TY - GEN
T1 - Modelling a Good Delivery of Bad News
AU - Aharonson, Vered
AU - Cocker, Brittany
AU - Buisson-Street, Keren
AU - Winter, Danielle
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/8
Y1 - 2021/8
N2 - The development of soft skills and specifically good delivery of bad news gain increasing importance in all healthcare disciplines. These skills improve the communication between healthcare professionals, patients and their families. Good delivery of bad news is defined and taught using qualitative and subjective means. Quantitative voice and language attributes could provide an automated practice and education tool for healthcare professionals and improve their delivery of bad news. We investigated acoustic and verbal features in a database recorded by healthcare professional simulating delivery of bad news. The recordings were rated by other healthcare professionals and labelled as 'good' or 'bad'. Prosodic features were extracted directly from the recordings and provided speech tone attributes. Automated speech recognition was applied to compute the speech pace feature. A bidirectional long short term memory network was trained on the features and labels. The classification model trained on the tone features yielded an accuracy of 81.8%. The model trained on the combined tone and pace features yielded an accuracy of 90.0%. This proof of concept implies a feasibility for a fully automated practice tool that could quantify good delivery attributes and train and improve the skills of healthcare professionals in their delivery of bad news.
AB - The development of soft skills and specifically good delivery of bad news gain increasing importance in all healthcare disciplines. These skills improve the communication between healthcare professionals, patients and their families. Good delivery of bad news is defined and taught using qualitative and subjective means. Quantitative voice and language attributes could provide an automated practice and education tool for healthcare professionals and improve their delivery of bad news. We investigated acoustic and verbal features in a database recorded by healthcare professional simulating delivery of bad news. The recordings were rated by other healthcare professionals and labelled as 'good' or 'bad'. Prosodic features were extracted directly from the recordings and provided speech tone attributes. Automated speech recognition was applied to compute the speech pace feature. A bidirectional long short term memory network was trained on the features and labels. The classification model trained on the tone features yielded an accuracy of 81.8%. The model trained on the combined tone and pace features yielded an accuracy of 90.0%. This proof of concept implies a feasibility for a fully automated practice tool that could quantify good delivery attributes and train and improve the skills of healthcare professionals in their delivery of bad news.
KW - Educating message delivery
KW - Healthcare communication
KW - Long-short term memory network
KW - Soft skills
KW - Speech analytics
KW - Speech rate
KW - Speech tone
UR - https://www.scopus.com/pages/publications/85118188794
U2 - 10.1109/ICHI52183.2021.00043
DO - 10.1109/ICHI52183.2021.00043
M3 - Conference contribution
AN - SCOPUS:85118188794
T3 - Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021
SP - 224
EP - 227
BT - Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th IEEE International Conference on Healthcare Informatics, ISCHI 2021
Y2 - 9 August 2021 through 12 August 2021
ER -