Method for screening psychiatric disorder based on conversation and apparatus therefor

Patent metadata

Field	Value
Publication number	US-12144639-B2
Application number	US-202117374831-A
Country	US
Kind code	B2
Filing date	Jul 13, 2021
Priority date	Jul 15, 2020
Publication date	Nov 19, 2024
Grant date	Nov 19, 2024

Abstract

Disclosed are a psychiatric disorder screening method and apparatus based on conversation. The psychiatric disorder screening apparatus outputs stimulation including at least one of a story, a word, a sound, a picture, a motion, a color or a direction, and when receiving a response to the stimulation from a testee, determines the presence or absence of a psychiatric disorder by comparing a correct answer ratio of the response or a voice feature included in the response with correct answer ratios or voice features of a normal group and a disease group.

First claim

The invention claimed is:

1. A psychiatric disorder screening method based on conversation,
the method comprising:
outputting first stimulation including at least one of a story, a word, a sound, a picture, a motion, a color or a direction;
receiving first response to the first stimulation from a testee and outputting second stimulation based on the first response; and
receiving second response to the second stimulation, and calculating likelihood of psychiatric disorder of the testee by considering at least one of the testee's correct answer ratio of the first response and the second response, the testee's voice feature of the first response and the second response, or conversation details of the first response and the second response, and
wherein outputting the first stimulation comprises changing type of the first stimulation or difficulty of the first stimulation when the correct answer ratio of the testee's the first response to the first stimulation is equal to or larger than a predetermined value.

2. The psychiatric disorder screening method based on conversation according to claim 1 ,
wherein outputting the first stimulation comprises outputting a predefined other word instead of a word included in the story stimulation to increase a difference between a normal group and a disease group with regard to the stimulation.

3. The psychiatric disorder screening method based on conversation according to claim 1 ,
wherein outputting the first stimulation comprises determining the stimulation to output according to response details of the testee.

4. The psychiatric disorder screening method based on conversation according to claim 1 ,
wherein outputting the first stimulation comprises controlling an output interval between stimuli or placing interference stimulation in the stimulation.

5. The psychiatric disorder screening method based on conversation according to claim 1 ,
wherein the voice feature includes at least one of a formant, Mel-Frequency Cepstral Coefficients (MFCCs), a pitch, a sound length or a voice quality.

6. A psychiatric disorder screening apparatus, comprising:
a data output unit to output first stimulation including at least one of a story, a word, a sound, a picture, a motion, a color or a direction;
a voice input unit to receive first response to the first stimulation from a testee;
wherein the data output unit to output second stimulation based on the first response, and
a voice analysis unit to calculate likelihood of psychiatric disorder of the testee by considering at least one of the testee's correct answer ratio of the first response and a second response, the testee's voice feature of the first response and the second response, or conversation details of the first response and the second response, and
wherein the data output unit changes type of the first stimulation or difficulty of the first stimulation when the correct answer ratio of the testee's the first response to the first stimulation is equal to or larger than a predetermined value.

7. A computer-readable recording medium having computer-readable instructions stored thereon, the instructions being executed by at least one processor to enable the at least one processor to perform the steps of:
outputting first stimulation including at least one of a story, a word, a sound, a picture, a motion, a color or a direction;
receiving first response to the first stimulation from a testee and outputting second stimulation based on the first response; and
receiving second response to the second stimulation, and calculating likelihood of psychiatric disorder of the testee by considering at least one of the testee's correct answer ratio of the first response and the second response, the testee's voice feature of the first response and the second response, or conversation details of the first response and the second response,
wherein outputting the first stimulation comprises changing type of the first stimulation or difficulty of the first stimulation when the correct answer ratio of the testee's the first response to the first stimulation is equal to or larger than a predetermined value.

Assignees

• Seoul Nat Univ R&Db Foundation
• Emocog Co Ltd

Inventors

• Lee Jun Young

Classifications

• A61B5/165 Primary

  Evaluating the state of mind, e.g. depression, anxiety · CPC title

• G10L25/66

  for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B5/00) · CPC title

• G16H10/20

  for electronic clinical trials or questionnaires · CPC title

• A61B5/4803

  Speech analysis specially adapted for diagnostic purposes · CPC title

• A61B5/4884

  inducing physiological or psychological stress, e.g. applications for stress testing · CPC title