Periodic Reporting for period 1 - ARTILLERY (Artificial Intelligence for early detection of non-communicable disease risk in people with breast cancer)
Reporting period: 2023-05-01 to 2024-10-31
The ultimate ambition of the ARTILLERY consortium is to enhance long term health of the growing population of breast cancer survivors by making optimal use of routine imaging for timely detection of actionable chronic conditions or their risk factors. ARTILLERY will develop trustworthy AI systems that allow robust and accurate risk prediction of common chronic conditions, including cardiovascular disease, chronic obstructive pulmonary disease, unfavorable body composition and osteoporosis. Implementation of these AI systems in routine care will provide healthcare professionals with objective and quantitative parameters of their patients’ individual chronic disease risks, permitting them to start prompt treatment and implement risk reducing strategies.
Unique aspects of ARTILLERY include the continuous and close interaction between renowned computational scientists, influential breast cancer professionals and the largest breast cancer patient advocacy organisation in Europe, as well as direct access to a large and comprehensive Real-World Data infrastructure that includes CT scans and clinical data from >26.000 patients with breast cancer.
This partnership will result in trustworthy AI systems for prevalent chronic conditions, relevant to breast cancer patients and physicians, and ready for implementation at radiotherapy workstations across Europe. ARTILLERY-manuals will be developed and made available to multidisciplinary tumour boards and will contain recommendations on how and when (not) to use AI systems in routine breast cancer care, and on optimal management of breast cancer patients identified to be at high risk of chronic conditions.
At the end of the project, we will have augmented the understanding and perception of the public towards the use of AI systems in routine healthcare and empowered breast cancer patients to make targeted lifestyle changes based on their individual risk profile, thus improving their life expectancy and quality of life.
Unique aspects of ARTILLERY include the continuous and close interaction between renowned computational scientists, influential breast cancer professionals and the largest breast cancer patient advocacy organisation in Europe, as well as direct access to a large and comprehensive Real-World Data infrastructure that includes CT scans and clinical data from >26.000 patients with breast cancer.
This partnership will result in trustworthy AI systems for prevalent chronic conditions, relevant to breast cancer patients and physicians, and ready for implementation at radiotherapy workstations across Europe. ARTILLERY-manuals will be developed and made available to multidisciplinary tumour boards and will contain recommendations on how and when (not) to use AI systems in routine breast cancer care, and on optimal management of breast cancer patients identified to be at high risk of chronic conditions.
At the end of the project, we will have augmented the understanding and perception of the public towards the use of AI systems in routine healthcare and empowered breast cancer patients to make targeted lifestyle changes based on their individual risk profile, thus improving their life expectancy and quality of life.
The main goal of this project is to develop trustworthy AI systems for early detection of actionable chronic diseases, or their risk factors, in people with breast cancer, with the aim to improve life expectancy and quality of life of the growing population of breast cancer survivors.
To this end, our first objective is to develop trustworthy AI systems for automated detection of chronic conditions that are relevant to breast cancer patients and health care professionals. These systems will be ready for installation at radiotherapy and radiology workstations across Europe.
Our second objective is to define recommendations and management/treatment strategies, including (lifestyle) advice, for breast cancer patients identified by AI systems to have (an increased risk of) chronic diseases. For this purpose, we will set up multidisciplinary teams, who will generate recommendations and follow up strategies of patients flagged by the AI systems to be at high risk of one or more chronic conditions. At the end of the project, we will have provided manuals that inform tumour boards on how and when (not) to use AI systems in routine breast cancer care. These manuals contain recommendations on optimal management of breast cancer patients identified to be at high risk of chronic conditions.
The third objective is to evaluate the impact of AI systems implementation on clinical decision making in routine breast cancer care, assessing and quantifying benefits for patients. At the end of the project, we will have actual insights about uptake and acceptability of the AI systems in routine patient care, the extent to which AI systems impact clinical decision making, and the impact on patients’ wellbeing.
Our fourth objective is to work towards valorization of trustworthy (ie. lawful, ethical and robust) AI-based software and product development. At the end of the project, we will have augmented the understanding and perception of the public towards the use of AI systems in routine health care and empowered breast cancer patients to have a good overview on their general health status and tools that specifically address risk factors or targets to optimize their individual health.
To this end, our first objective is to develop trustworthy AI systems for automated detection of chronic conditions that are relevant to breast cancer patients and health care professionals. These systems will be ready for installation at radiotherapy and radiology workstations across Europe.
Our second objective is to define recommendations and management/treatment strategies, including (lifestyle) advice, for breast cancer patients identified by AI systems to have (an increased risk of) chronic diseases. For this purpose, we will set up multidisciplinary teams, who will generate recommendations and follow up strategies of patients flagged by the AI systems to be at high risk of one or more chronic conditions. At the end of the project, we will have provided manuals that inform tumour boards on how and when (not) to use AI systems in routine breast cancer care. These manuals contain recommendations on optimal management of breast cancer patients identified to be at high risk of chronic conditions.
The third objective is to evaluate the impact of AI systems implementation on clinical decision making in routine breast cancer care, assessing and quantifying benefits for patients. At the end of the project, we will have actual insights about uptake and acceptability of the AI systems in routine patient care, the extent to which AI systems impact clinical decision making, and the impact on patients’ wellbeing.
Our fourth objective is to work towards valorization of trustworthy (ie. lawful, ethical and robust) AI-based software and product development. At the end of the project, we will have augmented the understanding and perception of the public towards the use of AI systems in routine health care and empowered breast cancer patients to have a good overview on their general health status and tools that specifically address risk factors or targets to optimize their individual health.
Over the past years, multiple AI-based algorithms for automatic quantification of cardiovascular risk, body composition, osteoporosis, and chronic obstructive pulmonary disease (COPD) from CT exams have been proposed. Many of those algorithms, including the ones developed by the ARTILLERY consortium, have demonstrated excellent performance. However, very few methods were developed for quantification in radiotherapy planning CT scans and hence, available methods are typically not directly applicable to this data. Moreover, the development of those algorithms has been mostly focussed on achieving accurate performance, while issues regarding trustworthy employment have not gained much attention. Consequently, clinicians lack tools for their daily practice to perform a simple and reliable assessment of actionable chronic disease risks in their patients with breast cancer. Hence, we aim to develop trustworthy AI-based software tools for analysis of medical images addressing four distinct but related, conditions in breast cancer patients: 1) cardiovascular disease, 2) unfavourable body composition, 3) low bone density / osteoporosis, and 4) COPD.
In the current project, we will establish a Real-World Data (RWD) infrastructure for algorithm development at an unprecedented scale: a large repository of routine (annotated) CT scans of >26.000 breast cancer patients, which can be combined with other patient variables and outcomes, and which can be used by partners and other parties for derivation, validation and clinical evaluation of new algorithms. Further, we will set up a collaboration, unique in the field of breast cancer, where AI system developers (AI scientists, software developers) and AI system users (health care professionals and patients) will actively interact along the different stages of AI system development. This way, the ARTILLERY project will facilitate the development of AI systems that are beneficial for and trusted by healthcare professionals and patients, are evidence-based, and ready to be implemented in clinical settings.
Overall, the ultimate ambition of the ARTILLERY consortium is to enhance long term health of breast cancer survivors by making optimal use of routine imaging to identify patients with risk factors or pre-symptomatic chronic conditions. This will empower patients to make targeted lifestyle changes based on their individual risk profile. At a teachable moment during the patient journey (ie. shortly after a life changing breast cancer diagnosis), physicians are facilitated to make use of objective and quantitative parameters of the patients’ general health status, which will help facilitate discussions about the need for risk reducing strategies.
In the current project, we will establish a Real-World Data (RWD) infrastructure for algorithm development at an unprecedented scale: a large repository of routine (annotated) CT scans of >26.000 breast cancer patients, which can be combined with other patient variables and outcomes, and which can be used by partners and other parties for derivation, validation and clinical evaluation of new algorithms. Further, we will set up a collaboration, unique in the field of breast cancer, where AI system developers (AI scientists, software developers) and AI system users (health care professionals and patients) will actively interact along the different stages of AI system development. This way, the ARTILLERY project will facilitate the development of AI systems that are beneficial for and trusted by healthcare professionals and patients, are evidence-based, and ready to be implemented in clinical settings.
Overall, the ultimate ambition of the ARTILLERY consortium is to enhance long term health of breast cancer survivors by making optimal use of routine imaging to identify patients with risk factors or pre-symptomatic chronic conditions. This will empower patients to make targeted lifestyle changes based on their individual risk profile. At a teachable moment during the patient journey (ie. shortly after a life changing breast cancer diagnosis), physicians are facilitated to make use of objective and quantitative parameters of the patients’ general health status, which will help facilitate discussions about the need for risk reducing strategies.