Systems and methods for mental health assessment

Abstract

The present disclosure provides systems and methods for assessing a mental state of a subject in a single session or over multiple different sessions, using for example an automated module to present and/or formulate at least one query based in part on one or more target mental states to be assessed. The query may be configured to elicit at least one response from the subject. The query may be transmitted in an audio, visual, and/or textual format to the subject to elicit the response. Data comprising the response from the subject can be received. The data can be processed using one or more individual, joint, or fused models. One or more assessments of the mental state associated with the subject can be generated for the single session, for each of the multiple different sessions, or upon completion of one or more sessions of the multiple different sessions.

What is claimed is: 
     
         1 . A method for assessing a mental state of a subject via a single session or over multiple different sessions, said method comprising:
 (a) presenting or formulating at least one query based at least in part on one or more target mental states of said subject, wherein said at least one query is configured to elicit at least one response from said subject;   (b) transmitting said at least one query in an audio, visual, or textual format to said subject to elicit said at least one response;   (c) receiving data comprising said at least one response from said subject in response to transmitting said at least one query, wherein said data comprises speech data;   (d) processing said data using one or more models comprising a natural language processing (NLP) model, an acoustic model, or a visual model, to yield processed data; and   (e) using said processed data from (d) to generate, (i) for said single session, (ii) for each of said multiple different sessions, or (iii) upon completion of one or more sessions of said multiple different sessions, analytics data of said mental state associated with said subject.   
     
     
         2 . The method of  claim 1 , further comprising: (f) using said analytics data to generate one or more assessments of said mental state associated with said subject. 
     
     
         3 . The method of  claim 1 , wherein said one or more models are provided as (i) one or more individual models, (ii) jointly as two or more separate models, or (iii) a fused model comprising a composite model that is an aggregate of two or more different models. 
     
     
         4 . The method of  claim 2 , wherein said at least one query comprises a plurality of queries and said at least one response comprises a plurality of responses, wherein said plurality of queries is transmitted in a sequential manner to said subject and configured to systematically elicit said plurality of responses from said subject. 
     
     
         5 . The method of  claim 4 , wherein said plurality of queries is structured in a hierarchical manner such that each subsequent query of said plurality of queries is structured as a logical follow on to said subject's response to a preceding query, and is configured to assess or draw inferences on a plurality of aspects of said mental state of said subject. 
     
     
         6 . The method of  claim 1 , wherein said at least one query is presented or formulated by an administrator based at least in part on a profile of said subject. 
     
     
         7 . The method of  claim 1 , wherein said one or more target mental states comprise depression, anxiety, post-traumatic stress disorder (PTSD), schizophrenia, suicidality, bipolar disorder, or addictive personality. 
     
     
         8 . The method of  claim 1 , wherein said one or more target mental states comprise one or more conditions or disorders associated with a list of predefined mental disorders, wherein said one or more conditions or disorders comprise fatigue, loneliness, low motivation, or stress. 
     
     
         9 . The method of  claim 5 , wherein said one or more assessments comprises at least one score that indicates whether said subject is (i) more likely than others to presently experience at least one of said target mental states or (ii) more likely than others to experience at least one of said target mental states at a future point in time, wherein said future point in time is within a clinically actionable future. 
     
     
         10 . The method of  claim 9 , further comprising: updating said at least one score with processed data obtained from each of said subject's follow-on response to said preceding query. 
     
     
         11 . The method of  claim 2 , further comprising: transmitting said one or more assessments to a healthcare provider for use in evaluating said mental state of said subject, wherein said transmitting is performed (1) in real-time during said one or more assessments, (2) just-in-time upon the completion of said one or more assessments, or (3) at a future point in time after said one or more assessments have been completed. 
     
     
         12 . The method of  claim 2 , further comprising:
 based on said at least one response, identifying additional information to be elicited from said subject;   transmitting a subsequent query to said subject, wherein said subsequent query relates to said additional information and is configured to elicit a subsequent response from said subject;   receiving data comprising said subsequent response from said subject in response to transmitting said subsequent query; and   processing said subsequent response to update said one or more assessments of said mental state of said subject.   
     
     
         13 . The method of  claim 12 , wherein said identifying of additional information to be elicited from said subject comprises:
 identifying (i) one or more elements of substantive content or (ii) one or more patterns in said data that are material to said mental state of said subject; and   for each of said one or more elements of substantive content or said one or more patterns:
 identifying one or more items of follow-up information that are related to said one or more elements or said one or more patterns to be asked of said subject, and 
 generating a subsequent query, wherein said subsequent query relates to said one or more items of follow-up information. 
   
     
     
         14 . The method of  claim 1 , wherein said NLP model comprises one or more of the following: a sentiment model, a statistical language model, a topic model, a syntactic model, an embedding model, a dialog or discourse model, an emotion or affect model, or a speaker personality model. 
     
     
         15 . The method of  claim 1 , wherein said data further comprises images or video of said subject, and wherein said data is further processed using said visual model to generate said analytics data of said mental state of said subject. 
     
     
         16 . The method of  claim 15 , wherein said visual model comprises one or more of the following: a facial cue model, a body movement/motion model, or an eye activity model. 
     
     
         17 . The method of  claim 1 , wherein said at least one query is configured to be transmitted in a conversational context in a form of a question, statement, or comment that is configured to elicit said at least one response from said subject. 
     
     
         18 . The method of  claim 17 , wherein said conversational context is configured to (1) promote elicitation of truthful, reflective, thoughtful, or candid responses from said subject, (2) influence an amount of time that said subject takes to compose said at least one response, or (3) enhance one or more performance metrics of said assessment of said mental state of said subject. 
     
     
         19 . The method of  claim 18 , further comprising: transmitting one or more prompts in said audio, visual, or textual format to said subject when a time latency threshold is exceeded, wherein said time latency threshold is based at least in part on said amount of time that said subject takes to compose said at least one response. 
     
     
         20 . The method of  claim 18 , wherein said one or more performance metrics comprise one or more of the following: an F1 score, an area under the curve (AUC), a sensitivity, a specificity, a positive predictive value (PPV), an equal error rate, or one or more standard metrics for binary or multiclass classification or for regression. 
     
     
         21 . The method of  claim 1 , wherein said at least one query is open-ended without limiting said at least one response from said subject to be a binary yes-or-no response. 
     
     
         22 . The method of  claim 10 , wherein said one or more assessments comprise at least one score having a clinical value that is usable by said healthcare provider to evaluate said mental state of said subject. 
     
     
         23 . The method of  claim 1 , wherein said acoustic model comprises one or more of the following: an acoustic embedding model, a spectral-temporal model, a supervector model, an acoustic affect model, a speaker personality model, an intonation model, a speaking rate model, a pronunciation model, a non-verbal model, or a fluency model. 
     
     
         24 . The method of  claim 1 , wherein said mental state comprises one or more medical, psychological, or psychiatric conditions or symptoms. 
     
     
         25 . The method of  claim 6 , wherein said administrator comprises an automated mental health screening module that is configured to dynamically formulate said at least one query based at least in part on said one or more target mental states to be assessed. 
     
     
         26 . The method of  claim 1 , wherein (d) further comprises:
 processing said data using said one or more models to generate an assessment of said physical state of said subject, wherein said assessment of said physical state comprises a score that indicates whether said subject is (i) more likely than others to experience at least one of a plurality of physiological conditions or (ii) more likely than others to experience at least one of said physiological conditions.   
     
     
         27 . The method of  claim 26 , wherein said physical state of said subject is manifested due to one or more physical conditions affecting a characteristic or a quality of voice of said subject. 
     
     
         28 . The method of  claim 1 , wherein said at least one query comprises subject matter that has been adapted, extracted or modified from one or more tests or questionnaires, which said tests or questionnaires are usable to separately evaluate said one or more target mental states. 
     
     
         29 . The method of  claim 22 , wherein said at least one score comprises a quantized score estimate of said mental state of said subject. 
     
     
         30 . The method of  claim 29 , wherein said quantized score estimate comprises a calibrated score estimate or a binary score estimate.