Periodic Reporting for period 1 - REBECCA (REsearch on BrEast Cancer induced chronic conditions supported by Causal Analysis of multi-source data)
Okres sprawozdawczy: 2021-04-01 do 2022-09-30
The REBECCA project aspires to tap into the potential of Real-World Data (RWD) for supporting groundbreaking clinical research on complex chronic conditions (CCC) as a complement to Randomised Controlled Trials (RCT). REBECCA moves beyond the analysis of Electronic health records (EHR), by combining it with detailed monitoring data from multiple wearable, online behaviour and registry data to monitor patients’ functional, emotional and Quality of Life trajectories, with high temporal granularity. REBECCA also targets explainable causal modelling combined with deep learning to account for observed and latent confounders in RWD analysis. The project focuses on the complex array of chronic comorbidities developed during breast cancer recovery, in particular studying the impact of primary and adjuvant cancer treatment on patients’ quality of life and assessing the value of detailed patient monitoring as a means for improved patient care, but it also intends to demonstrate the extensibility of REBECCA to other forms of cancer. To this end, a total of seven studies in Sweden, Norway and Spain will produce new knowledge on clinical management of cancer patients that will shape future guidelines and practices for post-cancer treatments. Best practices resulting from the REBECCA studies will be disseminated to researchers, public health and regulatory bodies throughout Europe to facilitate wider adoption of RWD in clinical research. In addition, the REBECCA platform, capable of detailed monitoring and privacy preserving federated cross-country data analysis, aims to provide an infrastructure for continued progress on use of RWD beyond the end of the project. Through these activities, REBECCA aims at the mass adoption of RWD for understanding CCCs and ultimately at establishing RWD as a valuable clinical research and patient management tool.
During this first reporting period research work has focused on three interrelated domains:
1. Design and development of the necessary Real World Data collection infrastructure: This includes the (i) REBECCA Patient mobile application for android and iOS including linking to Garmin wearables, (ii) web plugin for monitoring on line activity, (iii) REBECCA Electronic Case Report Forms (CRF) for capturing patient EHR, (iv) backend server(s) for storage, processing and analytics, (v) REBECCA web based Clinical Dashboard. Version V1+ of this complex infrastructure has already been released and is ready to support the three forthcoming clinical studies. Thanks to intensive cocreation activities the design has integrated patients’ opinion, and reflects their needs and priorities. More than 500 patients have contributed with feedback. In addition, patient representatives have participated in testing the apps before its official release.
2. Enriching Real World Data with behavioural and emotional indicators:
This includes (i) indicators related to how patients move in their living space mainly derived from continuous recordings of their location, (ii) indicators related to the eating habits of the patients like meal timing and schedule, meal duration, eating preferences etc., (iii) indicators of patient’s emotional status derived from their on-line behaviour (searches, social media). Signal processing and deep learning algorithms have been developed and tested towards the production of these novel types of information that will become the basis for assessing patients functional and emotional state. Detailed discussions between technology and clinical experts have been carried out in order to identify the link of these novel indicators and the three complex chronic conditions that are studied within REBECCA: Chemotherapy (paclitaxel) Induced Peripheral Neuropathy (CIPN) (ii) Cancer Related Fatigue (CRF) and (iii) Osteoporosis and Osteopenia resulting from treatment with aromatase inhibitors (OST).
3. Causal modeling of the complex relations between behaviours, emotional state, Complex Chronic Conditions and Treatment:
This includes the design of Directed Acyclic Graphs that model these causal relations as well as the development of mathematical tools for predicting the effects of treatment on the various behaviours, emotions, symptoms, that correspond to nodes of the graph.
In parallel during the first 18 months of the project the three participating clinics finalized the protocols of the three aforementioned studies and carried out all the preparatory work including the necessary application for ethical approvals, acquisition/identification of the necessary personnel etc. All study sites have submitted applications for ethical approval, one has already been already accepted my the corresponding ethics committee (SUH) while the other two (KI/RSTO, INCLIVA) are close to obtaining the final approval.
During this first period extensive dissemination work has been done including the creation of Project logo and web site, presence in the social media and production of fliers and newsletters. Scientific work has already some published results. Participation to over 30 workshops and other meetings including “Cancer Survivorship – AI for wellbeing meeting” and the “Garmin Health Summit 2022 (Rome)” must be highlighted. Regarding exploitation, a methodology for approaching health authorities and the identification of exploitable assets and relevant IPRs is the first step towards a REBECCA exploitation plan.
1. Design and development of the necessary Real World Data collection infrastructure: This includes the (i) REBECCA Patient mobile application for android and iOS including linking to Garmin wearables, (ii) web plugin for monitoring on line activity, (iii) REBECCA Electronic Case Report Forms (CRF) for capturing patient EHR, (iv) backend server(s) for storage, processing and analytics, (v) REBECCA web based Clinical Dashboard. Version V1+ of this complex infrastructure has already been released and is ready to support the three forthcoming clinical studies. Thanks to intensive cocreation activities the design has integrated patients’ opinion, and reflects their needs and priorities. More than 500 patients have contributed with feedback. In addition, patient representatives have participated in testing the apps before its official release.
2. Enriching Real World Data with behavioural and emotional indicators:
This includes (i) indicators related to how patients move in their living space mainly derived from continuous recordings of their location, (ii) indicators related to the eating habits of the patients like meal timing and schedule, meal duration, eating preferences etc., (iii) indicators of patient’s emotional status derived from their on-line behaviour (searches, social media). Signal processing and deep learning algorithms have been developed and tested towards the production of these novel types of information that will become the basis for assessing patients functional and emotional state. Detailed discussions between technology and clinical experts have been carried out in order to identify the link of these novel indicators and the three complex chronic conditions that are studied within REBECCA: Chemotherapy (paclitaxel) Induced Peripheral Neuropathy (CIPN) (ii) Cancer Related Fatigue (CRF) and (iii) Osteoporosis and Osteopenia resulting from treatment with aromatase inhibitors (OST).
3. Causal modeling of the complex relations between behaviours, emotional state, Complex Chronic Conditions and Treatment:
This includes the design of Directed Acyclic Graphs that model these causal relations as well as the development of mathematical tools for predicting the effects of treatment on the various behaviours, emotions, symptoms, that correspond to nodes of the graph.
In parallel during the first 18 months of the project the three participating clinics finalized the protocols of the three aforementioned studies and carried out all the preparatory work including the necessary application for ethical approvals, acquisition/identification of the necessary personnel etc. All study sites have submitted applications for ethical approval, one has already been already accepted my the corresponding ethics committee (SUH) while the other two (KI/RSTO, INCLIVA) are close to obtaining the final approval.
During this first period extensive dissemination work has been done including the creation of Project logo and web site, presence in the social media and production of fliers and newsletters. Scientific work has already some published results. Participation to over 30 workshops and other meetings including “Cancer Survivorship – AI for wellbeing meeting” and the “Garmin Health Summit 2022 (Rome)” must be highlighted. Regarding exploitation, a methodology for approaching health authorities and the identification of exploitable assets and relevant IPRs is the first step towards a REBECCA exploitation plan.
During the first reporting period (M1-M18) the following beyond state of the art progress is reported:
(1) REBECCA has already developed a stable version (V1+) of tools that allows the collection of new types of RWD capturing patients life parameters. In addition a number of algorithms that extract indicators linked to patients' functional and emotional status have been developed. The design of algorithms for complete set of indicators has been scheduled for the next period.
(2) Extensive discussions between technology and clinical experts have resulted to the identification of technically feasible indicators that can be extracted from sensors embedded in mobile and wearable devices and are relevant to the three CCCs of REBECCA (CIPN, CRF and OST)
(3) DAGs have been chosen for representing causal relations between behaviours, emotional state, Complex Chronic Conditions and Treatment; novel mathematical tools have been developed for predicting the effects of treatment on the various behaviours, emotions and symptoms. Three specific DAGs have been created for each of REBECCA's CCC.
(4) The first three studies involving RWD to be collected via REBECCA platform have been prepared and will start immediately.
Regarding REBECCA Impact. All impacts described in the DoA are still relevant. The project follows the scheduled roadmap towards their realization.
(1) REBECCA has already developed a stable version (V1+) of tools that allows the collection of new types of RWD capturing patients life parameters. In addition a number of algorithms that extract indicators linked to patients' functional and emotional status have been developed. The design of algorithms for complete set of indicators has been scheduled for the next period.
(2) Extensive discussions between technology and clinical experts have resulted to the identification of technically feasible indicators that can be extracted from sensors embedded in mobile and wearable devices and are relevant to the three CCCs of REBECCA (CIPN, CRF and OST)
(3) DAGs have been chosen for representing causal relations between behaviours, emotional state, Complex Chronic Conditions and Treatment; novel mathematical tools have been developed for predicting the effects of treatment on the various behaviours, emotions and symptoms. Three specific DAGs have been created for each of REBECCA's CCC.
(4) The first three studies involving RWD to be collected via REBECCA platform have been prepared and will start immediately.
Regarding REBECCA Impact. All impacts described in the DoA are still relevant. The project follows the scheduled roadmap towards their realization.