Premenstrual syndrome affects women’s daily functioning in various ways. The designed algorithm applied into mobile application is intended to support women’s health by enabling a better understanding of the processes occurring in their bodies during the cycle and detecting the pattern with specific symptoms groups appearing cyclically. The input data comes from an application that collects information about the woman’s health and symptoms. The AI algorithm determines the Information Granules and then analyzes them in terms of intensity and frequency of various symptom combinations. Ultimately determines the level of risk of PMS.

We discuss how to bridge a gap between low-level processing of measurements related to women’s menstrual cycles and high-level analysis of health disorders. On the one hand, such disorders can be associated with some well-describable symptoms by medical experts. On the other hand, such symptoms could be connected with anomalous menstrual patterns detected in the acquired data. This leads toward an opportunity to establish a hierarchical model of concepts based on data-driven recognition of an increased risk of disorders. In our study we rely on the menstrual cycle analysis system that has been already productized by the OvuFriend company. Going further, we discuss how to utilize medical knowledge and learn medical concepts from data in order to better assist the OvuFriend’s application users in self-monitoring of their health.

We discuss recent AI-related developments at OvuFriend's online platform which is designed to assist families in overcoming infertility problems. One of functionalities of the platform is to detect fertile days basing on often incomplete and uncertain data provided by the users. Besides discussing the particular layers of the underlying OvuFriend's system architecture, we concentrate on one of the proposed fertile day detection models which is based on the idea of utilizing multivariate similarities between the current cycle and the past cycles available for the given user or for users who have a similar profile, with an additional self-checking procedure that enables the algorithm to neglect insufficiently reliable inputs.

We present an overview of an approach to solving various real-life tasks related to Computational Intelligence by means of modeling with information granules. The particular methods of building the model are based on networks of fuzzy comparators. We demonstrate that comparator networks are a powerful and versatile tool suitable for applications. The introduction of methodology is accompanied with brief presentation of its formal basis. We also list existing and prospective, practical applications of the described approach.