Therapeutic decisions systems and method using stochastic techniques

A method, comprising:

• monitoring a plurality of physiological signals of a current patient;
• comparing said physiological signals of the current patient to stored physiological signals for previous patients stored in a database;
• determining patients in said database who are most similar to the current patient;
• and
• selecting a treatment from said database which has a maximum probability of survival for mathematically similar patients.

A system comprising:

• a monitoring device monitoring a plurality of physiological signals of a current patient;
• a database, which stores records indicative of a plurality of patients including at least some of said physiological signals for said plurality of patients and prognosis information for said plurality of patients;
• and
• a processor, that compares said physiological signals of the current patient to said stored records in the database, determines mathematically patients in the database which are most similar to a current patient and selects a treatment from said database which showed a maximum probability of survival for mathematically similar patients to the current patient, wherein said processor forms a state vector that includes at least a plurality of times t, with values associated with said times, wherein said values are at least one of said physiological signals and/or at least one treatment carried out at said times, and wherein said state vector is used to select the treatment that maximizes probability of survival based on other patients with similar state vectors.

A method, comprising:

• monitoring a plurality of physiological signals of a current patient;
• comparing said physiological signals of the current patient to stored physiological signals for previous patients stored in a database;
• determining patients in said database who are most similar to the current patient;
• and
• selecting a treatment from said database which has a maximum probability of survival for mathematically similar patients, wherein said selecting comprises forming a state vector that includes at least physiological signals, and treatments, as a function of time, and comparing said state vector to comparable information in the database.