Javascript must be enabled to continue!
Acoustic Features for Identifying Suicide Risk in Crisis Hotline Callers: Machine Learning Approach
View through CrossRef
Background
Crisis hotlines serve as a crucial avenue for the early identification of suicide risk, which is of paramount importance for suicide prevention and intervention. However, assessing the risk of callers in the crisis hotline context is constrained by factors such as lack of nonverbal communication cues, anonymity, time limits, and single-occasion intervention. Therefore, it is necessary to develop approaches, including acoustic features, for identifying the suicide risk among hotline callers early and quickly. Given the complicated features of sound, adopting artificial intelligence models to analyze callers’ acoustic features is promising.
Objective
In this study, we investigated the feasibility of using acoustic features to predict suicide risk in crisis hotline callers. We also adopted a machine learning approach to analyze the complex acoustic features of hotline callers, with the aim of developing suicide risk prediction models.
Methods
We collected 525 suicide-related calls from the records of a psychological assistance hotline in a province in northwest China. Callers were categorized as low or high risk based on suicidal ideation, suicidal plans, and history of suicide attempts, with risk assessments verified by a team of 18 clinical psychology raters. A total of 164 clearly categorized risk recordings were analyzed, including 102 low-risk and 62 high-risk calls. We extracted 273 audio segments, each exceeding 2 seconds in duration, which were labeled by raters as containing suicide-related expressions for subsequent model training and evaluation. Basic acoustic features (eg, Mel Frequency Cepstral Coefficients, formant frequencies, jitter, shimmer) and high-level statistical function (HSF) features (using OpenSMILE [Open-Source Speech and Music Interpretation by Large-Space Extraction] with the ComParE 2016 configuration) were extracted. Four supervised machine learning algorithms (logistic regression, support vector machine, random forest, and extreme gradient boosting) were trained and evaluated using grouped 5-fold cross-validation and a test set, with performance metrics, including accuracy, F1-score, recall, and false negative rate.
Results
The development of machine learning models utilizing HSF acoustic features has been demonstrated to enhance recognition performance compared to models based solely on basic acoustic features. The random forest classifier, developed with HSFs, achieved the best performance in detecting the suicide risk among the models evaluated (accuracy=0.75, F1-score=0.70, recall=0.76, false negative rate=0.24).
Conclusions
The results of our study demonstrate the potential of developing artificial intelligence–based early warning systems using acoustic features for identifying the suicide risk among crisis hotline callers. Our work also has implications for employing acoustic features to identify suicide risk in salient voice contexts.
JMIR Publications Inc.
Title: Acoustic Features for Identifying Suicide Risk in Crisis Hotline Callers: Machine Learning Approach
Description:
Background
Crisis hotlines serve as a crucial avenue for the early identification of suicide risk, which is of paramount importance for suicide prevention and intervention.
However, assessing the risk of callers in the crisis hotline context is constrained by factors such as lack of nonverbal communication cues, anonymity, time limits, and single-occasion intervention.
Therefore, it is necessary to develop approaches, including acoustic features, for identifying the suicide risk among hotline callers early and quickly.
Given the complicated features of sound, adopting artificial intelligence models to analyze callers’ acoustic features is promising.
Objective
In this study, we investigated the feasibility of using acoustic features to predict suicide risk in crisis hotline callers.
We also adopted a machine learning approach to analyze the complex acoustic features of hotline callers, with the aim of developing suicide risk prediction models.
Methods
We collected 525 suicide-related calls from the records of a psychological assistance hotline in a province in northwest China.
Callers were categorized as low or high risk based on suicidal ideation, suicidal plans, and history of suicide attempts, with risk assessments verified by a team of 18 clinical psychology raters.
A total of 164 clearly categorized risk recordings were analyzed, including 102 low-risk and 62 high-risk calls.
We extracted 273 audio segments, each exceeding 2 seconds in duration, which were labeled by raters as containing suicide-related expressions for subsequent model training and evaluation.
Basic acoustic features (eg, Mel Frequency Cepstral Coefficients, formant frequencies, jitter, shimmer) and high-level statistical function (HSF) features (using OpenSMILE [Open-Source Speech and Music Interpretation by Large-Space Extraction] with the ComParE 2016 configuration) were extracted.
Four supervised machine learning algorithms (logistic regression, support vector machine, random forest, and extreme gradient boosting) were trained and evaluated using grouped 5-fold cross-validation and a test set, with performance metrics, including accuracy, F1-score, recall, and false negative rate.
Results
The development of machine learning models utilizing HSF acoustic features has been demonstrated to enhance recognition performance compared to models based solely on basic acoustic features.
The random forest classifier, developed with HSFs, achieved the best performance in detecting the suicide risk among the models evaluated (accuracy=0.
75, F1-score=0.
70, recall=0.
76, false negative rate=0.
24).
Conclusions
The results of our study demonstrate the potential of developing artificial intelligence–based early warning systems using acoustic features for identifying the suicide risk among crisis hotline callers.
Our work also has implications for employing acoustic features to identify suicide risk in salient voice contexts.
Related Results
Macroeconomic and Social Precursors of Suicide Rates in the Philippines: A Quantitative Analysis (Preprint)
Macroeconomic and Social Precursors of Suicide Rates in the Philippines: A Quantitative Analysis (Preprint)
BACKGROUND
Suicide is a complex, serious and multifaceted public health issue that poses significant challenges to societies worldwide. In fact, it represen...
Acoustic Features for Identifying Suicide Risk in Crisis Hotline Callers: Machine Learning Approach (Preprint)
Acoustic Features for Identifying Suicide Risk in Crisis Hotline Callers: Machine Learning Approach (Preprint)
BACKGROUND
Crisis hotlines serve as a crucial avenue for the early identification of suicide risk, which is of paramount importance for suicide prevention a...
Po koncu: žalovanje in reintegracija bližnjih po samomoru
Po koncu: žalovanje in reintegracija bližnjih po samomoru
Suicide is one of the biggest social and public health problems. Every year about 450 Slovenians and about 800,000 people around the world die by suicide. Suicide represents a sign...
Zero Suicide Campaign: Establishing a National Suicide Prevention Hotline in Conflict-Affected Myanmar
Zero Suicide Campaign: Establishing a National Suicide Prevention Hotline in Conflict-Affected Myanmar
Aims:
Following the military coup in February 2021, Myanmar has experienced widespread human rights violations, insecurity, economic hardship, and disruption of...
Mental Health and Suicide Decriminalization: Connecting the Dots
Mental Health and Suicide Decriminalization: Connecting the Dots
Suicide is a current public health crisis as every year, more than 800,000 individuals die by suicide worldwide. According to World Health Organization (WHO) estimates, 77% of thes...
Cross-Sectional Examination of Hospital Visits in the Year Prior to Suicide Death in Illinois
Cross-Sectional Examination of Hospital Visits in the Year Prior to Suicide Death in Illinois
Introduction: Suicide is a growing public health issue in the United States. Healthcare visits in the year prior to suicide death, including those to emergency departments (ED) and...
Figurative Positioning in Hotline Stories
Figurative Positioning in Hotline Stories
Personal stories and tropes are ubiquitous in problem talk (e.g. therapy, counseling and hotline) which focuses on problem presentation, discussion and candidate solutions. Current...
Trend and gender-based association of the Bangladeshi student suicide during the COVID-19 pandemic: a GIS-based nationwide distribution
Trend and gender-based association of the Bangladeshi student suicide during the COVID-19 pandemic: a GIS-based nationwide distribution
Background:
Students are one of the most vulnerable groups to suicide. Before the COVID-19 pandemic, a Bangladeshi study was conducted assessing their suicide p...

