Modern medicine is undergoing a profound transformation. Digital technologies are no longer simply tools that help healthcare professionals manage information — they are becoming an integral part of diagnosis, patient monitoring, and medical decision-making.
This evolution is reflected in four research studies by Professor Niladri Maiti, published in 2026 by Springer Nature as chapters in the book Smart Healthcare.
Although each study focuses on a different aspect of digital healthcare, together they share a common vision: healthcare technologies should not simply collect vast amounts of medical data, but transform that data into timely, secure, and meaningful information that can support better-informed medical decisions.
From Data Collection to Intelligent Healthcare
One of the studies explores the use of Edge Computing and the Internet of Things (IoT) for efficient healthcare data processing.
Rather than sending all medical data exclusively to centralized cloud systems, Edge Computing enables information to be processed closer to where it is generated — directly on devices or at the network edge.
This approach can reduce processing delays, decrease network traffic, and improve the privacy and security of sensitive healthcare information. The research also examines the potential of federated learning, decentralized artificial intelligence, 5G, and blockchain technologies in the development of digital healthcare systems.
For healthcare, this is particularly important in situations where information needs to be processed in near real time. Data collected from different sensors and connected devices can be analyzed rapidly, allowing systems to identify potential warning signs that may require medical attention.
Medical Data Collected Directly from the Patient
Another study focuses on a more patient-centered technology: IoT-enabled wearable healthcare devices.
Modern wearable devices can continuously monitor a range of health indicators, including heart rate, blood pressure, blood glucose levels, and blood oxygen saturation. The collected data can be analyzed in real time and potentially used to identify health risks at an early stage.
This approach is particularly promising for people living with chronic conditions. Continuous monitoring provides healthcare professionals with information not only during a clinical visit, but also throughout a patient’s everyday life.
As a result, healthcare is gradually moving from a reactive model — in which patients seek medical assistance after significant symptoms appear — toward a more proactive approach based on continuous health monitoring and early intervention.
At the same time, the research highlights several challenges that still need to be addressed, including sensor accuracy, data privacy, interoperability between different systems, and the affordability of these technologies.
Artificial Intelligence and Early Diagnosis
The next stage of digital healthcare involves using collected data to predict diseases and support early diagnosis.
In Deep Learning for Disease Prediction and Early Diagnosis, Professor Maiti and his co-authors examine the potential of deep learning to analyze large and complex datasets, including electronic health records, medical images, genomic information, and data generated by wearable devices.
Deep learning algorithms can identify patterns within these datasets that may help detect diseases at an earlier stage. The research considers potential applications in the diagnosis of cancer, cardiovascular and neurological diseases, diabetes, as well as in predicting infectious disease outbreaks.
However, the authors emphasize an important principle: high predictive accuracy alone is not enough in healthcare.
Medical professionals need to understand why an artificial intelligence system has reached a particular conclusion. This issue leads directly to another important area of research: Explainable AI.
When Artificial Intelligence Needs to Explain Its Decisions
The fourth study, Explainable AI in Healthcare in Enhancing Trust in ML Models, examines the role of Explainable Artificial Intelligence (XAI) in healthcare.
Modern machine-learning models can be highly complex. They may analyze enormous amounts of data and produce highly accurate predictions, but healthcare professionals need more than a result — they need to understand the reasoning behind it.
Explainable AI aims to make the decisions of AI systems more understandable to medical professionals. This allows physicians to evaluate AI-generated recommendations, compare them with the patient’s clinical condition, and retain human oversight over the final medical decision.
The research emphasizes that trust in artificial intelligence cannot be built on accuracy alone. Transparency, model validation, human oversight, standardized approaches to explainability, and appropriate training for healthcare professionals are all essential for the responsible adoption of AI in medicine.
One Integrated Vision of Future Healthcare
When viewed together, the four studies present a coherent model for the development of Smart Healthcare.
First, IoT devices and wearable technologies collect information about a patient’s health. Edge Computing enables part of this information to be processed quickly and closer to the patient. Deep learning algorithms can then analyze the data to identify diseases or potential risks at an early stage. Finally, Explainable AI helps make the conclusions generated by artificial intelligence understandable to healthcare professionals.
In this sense, the four studies can be viewed not as separate technological developments, but as interconnected components of a new digital healthcare ecosystem:
data collection → real-time processing → intelligent analysis → explainable medical decision-making.
This approach has the potential to make healthcare more personalized, responsive, and focused on prevention and early intervention.
Research at the Intersection of Healthcare and Technology
A key feature of these studies is their interdisciplinary nature.
The development of Smart Healthcare requires collaboration between physicians, engineers, data scientists, artificial intelligence specialists, cybersecurity experts, and policymakers.
The research on Edge Computing, for example, highlights the importance of collaboration among healthcare professionals, engineers, data scientists, and regulatory stakeholders.
Professor Niladri Maiti’s research reflects this intersection between healthcare and emerging technologies. His work contributes to a broader international research effort focused on applying artificial intelligence, IoT, wearable technologies, and advanced computing to real-world healthcare challenges.
Four Studies, One Direction
Professor Niladri Maiti’s four research studies published in Smart Healthcare demonstrate how rapidly the concept of modern medicine is evolving.
The future of healthcare is not only about developing new treatments. It is also about the ability to continuously collect information about patients, process it securely, use artificial intelligence to identify and predict health risks, and ensure that AI-supported medical decisions remain transparent and understandable.
The next stage of healthcare can therefore be seen not simply as digitalization, but as the development of a more intelligent, personalized, proactive, and explainable healthcare system — one in which technology supports medical professionals in making better-informed decisions and enables patients to receive earlier and more targeted care.
Professor Niladri Maiti’s Four Springer Publications
This evolution is reflected in four research studies by Professor Niladri Maiti, published in 2026 by Springer Nature as chapters in the book Smart Healthcare.
Although each study focuses on a different aspect of digital healthcare, together they share a common vision: healthcare technologies should not simply collect vast amounts of medical data, but transform that data into timely, secure, and meaningful information that can support better-informed medical decisions.
From Data Collection to Intelligent Healthcare
One of the studies explores the use of Edge Computing and the Internet of Things (IoT) for efficient healthcare data processing.
Rather than sending all medical data exclusively to centralized cloud systems, Edge Computing enables information to be processed closer to where it is generated — directly on devices or at the network edge.
This approach can reduce processing delays, decrease network traffic, and improve the privacy and security of sensitive healthcare information. The research also examines the potential of federated learning, decentralized artificial intelligence, 5G, and blockchain technologies in the development of digital healthcare systems.
For healthcare, this is particularly important in situations where information needs to be processed in near real time. Data collected from different sensors and connected devices can be analyzed rapidly, allowing systems to identify potential warning signs that may require medical attention.
Medical Data Collected Directly from the Patient
Another study focuses on a more patient-centered technology: IoT-enabled wearable healthcare devices.
Modern wearable devices can continuously monitor a range of health indicators, including heart rate, blood pressure, blood glucose levels, and blood oxygen saturation. The collected data can be analyzed in real time and potentially used to identify health risks at an early stage.
This approach is particularly promising for people living with chronic conditions. Continuous monitoring provides healthcare professionals with information not only during a clinical visit, but also throughout a patient’s everyday life.
As a result, healthcare is gradually moving from a reactive model — in which patients seek medical assistance after significant symptoms appear — toward a more proactive approach based on continuous health monitoring and early intervention.
At the same time, the research highlights several challenges that still need to be addressed, including sensor accuracy, data privacy, interoperability between different systems, and the affordability of these technologies.
Artificial Intelligence and Early Diagnosis
The next stage of digital healthcare involves using collected data to predict diseases and support early diagnosis.
In Deep Learning for Disease Prediction and Early Diagnosis, Professor Maiti and his co-authors examine the potential of deep learning to analyze large and complex datasets, including electronic health records, medical images, genomic information, and data generated by wearable devices.
Deep learning algorithms can identify patterns within these datasets that may help detect diseases at an earlier stage. The research considers potential applications in the diagnosis of cancer, cardiovascular and neurological diseases, diabetes, as well as in predicting infectious disease outbreaks.
However, the authors emphasize an important principle: high predictive accuracy alone is not enough in healthcare.
Medical professionals need to understand why an artificial intelligence system has reached a particular conclusion. This issue leads directly to another important area of research: Explainable AI.
When Artificial Intelligence Needs to Explain Its Decisions
The fourth study, Explainable AI in Healthcare in Enhancing Trust in ML Models, examines the role of Explainable Artificial Intelligence (XAI) in healthcare.
Modern machine-learning models can be highly complex. They may analyze enormous amounts of data and produce highly accurate predictions, but healthcare professionals need more than a result — they need to understand the reasoning behind it.
Explainable AI aims to make the decisions of AI systems more understandable to medical professionals. This allows physicians to evaluate AI-generated recommendations, compare them with the patient’s clinical condition, and retain human oversight over the final medical decision.
The research emphasizes that trust in artificial intelligence cannot be built on accuracy alone. Transparency, model validation, human oversight, standardized approaches to explainability, and appropriate training for healthcare professionals are all essential for the responsible adoption of AI in medicine.
One Integrated Vision of Future Healthcare
When viewed together, the four studies present a coherent model for the development of Smart Healthcare.
First, IoT devices and wearable technologies collect information about a patient’s health. Edge Computing enables part of this information to be processed quickly and closer to the patient. Deep learning algorithms can then analyze the data to identify diseases or potential risks at an early stage. Finally, Explainable AI helps make the conclusions generated by artificial intelligence understandable to healthcare professionals.
In this sense, the four studies can be viewed not as separate technological developments, but as interconnected components of a new digital healthcare ecosystem:
data collection → real-time processing → intelligent analysis → explainable medical decision-making.
This approach has the potential to make healthcare more personalized, responsive, and focused on prevention and early intervention.
Research at the Intersection of Healthcare and Technology
A key feature of these studies is their interdisciplinary nature.
The development of Smart Healthcare requires collaboration between physicians, engineers, data scientists, artificial intelligence specialists, cybersecurity experts, and policymakers.
The research on Edge Computing, for example, highlights the importance of collaboration among healthcare professionals, engineers, data scientists, and regulatory stakeholders.
Professor Niladri Maiti’s research reflects this intersection between healthcare and emerging technologies. His work contributes to a broader international research effort focused on applying artificial intelligence, IoT, wearable technologies, and advanced computing to real-world healthcare challenges.
Four Studies, One Direction
Professor Niladri Maiti’s four research studies published in Smart Healthcare demonstrate how rapidly the concept of modern medicine is evolving.
The future of healthcare is not only about developing new treatments. It is also about the ability to continuously collect information about patients, process it securely, use artificial intelligence to identify and predict health risks, and ensure that AI-supported medical decisions remain transparent and understandable.
The next stage of healthcare can therefore be seen not simply as digitalization, but as the development of a more intelligent, personalized, proactive, and explainable healthcare system — one in which technology supports medical professionals in making better-informed decisions and enables patients to receive earlier and more targeted care.
Professor Niladri Maiti’s Four Springer Publications
- Edge Computing and IoT for Efficient Healthcare Data Processing - Smart Healthcare, pp. 49–65.
- Deep Learning for Disease Prediction and Early Diagnosis - Smart Healthcare, pp. 67–80.
- Explainable AI in Healthcare in Enhancing Trust in ML Models - Smart Healthcare, pp. 127–139.
- IoT-Enabled Wearable Health Devices for Real-Time Diagnosis - Smart Healthcare, pp. 141–154.
