Related Experiment Video
Updated: Jan 4, 2026
11:50
Clinical Practice Protocol of Creative Music Therapy for Preterm Infants and Their Parents in the Neonatal Intensive Care Unit
Published on: January 7, 2020
27.4K
Machine learning techniques to predict the effectiveness of music therapy: A randomized controlled trial
Alfredo Raglio1, Marcello Imbriani1, Chiara Imbriani1
1Istituti Clinici Scientifici Maugeri IRCCS, Via Boezio 28, Pavia 27100, Italy.
Computer Methods and Programs in Biomedicine
|November 12, 2019
Summary
Machine learning identified key factors influencing music listening relaxation effects. Initial relaxation, education, musical training, age, and listening frequency predict therapeutic outcomes in music therapy.
Area of Science:
- Music Therapy
- Machine Learning
- Psychology
Background:
- Effectiveness of music listening for therapeutic effects is documented.
- Predictive factors and music selection for optimal outcomes remain unclear.
Purpose of the Study:
- Establish main predictive factors for music listening's relaxation effects.
- Utilize machine learning methods for analysis.
Main Methods:
- 320 healthy participants listened to preferred or algorithmically generated music for 9 minutes.
- Relaxation levels measured using visual analogue scale (VAS) pre- and post-listening.
- Participants classified into relaxation increase, decrease, or no change groups; decision tree generated.
Main Results:
- Decision tree achieved 0.79 overall accuracy.
- Key predictive factors identified: initial relaxation level, education and musical training combination, age, and music listening frequency.
Conclusions:
- Interpretable machine learning model identifies factors influencing therapeutic music listening.
- Machine learning offers an innovative approach to support music therapy due to music's subjective nature.
Keywords:
Decision tree methodsMachine learning techniquesMedicineTherapeutic music listeningTherapeutic predictivity
