A new hospital information and patient prediction system has improved the quality of care, reduced the death rate and saved millions of dollars in resources at Anderson Memorial Hospital in South Carolina. The CRTS/QURI system uses neural networks trained with BrainMaker to predict the severity of illness and use of hospital resources. Developed by Steven Epstein, Director of Systems Development and Data Research, the CRTS/QURI system's goal is to provide educational information and feedback to physicians and others to improve resource efficiency and patient care quality.
The first study showed that the program was directly responsible for saving half a million dollars in the first fifteen months even though the program only included half of the physicians and three diagnoses. Since then, the number of diagnoses and physicians included in the program have increased. The quality of care has improved such that there are fewer deaths, fewer complications, and a lower readmission rate. Expenses have been reduced by fewer unnecessary tests and procedures, lowered length of stays, and procedural changes. The reported success has motivated several other hospitals to join in the program and has provided the impetus to begin a quality program with the state of South Carolina.
Individually trained neural networks learn how to classify and predict the severity of illness for particular diagnoses so that quality and cost issues can be addressed fairly. After attempts to use regression analysis to predict severity levels for several diagnoses failed, Epstein turned to the BrainMaker program for a new approach and taught his neural networks to classify and predict severity with 95% accuracy. The neural networks are also used to predict the mode of discharge - routine through death - for particular diagnoses.
Training information is based upon the length of stay in the hospital which has a direct relationship to the severity of the illness (acuity). The neural network uses variables of seven major types: diagnosis, complications/comorbidity, body systems involved (e.g., cardiac and respiratory), procedure codes and their relationships (surgical or nonsurgical), general health indicators (smoking, obesity, anemia, etc.), patient demographics (race, age, sex, etc.), and admission category.
Three years of patient data was chosen for training. There were approximately 80,000 patients and 473 primary diagnoses. For a given diagnosis, about 400 to 1000 cases were used for training. Two neural networks for each diagnosis were trained - one to predict the use of resources and the other to predict the type of discharge. For a single diagnosis network, there are 26 input variables and one output variable.
An example of one of the CRTS neural networks:
INPUTS
# body systems involved
# non-surgical procedural grps
anatomical surgical grps
diagnosis #
comorbid conditions
# complications
catastrophic conditions
obesity
hemhorragic disorders
smoker
hypertension
diabetes
rehabilitating
senility
diseases of blood
age
sex
financial class
race
insurance type
marital status
county codes
previous admissions
doctor status
OUTPUT
length of stay