The technology of KOLIBRI® is based on the processing of heart activity (HA) signals. KOLIBRI® system uses an autoregressive linear prediction model based on the properties determined from the HA signal for the determination of biochemical parameters (Patent US 10,531,836 B2 date: Jan.14, 2020). Big Data collected from clinical and pre-clinical trials over 10 years has built a base for neural network algorithms, which our industry-leading experts in non-invasive medical technologies are expected to develop further.

Data collected and analyzed by specially designed algorithms of the KOLIBRI® system allows assessment of the presence or absence of certain criteria, which characterizes certain pathologies. Therefore, the system can inform a user about suspected health risks. If you use the medical device KOLIBRI® at home and co-work with your medical institution or family doctor, you receive full support from the medical institution or family doctor in the field of remote monitoring of your health.

The device is integrated into a cloud infrastructure designed to improve remote health monitoring. In the KOLIBRI project, we implemented a full-featured real-time remote patient monitoring system. As a result, we have achieved maximum rapprochement between the patient and the doctor for daily (or regular) monitoring of his condition's health and remote monitoring.

We are constantly conducting further research to increase quality health parameters and further identify the following pathological conditions: diabetes, iron deficiency anaemia, chronic heart failure, myocardial infarction, hypertension, chronic obstructive pulmonary disease, dental status and others.

Studies of the influence of electromagnetic fields (EMF) on living organisms have been conducted since the middle of the last century. As a result, it has been established that EMFs can affect biochemical reactions and the behavior of charged molecules near membranes — namely: create electric fields in conductors, affect moving charge carriers, change the diffusion rate through membranes, distort bond angles, which influences the binding of proteins and the synthesis of macromolecules, etc.

Research in molecular biology has made it possible to detect the presence of endogenous bioelectric signals, as well as to determine their sources and influence on embryogenesis, regeneration and neoplasms formation. Ion flows and voltage gradients generated by ion channels and pumps are key regulators of cell proliferation, migration, and differentiation.

These particular features were taken into account during the device BIOL designing, and the frequency ranges of meter and decimetre waves were chosen. Our own studies and experiments with the device BIOL have been started in 2007.

In 2009, the device BIOL was clinically tested at the Kyiv Regional Hospital No.2 showing improvement in 80% of patients. In 2009, BIOL was used for 128 patients at the spa and rehabilitation center "Ukraine" with hypertension II-III degree — a reliable effect was obtained confirmed by hemodynamic parameters and laboratory studies. In 2011, studies in several research centers in Europe showed decrease in tumor size by an average of 15% in cancer patients treated with BIOL.

The shock-wave therapy device STARDEVICE® is intended for the treatment of the musculoskeletal system, rehabilitation of back and head injuries, including those complicated by partial or complete paralysis. Also, the device can be used for other types of therapy, which require forced stimulation of blood circulation in tissues.

The manipulator of the device generates mechanical shocks of a given frequency and force. A doctor with the manipulator makes a mechanical (percussive) effect on ligaments, muscles or vertebral segments of a patient. The shock-wave therapy is recommended for patients from 23 years and older, according to the recommendation of the Vertebrology and Rehabilitation Institute (Kiev, Ukraine).

ANESA (Automatic Noninvasive Express Screening Analyzer) uses advanced signal processing based on cardiac activity analysis to determine 136 health parameters without any blood sampling or invasive procedures. The system employs deep learning algorithms trained on extensive clinical datasets to identify pathological conditions and health risks.

The technology is based on an autoregressive linear prediction model that processes biosignals from the patient's body surface, enabling a comprehensive health assessment within 6–12 minutes. Results include CBC parameters, metabolic indicators, ECG morphology, heart rate variability and multiple organ system assessments.