Abstract
The significant increase in the number of individuals with chronic ailments (including the elderly and disabled) has dictated an urgent need for an innovative model for healthcare systems. The evolved model will be more personalized and less reliant on traditional brick-and-mortar healthcare institutions such as hospitals, nursing homes, and long-term healthcare centers. The smart healthcare system is a topic of recently growing interest and has become increasingly required due to major developments in modern technologies, especially in artificial intelligence (AI) and machine learning (ML). This paper discusses the current state-of-the-art smart healthcare systems, highlighting major areas like wearable and smartphone devices for health monitoring, machine learning for disease diagnosis, and assistive frameworks, including social robots developed for the ambient assisted living environment. Additionally, the paper demonstrates software integration architectures that are significant for creating smart healthcare systems, integrating seamlessly the benefits of data analytics and other tools of AI. The current research challenges with potential future directions are addressed to highlight the drawbacks of existing systems and possible methods to introduce novel frameworks.
Introduction
The global healthcare system is facing a "perfect storm": an aging population—with 22% of people expected to be over 60 by 2050—a rising tide of chronic diseases, and a shrinking ratio of professional caregivers to patients. The traditional "brick-and-mortar" model, relying on hospitals and nursing homes, is becoming unsustainable due to soaring costs and limited capacity. The solution lies in the Internet of Medical Things (IoMT), which shifts the focus from reactive hospital care to proactive, personalized remote monitoring.
Taxonomy of Smart Healthcare
The paper categorizes the state-of-the-art into four primary pillars that bridge the gap between hardware, software, and human-centric design:
- Health Monitoring in IoT: Utilizing wearable sensors and smartphone-based solutions. A key innovation is the use of Photoplethysmogram (PPG) data extracted from smartphone cameras to estimate blood pressure and glucose levels non-invasively.
- Machine Learning in IoHT: Reviewing deep learning architectures (like CNNs and ResNet) used to diagnose COVID-19, heart disease, and diabetes.
- Ambient Assisted Living (AAL): Smart home environments and social robots (e.g., Care-O-Bot) designed to provide physical assistance and emotional companionship.
- Software Integration Architectures: Evaluating multi-layered frameworks, specifically advocating for Fog Computing to achieve low latency for emergency responses.
System Architecture and IoMT
A unified smart healthcare system relies on a seamless flow of data from the user to various stakeholders. Beyond simple apps, smartphones are being transformed into sophisticated diagnostic tools using built-in sensors to capture PPG and PCG (phonocardiogram) signals for "cuff-less" monitoring.
While the Cloud offers unlimited storage, the authors emphasize that Fog nodes (local processing) are essential for handling "time-sensitive reactions"—such as detecting a fall or a heart attack—without the delay of round-trip data transfer to a distant server. The biggest technical challenge remains "data fusion": integrating signals from heterogeneous devices (like a Fitbit and a medical-grade ECG) into a single, meaningful health record.
Performance Milestones
The review cites impressive quantitative milestones from various studies using benchmark datasets like the Cleveland database and the mHealth dataset:
- COVID-19 Diagnosis: Deep learning models achieved accuracies as high as 98.54% to 99.06% using X-ray and sensor data.
- Heart Disease: Systems using MSSO-ANFIS classification reached 99.45% accuracy.
- Diabetes Prediction: Algorithms achieved 99.66% accuracy in monitoring glucose and activity levels.
- Fall Detection: Radar-based sensory systems in smart homes achieved 97% sensitivity without requiring the user to wear a device.
Challenges and Future Directions
Despite high laboratory accuracies, several real-world roadblocks remain:
- Clinical Validation: Most systems are prototypes; large-scale clinical trials are urgently needed.
- Security and Privacy: As data moves to the cloud, Blockchain integration is proposed for secure, decentralized records.
- Power Efficiency: Future research must focus on energy harvesting to enable long-term, maintenance-free monitoring for wearables.
- Data Reliability: Smartphone-based sensing is currently limited by sensitivity to skin color, ambient light, and motion artifacts.
Summary updated