The challenge we’re solving

Home Support Services (HSS) provide essential in-home care for people who need regular support with daily activities due to health or functional limitations. However, planning care delivery is complex and highly sensitive to human and logistical factors – from caregiver shortages to unpredictable patient needs.

Most existing tools are designed for logistics or transportation, not for social care. HSS providers lack tailored decision-support systems that account for patient vulnerability, caregiver well-being, skills alignment, unplanned absences, and continuity of care.

OHCare addresses this gap by developing a Decision Support System (DSS) that goes beyond route optimization – integrating the full range of operational, human, and care quality factors into planning.

Project partners

 

Project goals

  1. Model uncertainty in staffing, travel time, and service needs to better manage unpredictability.
  2. Optimize professional-to-patient assignments, considering skills, continuity of care, time windows, and scheduling constraints.
  3. Incorporate caregiver well-being and work-life balance into planning decisions.
  4. Support more effective admission decisions, moving beyond simple FIFO models to preserve care continuity.
  5. Develop and test a prototype DSS tailored to the specific challenges of Home Social Services planning.

Our role

VOH.CoLAB is leading the development of a software prototype for the DSS, integrating:

  • Optimization models from the research team;
  • A user-centered interface;
  • Privacy and GDPR compliance;
  • Iterative design with feedback from real HSS professionals.

Lead researcher at VOH

Federico Guede, PhD

Head of AI-based Multimodal Systems

The impact we hope to create

OHCare aims to improve how Home Support Services are planned and delivered, with a focus on both care quality and caregiver well-being. By using intelligent decision support, the project is expected to:

  • Improve continuity and quality of care through better staff-to-patient matching;
  • Reduce unplanned absences and overtime by supporting fairer, more balanced scheduling;
  • Increase efficiency in resource allocation, helping services reach more people;
  • Enhance caregiver well-being by factoring emotional and physical strain into planning;
  • Support more informed decisions about new patient admissions, avoiding service overload;
  • Demonstrate real-world feasibility through pilot testing, with the potential to scale to other regions or service types.