Adaptive artificial intelligence system for identifying behaviors associated with mental illness and modifying treatment plans based on emergent recognition of aberrant reactions
One or more embodiments described herein relate to predicting, using adaptive artificial intelligence techniques, typical and aberrant physiological reactions of a patient to psychiatric counseling. Treatment plans can be determined and calculated based on previously-gathered demographic and/or biometric data, and/or modifications to treatment plans can be determined and/or implemented based on emergent recognition of reaction types, such as reclassifying reactions that would previously have been deemed typical as aberrant (or vice versa).
1. A system, comprising:
at least one of (1) a video camera configured to capture video data or (2) an audio recorder configured to capture audio data, of a patient during a counseling session; and
at least one compute device operably coupled to the at least one of the video camera or the audio recorder, the at least one compute device configured to:
extract biometric data from at least one of the video data or the audio data, the biometric data including at least one of eye movement, body perspective, body language, facial expression, word selection, sentence structure, pauses in speech, length of a response to a question, or timeliness of the response to the question;
identify the patient as being a member of a cohort based on at least one of (i) the biometric data or (ii) demographic information for the patient;
perform a machine learning task on the biometric data to identify an aberrant reaction of the patient relative to at least one of a typical reaction of the patient or a reaction typical to the cohort to which the patient belongs, the machine learning task configured to quantitatively identify the aberrant reaction of the patient without comparing the plurality of biometric parameters to predefined thresholds;
define a modified treatment plan based on the aberrant reaction being identified; and
update the machine learning task with information associated with the aberrant reaction such that repeated occurrences of the aberrant reaction will cause the machine learning task to relabel the aberrant reaction as a typical reaction.
2. The system of claim 1 , wherein the biometric data includes at least two of the eye movement, the body perspective, the body language, the facial expression, the word selection, sentence structure, the pauses in speech, the length of the response to the question, or timeliness of the response to the question.
3. The system of claim 1 , wherein the aberrant reaction does not correspond to a predefined type of aberrant reaction.
4. The system of claim 1 , wherein the biometric data on which the machine learning task is performed and based on which the aberrant reaction is identified does not correspond to a pattern of biometric parameters previously identified as corresponding to an aberrant reaction.
5. The system of claim 1 , wherein the patient and the at least one of the video camera or the audio recorder are at a first location and at least one of the at least one compute device or a counselor administering the counseling session are at a second location remote from the first location.
6. The system of claim 1 , wherein:
the at least one compute device is operably coupled to a database containing biometric parameters for a plurality of previous patients and an indication of treatment outcome for each previous patient from the plurality of previous patients;
the cohort includes a subset of the plurality of previous patients; and
the at least one compute device is configured to train the machine learning task using the biometric parameters for the subset of the plurality of previous patients.
7. The system of claim 1 , further comprising an output device is configured to warn a counselor administering the counseling session of the aberrant reaction.
8. At least one compute device operably coupled to at least one of (1) a video camera configured to capture video data or (2) an audio recorder configured to capture audio data, of a patient during a counseling session administered by a first counselor, the at least one compute device configured to:
extract biometric data from at least one of the video data or the audio data, the biometric data including at least one of eye movement, body perspective, body language, facial expression, word selection, sentence structure, pauses in speech, length of a response to a question, or timeliness of the response to the question;
identify the patient as being a member of a cohort based on at least one of (i) the biometric data or (ii) demographic information for the patient;
perform a machine learning task on the biometric data to identify an aberrant reaction of the patient relative to at least one of a typical reaction of the patient or a reaction typical to the cohort to which the patient belongs, the machine learning task configured to quantitatively identify the aberrant reaction of the patient without comparing the plurality of biometric parameters to predefined thresholds; and
define a modified treatment plan based on the aberrant reaction being identified, the modified treatment plan including an indication that the patient should be treated by a second counselor different from the first counselor.
9. The at least one compute device of claim 8 , wherein the biometric data includes at least two of the eye movement, the body perspective, the body language, the facial expression, the word selection, the sentence structure, the pauses in speech, the length of the response to the question, or the timeliness of the response to the question.
10. The at least one compute device of claim 8 , wherein:
the counseling session is associated with a treatment plan for post-traumatic stress disorder;
the aberrant reaction is associated with anxiety related to a trauma; and
the modified treatment plan includes refocusing the counseling session away from the trauma to reduce the anxiety.
11. The at least one compute device of claim 8 , wherein:
the counseling session is associated with a treatment plan for post-traumatic stress disorder;
the aberrant reaction is associated with anxiety related to a trauma; and
the modified treatment plan includes focusing on the trauma in connection with prolonged exposure therapy.
12. The at least one compute device of claim 8 , wherein:
the at least one compute device is configured to identify the aberrant reaction by identifying a mental health crisis in real-time; and
the at least one compute device is configured to define the modified treatment plan by identifying a therapeutic intervention to reduce an impact of the mental health crisis.
13. The at least one compute device of claim 8 , wherein:
the at least one compute device is operably coupled to a database containing biometric parameters for a plurality of previous patients and an indication of treatment outcome for each previous patient from the plurality of previous patients;
the cohort includes a subset of the plurality of previous patients; and
the at least one compute device is configured to train the machine learning task using the biometric parameters for the subset of the plurality of previous patients.
14. At least one compute device operably coupled to at least one of (1) a video camera configured to capture video data or (2) an audio recorder configured to capture audio data, of a patient during a counseling session administered by a first counselor, the at least one compute device configured to:
extract biometric data for the patient from at least one of the video data or the audio data, the biometric data including at least one of eye movement, body perspective, body language, facial expression, word selection, sentence structure, pauses in speech, length of a response to a question, or timeliness of the response to the question;
identify the patient as being a member of a cohort based on at least one of (i) the biometric data for the patient or (ii) demographic information for the patient;
train a supervised machine learning model with biometric data for the cohort, after training the supervised machine learning model being configured to perform a machine learning task;
apply the machine learning task to the biometric data for the patient to identify an aberrant reaction; and
define a modified treatment plan based on the aberrant reaction being identified.
15. The at least one compute device of claim 14 , further comprising an output device communicatively coupled to the at least one compute device and configured to produce a warning signal that alerts a counselor to employ the modified treatment plan.
16. The at least one compute device of claim 14 , wherein the at least one compute device is further configured to update the machine learning task with information associated with the aberrant reaction such that repeated occurrences of the aberrant reaction will cause the machine learning task to relabel the aberrant reaction as a typical reaction.
17. A system, comprising:
at least one of (1) a video camera configured to capture video data or (2) an audio recorder configured to capture audio data, of a patient during a counseling session;
at least one compute device operably coupled to the at least one of the video camera or the audio recorder, the at least one compute device configured to:
extract biometric data for the patient from at least one of the video data or the audio data, the biometric data including at least one of eye movement, body perspective, body language, facial expression, word selection, sentence structure, pauses in speech, length of a response to a question, or timeliness of the response to the question;
identify the patient as being a member of a cohort based on at least one of (i) the biometric data for the patient or (ii) demographic information for the patient; and
perform an machine learning task on the biometric data for the patient to identify an aberrant reaction of the patient, the machine learning task being associated with an unsupervised machine learning model trained on biometric data for the cohort without associating biometric data for the cohort with a success metric.
18. The system of claim 17 , wherein the at least one compute device is further configured to:
define a modified treatment plan based on the aberrant reaction being identified; and
update the machine learning task with information associated with the aberrant reaction such that repeated occurrences of the aberrant reaction will cause the machine learning task to relabel the aberrant reaction as a typical reaction.
19. The system of claim 17 , wherein:
the at least one compute device is operably coupled to a database containing biometric parameters for a plurality of previous patients and an indication of treatment outcome for each previous patient from the plurality of previous patients;
the cohort includes a subset of the plurality of previous patients; and
the at least one compute device is configured to train the unsupervised machine learning model using the biometric parameters for the subset of the plurality of previous patients.
20. The system of claim 17 , wherein the biometric data includes at least two of the eye movement, the body perspective, the body language, the facial expression, the word selection, the sentence structure, the pauses in speech, the length of the response to the question, or the timeliness of the response to the question.