Risk prediction model using fuzzy regression method for predicting unplanned hospital admissions

Unplanned admission of a patient which is vague or fuzzy event has important economic implications for efficient hospital resource utilization. Several studies have targeted the preventability of unplanned admissions, but it is clear that unplanned admissions consume large amount of hospital resources. It is challenging to predict risk of admissions due to their vague nature. Patients at high risk of admission could be appropriate targets for models designed to reduce admissions in hospitals. Variation in decisions on admission may occur due to introduction of uncertainty in health system variables. Traditional approaches are not capable to account for the complex action of uncertainty and vague nature of hospital admissions. Therefore, in order to model decision making of experts, predictive model adapting fuzzy regression method has been developed. For this JAVA program was developed, upper and lower bounds are computed for regression equations. This approach is useful in identifying the risk factors for admission of a patient.