Deliverables

The IDEA-FAST Project Handbook has two main functions. Firstly, it acts as a reference source for all Consortium members, covering many of the day-to-day activities and providing links to further information where required. Secondly, it aims to standardise various elements of the project e.g. project reports, deliverables, file naming conventions etc. through the use of agreed procedures and templates where relevant.

This document details the procedure within IDEA-FAST by which the project risks are identified, categorised and monitored. The most important, critical risks are already described in Annex I of the Grant Agreement. Additional risks will be identified as part of the project review and planning process.

The first study subject approvals package includes the final version of the feasibility study (FS) protocol, the registration number of the feasibility study as well as a short report on the ethical approval status at all four sites. Ethical approval was obtained at one of the four sites so far. As a result, the first subject was included in the IDEA-FAST FS as planned in July 2020 (Month 9).

The FS aims to identify candidate digital parameters of fatigue and sleep disturbances to be further tested in the subsequent, larger clinical validation study (CVS). Four European centres (Universitätsklinikum Schleswig-Holstein, Campus Kiel (UKSH), Newcastle upon Tyne Hospitals NHS Foundation Trust/Newcastle University (UNEW), Erasmus University Medical Centre (EMC), and George-Huntington-Institut GmbH (GHI)) will investigate this research question in four parallel studies in different disease populations which include Parkinson’s disease (PD), Huntington’s Disease (HD) inflammatory bowel disease (IBD), primary Sjögren’s syndrome (PSS), rheumatoid arthritis (RA) and systemic lupus erythematosus (SLE) as well as healthy volunteers (HV). Participants will be asked to report sleep disturbances and fatigue by means of questionnaires and a digital diary during a study period of 28-36 days. During the study period, they will also use various digital devices/technologies for four periods of five days each (devices worn consecutively, maximum of three devices simultaneously in addition to a smartphone). Measures collected through novel digital tools will be compared with traditional measures: i) clinical outcomes (e.g., surveys) and ii) patient-reported outcomes (questionnaires and diaries). Digital measures which best correlate with the patient-reported measures of sleep disturbances and fatigue as well as the clinical outcome measures will be considered for further investigations in the CVS. The FS will also assess usability, acceptability, tolerability and compliance aspects concerning the different digital technologies as well as social functioning measures.

The aim of the work reported in this deliverable was to develop and build a robust Data Capture System
(database) to collect all necessary participant information for the CVS protocol. Similarly to the FS,
this included participant registration, clinical data collection in an electronic case report form (CRF)
together with appropriate device information. Data collected on the clinical database would then be
securely transferred to the Data Management Platform (DMP).

This report presents the device selection process and materials for the IDEA-FAST project. The project aims to identify digital endpoints to assess fatigue, sleep and activities of daily living in neurodegenerative disorders and immune-mediated inflammatory diseases. The project includes a feasibility study that will serve to assess the possibility of mapping data collected through a range of different sensor devices and behaviour tracking applications to several clinical concepts of interest. The feasibility study (FS) will also assess the acceptability of the devices in order to inform a further selection of devices towards a large-scale clinical validation study.

This report provides information on the device selection criteria, processes and documents produced in the pre-FS phase of the project, which also forms the first deliverable that is part of work-package (WP) 3 Devices and Technology (deliverable D3.1 [project internal numbering] or 8 [in the project officer count]: Device selection criteria and documents / processes for gathering evidence). This includes the rationale and development report for device selection criteria as well as evidence collection processes and materials (as designed for and employed in pre-FS phase, together with – where applicable – adjustments in preparation for the FS).

The IDEA-FAST project assesses the value of modern wearable measurement devices and the data and information they generate in the context of sleep disturbance and fatigue assessments. The assessment is based on two studies: Feasibility Study (FS) and Clinical Validation Study (CVS). The subjects in the studies will be patients of chronic diseases such as neurodegenerative disorders (NDD) and immune-mediated inflammatory diseases (IMID) as well as healthy participants. Work package 4 (WP4) in the project is responsible for device specific data analytics. This document describes the assessment protocol for the FS which is the first deliverable of WP4.

The assessment protocol described in this document will be based on data that will be collected in the FS: clinical data, baseline and online questionnaire data and device data. As the absolute reference of the sleep- and fatigue related data will not be available, the assessment will be based on three factors: 1) Data quality and reliability of the digital measure, 2) Performance as compared to patient reported outcomes, 3) Performance across patient cohorts.

The protocol suggests that the outcome of device assessment will be provided as a recommendation based on the above 3 factors. The device performance will be represented in visual formats like Bland-Altman plots and radar charts. This allows reader to compare the devices across the above factors in an intuitive objective manner.

This document specifies the preliminary requirements for the data analysis software package in the IDEA-FAST project. The package was agreed to run in the analytical environment which is a part of the Data Management Platform (DMP) developed in the project. Therefore, the document is written for: 1) the developers of the analytical environment to understand the specific needs of the analysis process; and 2) researchers and analysts to realise the data characteristics and analysis methods developed in the project so far.

The DMP has been developed to store and manage the data collected throughout the project. The analytical environment (AE) will allow users to analyse the project datasets without downloading and keeping a copy of the dataset on their local computers, which further prevents data breaches. The AE provides a web-based UI for users to access remote computing resources. Users can access the AE via web browsers, using their email address and password to securely login. Scientific applications such as Jupyter, Matlab, Tensorboard, RStudio will be available via the AE while the primary programming language is Python. Access to Github repositories which are hosting code to perform the analysis is also supported.

The main aim of the analysis is to predict fatigue and sleep disturbances. The analysis methods presented in this document are based on the analysis pipeline described in detail in deliverables D4.1 and D4.3. They focus on device specific data processing methods divided in to 4 Concepts of Interest (COI): Activity, Physiology, Sleep and Social/Cognitive. Devices of the Activity, Sleep and Physiology COI share similar characteristics: they are collecting data continuously with a sampling rate of 25-250Hz. The features of interest, step count, movement magnitude, heart rate and heart rate variability, are calculated using basic signal processing methods available in Python libraries such as Scipy and Numpy and the Matlab Signal processing toolbox. With cognitive and social COIs, the data contains responses to cognitive tests conducted twice a day on a tablet, or mobile phone usage logs. The amount of data in these cases is rather low and usually compressed to daily aggregates for further analysis.

Actual prediction of fatigue and sleep disturbances is based on association- and multivariate analysis. Featured device data is aggregated into time windows and then compared to each other and subjective fatigue and sleep related ratings (PROs). General methods to be used are data normalisation, repeated measures of correlation and regressor investigations. These methods can be implemented e.g. using following Python libraries: pandas, numpy, scipy, pingouin, statsmodels, and sklearn. Finally, the analysis results are typically reported in table or graph format using e.g. the matplotlib library.

This document details how the data collected, processed and generated by the IDEA-FAST project will be managed during and after the end of the project. It explains the purpose of the data collection and describes the different types of data and the associated data standards. Plans for the preservation, sharing and re-use of the data are also outlined.

This document details the specification of the IDEA-FAST Data Management Platform (DMP). It defines the functionality requirements of the DMP, with detailed explanations on the DMP components including Data Storage and Sharing, Authentication, Authorisation and User Management, APIs and Analytical Environment. It also describes the technical specifications of the underlying infrastructure of the DMP. System security features and requirements are also outlined.

This document describes the data standards designed for the clinical studies of the IDEA-FAST project with respect to sleep/fatigue/activities of daily living (ADL) and the ontology for sensor measurements. It provides examples and guidelines for standardising clinical data and device data collected by the IDEA-FAST project. The data standards defined in this document are based on the Study Data Tabulation Model (SDTM) developed by the Clinical Data Interchange Standards Consortium (CDISC). This document (deliverable D5.4) was intended to be a public version of deliverable D5.3, with any confidential information removed. However, on review, it was decided that the full content of D5.3 can be made publicly available. Thus D5.4 is essentially the same document as D5.3.

Deliverable D6.1 describes the first version of the protocol for the clinical observational study (COS; formerly clinical validation study – CVS). As the study will be of observational nature and the focus is on identifying and evaluating digital parameters of fatigue, sleepiness and sleep disturbances in general, the consortium decided to rename the study “clinical observational study” to avoid the impression that the focus is on validating specific digital devices. The COS will follow 2000 participants (500 subjects each for Parkinson’s Disease (PD) and Inflammatory bowel disease (IBD), 200 each for Huntington’s Disease (HD), Rheumatoid Arthritis (RA), Systemic Lupus Erythematosus (SLE), Primary Sjögren’s Syndrome (PSS) and healthy controls) in four visits over six months each. Each participant will attend two study visits at the recruitment centres at Month 0 and Month 6 of the COS, as well as two remote visits in between. Following each visit, participants will use a combination of digital health technologies in their own environment for one week each. We selected seven digital health technologies based on the Feasibility Study (FS) results, feature engineering exercises, analyses of relevant extant datasets and a literature review. Concomitant data on fatigue, sleep, selected ADLs and other confounding variables, together with other relevant contextual information will be collected remotely several times a day during the period of digital health technology use. The inclusion of two “remote visits” will enable us to collect data on acceptability, feasibility and operational challenges relating to the future use of these digital endpoints in a remote decentralised clinical trial setting, and will permit direct comparison of data quality, patient compliance and cost of a remote study versus a traditional clinical study. As far as possible in the framework of an observational study, a baseline blood test to screen for potential contributing factors of fatigue will be performed. We will also collect blood, urine and stool samples for biobanking (optional for participants, samples to be stored but not analysed in the context of this project). Our cohorts will be drawn from 22 centres across 10 countries within Europe, representing geographic, ethnic and healthcare diversity.

Deliverable D6.2 provides the study protocol V2.0 & participant information material for the clinical observational study (COS). As the study will be observational in nature and the focus is on identifying and evaluating digital parameters of fatigue, sleepiness and sleep disturbances in general, the consortium decided to rename the study “COS” to avoid the impression that the focus is on validating specific digital devices. The COS will follow 2,000 participants (500 subjects each for PD and IBD, 200 each for HD, RA, SLE, PSS and healthy controls). The study will run for 29 months, and each participant will be enrolled for a period of 24 weeks. During this time, each participant will attend two study visits at the recruitment centre (at week 0 and week 24 of their respective study period) as well as two remote visits in between (at week 8 and 16). During the visits, participants undergo a comprehensive assessment of demographic and clinical aspects as well as a granular assessment of fatigue, sleepiness and sleep disturbances using current reference tools (e.g. patient-reported outcomes, PROs). Furthermore, data on mood and pain are collected. Following each face-to-face / remote visit, participants use a combination of digital health technologies in their own environment for one week each. This is designated the technology use period (TUP). We selected two digital health technologies (and an additional one on an optional basis) based on the results of the Feasibility Study (FS), feature engineering exercises, analyses of relevant extant datasets and a literature review. Concomitant data on fatigue, sleep, selected ADLs and other confounding variables, together with other relevant contextual information will be collected remotely up to three times a day during the period of digital health technology use with Apps. The inclusion of two remote visits will enable us to collect data on acceptability, feasibility and operational challenges of the future use of these digital endpoints in a remote decentralised setting, and permits direct comparison of data quality and patient compliance in a remote study versus a clinical study. As far as possible in the framework of an observational study, blood, urine and stool samples will be collected for biobanking. Our cohorts will be drawn from 17 centres across 10 countries within Europe, representing geographic, ethnic and healthcare diversity.

Deliverable D6.4 provides the first study subject approvals package of the Clinical Observation Study (COS; formerly clinical validation study – CVS). This includes the registration number of the COS, a short report on the ethical approval status at all sites, and the document of the ethics board of the Sponsor (ethical committee of the Medical Faculty, University Hospital Schleswig-Holstein, Kiel, Germany) that reports about approval of the COS for Kiel site.

This deliverable reports on the recruitment situation of the 29-month IDEA-FAST Clinical Observational Study (COS, initially called Clinical Validation Study) after the first 6 months. Up to the date of submission, 265 participants have been recruited, which is encouraging given that circumstances such as different regulations and requirements of local ethics committees (concerning ethics applications) and legal departments (concerning site agreements) led to a delayed start of the COS. In addition, recruitment was markedly hampered by the Corona pandemic. Those teams that were able to recruit report feasible assessment across the visits. Participants are reporting back that the study is meaningful and future-oriented in their view. As far as can be judged with the current data and our own experience as sponsor / cohort leads, the compliance of the participants is excellent and there is a very good retention rate. Nevertheless, the current recruitment rate is still below our target recruitment rate. This is partly because it took considerably longer to implement the required site agreement at some of the recruiting sites due to slow responses from their legal teams. Until this agreement was in place, recruitment could not start at these sites. In order to overcome this slow start, the following adaptations to the initial COS strategy have been initiated: (i) facilitating recruitment of participants at the individual sites, (ii) adding more institutions to the recruiting centres, i.e. departments that are located at already recruiting sites, and (iii) supporting teams from local study sites and inform them as well as possible. With these adaptations, we are optimistic that we will still reach our final target of N=2000 in January 2025. This is supported by the enormous commitment of all people involved, including patients.

The Feasibility Study must be based on a standard model informed consent form. That model informed consent form should then be adapted by each participating centre according to its own customs (to which the IRB is used) and be made disease specific. The model is attached here. In order to make the text more readable, the informed consent to participate and the privacy statement following article 13 of the General Data Protection Regulation have been separated. The model is based on the model which had been developed in the IMI Big Data for Better Outcomes (BD4BO) project.

The Clinical Observational Study (COS), formerly the Clinical Validation Study (CVS), must be based on a standard model informed consent form. That model informed consent form should then be adapted by each participating centre according to its own language and customs (to which the IRB is used) and be made disease-specific. The model is attached here. In order to make the text more readable, the informed consent to participate and the privacy statement following article 13 of the General Data Protection Regulation are shown separately in the Appendices. The model is based on the model which had been developed in the IMI Big Data for Better Outcomes (BD4BO) project.

In this Deliverable raw device data are seen as the electronic signals which a device generates before
they are via software translated into human intelligible data. This Deliverable discusses the legal
possibilities to open up such raw data for research outside the context of a research plan and consortium
agreement where the manufacturers had agreed in advance that the raw data would be shared. Such
projects are rare while with the digital transformation in health care more and more devices will come
onto the market. There will always be a certain loss of information in the translation of raw data into
human intelligible data. The Deliverable assumes that in certain research projects one would need the
full data for a better clinical understanding or simply to control the software which translates raw data
to the human understandable data or clinical interventions as happens which devices such as ICD’s.

The objective of IDEA-FAST is to identify digital endpoints that provide reliable, objective and sensitive evaluation of, fatigue, sleep, activity of daily living (ADL), and health-related quality of life (HRQoL) for patients with chronic diseases such as neurodegenerative disorders (NDD) and immune-mediated inflammatory diseases (IMID). A critical part of the work plan is to ensure that IDEA-FAST is disseminated to stakeholders in the most effective and timely way. Deliverable D9.1 Detailed Dissemination Plan develops an implementable strategy with related methodologies to maximise the impact of IDEA-FAST. The strategy is built around providing key knowledge at the right time in the most appropriate format to stakeholders including the general public. For each stakeholder group key objectives and messages are identified together with their timing. In addition, the dissemination methodologies have been identified and roles and responsibilities assigned to IDEA-FAST participants.

The IDEA-FAST project aims to identify novel digital endpoints to assess fatigue and sleep disturbances in neurodegenerative disorders and immune-mediated inflammatory diseases. The project’s initial investment will result in several exploitable assets that will aid key stakeholders to investigate fatigue and sleep disturbances and make use of the digital endpoints. To design an effective strategy for sustainability and exploitation, Work Package 9 aims to provide a thorough understanding of how various stakeholders can benefit from the proposed digital endpoints and ensure uptake of all other exploitable assets developed within the lifetime of the project. The present deliverable provides an initial framework for the socio-economic impact assessment and sets out the exploitation analysis framework. This work will contribute to ensuring that the exploitable assets generated within the project survive post-project funding and are consequently sustained.