Patient monitoring systems and methods

A system comprising:

• one or more processors;
• one or more vital sign acquisition cameras operably coupled with the one or more processors;
• and
• memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to:
• acquire one or more initial vital signs from each of a plurality of patients;
• determine a patient acuity measure associated with each of the plurality of patients based on the acquired one or more vital signs from each of the plurality of patients;
• establish a patient monitoring queue that includes the plurality of patients, the plurality of patients being located an area that can be captured by the one or more vital sign acquisition cameras;
• unobtrusively acquire, by one or more of the vital sign acquisition cameras, one or more updated vital signs from a given patient selected from the patient monitoring queue;
• determine an updated patient acuity measure for the given patient based on the one or more updated vital signs unobtrusively acquired by the one or more vital sign acquisition cameras from the given patient using a machine learning model;
• detect, based on a comparison of the updated patient acuity measure for the given patient and the previously determined patient acuity measure for the given patient, deterioration of the given patient;
• update the machine learning model by writing new trained weights for a least one module of the machine learning model;
• and
• provide output alerting medical personnel of the deterioration of the given patient,
• wherein the one or more vital signs cameras acquire the one or more updated vital signs by applying image detection algorithms, and
• wherein the one or more updated vital signs comprise one or more of blood pressure, pulse, glucose level, SO2, photoplethysmogram, respiration rate, temperature, skin color, blood pressure, posture, or sweat levels.

At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations:

• acquiring one or more initial vital signs from each of a plurality of patients;
• determining a patient acuity measure associated with each of the plurality of patients based on the acquired one or more initial vital signs from each of the plurality of patients;
• establishing a patient monitoring queue that includes the plurality of patients, the plurality of patient being located in an area that can be captured by one or more vital sign acquisition cameras;
• unobtrusively acquiring, by one or more of the vital sign acquisition cameras, one or more updated vital signs from a given patient selected from the patient monitoring queue;
• determining an updated patient acuity measure for the given patient based on the one or more updated vital signs unobtrusively acquired by the one or more vital sign acquisition cameras from the given patient using a machine learning model;
• detecting, based on a comparison of the updated patient acuity measure for the given patient and the previously determined patient acuity measure for the given patient, deterioration of the given patient;
• updating the machine learning model by writing new trained weights for at least one module of the machine learning model;
• and
• providing output alerting medical personnel of the deterioration of the given patient,
• wherein the one or more vital signs cameras acquire the one or more updated vital signs by applying image detection algorithms, and
• wherein the one or more updated vital signs comprise one or more of blood pressure, pulse, glucose level, SO2, photoplethysmogram, respiration rate, temperature, skin color, blood pressure, posture, or sweat levels.