System and method for dispensing medication

Patent metadata

Field	Value
Publication number	US-11081220-B2
Application number	US-201815887222-A
Country	US
Kind code	B2
Filing date	Feb 2, 2018
Priority date	Feb 2, 2018
Publication date	Aug 3, 2021
Grant date	Aug 3, 2021

Abstract

A method for detecting diversion may include receiving, from a dispensing cabinet including medication, data associated with a plurality of individuals accessing the dispensing cabinet to retrieve and/or return the medication. Diversion of the medication may be detected by at least applying, to at least a portion of the data received from the dispensing cabinet, a machine learning model trained to detect diversion. An identity of a first individual responsible for the diversion may be determined based on the data received from the dispensing cabinet. In response to the determination of the first individual as being responsible for the diversion, an investigative workflow may be triggered at the dispensing cabinet. Related systems and articles of manufacture, including apparatuses and computer program products, are also disclosed.

First claim

What is claimed is:

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, result in operations comprising:
receiving, from a dispensing cabinet including medication, data associated with a plurality of individuals accessing the dispensing cabinet to retrieve and/or return the medication, the data including one or more videos, images, and/or audio recordings;
detecting a diversion of the medication by at least applying, to at least a portion of the data received from the dispensing cabinet, a machine learning model, the machine learning model being trained to identify, based on at least on the one or more videos, images, and/or audio recordings, one or more physical traits indicative of diversion;
determining, based on the data received from the dispensing cabinet, an identity of a first individual responsible for the diversion;
in response to the first individual being determined to be responsible for the diversion, triggering an investigative workflow that includes providing access to a designated portion of the dispensing cabinet, the designated portion of the dispensing cabinet being configured to receive a first medication returned by the first individual to the dispensing cabinet, and the designated portion of the dispensing cabinet being inaccessible to other individuals such that the first medication returned by the first individual is isolated from one or more medications returned by the other individuals to the dispensing cabinet; and
in response to detecting a second individual accessing the dispensing cabinet to return a second medication, providing access to a different portion of the dispensing cabinet configured to receive the second medication returned by the second individual to the dispensing cabinet.

2. The system of claim 1 , wherein the one or more videos, images, and/or audio recordings are captured at the dispensing cabinet of the plurality of individuals accessing the dispensing cabinet.

3. The system of claim 2 , wherein the one or more physical traits include a facial feature, a facial expression, a body posture, a hand gesture, and an eye movement associated with drug abuse and/or theft.

4. The system of claim 1 , wherein the data received from the dispensing cabinet further includes a fingerprint, an iris pattern, a retina pattern, a handwritten signature, a voice, an identification number, and/or a passcode of the plurality of individuals accessing the dispensing cabinet.

5. The system of claim 1 , wherein the machine learning model is trained to detect, based at least in part on the data received from the dispensing cabinet, one or more behavioral patterns associated with diversion, and wherein the one or more behavioral patterns include accessing the dispensing cabinet at inconsistent hours and/or with an abnormal frequency.

6. The system of claim 1 , wherein the investigative workflow further comprises:
detecting that the first individual is accessing a drawer in the dispensing cabinet; and
in response to the detection of the first individual accessing the drawer in the dispensing cabinet, activating a first camera at the dispensing cabinet to capture a first image and/or a first video of the first individual retrieving the medication from the drawer and/or returning the medication to the drawer.

7. The system of claim 6 , wherein the investigative workflow further comprises activating a second camera at the dispensing cabinet to capture a second image and/or a second video of the first individual, and wherein the second image and/or the second video includes a face of the first individual to enable a verification of the identity of the first individual.

8. The system of claim 1 , wherein the machine learning model is trained to perform anomaly detection.

9. The system of claim 8 , further comprising:
training, based at least on training data, the machine learning model, the training data including anomalous data indicative of diversion, and the machine learning model being trained to differentiate between the anomalous data and non-anomalous data.

10. A computer-implemented method, comprising:
receiving, from a dispensing cabinet including medication, data associated with a plurality of individuals accessing the dispensing cabinet to retrieve and/or return the medication, the data including one or more videos, images, and/or audio recordings;
detecting a diversion of the medication by at least applying, to at least a portion of the data received from the dispensing cabinet, a machine learning model, the machine learning model being trained to identify, based on at least on the one or more videos, images, and/or audio recordings, one or more physical traits indicative of diversion;
determining, based on the data received from the dispensing cabinet, an identity of a first individual responsible for the diversion;
in response to the first individual being determined to be responsible for the diversion, triggering an investigative workflow that includes providing access to a designated portion of the dispensing cabinet, the designated portion of the dispensing cabinet being configured to receive a first medication returned by the first individual to the dispensing cabinet, and the designated portion of the dispensing cabinet being inaccessible to other individuals such that the first medication returned by the first individual is isolated from one or more medications returned by the other individuals to the dispensing cabinet; and
in response to detecting a second individual accessing the dispensing cabinet to return a second medication, providing access to a different portion of the dispensing cabinet configured to receive the second medication returned by the second individual to the dispensing cabinet.

11. The method of claim 10 , wherein the one or more videos, images, and/or audio recordings are captured at the dispensing cabinet of the plurality of individuals accessing the dispensing cabinet.

12. The method of claim 11 , wherein the one or more physical traits include a facial feature, a facial expression, a body posture, a hand gesture, and an eye movement associated with drug abuse and/or theft.

13. The method of claim 10 , wherein the data received from the dispensing cabinet further includes a fingerprint, an iris pattern, a retina pattern, a handwritten signature, a voice, an identification number, and/or a passcode of the plurality of individuals accessing the dispensing cabinet.

14. The method of claim 10 , wherein the machine learning model is trained to detect, based at least in part on the data received from the dispensing cabinet, one or more behavioral patterns associated with diversion, and wherein the one or more behavioral patterns include accessing the dispensing cabinet at inconsistent hours and/or with an abnormal frequency.

15. The method of claim 10 , wherein the investigative workflow further comprises:
detecting that the first individual is accessing a drawer in the dispensing cabinet; and
in response to the detection of the first individual accessing the drawer in the dispensing cabinet, activating a first camera at the dispensing cabinet to capture a first image and/or a first video of the first individual retrieving the medication from the drawer and/or returning the medication to the drawer.

16. The method of claim 15 , wherein the investigative workflow further comprises activating a second camera at the dispensing cabinet to capture a second image and/or a second video of the first individual, and wherein the second image an

Assignees

• Carefusion 303 Inc

Inventors

• Loebig Scott
• Yamaga Cynthia
• Nag Abhikesh

Classifications

• G16H20/13 Primary

  delivered from dispensers · CPC title

• G16H50/20

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

• G06N20/20

  Ensemble learning · CPC title

• G06N20/00

  Machine learning · CPC title