INTRODUCTION

INTRODUCTION

Existing initiatives on early detection and intervention on health and social risks are demonstrated only in clinical trials. Several healthcare systems in Europe – including many recruited in this project – have put in place strategies to stratify populations at risk based on the level of complexity. In some of these cases such stratifications is based on digitalized health records and in few of them the health records are integrating information from primary and secondary care settings. However, risk prevention and management is not implemented proactively.

GATEKEEPER Large Scale Pilots (LSP) will establish and consolidate the different Use Cases through Europe enabling the deployment of digital solutions for early detection and intervention and support the risk stratification models. They ensure that GATEKEEPER users’ and medical requirements for early detection and intervention are correctly deployed in a coordinated way in all pilot sites.

The ambition of carrying out LSP across Europe is to cooperate together among the pilot sites and with the involvement of a large number of users in order to assess and contribute to the understanding of differentiating factors of successful solutions in the area of health and social risks prevention for understanding AHA. 

The Use Cases that will be implemented in the different Pilot Sites will cover:

Lifestyle-related early detection and interventions

Big data Analytics techniques will be exploited to address risk stratification and early detection.

More info

COPD exacerbations management

Machine learning methods to implement apps that predict exacerbations and avoid hospitalizations.

More info

Diabetes: predictive modeling of glycemic status

Short-term prediction of glycemic dynamic is essential to improve Diabetes self-management.

More info

Parkinson’s disease treatment DSS

Key enabling technologies to continuously or periodically measure motor and non-motor symptoms.

More info

Predictive readmissions and decompensations in HF

Telemonitoring services and to implement an advanced model for predicting acute Heart Failure decompensations

More info

Primary and secondary stroke prevention

Image recognition to detect signs for active early warning alarms to target secondary stroke prevention

More info

Multi-chronic elderly patient management including polimedication

Sensing technologies to monitor parameters in Chronic Care Models for multi-morbid subjects.

More info

Pilot Sites

Aragon

Basque Country

Attica and Central

Milton Keynes

Lodz

Plugia

Saxony

Cyprus

Bullet

COPD exacerbations management

Machine learning methods based on Dynamic Bayesian Networks, suitable for modelling knowledge and handing time series data, are added to the Ecosystem Transaction Space to implement apps that predict exacerbations and avoid hospitalizations. These apps will be built on top of advanced wearable monitoring KETs, available in the GK Things Catalogue, that combine, in a single wearable garment piece, time series data for blood pressure, pulse oximetry, ECG, respiration, skin temperature and activity.

Target population:

Both Aragon and Puglia plan on including COPD patients 65+ years, participating in already existing regional programs that would be enhanced by GK’s machine learning prediction models and a set of wearables.

Key enabling technologies:

  • Wearables/medical devices, intended to monitor and track key variables such as physical activity, oxygen saturation, blood pressure, heart rate or SpO2. 
  • Professional’s online platform/dashboard, providing overview of alarm signs and/or relevant information. 
  • App for smartphone or tablet, enabling self-management, healthy lifestyle promotion, and regular follow up of patients through their interaction with a digital coach or chat-bot. 

A key requirement in both sites will be the integration of these KETs, and the data flows associated with them, into the current regional systems while complying with all the regulatory standards and being reliable, safe and robust.

Aragon (Spain)

Plugia

 

Bullet

Diabetes: predictive modelling of glycaemic status

Short-term prediction of glycaemic dynamics is essential to improve Diabetes self-management. GK will provide a personalized, adaptive, real-time data driven computational solution based on data federation in the Healthcare Space, identifying the different modes of the underlying glucose metabolism and eventually prevention, of hypoglycaemic events. Advanced GK “things” will collect clinical data at home such as bio- and physiological signals (i.e. blood glucose concentration data or continuous glucose monitoring data, galvanic skin response, heart rate variability) combining them with adaptive machine-learning regression models.

Target population:

Although all sites plan on including patients 65+ years with diabetes or poor metabolic control and associated comorbidities, the specific target population varies from site to site.

Key enabling technologies: 

  • Continuous Glucose Monitoring system. 
  • Wearables/medical devices intended to monitor and track key variables including: glucose levels; physical activity; sleep pattern; blood pressure; weight and body composition; and adherence to treatment with electronic pill-boxes. 
  • App for smartphone or tablet, enabling self-management, healthy lifestyle promotion, and regular follow up of patients through their interaction with a digital coach or chat-bot, including the possibility of answering questionnaires; screening cognitive, behavioural and mood status; and, monitoring drug intake and fostering adherence. 
  • Professional’s online platform/dashboard, providing overview of alarm signs and/or relevant information. • Raspberry Pi Gateway (Greece). 
  • Homebound educational support based on a social robot (Puglia, optional).

 

Basque Country (Spain)

Attica and Central Greece (Greece)

Plugia

Bullet

Parkinson’s disease treatment DSS

The medication change model, which was developed in collaboration with medical experts, using a qualitative multi-criteria method, identifies situations in which the disease has progressed to the point which requires a change of medical therapy and then suggests what kind of changes should be made. GATEKEEPER KETs such as wearable sensors to continuously or periodically measure motor symptoms (depending on disease severity) and digital applications, such as Smart TVs, that can be used to detect non-motor symptoms are used to record data into the patient’s EHR, accessible in the GK Healthcare Space. The model will alert clinicians that the patient’s current medication plan is not optimal any more, and will derive suggestions on how to improve it.

Target population

Up to 100 PD patients, with confirmed PD diagnosis according to Movement Disorders Society Clinical Diagnostic Criteria for Parkinson's Disease; moderate PD clinical stage: moderate motor symptoms, limitations in Activities of Daily living but somewhat independent and good response to conventional pharmacologic therapy.

Key enabling technologies:

  • STAT-ON Parkinson’s Holter (Sense4care). 
  • Devices/wearables to measure blood pressure and sleep patterns. 
  • Cognitive, behavioural and mood screening app including the following validated tests and questionnaires: MoCA test,  QUIP-RS questionnaire, PsycH-Q questionnaire, LARS questionnaire, and GDS test. 
  • Professional’s online platform/dashboard, providing overview of alarm signs and/or relevant information. 

Basque Country (Spain)

 

 

Bullet

Predicting readmissions and decompensations in HF

Telemonitoring services and machine learning with Dynamic Bayes Networks will be harnessed to implement an advanced model for predicting acute HF decompensations, taking comorbidities into account. Building on the experience of the Multisensor Monitoring in Congestive Heart Failure (MUSIC) Trial, GK Healthcare Space apps allow to explore which other longitudinal data (measured by GK Consumer Space “things” , e.g. bio-impedance, heart rate, respiratory rate and volume, physical activity duration and intensity, body posture, gathered with a wearable platform as the one depicted in can be used for predicting decompensations.

Target population:

Both Aragon and Puglia plan on including HF patients 65+ years, participating in already existing regional programs that would be enhanced by GK’s machine learning prediction models and a set of wearables.

Key enabling technologies:

  • Wearables/medical devices, intended to monitor and track key variables such as physical activity, weight, blood pressure, heart rate or SpO2. 
  • Professional’s online platform/dashboard, providing overview of alarm signs and/or relevant information. 
  • App for smartphone or tablet, enabling self-management, healthy lifestyle promotion, and regular follow up of patients through their interaction with a digital coach or chat-bot.

Aragon (Spain)

Plugia

 

Bullet

Primary and secondary stroke prevention

Image recognition algorithms can be added to the Ecosystem Transaction Space, able to detect stroke signs from images recorded at home, for example on the basis of pathological facial weakness detection. These algorithms, coupled with smart-home/smart-hospital interactions supported in the GK Healthcare Space, will activate early warning alarms which effectively target secondary stroke prevention, particularly for subjects affected by recurrent strokes. GK “Things” involved in this scenario include image detection technologies (e.g. camera in smartphone) and/or MYSPHERA real-time location system. Primary prevention can be addressed through AI-based smart assistants, like Samsung Bixby, aimed at coaching patients on stroke-related healthy habits, similarly to Use Case 1.

Target population:

The target population will consist on 50 patients at high risk of stroke (primary prevention) and 50 patients at risk of reinfarction (secondary prevention), being controlled both in primary care and in the neurologist's outpatient office.  

Key enabling technologies:

  • Advanced educational tools, including virtual or augmented reality.
  • Physical activity monitor devices/wearables. 
  • Patient’s app screening for cognitive, behavioral and mood status. 
  • A system for the monitoring of drug intake and improvement of adherence to treatment. 
  • A virtual coaching app fostering promotion of self-management

Basque Country (Spain)

 

 

Bullet

Multi-chronic elderly patient management including polimedication

Several sensing technologies, available in the GK Things Catalogue, can be leveraged and integrated in an unobtrusive mobile data collection platform (e.g. based on smartphones, smart-trackers, smart-textiles, etc.), able to monitor the multiple parameters required in Chronic Care Models (CCM) for multi-morbid subjects. Through the GK Healthcare Space, data can be shared with clinical professionals in charge of managing the CCMs, in order to adjust individual care plans accordingly. Through the GK Ecosystem Transaction Space, robotics KETs (from very simple pill dispensers to more complex social robots [26]) can be integrated with digital coaching systems to assist polymedicated patients (e.g. in particular for patients which are concurrently affected by cognitive impairments).

Target population:

Targets elderly chronic patients with variable complexity according to GK’s risk stratification pyramid. There are significant differences among sites on the preliminary inclusion / exclusion criteria, which reflect the specificities of the planned interventions. For instance, the planned minimum age for inclusion varies from 50 years in Aragon, Cyprus, Poland or Saxony up to 70 years in the Basque country. Similarly, the scope of the use case varies notably across sites, with Saxony focusing on psychological and social aspects, and thus the target population will have suspected mental health impairment; Poland targeting exclusively the problem of effectively managing polymedication; and, as a last example, Cyprus implementing a program exclusively for cancer patients

Key enabling population:

  • Wearables/medical devices, intended to monitor and track key variables such as drug adherence, physical activity, falls, sleep patterns, pain, oxygen saturation, blood pressure, heart rate or SpO2 (all sites). 
  • Home sensors/robots permanently assessing the house for risks, learning the position of objects of daily use and monitoring the activities of the patient, suggesting activities, and, when needed, requesting telepresence support (Milton Keynes). 
  • App for smartphone or tablet/online platform, enabling self-management, healthy lifestyle promotion, fostering medical education and health literacy, adherence to medication and control of polymedication, or social Engagement, and allowing regular follow up of patients through their interaction with a digital coach or chatbot (all sites). 
  • Professional’s online platform/dashboard, providing overview of alarm signs and/or relevant information (all sites).

 

Aragon (Spain)

Basque Country (Spain)

Attica and Central Greece (Greece)

Milton Keynes

LODZ

Plugia

Saxony

Cyprus