Assisted Intelligence in Medicine using Interactive Graphs
AIMIG.org

ES, version 2025-11-10

• Problem
  • Healthcare is far from optimal as well in developing regions as well in developed ones for many reasons including lack of appropriate access to knowledge, delays for access to doctors, budget constraints, poor availability in rural areas. No individual doctor can any more master all medical knowledge domains, including "rare disease".
    
• Mission
  • Make medical knowledge better available for decisions in a practical way for patient care.
    
  • Moreover useful for education, research, care quality and cost limitation.
    
• Approaches
  • "AI" as explainable "Assisted Intelligence" rather than "Artificial Intelligence". To be seen as assistance from consultants, but here virtual remote assistance, based on the know-how of teams of human medical experts.
    
  • Helping but not replacing healthcare professionals. The Care Provider in contact with the patient, taking the final decision.
  • A task oriented approach, identifying problems and seeking solutions.
  • Medical reasoning essentially based on graphs, while language technologies are seen as secondary, useful for input and output.
    
  • Complex Medical Knowledge representation by means of graphs. Concepts as "nodes" and relationships as "edges" where any node can have a relationship with any other node in a space of millions of concepts and where relationships may be qualified. Decisions taking account of many factors presented as graphs, with the relative weights of relationships between concepts. This require the management of complex medical information in a N-dimentional space, by means of graph technologies. Therefore both medical knowledge and patient records need to be converted in graphs.
  • A multidisciplinary community including doctors, data scientists and software developers. Here trust is essential.
    
  • Seeking grants for international Open Source and Open Data collaborations as a not-for-profit initiative. Transparency of the sources of information by trusted authors. With support from scientific communities, universities and seeking grants of common goods.
  • However "support services" remain usual business for every healthcare organization, including installations, training and maintenance.
    
• Medical Knowledge as graph
  • Better access to already existing medical knowledge. Conversion of current medical knowledge into graphs. A synthesis from different sources as medical, courses, textbooks, ontologies, literature, and above all medical experts from specialized scientific communities.
  •  A large amount of biomedical knowledge is in principle already available but the question is now how to use this knowledge in a more efficient way.
    
  • Focus on the relations between symptoms, problems and to be recommended actions.
  • Maintenance of a synthesis of agreed medical know-how, based on an international community of experts.
    
• Patient record as graph
  • Patient information also structured as a graph with links to related knowledge. For example easy navigation from every "health issue" to symptoms, complication, actions, patient-doctor encounter, ...
    
• Decision support
  • Given information from both  the patient and from medical knowledge, try to provide recommendations. Using "graph navigation", "vectors", "agents", etc...
    
  • Qualified recommendations with both probability and degree of certainty.
  • What most matter here is the medical logic and logic, with explanations.
    
  • Typical Use Case:
  • A patient arrive in emergency with a problem, for example shortness of breath, what are the likelihoods of possible issues and what are the relative priorities of what should be done next?
    Step by step priorities may be of giving oxygen? of which questions ? which physical examination ? ask thorax xRay images ? ask an ECG ? ask lab tests ? begin a treatment ? decision about admission ?
    
  • After every new information, re-evaluate the new situation and adapt the visual graph of likelihoods and priorities.
• Intended users:
  • Telemedicine in situations where there is limited local qualifications and/or not enough doctor time per patient.
  • Many specialized health organizations are working on knowledge bases in traditional and incompatible ways.  The challenges  are integration and accessibility in a format suited for decision support.
  • Quality checks which may provide warnings.
  • Contribution to medical education and training, in front of interactive decision strategies.
• Human graph interface
  • Facilitate the understanding between graphs in human minds, based on neuron and synapses, and graphs in machines. Both humans and machine can understand and share isual graphs.
    
• Education
  • Involvement of teachers and training of students playing with graphs in order to discuss differential diagnosis and the potential benefits of next actions.
    
• Research
  • At a later stage, analysis of large populations of patient records in order to improve the knowledge base. Fine-tuning of the weights of relations between concepts. Evaluation of the results of treatments.
  • Discovery of unsuspected patterns using graphs software tools.
• Experimental prototype
  • Call for a community of physicians, data scientists and software developers.
  • Incremental Roadmap:
    
  • Technical: Make a basic working prototype. To be shared in Open Source with research centers. Making it eligible for collaborations and grants.
  • Build a small experimental graph as an example of Knowledge Base from some chapter of medical know-how (emergencies ? hematology ? lab ? ....).
    
  • Involve medical colleagues to play with the prototype, in order to understand what is still missing.
  • Contacts with international knowledge bases available in the public domain.
    
  • Contact: etienne@saliez.be, ...