Healthcare
❯
Real-Time Patient Triage
❯Hospital Patient Management
❯Discharge summary classifier
Hospital management tools
For:
Hospital administrator
Scope:
Temporal data mining, visualization
Goal:
Improve Operation Efficiency
Generation of clinical pathways
For:
Nursing staff
Scope:
Decision tree, clustering
Goal:
Improve Operation Efficiency
Machine-learning based triage to determine low-severity patients that can be fast-tracked to admission in ED due to their short discharge length
For:
Emergency Departments in hospitals.
Goal:
Improved Employee Efficiency
Discharge summary classifier
For:
Medical staff
Scope:
Decision tree, random forest, SVM, BNN, deep learning
Goal:
Improve Operation Efficiency
Real-time patient support and medical information service applying spoken dialogue system
For:
Dentist
Hospital
Scope:
Medical business support system using artificial intelligence-based human-
computer interface technology.
Goal:
Other
Discharge summary classifier
For:
Medical staffGoal:
Improve Operation EfficiencyProblem addressed
Classification of discharge summaries
Scope of use case
Decision tree, random forest, SVM, BNN, deep learning
Description
This system proposes a method for construction of classifiers
for discharge summaries. First, morphological analysis is
applied to a set of summaries and a term matrix is generated.
Second, correspond analysis is applied to the classification
labels and the term matrix and generates two dimensional
coordinates. By measuring the distance between categories
and the assigned points, ranking of key words is generated.
Then, keywords are selected as attributes according to the
rank, and training examples for classifiers are generated.
Finally learning methods are applied to the training
examples. Experimental validation shows that random forest
achieved the best performance and the second best was the
deep learner with a small difference, but decision tree
methods with many keywords performed only a little worse
than neural network or deep learning methods.