Deprecated: Creation of dynamic property Sober\Unravel\Migrate\AdvancedCustomFields::$pathDefault is deprecated in /mnt/web507/d2/21/510769221/htdocs/pi/pi-health-solutions/wp-content/plugins/unravel/src/Migrate.php on line 30 Deprecated: Creation of dynamic property Sober\Unravel\Migrate\Models::$pathDefault is deprecated in /mnt/web507/d2/21/510769221/htdocs/pi/pi-health-solutions/wp-content/plugins/unravel/src/Migrate.php on line 30 Our Services - PI Health Solutions Notice: file_get_contents(): Read of 12288 bytes failed with errno=21 Is a directory in /mnt/web507/d2/21/510769221/htdocs/pi/pi-health-solutions/wp-includes/functions.php on line 4570 Notice: Error when decoding a JSON file at path /mnt/web507/d2/21/510769221/htdocs/pi/pi-health-solutions/wp-content/themes/pi-health-solutions/resources: Syntax error in /mnt/web507/d2/21/510769221/htdocs/pi/pi-health-solutions/wp-includes/functions.php on line 4573 Notice: file_get_contents(): Read of 12288 bytes failed with errno=21 Is a directory in /mnt/web507/d2/21/510769221/htdocs/pi/pi-health-solutions/wp-includes/functions.php on line 4570 Notice: Error when decoding a JSON file at path /mnt/web507/d2/21/510769221/htdocs/pi/pi-health-solutions/wp-content/themes/pi-health-solutions/resources: Syntax error in /mnt/web507/d2/21/510769221/htdocs/pi/pi-health-solutions/wp-includes/functions.php on line 4573

Study Logistic Support

In modern medicine, it is often necessary to rapidly obtain information on the health status of certain target populations and to quickly develop pharmaceutical and non-pharmaceutical measures to address health-related problems. PI Health Solutions applies novel concepts of study logistic support in order to carry out clinical and/or epidemiological studies with ultra high-speed and maximum flexibility. This is currently best achieved with support of Social Media that facilitate the recruitment of a large number of study probands and medical professionals via virtual communities and networks.

When conducting population-based studies two different approaches can be adopted. The classic strategy is based on the selection of study probands who are generally selected at random from Residents’ Registration Offices and subsequently contacted by letter and/or by fixed network phone. More recently, the online sampling method based on so-called River Sampling has become increasingly popular. The online sampling method drives potential respondents to an online portal where they are screened for studies in real-time. Qualified respondents are then randomly assigned to a survey or study. Both selection strategies require a posteriori correction to achieve “population representativity” of the final results because of inherent method-specific distortions of the sample (e.g. sociodemographic). An important advantage of the online selection method over the classic method is that it is much easier to contact and recruit a large population within a very short time period. That in turn enables the application of a Zoom-In process (in-depth analyses) which we recently developed. Under preservation of “population representativity”, specific target subpopulations can be easily selected, e.g. subjects who recently suffered from a Corona virus infection or subjects who are willing to participate in a vaccination study.

Health App Development Support

Health Apps are now increasingly used in the population to obtain information on health-related issues or to enable patients to communicate with medical or other health care professionals. A more recent development is the use of professional health apps by physicans for diagnostic and patient monitoring purposes. However, the development of professional health apps is highly demanding in different ways: 1) research (pattern recognition), 2) design an app which combines different sources of information, 3) regulatory issues. PI Health Solutions GmbH has the expertise and know-how to develop professional health apps.

Algorithm Development

PI Health Solutions GmbH develops risk prediction algorithms for application in medicine and health care. This class of algorithm allows the prediction of disease trajectories in individual patients. Modern tools of pattern recognition based on artifical intelligence (AI) are used which currently include Logistic Regression, Random Forest, Gradient Boosted Tree, Support Vector Machine, Artifical Neural Network.


Consulting is provided to all players in the health care sector who either:

  1. plan to conduct a clinical or epidemiological study – in particular when the study needs to be conducted and completed rapidly in large patient or proband groups.
  2. wish to develop algorithms for disease risk prediction in large populations of probands or patients.