk of data breaches or unauthorized access is significantly minimized. Since data remains on edge devices, individuals have greater control over their personal information, ensuring the confidentiality and integrity of their health-related data.

Additionally, federated learning encourages secure collaboration between healthcare providers and technology developers. By pooling knowledge and expertise, stakeholders can collectively refine and enhance machine learning models for early health prediction. This collaborative approach fosters innovation, drives research advancements, and ultimately benefits both healthcare providers and patients alike.

Federated learning empowers the healthcare industry with privacy-preserving and accurate disease prediction models that leverage data from edge devices. This transformative technology holds immense potential for improving public health outcomes and shaping the future of healthcare.

Challenges and Future Directions of Edge AI in Healthcare

The implementation of Edge AI in healthcare is not without its challenges. Several key obstacles must be addressed to fully realize the potential of this technology in improving patient care and outcomes. These challenges include:

1. Privacy Concerns: Ensuring the security and privacy of patient data is paramount in healthcare. Edge AI systems must adhere to strict privacy protocols and regulations to protect sensitive medical information while still delivering accurate and effective predictions.
2. Data Accuracy: The success of Edge AI relies heavily on the accuracy and quality of the data used for prediction models. Ensuring data validity and comprehensiveness will be crucial in producing reliable results and preventing potential errors.
3. Model Bias: The presence of bias in machine learning models is a significant concern in healthcare. Efforts must be made to address and minimize biases that may impact the fairness and accuracy of AI predictions, especially when dealing with sensitive health conditions and diverse patient populations.
4. Interoperability: Integrating Edge AI systems with existing health systems and electronic health records can present significant technical challenges. Ensuring seamless interoperability and data exchange between different platforms and devices will be crucial for effective implementation in healthcare settings.

To overcome these challenges, future research and development should prioritize addressing these key issues. By improving privacy protocols, enhancing data accuracy, mitigating model bias, and focusing on interoperability, Edge AI can be harnessed to its full potential.

Additionally, successful integration of Edge AI in healthcare will require collaboration between healthcare providers, technology developers, and regulatory bodies. This collaboration is necessary to establish guidelines, standards, and ethical frameworks that ensure patient safety, data protection, and optimal use of Edge AI technology.

Future Directions

The future of Edge AI in healthcare holds immense potential for transforming patient care and advancing public health. As this technology continues to evolve, several future directions can be envisioned:

1. Further Advancements in Privacy and Security: Research and development efforts should focus on enhancing privacy protocols and cybersecurity measures to protect patient data from potential breaches and attacks.
2. Improved Data Collection and Standardization: Efforts should be made to streamline data collection processes and ensure standardized formats for seamless integration and analysis across diverse healthcare systems and devices.
3. Enhanced Model Explainability: Developing techniques to interpret and explain AI predictions will be crucial for building trust and acceptance among healthcare professionals and patients.
4. Greater Personalization and Precision: The future of Edge AI in healthcare lies in developing more personalized interventions and treatments tailored to individual patient needs, leveraging the power of AI to provide targeted and precise healthcare solutions.
5. Expanded Healthcare Integration: Edge AI can be integrated into various healthcare domains, including telemedicine, remote patient monitoring, and preventive interventions, to provide accessible and effective healthcare solutions.

By addressing the current challenges and focusing on these future directions, Edge AI has the potential to revolutionize healthcare delivery, improve patient outcomes, and transform public health on a global scale.

The Future of Edge AI in Public Health

As the future unfolds, the potential of Edge AI in public health is becoming increasingly apparent. This technology holds great promise for revolutionizing healthcare by enabling personalized healthcare, enhancing disease prevention, and improving early health prediction.

One area where Edge AI can significantly impact public health is in providing real-time insights. By leveraging the power of edge computing, healthcare providers can access and process data closer to its source, reducing latency and enabling faster analysis. This real-time information can drive targeted interventions and timely decision-making, leading to improved patient outcomes.

The future of Edge AI in public health also involves advancements in personalized healthcare. By analyzing diverse data sources, such as electronic health records, wearable devices, and environmental factors, Edge AI can develop comprehensive profiles of individual health. These profiles enable healthcare professionals to provide tailored interventions and treatments, optimizing patient care.

“Edge AI has the potential to transform public health outcomes by providing real-time insights and targeted interventions.”

Furthermore, early health prediction is another key area where Edge AI can make a substantial impact. By leveraging machine learning algorithms, Edge AI can analyze vast amounts of data to identify patterns and trends that indicate the onset of chronic diseases. This early detection allows for proactive interventions, reducing the burden of chronic illnesses on individuals and society as a whole.

Continued research and collaboration between healthcare providers, researchers, and technology developers will be instrumental in driving the future of Edge AI in public health. These partnerships will facilitate the development of innovative solutions, address privacy concerns, and ensure the seamless integration of Edge AI into existing healthcare systems.

Real-World Applications of Edge AI in Healthcare

Edge AI, combined with the power of edge computing and AI algorithms, is driving real-world innovation in healthcare. These applications are revolutionizing the way healthcare is delivered, improving access, and enhancing patient outcomes. Some of the key real-world applications of Edge AI in healthcare include:

1. Remote Patient Monitoring

Edge AI enables remote patient monitoring, allowing healthcare providers to collect and analyze vital health data in real-time. Wearable devices equipped with AI algorithms can continuously monitor patients’ biometric measurements, such as heart rate, blood pressure, and glucose levels. This data can be transmitted securely to healthcare professionals, enabling remote monitoring and timely interventions.

2. Telemedicine

Telemedicine, powered by Edge AI, has transformed the delivery of healthcare services. Through video consultations and remote diagnostics, patients can access medical experts regardless of their geographical location. AI algorithms assist healthcare professionals in interpreting medical images and data, facilitating accurate diagnoses and treatment plans.

3. Preventive Interventions

Edge AI plays a crucial role in preventive interventions aimed at reducing the risk of chronic diseases. By analyzing a patient’s health data in real-time, AI algorithms can identify early warning signs and provide personalized recommendations for lifestyle modifications, medication adherence, and preventive measures. This proactive approach helps in reducing the incidence of chronic diseases and improving overall population health.

Edge AI, through remote patient monitoring, telemedicine, and preventive interventions, is transforming healthcare delivery and improving patient outcomes.

These real-world applications of Edge AI demonstrate its potential to revolutionize healthcare by providing personalized, timely care, especially in remote and underserved areas. By leveraging the power of edge computing, AI algorithms can process and analyze large volumes of data quickly, enabling actionable insights and informed decision-making.

The Impact of Edge AI on Healthcare Costs

Edge AI has the potential to significantly impact healthcare costs by improving early prediction and disease management. By detecting and addressing health issues at an early stage, healthcare providers can prevent the need for more expensive treatments and hospitalizations. This not only reduces the financial burden on patients and healthcare systems but also leads to more efficient allocation of healthcare resources.

Through the use of AI algorithms and real-time data processing, Edge AI can aid in the early detection of chronic diseases such as diabetes and heart disease. By analyzing data from wearable devices, electronic health records, and other sources, Edge AI can identify subtle patterns and trends that may indicate the onset of these conditions.

Early prediction allows for timely interventions and preventive measures to be implemented, which can help curb the progression of diseases and minimize the need for costly medical interventions in the future. This approach promotes proactive and personalized healthcare, empowering individuals to take control of their health and well-being.

Moreover, Edge AI facilitates remote patient monitoring, enabling healthcare providers to deliver care and guidance to patients from a distance. This reduces the need for frequent hospital visits and readmissions, which are often associated with high costs. With Edge AI, healthcare professionals can remotely monitor vital signs, medication adherence, and overall health status, intervening when necessary to prevent complications.

The cost-effectiveness of Edge AI lies in its ability to optimize healthcare delivery through personalized interventions and targeted resource allocation. By leveraging AI technology, healthcare providers can identify individuals at high risk of developing chronic diseases and tailor preventive strategies to their specific needs. This significantly reduces the financial burden on individuals and healthcare systems, ensuring that resources are used efficiently and effectively.

Realizing the Potential of Edge AI in Healthcare Cost Optimization

While the impact of Edge AI on healthcare costs is promising, there are still challenges that need to be addressed. For instance, ensuring data privacy and security is crucial when utilizing AI algorithms and processing sensitive patient information. Additionally, integrating Edge AI with existing healthcare systems and infrastructure requires careful planning and collaboration between technology developers and healthcare providers.

Despite these challenges, the potential benefits of Edge AI in healthcare cost optimization cannot be overlooked. By leveraging the power of AI technology, healthcare providers can proactively manage chronic diseases, reduce hospitalization rates, and allocate resources more effectively. This ultimately leads to a more sustainable and cost-effective healthcare system that prioritizes patient well-being and financial viability.

As Edge AI continues to evolve and mature, it holds immense potential to revolutionize healthcare cost optimization. By harnessing the power of AI algorithms, real-time data processing, and remote patient monitoring, healthcare providers can deliver more efficient, cost-effective, and personalized care to their patients. The integration of Edge AI into healthcare systems will require ongoing collaboration between healthcare professionals, technology developers, and policymakers to ensure the successful implementation and widespread adoption of this transformative technology.

Conclusion

AI-powered solutions and edge computing technologies have tremendous potential in revolutionizing the management of chronic diseases, particularly diabetes and heart disease. By enabling early health prediction and personalized interventions, these technologies have the ability to significantly improve public health outcomes. However, it is important to address challenges related to privacy concerns and integration with existing health systems.

With continued research and collaboration, Edge AI can play a crucial role in managing chronic diseases and enhancing healthcare delivery. The combination of AI-powered solutions and edge computing can empower healthcare providers to make accurate predictions, develop targeted interventions, and improve patient outcomes. By leveraging the power of AI, we can transform the way chronic diseases are managed, leading to better healthcare access and cost-effective treatments.

To fully unlock the potential of AI for managing chronic diseases, it is essential for healthcare providers, researchers, and technology developers to work together. By addressing privacy concerns and incorporating AI technologies seamlessly into existing health systems, we can ensure that AI becomes an integral part of chronic disease management. The future of healthcare lies in leveraging AI for personalized healthcare and early prediction of chronic diseases.

Source Links

• https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9008324/
• https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6882991/
• https://www.mdpi.com/1999-5903/15/11/370