โก Quick Summary
This study explored the use of voice recognition and machine learning to automatically evaluate patient-reported outcome measures (PROMs) in palliative care patients. The findings indicate a voice recognition rate of 55.6%, highlighting the potential for reducing the burden on healthcare providers while improving data collection efficiency.
๐ Key Details
- ๐ Participants: 100 home-based palliative care patients
- ๐งฉ Methodology: Integrated Palliative Care Outcome Scale (IPOS) interviews and voice data transcription
- โ๏ธ Technology: Existing voice recognition tool and machine learning model
- ๐ Performance Metrics: F1 scores for symptom detection ranged from 0.31 to 0.46
๐ Key Takeaways
- ๐ PROMs are essential for evaluating symptoms in palliative care.
- ๐ค Voice recognition technology can alleviate the manual data entry burden on healthcare providers.
- ๐ Recognition rates for patient voices were significantly lower than overall rates.
- ๐ Machine learning models showed promise but require further refinement.
- ๐ฅ Patient demographics: Mean age of participants was 80.6 years, with 34% being men.
- ๐ฏ Future research is needed to enhance model performance and reliability.
- ๐ Insights gained could lead to broader use of PROMs in clinical settings.
๐ Background
In palliative care, patient-reported outcome measures (PROMs) play a crucial role in assessing patients’ symptoms and overall well-being. Traditionally, these measures are collected through conversations, which can be time-consuming and labor-intensive for healthcare providers. The integration of voice recognition technology offers a promising solution to streamline this process, yet research in this area remains limited.
๐๏ธ Study
Conducted between February and May 2023, this study recruited 100 home-based palliative care patients to evaluate the effectiveness of voice recognition and machine learning in capturing PROMs. The researchers utilized the Integrated Palliative Care Outcome Scale (IPOS) for interviews and employed an existing voice recognition tool to transcribe the collected voice data.
๐ Results
The study revealed a patient voice recognition rate of 55.6%, which was significantly lower than the overall recognition rate of 76.1%. The F1 scores for detecting five total symptoms ranged from 0.31 to 0.46, indicating that while the technology shows potential, there is substantial room for improvement in its accuracy and reliability.
๐ Impact and Implications
The findings from this study have significant implications for the field of palliative care. By leveraging voice recognition and machine learning, healthcare providers could potentially reduce the burden of recording PROMs, leading to more efficient data collection processes. This could enhance the overall quality of care for palliative patients and encourage the broader adoption of PROMs in clinical practice.
๐ฎ Conclusion
This study highlights the potential of voice recognition and machine learning in improving the collection of patient-reported outcomes in palliative care settings. While the current model requires further enhancements, the insights gained pave the way for future research and development in this innovative area. The integration of such technologies could significantly improve the efficiency of healthcare delivery and patient care.
๐ฌ Your comments
What are your thoughts on the use of voice recognition technology in healthcare? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
Using voice recognition and machine learning techniques for detecting patient-reported outcomes from conversational voice in palliative care patients.
Abstract
AIM: Patient-reported outcome measures (PROMs) are increasingly used in palliative care to evaluate patients’ symptoms and conditions. Healthcare providers often collect PROMs through conversations. However, the manual entry of these data into electronic medical records can be burdensome for healthcare providers. Voice recognition technology has been explored as a potential solution for alleviating this burden. However, research on voice recognition technology for palliative care is lacking. This study aimed to verify the use of voice recognition and machine learning to automatically evaluate PROMs using clinical conversation voice data.
METHODS: We recruited 100 home-based palliative care patients from February to May 2023, conducted interviews using the Integrated Palliative Care Outcome Scale (IPOS), and transcribed their voice data using an existing voice recognition tool. We calculated the recognition rate and developed a machine learning model for symptom detection. Model performance was primarily evaluated using the F1 score, harmonic mean of the model’s positive predictive value, and recall.
RESULTS: The mean age of the patients was 80.6โyears (SD, 10.8โyears), and 34.0% were men. Thirteen patients had cancer, and 87 did not. The patient voice recognition rate of 55.6% (SD, 12.1%) was significantly lower than the overall recognition rate of 76.1% (SD, 6.4%). The F1 scores for the five total symptoms ranged from 0.31 to 0.46.
CONCLUSION: Although further improvements are necessary to enhance our model’s performance, this study provides valuable insights into voice recognition and machine learning in clinical settings. We expect our findings will reduce the burden of recording PROMs on healthcare providers, increasing the wider use of PROMs.
Author: [‘Dong L’, ‘Hirayama H’, ‘Zheng X’, ‘Masukawa K’, ‘Miyashita M’]
Journal: Jpn J Nurs Sci
Citation: Dong L, et al. Using voice recognition and machine learning techniques for detecting patient-reported outcomes from conversational voice in palliative care patients. Using voice recognition and machine learning techniques for detecting patient-reported outcomes from conversational voice in palliative care patients. 2025; 22:e12644. doi: 10.1111/jjns.12644