Systems and methods for analyzing patient data and allocating medical resources

1 . A method of treating a patient, comprising:

determining by a processor, a current state of a medical condition of a patient;

determining by the processor, a likelihood of the patient entering a more severe state of the medical condition than the current state, wherein the determining of the likelihood of the patient entering a more severe state of the medical condition further comprises:

acquiring by the processor data characterizing the current state of the medical condition of the patient, the acquired data including at least two different types or sources of data, the types or sources of data including one or more of an X-Ray or data store for X-Rays, an MRI or data store for MRIs, an EKG or data store for EKGs, an ultrasound or data store for ultrasound data, or a lab result or a data store for lab results;

for each different type or source of data, using the processor to apply at least one of a plurality of machine learning models by inputting the data characterizing the current state of the medical condition of the patient;

generating by the processor an output metric for each of the plurality of applied machine learning models;

combining, by the processor, the output metric of each of the plurality of applied machine learning models into a composite metric, wherein the composite metric represents the likelihood of the patient condition entering the more severe state of the medical condition, wherein the composite metric is generated by forming a weighted combination of the output metric of each of the plurality of applied machine learning models, wherein one or more weights in the weighted combination are a function of an amount of time since the current state of the medical condition of the patient was determined;

in response to determining the composite metric, the processor automatically initiating a request for a specific process, resource, test, follow-up procedure, or additional assistance, wherein the request is for one or more of an increase of supplemental oxygen, application of an additional therapy, noninvasive ventilation, ventilation, prone positioning of the patient, or Extracorporeal Membrane Oxygenation (ECMO) prior to the patient entering a more severe state of the medical condition and thereby more efficiently allocating resources within a clinical setting;

receiving the requested process, resource, test, follow-up procedure, or additional assistance from a resource within the clinical setting; and

administering or treating the patient with one or more of an increase of supplemental oxygen, the additional requested therapy, a form of ventilation, an adjustment to the positioning of the patient, or application of Extracorporeal Membrane Oxygenation (ECMO) prior to the patient entering a more severe state of the medical condition.

2 . The method of claim 1 , wherein the acquired data comprises two or more of lab results, x-rays, ultrasound images, lung images, waveforms indicating a state of the patient's organs or body functions, clinical observations, and psychological profile information.

3 . The method of claim 1 , wherein the medical condition is a viral infection, and further, wherein the viral infection is a coronavirus.

4 . The method of claim 1 , further comprising receiving a selection of one of one or more selectable resources, tests, follow-up procedures, or requests for additional assistance, wherein the resource is an item of medical equipment, a staff member, a trained operator, a doctor, a nurse, a hospital bed, or other aspect of a hospital's capacity to treat patients.

5 . The method of claim 1 , further comprising the processor generating a user interface display on a device, wherein the generated user interface display includes a recommended treatment approach based on both the composite metric and a threshold value or range for the composite metric selected by a clinical professional or other medical service provider.

6 . The method of claim 1 , further comprising:

the processor accessing information describing a level of a resource expected to be needed to treat the patient when the medical condition of the patient enters the more severe state; and

the processor generating a display of the composite metric and the accessed information describing the level of the resource expected to be needed on a device viewable by a clinical professional.

7 . The method of claim 6 , further comprising receiving an instruction from the clinical professional to alter a current level of the resource to the level of the resource expected to be needed to treat the patient when the medical condition of the patient enters the more severe state.

8 . The method of claim 1 , wherein each of the plurality of machine learning models is trained by a process comprising:

identifying a type of medical data associated with progression of a disease or illness;

acquiring examples of the identified type of medical data for a set of patients;

separating the acquired examples of the medical data into a first group indicative of a specific stage of the disease or illness and a second group that is not indicative of the specific stage of the disease or illness; and

training the model using each group of data and an associated label, wherein the associated label indicates whether the group of data is indicative or is not indicative of the specific stage of the disease or illness.

9 . The method of claim 1 , wherein the more severe state of the medical condition indicated by the composite metric is Acute Respiratory Distress Syndrome (ARDS).

10 . A system for treating a patient, comprising:

one or more electronic processors configured to execute a set of computer-executable instructions;

one or more non-transitory electronic data storage media containing the set of computer-executable instructions, wherein when executed, the instructions cause the one or more electronic processors to:

determine a current state of a medical condition of a patient;

determine a likelihood of the patient entering a more severe state of the medical condition than the current state, wherein determining the likelihood of the patient entering a more severe state of the medical condition further comprises;

acquiring data characterizing the current state of the medical condition of the patient, the acquired data including at least two different types or sources of data, the types or sources of data including one or more of an X-Ray or data store for X-Rays, an MRI or data store for MRIs, an EKG or data store for EKGs, an ultrasound or data store for ultrasound data, or a lab result or a data store for lab results;

for each different type or source of data, applying at least one of a plurality of machine learning models by inputting the data characterizing the current state of the medical condition of the patient;

generating an output metric for each of the plurality of applied machine learning models;

combining the output metric of each of the plurality of applied machine learning models into a composite metric, wherein the composite metric represents the likelihood of the patient condition entering the more severe state of the medical condition, wherein the composite metric is generated by forming a weighted combination of the output metric of each of the plurality of applied machine learning models, wherein one or more weights in the weighted combination are a function of an amount of time since the current state of the medical condition of the patient was determined;

in response to determining the composite metric, automatically initiating a request for a specific process, resource, test, follow-up procedure, or additional assistance, wherein the request is for one or more of an increase of supplemental oxygen, application of an additional therapy, noninvasive ventilation, ventilation, prone positioning of the patient, or Extracorporeal Membrane Oxygenation (ECMO) prior to the patient entering a more severe state of the medical condition and thereby more efficiently allocating resources within a clinical setting;

determine that the requested process, resource, test, follow-up procedure, or additional assistance has been received from a resource within the clinical setting; and

determine that the patient has had administered or been treated with one or more of an increase of supplemental oxygen, the additional requested therapy, a form of ventilation, an adjustment to the positioning of the patient, or application of Extracorporeal Membrane Oxygenation (ECMO) prior to the patient entering a more severe state of the medical condition.

11 . The system of claim 10 , wherein the acquired data comprises two or more of lab results, X-rays, ultrasound images, waveforms or signals indicating a state of the patient's organs or body functions, clinical observations, and psychological profile information.

12 . The system of claim 10 , wherein the medical condition is a viral infection, and further, wherein the viral infection is a coronavirus.

13 . The system of claim 10 , wherein the instructions further cause the one or more processors to receive a selection of one of one or more selectable resources, tests, follow-up procedures, or requests for additional assistance, wherein the resource is an item of medical equipment, a staff member, a trained operator, a doctor, a nurse, a hospital bed, or other aspect of a hospital's capacity to treat patients.

14 . The system of claim 10 , wherein the instructions further cause the one or more processors to generate a user interface display on a device, wherein the generated user interface display includes a recommended treatment approach based on both the composite metric and a threshold value or range for the composite metric selected by a clinical professional or other medical service provider.

15 . The system of claim 10 , wherein the instructions further cause the one or more electronic processors to:

access information describing a level of a resource expected to be needed to treat the patient when the medical condition of the patient enters the more severe state; and

generate a display of the composite metric and the accessed information describing the level of the resource expected to be needed on a device viewable by a clinical professional.

16 . The system of claim 15 , wherein the instructions further cause the one or more electronic processors to receive an instruction from the clinical professional to alter a current level of the resource to the level of the resource expected to be needed to treat the patient when the medical condition of the patient enters the more severe state.

17 . One or more non-transitory computer-readable media comprising a set of computer-executable instructions that when executed by one or more programmed electronic processors, cause a patient to be treated by:

determining a current state of a medical condition of a patient;

determining a likelihood of the patient entering a more severe state of the medical condition than the current state, wherein determining the likelihood of the patient entering a more severe state of the medical condition further comprises;

acquiring data characterizing the current state of the medical condition of the patient, the acquired data including at least two different types or sources of data, the types or sources of data including one or more of an X-Ray or data store for X-Rays, an MRI or data store for MRIs, an EKG or data store for EKGs, an ultrasound or data store for ultrasound data, or a lab result or a data store for lab results;

for each different type or source of data, applying at least one of a plurality of machine learning models by inputting the data characterizing the current state of the medical condition of the patient;

generating an output metric for each of the plurality of applied machine learning models;

combining the output metric of each of the plurality of applied machine learning models into a composite metric, wherein the composite metric represents the likelihood of the patient condition entering the more severe state of the medical condition, wherein the composite metric is generated by forming a weighted combination of the output metric of each of the plurality of applied machine learning models, wherein one or more weights in the weighted combination are a function of an amount of time since the current state of the medical condition of the patient was determined;

in response to determining the composite metric, automatically initiating a request for a specific process, resource, test, follow-up procedure, or additional assistance, wherein the request is for one or more of an increase of supplemental oxygen, application of an additional therapy, noninvasive ventilation, ventilation, prone positioning of the patient, or Extracorporeal Membrane Oxygenation (ECMO) prior to the patient entering a more severe state of the medical condition and thereby more efficiently allocating resources within a clinical setting;

determining that the requested process, resource, test, follow-up procedure, of additional assistance has been received from a resource within the clinical setting; and

determining that the patient has had administered or been treated with one or more of an increase of supplemental oxygen, the additional requested therapy, a form of ventilation, an adjustment to the positioning of the patient, or application of Extracorporeal Membrane Oxygenation (ECMO) prior to the patient entering a more severe state of the medical condition.

18 . The one or more non-transitory computer-readable media of claim 17 , wherein the acquired data comprises two or more of lab results, X-rays, ultrasound images, waveforms or signals indicating a state of the patient's organs or body functions, clinical observations, and psychological profile information, and wherein the instructions cause the one or more programmed electronic processors to receive a request for a resource, wherein the resource is an item of medical equipment, a staff member, a trained operator, a doctor, a nurse, a hospital bed, or other aspect of a hospital's capacity to treat patients.