Information management apparatus and non-transitory computer-readable recording medium

A non-transitory computer-readable recording medium having recorded thereon a computer program for causing at least one processor, when executed, to perform operations comprising:

• acquiring first time information and second time information for a plurality of cancer patients, respectively,
• the first time information being related to a time taken to acquire a predetermined amount of at least one or more specific nucleic acids based on a first cell acquired from each of the plurality of cancer patients,
• the second time information being related to a time taken to culture a second cell acquired from the each of the plurality of cancer patients, which is different from the first cell, until a predetermined amount is reached;
• storing individual patient information in which the first time information and the second time information are associated with attribute information of the each of the plurality of cancer patients, respectively;
• acquiring first correlation information and second correlation information based on a plurality of pieces of the stored individual patient information,
• the first correlation information being related to a correlation between the first time information and the attribute information, and
• the second correlation information being related to a correlation between the second time information and the attribute information;
• acquiring a first prediction value related to the first time information and a second prediction value related to the second time information of a new cancer patient, based on the attribute information of the new cancer patient and the first correlation information and the second correlation information;
• and
• generating and outputting at least a portion of a treatment schedule of the new cancer patient, based on the first prediction value and the second prediction value, wherein:
• the first time information includes at least one of first detailed time information or second detailed time information, the first detailed time information being related to a time taken to culture the first cell until a predetermined amount is reached, the second detailed time information being related to a time taken to synthesize the at least one or more specific nucleic acids contained in the first cell until a predetermined amount is reached,
• the first correlation information is acquired by using a first neural network and a second neural network wherein:
• the first neural network is trained by first training data including:
• (1-i) the attribute information of the each of the plurality of cancer patients as first input values;
• and
• (1-ii) the first detailed time information associated with the each of the plurality of cancer patients as first output values, and
• the second neural network is trained by second training data including:
• (2-i) the attribute information of the each of the plurality of cancer patients as second input values;
• and
• (2-ii) the second detailed time information associated with the each of the plurality of cancer patients as second output values, and
• the second correlation information is acquired by using a third neural network trained by third training data including:
• (3-i) the attribute information of the each of the plurality of cancer patients as third input values;
• and
• (3-ii) the second time information associated with the each of the plurality of cancer patients as third output values.

A method, comprising:

• acquiring, by at least one processor, first time information and second time information for a plurality of cancer patients, respectively,
• the first time information being related to a time taken to acquire a predetermined amount of at least one or more specific nucleic acids based on a first cell acquired from each of the plurality of cancer patients,
• the second time information being related to a time taken to culture a second cell acquired from the each of the plurality of cancer patients, which is different from the first cell, until a predetermined amount is reached;
• storing, by the at least one processor, individual patient information in which the first time information and the second time information are associated with attribute information of the each of the plurality of cancer patients, respectively;
• acquiring, by the at least one processor, first correlation information and second correlation information based on a plurality of pieces of the stored individual patient information,
• the first correlation information being related to a correlation between the first time information and the attribute information, and
• the second correlation information being related to a correlation between the second time information and the attribute information;
• acquiring, by the at least one processor, a first prediction value related to the first time information and a second prediction value related to the second time information of a new cancer patient, based on the attribute information of the new cancer patient and the first correlation information and the second correlation information;
• and
• generating and outputting, by the at least one processor, at least a portion of a treatment schedule of the new cancer patient, based on the first prediction value and the second prediction value, wherein:
• the first time information includes at least one of first detailed time information or second detailed time information, the first detailed time information being related to a time taken to culture the first cell until a predetermined amount is reached, the second detailed time information being related to a time taken to synthesize the at least one or more specific nucleic acids contained in the first cell until a predetermined amount is reached,
• the first correlation information is acquired by using a first neural network and a second neural network wherein:
• the first neural network is trained by first training data including:
• (1-i) the attribute information of the each of the plurality of cancer patients as first input values;
• and
• (1-ii) the first detailed time information associated with the each of the plurality of cancer patients as first output values, and
• the second neural network is trained by second training data including:
• (2-i) the attribute information of the each of the plurality of cancer patients as second input values;
• and
• (2-ii) the second detailed time information associated with the each of the plurality of cancer patients as second output values, and
• the second correlation information is acquired by using a third neural network trained by third training data including:
• (3-i) the attribute information of the each of the plurality of cancer patients as third input values;
• and
• (3-ii) the second time information associated with the each of the plurality of cancer patients as third output values.