Medical Knowledge graph
ES, version 2022-05-02 /
- Introduction:
- 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.
- Objectives:
- A medical knowledge base suitable for decision support and
including quantitative evaluations.
- Approaches:
- 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 necessary.
- 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.
- .....
- Concepts:
- Identification:
- 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
languages.
- 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.
- Attributes:
- In patient records the likelihood of concepts is
essential. This probability can be represented in 3
different ways:
- Precise figures intended to be used inside the
decision engine.
- 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:
- Identification:
- A set of preferred relationships types between
concepts will be defined, for example "suggest",
"confirm", "exclude", "recommend", etc...
- Attributes:
- 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 Logic".
- Fuzzy Logic require a standardization in
principle based on ranges from 0. to 1.
- Multiple kinds of weights:
- Specificity:
- Sensivity:
- 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 experts.
- A separate chapter is dealing with research issues,
about improvement of the current synthesis of medical
knowledge.
- Procedures:
- Nodes may contain reference to procedures in the
decision support engine.
- Data Model:
- Most essential concepts:
- Knowledge base:
- Definition of 3 small sets of concepts:
- Some "Observations", eg symptoms, lab
tests.
- Some "Problems", eg issues or diagnoses.
- Some "Actions", seeking more information
or recommend treatment. For example which
questions should be asked, which lab test should
be ordered.
- Relations between these 3 sets:
- What most matter here is the relations between
concepts. Relations will be qualified with a
type, relative weights, etc...
- Patients:
- A few experimental patient instances with:
- A few profile information, name sex, DoB, ..
- Having a few instance of results of
Observations.
- Will get a few instances of "Problems" with
their current relative likelihood.
- May get a list of recommended actions, sorted on
their relative priority. For example in emergency
situation what to do next.
- Knowledge sources:
- Care provider:
- ...
- Knowledge sources:
- Many biomedical knowledge bass already exist:
- Traditional data bases:
- As far as possible extraction of knowledge by
means of NLP.
- Graphs:
- 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 it up-to-date:
- 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:
- Results:
- Graph extracted from natural language sources are
already created from RxNorm,
MED-RT
and MeSH.
- A preliminary list of common relation types found in
these sources.
- 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 and textbooks.
- 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: