Feasibility of Mental Health Triage Call Priority Prediction Using Machine Learning
Background: Optimum efficiency and responsiveness to callers of mental health helplines can only be achieved if call priority is accurately identified. Currently, call operators making a triage assessment rely heavily on their clinical judgment and experience. Due to the significant morbidity and mo...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Nursing Reports |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2039-4403/14/4/303 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850037149491003392 |
|---|---|
| author | Rajib Rana Niall Higgins Kazi Nazmul Haque Kylie Burke Kathryn Turner Terry Stedman |
| author_facet | Rajib Rana Niall Higgins Kazi Nazmul Haque Kylie Burke Kathryn Turner Terry Stedman |
| author_sort | Rajib Rana |
| collection | DOAJ |
| description | Background: Optimum efficiency and responsiveness to callers of mental health helplines can only be achieved if call priority is accurately identified. Currently, call operators making a triage assessment rely heavily on their clinical judgment and experience. Due to the significant morbidity and mortality associated with mental illness, there is an urgent need to identify callers to helplines who have a high level of distress and need to be seen by a clinician who can offer interventions for treatment. This study delves into the potential of using machine learning (ML) to estimate call priority from the properties of the callers’ voices rather than evaluating the spoken words. Method: Phone callers’ speech is first isolated using existing APIs, then features or representations are extracted from the raw speech. These are then fed into a series of deep learning neural networks to classify priority level from the audio representation. Results: Development of a deep learning neural network architecture that instantly determines positive and negative levels in the input speech segments. A total of 459 call records from a mental health helpline were investigated. The final ML model achieved a balanced accuracy of 92% correct identification of both positive and negative instances of call priority. Conclusions: The priority level provides an estimate of voice quality in terms of positive or negative demeanor that can be simultaneously displayed using a web interface on a computer or smartphone. |
| format | Article |
| id | doaj-art-975ae9d6ddaf4fc28e3dac1adc16cc3b |
| institution | DOAJ |
| issn | 2039-439X 2039-4403 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Nursing Reports |
| spelling | doaj-art-975ae9d6ddaf4fc28e3dac1adc16cc3b2025-08-20T02:56:57ZengMDPI AGNursing Reports2039-439X2039-44032024-12-011444162417210.3390/nursrep14040303Feasibility of Mental Health Triage Call Priority Prediction Using Machine LearningRajib Rana0Niall Higgins1Kazi Nazmul Haque2Kylie Burke3Kathryn Turner4Terry Stedman5School of Mathematics, Physics and Computing, Springfield Campus, University of Southern Queensland, Springfield Education City, QLD 4300, AustraliaSchool of Mathematics, Physics and Computing, Springfield Campus, University of Southern Queensland, Springfield Education City, QLD 4300, AustraliaSchool of Mathematics, Physics and Computing, Springfield Campus, University of Southern Queensland, Springfield Education City, QLD 4300, AustraliaMetro North Mental Health, Metro North Health, Brisbane, QLD 4029, AustraliaMetro North Mental Health, Metro North Health, Brisbane, QLD 4029, AustraliaMental Health and Specialist Services, West Moreton Health, Brisbane, QLD 4076, AustraliaBackground: Optimum efficiency and responsiveness to callers of mental health helplines can only be achieved if call priority is accurately identified. Currently, call operators making a triage assessment rely heavily on their clinical judgment and experience. Due to the significant morbidity and mortality associated with mental illness, there is an urgent need to identify callers to helplines who have a high level of distress and need to be seen by a clinician who can offer interventions for treatment. This study delves into the potential of using machine learning (ML) to estimate call priority from the properties of the callers’ voices rather than evaluating the spoken words. Method: Phone callers’ speech is first isolated using existing APIs, then features or representations are extracted from the raw speech. These are then fed into a series of deep learning neural networks to classify priority level from the audio representation. Results: Development of a deep learning neural network architecture that instantly determines positive and negative levels in the input speech segments. A total of 459 call records from a mental health helpline were investigated. The final ML model achieved a balanced accuracy of 92% correct identification of both positive and negative instances of call priority. Conclusions: The priority level provides an estimate of voice quality in terms of positive or negative demeanor that can be simultaneously displayed using a web interface on a computer or smartphone.https://www.mdpi.com/2039-4403/14/4/303artificial intelligenceautomated distress screendeep learningdistressmental healthspontaneous speech |
| spellingShingle | Rajib Rana Niall Higgins Kazi Nazmul Haque Kylie Burke Kathryn Turner Terry Stedman Feasibility of Mental Health Triage Call Priority Prediction Using Machine Learning Nursing Reports artificial intelligence automated distress screen deep learning distress mental health spontaneous speech |
| title | Feasibility of Mental Health Triage Call Priority Prediction Using Machine Learning |
| title_full | Feasibility of Mental Health Triage Call Priority Prediction Using Machine Learning |
| title_fullStr | Feasibility of Mental Health Triage Call Priority Prediction Using Machine Learning |
| title_full_unstemmed | Feasibility of Mental Health Triage Call Priority Prediction Using Machine Learning |
| title_short | Feasibility of Mental Health Triage Call Priority Prediction Using Machine Learning |
| title_sort | feasibility of mental health triage call priority prediction using machine learning |
| topic | artificial intelligence automated distress screen deep learning distress mental health spontaneous speech |
| url | https://www.mdpi.com/2039-4403/14/4/303 |
| work_keys_str_mv | AT rajibrana feasibilityofmentalhealthtriagecallprioritypredictionusingmachinelearning AT niallhiggins feasibilityofmentalhealthtriagecallprioritypredictionusingmachinelearning AT kazinazmulhaque feasibilityofmentalhealthtriagecallprioritypredictionusingmachinelearning AT kylieburke feasibilityofmentalhealthtriagecallprioritypredictionusingmachinelearning AT kathrynturner feasibilityofmentalhealthtriagecallprioritypredictionusingmachinelearning AT terrystedman feasibilityofmentalhealthtriagecallprioritypredictionusingmachinelearning |