18463690. MACHINE LEARNING METHOD FOR DETERMINING PATIENT BEHAVIOR USING AUDIO ANALYTICS simplified abstract (Insight Direct USA, Inc.)

MACHINE LEARNING METHOD FOR DETERMINING PATIENT BEHAVIOR USING AUDIO ANALYTICS

Organization Name

Insight Direct USA, Inc.

Inventor(s)

Michael Griffin of Wayland MA (US)

Hailey Kotvis of Wauwatosa WI (US)

Josephine Miner of Hope RI (US)

Porter Moody of Wayland MA (US)

Kayla Poulsen of Natick MA (US)

Austin Malmin of Gilbert AZ (US)

Sarah Onstad-hawes of Seattle WA (US)

Gloria Solovey of Arlington MA (US)

Austin Streitmatter of Palm Harbor FL (US)

MACHINE LEARNING METHOD FOR DETERMINING PATIENT BEHAVIOR USING AUDIO ANALYTICS - A simplified explanation of the abstract

This abstract first appeared for US patent application 18463690 titled 'MACHINE LEARNING METHOD FOR DETERMINING PATIENT BEHAVIOR USING AUDIO ANALYTICS

Simplified Explanation

The patent application describes a method and apparatus for invoking an alert based on a patient's behavior as determined by a machine learning model operating on an audio stream of the patient.

• Audio and semantic text data are extracted from the audio stream of the patient.
• The audio data are analyzed to identify a first feature set.
• The semantic text data are analyzed to identify a second feature set.
• A machine-learning model determines the patient behavior based on the first and/or second feature sets.
• The patient behavior is compared with a set of alerting behaviors corresponding to the patient classification.
• An alert is automatically invoked when the patient behavior is included in the set of alerting behaviors corresponding to the patient classification.

Potential Applications

This technology could be applied in healthcare settings to monitor patients and alert healthcare providers of any concerning behaviors or situations.

Problems Solved

This technology helps in early detection of potential issues or emergencies with patients, allowing for timely intervention and care.

Benefits

The benefits of this technology include improved patient monitoring, early detection of issues, and timely alerts to healthcare providers.

Potential Commercial Applications

Potential commercial applications of this technology could include medical device companies, healthcare facilities, and telemedicine providers.

Possible Prior Art

One possible prior art for this technology could be existing patient monitoring systems that use machine learning algorithms to analyze patient data and detect abnormal patterns or behaviors.

How does the machine learning model differentiate between different patient classifications?

The machine learning model likely uses a training dataset with labeled patient behaviors to learn the patterns associated with each classification.

What measures are in place to ensure the accuracy and reliability of the alerts generated by the system?

Quality control measures, validation studies, and continuous monitoring of the system's performance are likely implemented to ensure the accuracy and reliability of the alerts.

Original Abstract Submitted

Apparatus and associated methods relate to invoking an alert based upon a behavior of a patient as determined by a machine learning model operating on an audio stream of the patient. Audio data, and semantic text data are extracted from an audio stream of the patient. The audio data are analyzed to identify a first feature set. The semantic text data are analyzed to identify a second feature set. Using a computer-implemented machine-learning model, a patient behavior of the patient is determined based on the first and/or second features sets. The patient behavior is compared with a set of alerting behaviors corresponding to a patient classification of the patient. The alert is automatically invoked when the patient behavior is determined to be included in the set of alerting behaviors corresponding to the patient classification of the patient.