Summary
One over three women with breast cancer will develop mental health issues, adding the burden of a deterioration of their quality of life to the management of cancer itself.
The objective of the MATER project is to improve the detection and monitoring of mental health in women with breast cancer by leveraging symptom networks and vocal biomarkers. The project addresses three research questions. We first hypothesize that the use of symptom networks will allow a better understanding of the links between depressive symptoms, fatigue and a decreased quality of life, and identify the most important symptoms in the deterioration of the mental health of these women.
We also assume that automatically estimating these symptoms using voice descriptors extracted from real-life recordings and machine learning pipelines will make it easier to monitor them in the patients' homes. Finally, we hypothesize that the use of a Bayesian network algorithm combining the symptom network and the voice-based symptom estimations will allow a more accurate joint estimation of these symptoms - and thus improve the identification and monitoring of mental health-related symptoms in women with breast cancer.
The interdisciplinary MATER project is based on Colive Voice, a unique dataset of clinical and voice data and leverages both the complementary host's and supervisor's extensive experience in digital and personalized health and the applicant's knowledge of vocal biomarker design and machine learning, mental disorder semiology, and Bayesian networks. This project will allow the applicant to improve his skills in voice signal processing, precision health (in particular in oncology), but also in scientific project management and in research valorization, creating an international network and elevating his profile to such levels as to accelerate his access to high-level academic positions.
The objective of the MATER project is to improve the detection and monitoring of mental health in women with breast cancer by leveraging symptom networks and vocal biomarkers. The project addresses three research questions. We first hypothesize that the use of symptom networks will allow a better understanding of the links between depressive symptoms, fatigue and a decreased quality of life, and identify the most important symptoms in the deterioration of the mental health of these women.
We also assume that automatically estimating these symptoms using voice descriptors extracted from real-life recordings and machine learning pipelines will make it easier to monitor them in the patients' homes. Finally, we hypothesize that the use of a Bayesian network algorithm combining the symptom network and the voice-based symptom estimations will allow a more accurate joint estimation of these symptoms - and thus improve the identification and monitoring of mental health-related symptoms in women with breast cancer.
The interdisciplinary MATER project is based on Colive Voice, a unique dataset of clinical and voice data and leverages both the complementary host's and supervisor's extensive experience in digital and personalized health and the applicant's knowledge of vocal biomarker design and machine learning, mental disorder semiology, and Bayesian networks. This project will allow the applicant to improve his skills in voice signal processing, precision health (in particular in oncology), but also in scientific project management and in research valorization, creating an international network and elevating his profile to such levels as to accelerate his access to high-level academic positions.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101106577 |
| Start date: | 01-09-2023 |
| End date: | 31-08-2025 |
| Total budget - Public funding: | - 175 920,00 Euro |
Cordis data
Original description
One over three women with breast cancer will develop mental health issues, adding the burden of a deterioration of their quality of life to the management of cancer itself.The objective of the MATER project is to improve the detection and monitoring of mental health in women with breast cancer by leveraging symptom networks and vocal biomarkers. The project addresses three research questions. We first hypothesize that the use of symptom networks will allow a better understanding of the links between depressive symptoms, fatigue and a decreased quality of life, and identify the most important symptoms in the deterioration of the mental health of these women.
We also assume that automatically estimating these symptoms using voice descriptors extracted from real-life recordings and machine learning pipelines will make it easier to monitor them in the patients' homes. Finally, we hypothesize that the use of a Bayesian network algorithm combining the symptom network and the voice-based symptom estimations will allow a more accurate joint estimation of these symptoms - and thus improve the identification and monitoring of mental health-related symptoms in women with breast cancer.
The interdisciplinary MATER project is based on Colive Voice, a unique dataset of clinical and voice data and leverages both the complementary host's and supervisor's extensive experience in digital and personalized health and the applicant's knowledge of vocal biomarker design and machine learning, mental disorder semiology, and Bayesian networks. This project will allow the applicant to improve his skills in voice signal processing, precision health (in particular in oncology), but also in scientific project management and in research valorization, creating an international network and elevating his profile to such levels as to accelerate his access to high-level academic positions.
Status
SIGNEDCall topic
HORIZON-MSCA-2022-PF-01-01Update Date
31-07-2023
Images
No images available.
Geographical location(s)
