Machine learning based clinical resource controller

Patent metadata

Field	Value
Publication number	US-2023402182-A1
Application number	US-202318236374-A
Country	US
Kind code	A1
Filing date	Aug 21, 2023
Priority date	Feb 22, 2021
Publication date	Dec 14, 2023
Grant date	—

Abstract

A method may include receiving, from one or more data systems, a message. A machine learning model may be applied to the message to determine whether the message is an actionable message or a non-actionable message. In response to the message being the actionable message, the machine learning model may be applied to extract, from the message, a clinically significant data. One or more tasks may be performed based on the clinically significant data. The one or more tasks may include performing, based on the clinically significant data, a resource allocation for a clinical workflow associated with the data systems. The one or more tasks may also include detecting systematic inefficiencies and bottlenecks associated with the clinical workflow. Related methods and articles of manufacture, including computer program products, are also disclosed.

First claim

1 . A system, comprising:
at least one data processor; and at least one memory storing instructions which, when executed by the at least one data processor, cause the system to perform operations comprising:
receiving, at a machine learning model, from one or more laboratory information systems, one or more messages for a patient as at least one input value to the machine learning model, wherein the one or more messages provide information about a clinical workflow;
based on the machine learning model receiving the one or more messages as the at least one input value to the machine learning model, outputting, by the machine learning model, at least one output value indicating that the one or more messages are actionable;
extracting, from the one or more messages, clinically significant data; and
controlling, based at least on the clinically significant data, at least one medical device associated with the patient to perform one or more tasks.

2 . The system of claim 1 , wherein the one or more tasks include:
identifying, based at least on the clinically significant data, a stage of the clinical workflow associated with the one or more messages; determining, based at least on a timestamp associated with the one or more messages, a quantity of time between two or more successive stages of the clinical workflow; and in response to the quantity of time between the two or more successive stages of the clinical workflow exceeding a threshold value, determining one or more corrective actions.

3 . The system of claim 2 , wherein the one or more corrective actions include one or more of: 1) modifying a scheduling of one or more activities associated with the clinical workflow; or 2) adjusting an allocation of resources associated with the one or more activities.

4 . The system of claim 2 , wherein the stage of the clinical workflow includes a start of a culturing process for a microbe, a gram positive or gram negative identification for the microbe, a species or organism identification for the microbe, or an antimicrobial susceptibility of the microbe.

5 . The system of claim 1 , wherein the clinical workflow comprises a microbial testing workflow or a virology assay.

6 . The system of claim 1 , wherein the one or more tasks include:
determining, based at least on the clinically significant data, to allocate a resource to the one or more laboratory information systems.

7 . The system of claim 6 , wherein the resource includes an antimicrobial based at least on the clinically significant data indicating a presence of a microbe susceptible to the antimicrobial.

8 . The system of claim 6 , wherein to allocate the resource comprises:
determining, based at least on the clinically significant data, a subsequent stage of the clinical workflow and a time for the subsequent stage of the clinical workflow; and scheduling, in accordance with the time of the subsequent stage of the clinical workflow, a quantity of resources required for the subsequent stage of the clinical workflow.

9 . The system of claim 1 , wherein extracting the clinically significant data comprises inputting the one or more messages into one or more of the machine learning model or a different machine learning model, the one or more of the machine learning model or the different machine learning model outputting the clinically significant data.

10 . The system of claim 1 , wherein the one or more messages are determined to be actionable in response to more than a threshold quantity of data in the one or more messages being tagged as clinically significant by the machine learning model.

11 . The system claim 1 , wherein receiving the one or more messages comprises receiving a sequence of messages, and wherein the at least one output value indicates whether the sequence of messages are actionable.

12 . The system of claim 11 , wherein the at least one output value indicates that a message of the sequence of messages is associated with a first actionable event, and wherein the at least one output value further indicates that the sequence of messages are associated with a second actionable event.

13 . The system of claim 12 , wherein the machine learning model determines the message to be actionable as part of the sequence of messages.

14 . The system of claim 1 , wherein the at least one medical device comprises one or more of a diagnostic device, an infusion pump, a dispensing cabinet, or a wasting station.

15 . The system of claim 1 , wherein controlling the at least one medical device comprises transmitting, to the at least one medical device, at least one message to adjust one or more of an operational state or a functional element of the at least one medical device.

16 . The system of claim 1 , wherein the machine learning model comprises one or more of: a regression model, an instance-based model, a regularization model, a decision tree, a Bayesian model, a clustering model, an associative model, a neural network, a deep learning model, a dimensionality reduction model an ensemble model, a recurrent neural network (RNN), a hidden Markov model, a conditional random field (CRF) model, or a gated recurrent unit (GRU).

17 . A computer-implemented method, comprising:
receiving, at a machine learning mode, from one or more laboratory information systems, one or more messages for a patient as at least one input value to the machine learning model, wherein the one or more messages provide information about a clinical workflow; based on the machine learning model receiving the one or more messages as the at least one input value to the machine learning model, outputting, by the machine learning model, at least one output value indicating that the one or more messages are actionable; extracting, from the one or more messages, clinically significant data; and controlling, based at least on the clinically significant data, at least one medical device associated with the patient to perform one or more tasks.

18 . The method of claim 17 , wherein the clinical workflow comprises a microbial testing workflow or a virology assay.

19 . A non-transitory computer readable medium storing instructions, which when executed by at least one data processor, cause the at least one data processor to perform operations comprising:
receiving, at a machine learning model, from one or more laboratory information systems, one or more messages for a patient as at least one input value to the machine learning model, wherein the one or more messages provide information about a clinical workflow; based on the machine learning model receiving the one or more messages as the at least one input value to the machine learning model, outputting, by the machine learning mode, at least one output value indicating that the one or more messages are actionable; extracting, from the one or more messages, clinically significant data; and controlling, based at least on the clinically significant data, at least one medical device associated with the patient to perform one or more tasks.

20 . The non-transitory computer readable medium of claim 19 , wherein the clinical workflow comprises a microbial testing workflow or a virology assay.

Assignees

• Carefusion 303 Inc

Inventors

• Nag Abhikesh
• Segizbayeva Lyazzat
• Vankeepuram Latha
• Tabak Ying

Classifications

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H10/40 Primary

  for data related to laboratory analysis, e.g. patient specimen analysis · CPC title

• G16H10/60

  for patient-specific data, e.g. for electronic patient records · CPC title

• G16H40/40

  for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades · CPC title

• Y02A90/10

  Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation · CPC title