Challenge 1: Health, Demographic Change and Well-being

Modeling the interaction between drugs and cell receptors allows virtual screening of thousands of drug candidates; As a result, pharmaceutical companies can reduce the number of costly enzyme assays and time to market for new drugs.

MSO-ED tools also play an essential role in the efficient and accurate diagnosis of cancer or viral diseases, as well as the development of personalized radiotherapy or medical technologies such as artificial hip or knee therapy, and stents. In addition, the spread of epidemics (such as the current Coronavirus disease) can be studied through mathematical models to help make more efficient health and economic decisions.

On the other hand, the challenges that hospitals or pharmaceutical companies face within Industry 4.0 and 5.0 show an unprecedented level of complexity, thus requiring holistic approaches and solution processes based on optimized algorithms. Decision makers need advanced tools that enable long-term risk analysis, clean processes, and prototype improvements, along with an appropriate set of optimization and control methods. The key technologies of these processes are often very complex and require the support of highly qualified experts, which are often not available in small and medium-sized companies. In addition, the providers of the necessary skills are spread over different areas of specialization in universities, research and technological institutions. These characteristics require the collaboration and integration of different advanced providers and other innovation players in different sectors and regions. This integrative role is one of the proposed goals for the PET MSO-ED platform.

• Capacities of MSO-ED Technologies in the field of Challenge 1
  • Visualization, processing and analysis of medical images. Characterization of false positives. Learning models using large databases (machine/deep learning).
  • Characterization of medical waste. Biological sample classification algorithms.
  • Evolution of demographic rates. Population projections, and generation of scenario trees in a time horizon.
  • Characterization of habits in the population. Simulation of the flow of users by services.
  • Optimization of the planning of the location of primary health centers in uncertain environments of the evolution of demographic rates over a time horizon.
  • Optimization of the planning of the acquisition of medical supplies in uncertain environments of the evolution of demographic rates and types and intensity of diseases and epidemics over a time horizon.
  • Optimization of types of ambulance fleets: Sizing and location in an uncertain service demand environment.
  • Optimization of the distribution of both human and material health resources in emergency situations.
• Success stories already implemented in the field of Challenge 1
  • Optimize the supply of health services. See math-in Success Case Book, pg. 13.
  • Improve the management of human resources in companies. See math-in Success Case Book, pg. 14.
  • Evaluate the efficacy of drugs against Alzheimer’s. See math-in Success Case Book, pg. 17.
    Simulation of the biomechanical behavior of the jaw and dental pieces for dentistry. See math-in Success Case Book, pg. 27.
  • Simulation of bone remodeling. See math-in Success Case Book, pg. 28.
  • Models for reducing failure in prostate cancer surgery. See math-in Success Case Book, pg. 29.
  • Epidemiological analysis of the escalation and de-escalation of COVID-19. See Report of the Committee of Experts of the CEMAT in its for the initiative “Mathematical Action against Coronavirus”. Also in this link you can see how COVID 19 outbreaks can be predicted through wastewater analysis.
  • Machine learning approaches for blind separation of high-dimensional mass spectrometry data sources for molecular analysis of tissue samples. (See on EU-Maths-IN Web).
  • Parametric equations of the human gait. Geometric modeling of the human gait for medical rehabilitation. (See on EU-Maths-IN Web).