Takahashi et al used a classification and regression tree analysis (CART) to predict outcome in patients with spontaneous intracerebral hemorrhage (ICH). These can help identify patients who may benefit from more aggressive or novel therapies. The authors are from St. Luke's International Hospital in Tokyo, Brigham and Women's Hospital in Boston, and Shimane Prefectural Central Hospital in Izumo, Japan.
Parameters:
(1) coma
(2) volume of intracerebral hemorrhage in mL
(3) age of the patient in years
Coma
Volume ICH
Age in Years
Risk Group
present
NA
NA
high
negative
> 10.4 mL
>= 75 years
intermediate
negative
> 10.4 mL
< 75 years
low to intermediate (low risk 1)
negative
<= 10.4 mL
NA
low (low risk 2)
Risk Group
In-Hospital Mortality Rate
high
59%
intermediate
30%
low to intermediate (low risk 1)
11%
low (low risk 2)
2%
To read more or access our algorithms and calculators, please log in or register.