Prediction of probability distribution function of classifiers

A computer system, comprising:

• a computing device;
• and
• memory coupled to the computing device, wherein, when executed by the computing device, the computer system performs operations comprising:
• receiving information corresponding to medical imaging and clinical data for a plurality of individuals;
• applying a pretrained predictive model to the information for at least a subset of the plurality of individuals;
• determining levels of uncertainty in results of the pretrained predictive model for at least the subset of the plurality of individuals;
• dynamically adapting a lower acceptable limit and an upper acceptable limit that define at least one threshold range based at least in part on the determined levels of uncertainty and a predefined target performance of the pretrained predictive model for the plurality of individuals;
• performing a first remedial action for a first group of individuals in the plurality of individuals having the results where the levels of uncertainty are within the at least one threshold range;
• and
• performing a second remedial action for a second group of individuals in the plurality of individuals having the results where the levels of uncertainty are outside of the at least one threshold range.

A non-transitory computer-readable storage medium for use in conjunction with a computer system, the non-transitory computer-readable storage medium configured to store program instructions that, when executed by the computer system, causes the computer system to perform operations comprising:

• receiving information corresponding to medical imaging and clinical data for a plurality of individuals;
• applying a pretrained predictive model to the information for at least a subset of the plurality of individuals;
• determining levels of uncertainty in results of the pretrained predictive model for at least the subset of the plurality of individuals;
• dynamically adapting a lower acceptable limit and an upper acceptable limit that define at least one threshold range based at least in part on the determined levels of uncertainty and a predefined target performance of the pretrained predictive model for the plurality of individuals;
• performing a first remedial action for a first group of individuals in the plurality of individuals having the results where the levels of uncertainty are within the at least one threshold range;
• and
• performing a second remedial action for a second group of individuals in the plurality of individuals having the results where the levels of uncertainty are outside of the at least one threshold range.