Skip to main content

Predicting Effective Adaptation to Breast Cancer to Help Women to BOUNCE Back

Periodic Reporting for period 2 - BOUNCE (Predicting Effective Adaptation to Breast Cancer to Help Women to BOUNCE Back)

Okres sprawozdawczy: 2019-05-01 do 2020-10-31

The goal of BOUNCE is to incorporate elements of a dynamic, predictive model of patient outcomes in building a decision-support module used in routine clinical practice to provide physicians and other health professionals with concrete, personalized recommendations regarding optimal psychosocial support strategies of early breast cancer patients.
There is need to improve understanding and better predict resilience of women with stressful experiences and practical challenges related to breast cancer. This leads toward efficient recovery through personalized interventions. BOUNCE will take into consideration clinical, cancer related, lifestyle, and psychosocial parameters in order to predict individual resilience trajectories and eventually increase resilience in breast cancer survivors and improve their quality of life.
1.To survey personal, clinical, and biological measures available for existing patient cohorts, in order to construct a preliminary model of patient resilience and quality of life.
2.To construct a measurement model of patient resilience to the physical and emotional challenges associated with the disease itself and with the burden incurred by BC treatments using data from the clinical pilot.
3.To develop operational algorithms for predicting long-term patient outcomes by taking into account individual levels of resilience at each time point during the course of illness, and current/past biological, sociodemographic, psychosocial, personal, clinical, and life-style patient characteristics.
4. To address long-standing issues in the field of psycho-oncology regarding the dynamics of time-varying relationships between determinants of resilience and disease outcomes.
5. To define measurable and potentially modifiable social, psychological, and lifestyle parameters that optimally define successful adaptation to BC-related stressors as determinants of long-term patient outcomes.
6.To ensure wide communication and scientific dissemination of the innovative BOUNCE results to the research, academic, and international community, the efficient exploitation and business planning of the BOUNCE concepts and tools as well as the contribution of specific project results to relevant standardization bodies.
First in WP1 the value chain for the project was defined, different stakeholders identified, the requirements for the outputs of the computer models and the overall BOUNCE platform and services/tools were defined and methodology was elaborated.

WP2 dealt with definition and assessment of 1. resilience in women with breast cancer, 2. resilience as a dynamic process critically involved in effective illness adaptation and recovery , 3. multi-level factors potentially affecting resilience, 4.multi-scale factors related to the evolution of resilience, in relation to both constant and time-varying patient characteristics, 5. changes in social and other life circumstances.

WP3 delivered the Data Cleaner (front-end and back-end), introducing several optimisations based on statistical methods, which are now applied on all the collected prospective data. All data collected till M36 were successfully ingested and provided as input to WP4/WP5, after being processed with the corresponding tools for data cleaning, recoding, identification of missing data, assessment of missing data patterns, integration and homogenization.

In WP4 pertinent clinical scenarios involving the use of several modelling components have been formulated. One scenario aims at the prediction of the psychological outcome for a new patient, based on the sociodemographic and medical characteristics, and the patient’s psychological profile at baseline. The predictors refer to the baseline only and the outcome refers either to month 3 or 6 after the baseline. Features explaining the outcome have been identified. Indicative variables that have been considered as outcomes are HADS: anxiety and depression and QLQ30: global quality of life and physical functioning. Artificial Intelligence models based on supervised learning have been constructed. The following major steps regarding modelling have been extensively addressed: 1. data preprocessing 2. model construction, and 3. evaluation. Patient classification based on trajectory clustering is in progress.

In WP5, new versions of all the functional components of the BOUNCE platform have been released, including the Temporary Research Support Tool, the Model Repository, the In silico Prediction Repository, the Execution Engine, the Integrated Predictive Tool and the Recommendation Engine. As a result, BOUNCE platform (second iteration) has been completed and successfully delivered.

In WP6 prospective data on clinical, psychological, functional and quality of life factors were collected at baseline in Finland, Italy, Israel, Portugal for 748 breast cancer patients. Follow-up data collection was performed on months 3 and 6, while it is still on going for months 9-18. Collected data have been provided to the technical partners for a first modelling of resilience. Following the first analyses on prospective data, a pilot study has been designed to test the efficacy of the preliminary resilience model.

In WP7 a cost-benefit analysis of the Desicion support tool aims at demonstrating the benefits to different stakeholders. A preliminary cost benefit model has been constructed were the cost and the benefit parameters have been defined, the data sources outlined, and a preliminary literature review of parameter values conducted.

In WP8 the work focused on dissemination and exploitation. Stakeholders have been engaged via conference presentations, workshops, individual interviews, and focus group interviews. The consortium has discussed and identified ownership interests, identified and evaluated different busines models’ scenarios for the BOUNCE assets, and a preliminary marked analysis has been conducted.

In WP9 deals with ethics, risk management and administration.
The main exploitable asset of BOUNCE will be a decision support module for clinicians treating breast cancer patients. The system is comprised of a set of clinically validated, in silico resilience trajectory prediction algorithms and the integrated BOUNCE technological platform. The algorithms will form the basis of a prediction system capable of providing individualized predictions of resilience levels. The resilience trajectory models can support the selection of personalized interventions and ultimately enhance the capacity of individual breast cancer patients to better adapt to the illness.
aims to achieve this by:
-Making the prediction algorithms and the BOUNCE technological platform available for interested users
-Identifying consortium partners to manage the system licences, distribution and user support
-Describing the roadmap and developing a business model for commercialization
BOUNCE aims to contribute to the academic community and have a societal impact. BOUNCE partners strive to reach out and engage closely with project stakeholders throughout the project. BOUNCE partners will build a scientific community around the project via organizing and participating in workshops and conferences.
Wider implications so far:
Data collection has been completed up tp months 6 and the first results has been analysed. As the modeling of resilience trajectories will proceed the understanding of exploitation possibilities will increase significantly.
A schematic diagram highlighting the vision and key aspects of BOUNCE