METHOD AND SYSTEM TO PREDICT PROGNOSIS FOR CRITICALLY ILL PATIENTS
A method for evaluating one or more diagnostic linages of a patient obtained in different examination sessions and evaluating the diagnostic images using trained machine learning logic to generate prognosis and treatment information related to a medical condition of the patient detected during the evaluation. The prognosis-related information is recorded and displayed.
1 . A computer implemented method for evaluating diagnostic images of a patient, the method comprising:
acquiring and storing the diagnostic images of the patient each obtained during different examination sessions;
evaluating the diagnostic images of the patient using trained machine learning logic to generate prognosis and treatment information for the patient based on a medical condition detected in the diagnostic images during the evaluation; and
generating and outputting the prognosis and treatment information.
2 . The computer implemented method of claim 1 , further comprising generating and outputting a schedule for patient treatment according to the generated prognosis and treatment information.
3 . The computer implemented method of claim 2 , wherein outputting the schedule further comprises displaying human readable instructions for one or more treatment sequences.
4 . The computer implemented method of claim 3 , further comprising reconstructing a tomosynthesis image from acquired diagnostic x-ray images of the patient.
5 . The computer implemented method of claim 4 , wherein acquiring the diagnostic x-ray images of the patient comprises obtaining a spectral radiography image of the patient using a wheeled mobile radiography apparatus.
6 . The computer implemented method of claim 1 , wherein acquiring the diagnostic images of the patient comprises acquiring a progressive series of diagnostic images over time.
7 . The computer implemented method of claim 1 , further comprising:
acquiring and recording vital signs measurements of the patient; and
evaluating the diagnostic images of the patient and the acquired vital signs measurements of the patient using trained machine learning logic to generate the prognosis and treatment information for the patient.
8 . The computer implemented method of claim 7 , further comprising acquiring and recording heart rate data, blood pressure data, blood oxygen level data, lung fluid level data, or a combination thereof.
9 . The computer implemented method of claim 8 , further comprising outputting a probability of disease progression and/or mortality of the patient as a function of time.
10 . The computer implemented method of claim 9 , further comprising outputting recommendations for changes in a treatment regimen for the patient to improve a probability or timing of the patient's probability of disease progression or mortality.
11 . The computer implemented method of claim 10 , further comprising outputting changes to respirator settings, changes to flow rates for IV fluid, changes to antibiotic concentration, or a combination thereof.