Provided are an apparatus and a program that can determine keratoconus with a simple configuration so as to allow the apparatus and the program to be distributed widely and contribute to early diagnosis of keratoconus.A keratometer 1 as a keratoconus determination apparatus measures, for example, a steep meridian refractive power of a cornea, a flat meridian refractive power thereof, and an angle of the meridian. In the keratometer 1, a prediction model 5 for keratoconus is stored in a memory 3 of a control unit 2. The prediction model 5 is a logistic regression model in which three parameters that are the steep meridian refractive power, the flat meridian refractive power, and a value indicating whether or not a subject eye has a with-the-rule astigmatism, are independent variables, and a probability of keratoconus is a dependent variable. The control unit 2 substitutes the three parameter values, among kerato values obtained by measurement, which are the steep meridian refractive power, the flat meridian refractive power, and the value indicating whether or not the subject eye has a with-the-rule astigmatism, into the prediction model 5, to obtain a probability of keratoconus as the output value. When the probability is greater than a cutoff value, the subject eye is determined to be suspected of having keratoconus. When the probability is less than or equal to the cutoff value, the subject eye is determined as a normal case. The determination result is outputted to a display portion 12.
