Intelligent wearable-assisted digital healthcare industry 5.0.

Area of Science:

• Digital Health
• Healthcare Technology
• Machine Learning Applications

Background:

• The evolution to Healthcare Industry 5.0 integrates smart wearables and digital technologies, enhancing patient treatment and healthcare delivery.
• Smart wearables offer advantages like remote monitoring, personalized care, and telemedicine, driven by technologies such as Machine Learning (ML) and the Internet of Medical Things (IoMT).
• Despite advancements, the application of ML in conjunction with wearable technology for digital healthcare requires further exploration.

Purpose of the Study:

• To comprehensively examine and evaluate advanced ML techniques for digital healthcare Industry 5.0 and wearable technology.
• To propose a taxonomy and innovative process model for digital healthcare Industry 5.0, addressing challenges in data collection, health tracking, security, and privacy.
• To demonstrate the efficacy of ML models in analyzing wearable data for improved patient care and decision-making.

Main Methods:

• A detailed taxonomy for digital healthcare Industry 5.0 was developed, establishing an innovative process model.
• Data collection from wearables (e.g., smartwatches) and subsequent data pre-processing were performed.
• Machine Learning models including Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) were applied for activity prediction and classification.

Main Results:

• The proposed ML-based process model effectively utilizes data from smart wearables for analysis.
• ML algorithms demonstrated capability in analyzing extensive healthcare data, including electronic health records (EHR), to provide valuable insights.
• A case study highlighted the Random Forest (RF) model's superior performance, achieving the lowest Root Mean Square Error (RMSE) of 0.94, Mean Squared Error (MSE) of 0.88, and Mean Absolute Error (MAE) of 0.27 in activity prediction.

Conclusions:

• Digital healthcare Industry 5.0, powered by smart wearables and ML, offers personalized, proactive, and patient-centric healthcare solutions.
• The study provides a robust framework and validates the use of ML techniques for analyzing wearable data in healthcare.
• The findings underscore the potential of ML, particularly RF, in enhancing activity prediction accuracy and improving healthcare decision-making processes.