Use of Digitalisation and Machine Learning Techniques in Therapeutic Intervention at Early Ages: Supervised and...

Area of Science:

• Health Sciences
• Artificial Intelligence
• Machine Learning

Background:

• Technological advancements, including artificial intelligence (AI), offer new avenues for precision interventions in health sciences.
• Smart healthcare applications are increasingly vital for analyzing patient data and improving health outcomes.

Purpose of the Study:

• To analyze the efficacy of supervised (prediction, classification) and unsupervised (clustering) machine learning techniques.
• To evaluate functional skill development in children aged 0-6 years using these AI methods.

Main Methods:

• Utilized supervised and unsupervised machine learning algorithms.
• Analyzed data from 113 pediatric patients (0-6 years) in two groups: motor impairments (n=49) and diverse impairments in early care (n=64).

Main Results:

• Chronological age predicted functional skills in 85% of patients with motor impairments and 65% in the early care group.
• Functional upper extremity development was a key classification variable.
• Identified two distinct clusters within each group, revealing specific functional development patterns.

Conclusions:

• Smart healthcare and machine learning demonstrate significant potential for enhancing early intervention services.
• Systematic data recording in web applications and automated result processing are crucial for future development.