Machine learning techniques to predict the effectiveness of music therapy: A randomized controlled trial.

BACKGROUND: The literature shows the effectiveness of music listening, but which factors and what types of music produce therapeutic effects, as well as how music therapists can select music, remain unclear. Here, we present a study to establish the main predictive factors of music listening's relaxation effects using machine learning methods. METHODS: Three hundred and twenty healthy participants were evenly distributed by age, education level, presence of musical training, and sex. Each of them listened to music for nine minutes (either to their preferred music or to algorithmically generated music). Relaxation levels were recorded using a visual analogue scale (VAS) before and after the listening experience. The participants were then divided into three classes: increase, decrease, or no change in relaxation. A decision tree was generated to predict the effect of music listening on relaxation. RESULTS: A decision tree with an overall accuracy of 0.79 was produced. An analysis of the structure of the decision tree yielded some inferences as to the most important factors in predicting the effect of music listening, particularly the initial relaxation level, the combination of education and musical training, age, and music listening frequency. CONCLUSIONS: The resulting decision tree and analysis of this interpretable model makes it possible to find predictive factors that influence therapeutic music listening outcomes. The strong subjectivity of therapeutic music listening suggests the use of machine learning techniques as an important and innovative approach to supporting music therapy practice.

The Music Therapy Session Assessment Scale (MT-SAS): Validation of a new tool for music therapy process evaluation.

BACKGROUND: Music therapy (MT) interventions are aimed at creating and developing a relationship between patient and therapist. However, there is a lack of validated observational instruments to consistently evaluate the MT process. AIM: The purpose of this study was the validation of Music Therapy Session Assessment Scale (MT-SAS), designed to assess the relationship between therapist and patient during active MT sessions. METHODS: Videotapes of a single 30-min session per patient were considered. A pilot study on the videotapes of 10 patients was carried out to help refine the items, define the scoring system and improve inter-rater reliability among the five raters. Then, a validation study on 100 patients with different clinical conditions was carried out. The Italian MT-SAS was used throughout the process, although we also provide an English translation. RESULTS: The final scale consisted of 7 binary items accounting for eye contact, countenance, and nonverbal and sound-music communication. In the pilot study, raters were found to share an acceptable level of agreement in their assessments. Explorative factorial analysis disclosed a single homogeneous factor including 6 items (thus supporting an ordinal total score), with only the item about eye contact being unrelated to the others. Moreover, the existence of 2 different archetypal profiles of attuned and disattuned behaviours was highlighted through multiple correspondence analysis. CONCLUSIONS: As suggested by the consistent results of 2 different analyses, MT-SAS is a reliable tool that globally evaluates sonorous-musical and nonverbal behaviours related to emotional attunement and empathetic relationship between patient and therapist during active MT sessions.

Improvement of spontaneous language in stroke patients with chronic aphasia treated with music therapy: a randomized controlled trial.

AIM OF THE STUDY: The aim of this research is to evaluate the effects of active music therapy (MT) based on free-improvisation (relational approach) in addition to speech language therapy (SLT) compared with SLT alone (communicative-pragmatic approach: Promoting Aphasic's Communicative Effectiveness) in stroke patients with chronic aphasia. MATERIALS AND METHODS: The experimental group (n = 10) was randomized to 30 MT individual sessions over 15 weeks in addition to 30 SLT individual sessions while the control group (n = 10) was randomized to only 30 SLT sessions during the same period. Psychological and speech language assessment were made before (T0) and after (T1) the treatments. RESULTS: The study shows a significant improvement in spontaneous speech in the experimental group (Aachener Aphasie subtest: p = 0.020; Cohen's d = 0.35); the 50% of the experimental group showed also an improvement in vitality scores of Short Form Health Survey (chi-square test = 4.114; p = 0.043). CONCLUSIONS: The current trial highlights the possibility that the combined use of MT and SLT can lead to a better result in the rehabilitation of patients with aphasia than SLT alone.

Effect of Active Music Therapy and Individualized Listening to Music on Dementia: A Multicenter Randomized Controlled Trial.

OBJECTIVES: To assess the effects of active music therapy (MT) and individualized listening to music (LtM) on behavioral and psychological symptoms of dementia (BPSDs) in persons with dementia (PWDs). DESIGN: Randomized controlled trial. SETTING: Nine Italian institutions. PARTICIPANTS: Persons with moderate to severe dementia and BPSDs (N = 120) were randomized to one of three treatments. INTERVENTIONS: All groups received standard care (SC), and two groups attended 20 individualized MT or LtM sessions, twice a week, in addition to SC. MEASUREMENTS: The Neuropsychiatric Inventory (NPI), Cornell Scale for Depression in Dementia (CSDD), and Cornell-Brown Scale for Quality of Life in Dementia (CBS-QoL) were administered before treatment, after treatment, and at follow-up to evaluate behavioral and psychological outcomes. A specific coding scheme (Music Therapy Check List-Dementia) was used to evaluate the MT process. RESULTS: Behavioral assessment did not show significant differences between groups. All groups showed a reduction over time in NPI global score (P ≤ .001), CSDD (P = .001), and CBS-QoL (P = .01). The NPI global score fell 28% in the MT group, 12% in the LtM group, and 21% in the SC group at the end of treatment. An exploratory post hoc analysis showed similar within-group improvements for the NPI Delusion, Anxiety, and Disinhibition subscales. In the MT group, communication and relationships between the music therapists and PWDs showed a positive albeit nonsignificant trend during treatment. CONCLUSION: The addition of MT or LtM to standard care did not have a significant effect on BPSDs in PWDs. Further studies on the effects of the integration of standard care with different types of music interventions on BPSD in PWD are warranted.

Music therapy, emotions and the heart: a pilot study.

BACKGROUND: The autonomic nervous system plays an important role in the control of cardiac function. It has been suggested that sound and music may have effects on the autonomic control of the heart inducing emotions, concomitantly with the activation of specific brain areas, i.e. the limbic area, and they may exert potential beneficial effects. OBJECTIVE: This study is a prerequisite and defines a methodology to assess the relation between changes in cardiac physiological parameters such as heart rate, QT interval and their variability and the psychological responses to music therapy sessions. METHODS: We assessed the cardiac physiological parameters and psychological responses to a music therapy session. ECG Holter recordings were performed before, during and after a music therapy session in 8 healthy individuals. The different behaviors of the music therapist and of the subjects have been analyzed with a specific music therapy assessment (Music Therapy Checklist). RESULTS: After the session mean heart rate decreased (p = 0.05), high frequency of heart rate variability tended to be higher and QTc variability tended to be lower. During music therapy session "affect attunements" have been found in all subjects but one. A significant emotional activation was associated to a higher dynamicity and variations of sound-music interactions. CONCLUSION: Our results may represent the rational basis for larger studies in diferent clinical conditions.

Effects of music therapy on psychological symptoms and heart rate variability in patients with dementia. A pilot study.

We assessed the effects of music therapy (MT) on behavioral and psychological symptoms (BPSD) in dementia associated with changes in physiological parameters, as heart rate (HR) and heart rate variability (HRV). Twenty subjects were randomly assigned to MT treatment or standard care; all patients underwent neuropsychological assessment and ECG Holter recordings before and after the 15-week treatment. The treatment included 30 MT sessions. Depression significantly decreased (p=0.021) in the MT group. PNN50 improved in 50% patients of the MT group, but in none of the control group (p=0.013). MT may improve symptoms of depression and increase HRV in demented patients.

Efficacy of music therapy in the treatment of behavioral and psychiatric symptoms of dementia.

BACKGROUND: Music therapy (MT) has been proposed as valid approach for behavioral and psychologic symptoms (BPSD) of dementia. However, studies demonstrating the effectiveness of this approach are lacking. OBJECTIVE: To assess MT effectiveness in reducing BPSD in subjects with dementia. METHOD: Fifty-nine persons with dementia were enrolled in this study. All of them underwent a multidimensional assessment including Mini Mental State Examination, Barthel Index and Neuropsychiatry Inventory at enrollment and after 8, 16, and 20 weeks. Subjects were randomly assigned to experimental (n=30) or control (n=29) group. The MT sessions were evaluated with standardized criteria. The experimental group received 30 MT sessions (16 wk of treatment), whereas the control group received educational support or entertainment activities. RESULTS: NPI total score significantly decreased in the experimental group at 8th, 16th, and 20th weeks (interaction time x group: F3,165=5.06, P=0.002). Specific BPSD (ie, delusions, agitation, anxiety, apathy, irritability, aberrant motor activity, and night-time disturbances) significantly improved. The empathetic relationship and the patients' active participation in the MT approach, also improved in the experimental group. CONCLUSIONS: The study shows that MT is effective to reduce BPSD in patients with moderate-severe dementia.