Medical Knowledge graph
ES, version 2022-05-02 /
- A large amount of biomedical knowledge is already available but ln
too many different sources and formats. However this expertise is
not always applied in practice.
- A medical knowledge base suitable for decision support and
including quantitative evaluations.
- Steering for decision support:
- Decision support require a very comprehensive representation
of the knowledge. Therefore graphs can represent concepts and
the very many relationships between these concepts.
- Steering information intended to be processable by the
decision support engine.
- Normally medical experts will work mainly here on the content
of knowledge graphs and much less inside the software of the
decision engine, except when a new type of rule would appear
- Multi-directional navigation:
- From a symptom to potential problems AND from a problem to
usual symptoms with their relative importance.
- From a problem to possible treatment AND from a treatment to
all his possible effects, both positive or negative.
- From a diagnose to frequent complications.
- As far as possible concepts and relationships should be
seen as logical notions. Medical concepts are in principle
independent from any spoken language. For example the same
problem can expressed as 胃溃疡, язва желудка, úlcera gástrica, Magengeschwür, maagzweer, قرحة المعدة, ulcère gastrique or gastric ulcer !
- As far as possible keep compatibility with existing
ontologies. At international level one of the most
comprehensive identification system seems to be the ULMS,
Unified Medical Language System, www.nlm.nih.gov/research/umls/
, including other ontologies and translated in many
- However keep in mind that existing ontologies have been
intended for 2 specific goals, epidemiology classifications
and for retrieval in scientific literature. Decision support
could require a little different approach.
- In patient records the likelihood of concepts is
essential. This probability can be represented in 3
- Precise figures intended to be used inside the
- Textual expressions intended for traditional reports.
Here the coefficients are rounded, for example 0.9 as
"evident", 0.7 as "probable", .5 as "possible", 0.2 as
"not to exclude". ... or in time dimension 1 as
"permanent", 0.7 as "frequent", 0.3 as "occasional", 0.1
as "very rare".
- Graphs visual attributes intended for quick
understanding of the situation, as for example relative
size of visual object in a graph, color from red to
orange, yellow, green, blue.
- Relations between concepts:
- A set of preferred relationships types between concepts
will be defined, for example "suggest", "confirm",
"exclude", "recommend", etc...
- Relative weights are essential:
- Medical decision are based on many factors having
different relative weight in decisions as well many
uncertainties. This require an approach based on "Fuzzy
- Fuzzy Logic require a standardization in principle
based on ranges from 0. to 1.
- Multiple kinds of weights:
- Positive or negative relation:
- Synthesis of knowledge:
- In order to provide Assisted Intelligence in Decision Support,
we need the best possible current synthesis of medical
knowledge. The sources of knowledge are:
- Courses of professors teaching medicine in universities.
- CME, Continuing Medical Education networks, to be
converted and restructured as graphs.
- Agreed common opinions in scientific associations of
specialists, e.g. in cardiology, pneumology, gastro, etc...
- Textbooks, if up to date.
- Healthcare professionals in practice have not much time nor
interest to delve directly in the details of scientific
publications. Most of the time they relay on opinions of trusted
- A separate chapter is dealing with research
issues, about improvement of the current synthesis of
- Nodes may contain reference to procedures in the decision
- Knowledge sources:
- Many biomedical knowledge bass already exist:
- Traditional data bases:
- As far as possible extraction of knowledge by means of
- Some knowledge bases are already formatted as graph but
could need adaptation and extensions.
- Anyhow medical experts have to validate the knowledge and to keep
- A good human interface is here very important.
- Expected results:
- Make assisted Intelligence possible.
- Support of teaching and training of medical students.
- Work in progress:
- Graph extracted from natural language sources are already
created from RxNorm,
- A preliminary list of common relation types found in these
- Next steps:
- At a begin stage experimental work on relatively small graphs
in only a few limited medical domains. Every contribution is
welcomed even drawings on paper.
- More sources of knowledge must be explored as medicine courses
- Seek more about the weights of relationships.
- Experimental setup of information about some specific
challenges, for example starting from a symptoms like dyspnoe,
icterus, antibiotic, ... with directly related knowledge.
- Basic schemas examples:
- Starting from a given symptom, what could be the Problem(s) ?
- Starting from every Problem, what are usual symptoms which should
be investigated ?
- In next versions attributes as likelihood, severity, etc ... will
have visual styles like shape, size, color, thickness, etc...
- Contact persons: