System and methods for transitioning patient care from signal based monitoring to risk based monitoring

Inventors

Baronov, Dimitar V. • Butler, Evan J. • Lock, Jesse M. • McManus, Michael F.

Assignees

Etiometry LLC

Abstract

A risk-based patient monitoring system for critical care patients combines data from multiple sources to assess the current and the future risks to the patient, thereby enabling providers to review a current patient risk profile and to continuously track a clinical trajectory. A physiology observer module in the system utilizes multiple measurements to estimate Probability Density Functions (PDF) of a number of Internal State Variables (ISVs) that describe a components of the physiology relevant to the patient treatment and condition. A clinical trajectory interpreter module in the system utilizes the estimated PDFs of ISVs to identify under which probable patient states the patient can be currently categorized and assign a probability value that the patient will be in each of the identified states. The combination of patient states and their probabilities is defined as the clinical risk to the patient.

Core Innovation

The invention provides a risk-based monitoring method and system in which physiological data are acquired substantially continuously from a plurality of physically attachable sensors, including at least a heart rate sensor and an SpO2 sensor. A computer generates a clinical trajectory described by probabilities of possible patient states, where the possible patient states cannot be directly measured, and displays the clinical trajectory as probabilities as a function of a plurality of time steps on a graphical user interface.

A physiology observer generates predicted probability density functions of internal state variables for a subsequent time step using posterior estimated probability density functions for internal state variables from a preceding time step. The predicted probability density functions are generated by computing conditional probability density functions of the data acquired at a time step given the internal state variables and the predicted probability density functions of the internal state variables. Based on the generated posterior predicted probability density functions, the invention determines a set of possible states of a hidden internal state variable and maps these to probabilities of possible patient states.

The invention further supports updating and handling across time steps, including storing acquired data associated with the internal state variables that may be intermittent or aperiodic, and generating predicted and posterior probability density functions across time steps using evolving backwards and generating posterior probability density functions. The invention includes generating data to cause display of graphical indicators corresponding to the possible patient states, including a hazard level, and generating a timeline controller that allows dynamic selection of time points to display evolution of one possible patient state over a range of time.

Claims Coverage

The partial content identifies three independent claims: a method for risk-based monitoring, a computer program product for implementing that monitoring, and a system for monitoring. Across these independent claims, the inventive features focus on acquiring physiological sensor data from physically attachable sensors, generating predicted and posterior predicted probability density functions for internal state variables using conditional probability density functions and posterior estimated probability density functions, deriving probabilities of possible patient states for states that cannot be directly measured, and displaying the resulting clinical trajectory over time via a graphical user interface and indicators.

Across the independent claims, the document covers a risk-based patient monitoring framework in which attachable sensor data drive prediction and Bayesian-style updating of probability density functions for internal state variables, yielding probabilities for qualitative patient states that cannot be directly measured. The results are presented as a clinical trajectory over time on a graphical user interface, with the program-product claim further emphasizing graphical indicators with hazard levels and an interactive timeline controller.

Stated Advantages

Documented Applications

No documented applications found