Healthentia Smart Services

A large number of innovation features are evaluated for their feasibility and assessed for integration into future versions of Healthentia. In this section you can find descriptions of features that are currently under investigation; most of them under the framework of R&D initiatives. These features are not medical device modules and their inclusion into the SaMD is subject to the D&D procedure, by considering patients' safety and performance.


in silico



Data Structure & Normalization

Data sources need to be structured and get normalized in order to be uniform.


Habits Monitoring

Physical activity sensing of patients, extraction of their habits and monitoring of deviations.

Group 226

Behavioral Change Models

Different behavioral change models are used for coaching and goal setting to assess motivation and capacity.

Frame 17

Outcome Prediction

The discovered biomarkers have predictive power in what patients will report about themselves.

Group 229

Digital Phenotyping

Unsupervised, automatic biomarker discovery in data and grouping of validated biomarkers into phenotypes

Virtual Coaching

Healthentia’s Virtual Coach is orchestrated through a clinical pathway engine and powered by explainable AI, that can tailor its coaching to every individual at the right time with the right way and the right topic. 

Digital Biomarkers Discovery

Our flow for biomarker discovery utilizes Healthentia for data collection and Healthentia Smart Services to establish the important attributes that indicate any clinical outcome, as well as the way these attributes should be combined into the biomarker via learning predictive models. It facilitates data-driven and clinical validation of these models into digital composite biomarkers.

Digital Phenotyping

Multi-dimensional vectors create a visual patient phenotype model with characteristic behavioral habits

Pattern recognition algorithms cluster patients of similar phenotypes that can be then addressed by the system/investigator in a similar way.

Any deviation from the model is enumerated and monitored