CPC G16H 50/30 (2018.01) [C12Q 1/6886 (2013.01); G16B 20/00 (2019.02); G16B 20/10 (2019.02); G16B 20/20 (2019.02); G16B 40/00 (2019.02); G16H 50/20 (2018.01); C12Q 2535/122 (2013.01); C12Q 2600/156 (2013.01)] | 17 Claims |
1. A method, comprising:
(a) obtaining information about a subject comprising at least a genetic profile of a tumor and a treatment previously or currently provided to the subject, if any, and determining an initial state of the subject based on the information;
(b) providing a decision tree, wherein a root node represents an initial subject state, decision branches represent alternative treatments available to the subject, chance nodes represent points of uncertainty, and decision nodes or terminal nodes represent subsequent states,
wherein each branch of the decision branches is assigned a probability, and each node of the terminal nodes is assigned a probability,
wherein one or more of the probability for each decision branch and one or more of the probability for each terminal node is at least in part a function of a treatment choice from among a plurality of treatment choices, and
wherein one or more of the probability for each decision branch and one or more of the probability for each terminal node is generated from a database and one or more machine learning algorithms;
(c) providing a course of treatment for the subject that maximizes a probability of the subject achieving a living state at a terminal node; and
(d) generating an electronic output indicative of the course of treatment provided in (c).
|