Abstract: A system for remotely determining the potential presence of depression in a user. The system includes a virtual agent that administers one or more tasks to the user. The user performs the tasks and the performance is captured by a camera. The captured audiovisual data is sent to a server that derives objective metrics which are then applied to a classifying algorithm. If certain metrics meet certain thresholds, the system determines that the user is exhibiting depression symptoms. In embodiments, the system can further determine whether a user has been taking depression medication.

Abstract: A system for remotely determining the potential presence of autism spectrum disorder in a user. The system includes a virtual agent that administers one or more tasks to the user. The user performs the tasks and the performance is captured by a camera. The captured audiovisual data is sent to a server that derives objective metrics which are then applied to a classifying algorithm. If certain metrics meet certain thresholds, the system determines that the user is exhibiting autism symptoms.

Abstract: A system for identifying efficacious markers comprises memory storing collected multimodal digital markers from a first cohort experiencing a sign onset and a second cohort experiencing a non-sign onset. The system further comprises selection logic that identifies a subset of markers that best capture differences between the sign and non-sign onsets. The system further comprises responsiveness logic that determines a responsiveness parameter that specifies a rate of change in the subset. The system further comprises time to detect change logic that determines a time parameter that specifies a time required to detect change in the subset. The system further comprises sample size logic that determines how the responsiveness parameter and the time parameter change depending on sample size. The system further comprises sensitivity logic that determines a sensitivity parameter that specifies whether the subset detects condition deterioration during intervals when no changes are reported in an external standard.

Abstract: A computer-implemented method of generating interpretable, composite marker indexes that are discriminative and noise-robust is provided. The method comprises storing remotely collected multimodal digital markers from a first cohort and a second cohort. The method further comprises grouping multicollinear features in the multimodal digital markers into clusters, and then selecting representative features for the clusters for multiple classification tasks that require discrimination between the first cohort and the second cohort. The method further comprises linearly combining the representative features into an interpretable, composite marker index such that relative contributions of each of the representative features to the interpretable, composite marker index are known.

Abstract: A system for identifying efficacious markers comprises memory storing collected multimodal digital markers from a first cohort experiencing a sign onset and a second cohort experiencing a non-sign onset. The system further comprises selection logic that identifies a subset of markers that best capture differences between the sign and non-sign onsets. The system further comprises responsiveness logic that determines a responsiveness parameter that specifies a rate of change in the subset. The system further comprises time to detect change logic that determines a time parameter that specifies a time required to detect change in the subset. The system further comprises sample size logic that determines how the responsiveness parameter and the time parameter change depending on sample size. The system further comprises sensitivity logic that determines a sensitivity parameter that specifies whether the subset detects condition deterioration during intervals when no changes are reported in an external standard.

Abstract: A computer-implemented method of generating interpretable, composite marker indexes that are discriminative and noise-robust is provided. The method comprises storing remotely collected multimodal digital markers from a first cohort and a second cohort. The method further comprises grouping multicollinear features in the multimodal digital markers into clusters, and then selecting representative features for the clusters for multiple classification tasks that require discrimination between the first cohort and the second cohort. The method further comprises linearly combining the representative features into an interpretable, composite marker index such that relative contributions of each of the representative features to the interpretable, composite marker index are known.

Abstract: A computer-generated dialog session is customized for a user having a pathology characterized at least in part by a speech pathology. The user's speech is analyzed for spans of speech in which the starts and ends of the spans satisfy predetermined thresholds of time. Customization occurs by altering at least one of the following configurable parameters: (a) a threshold minimum signal strength of speech (dB) to consider as the start of the span of speech; (b) an adjustment factor by which signal strengths of background noise increases between consecutive spans of speech; (c) a threshold between signal strength during the span of speech and signal strength during the span of non-speech; (d) a start speech time threshold; and (e) an end speech time threshold.

Abstract: A system for remotely determining the potential presence of depression in a user. The system includes a virtual agent that administers one or more tasks to the user. The user performs the tasks and the performance is captured by a camera. The captured audiovisual data is sent to a server that derives objective metrics which are then applied to a classifying algorithm. If certain metrics meet certain thresholds, the system determines that the user is exhibiting depression symptoms. In embodiments, the system can further determine whether a user has been taking depression medication.

Abstract: A system for administering performance tests to patients remotely has a server that can execute one or more performance tests, presented to the patient via a virtual agent running on the patient's computing device. The performance tests ask the patient to perform a task and then the patient's computing device captures the performance of the task such that the server can analyze the results and determine whether the patient suffers from a condition. The system is capable of adapting based on how a patient performs the tests, whether additional tests are needed or due to technical difficulties.

Abstract: A system and method for remote monitoring of patient motor functions includes a computing device that uses captured image data depicting a patient's body part and, based on movement information, detects whether a condition may exist that is affecting motor functions. The body part can be a hand that is tracked as the user performs a tapping exercise. The body part can also include the patient's face during speech and also without speech.

Abstract: A cloud or other network-based multimodal dialogue system is used to conduct automated screening interviews by engaging with conversational AI over a device of the user's choice (smartphone, tablet, laptop) from the comfort of their home. A screening interview will typically guide a user to blow towards a microphone, use signals from the microphone to calculate amplitudes, and use the amplitudes to calculate a flow rate and a flow volume. Contemplated systems and methods can be deployed in an automatically scalable cloud environment allowing it to serve an arbitrary number of end users at a very small cost per interaction. No special devices unique to the task are needed, which makes the technology accessible to a vast number of users.

Abstract: A virtual agent instructs a responding person to perform specific verbal exercises. Audio and image inputs from the responding person's performance of the exercises are used to identify speech, video, cognitive, and/or respiratory biomarkers, which are then used to evaluate speech motor function and/or neurological health. Contemplated exercises include test aspects of oral motor proficiency, sustained phonation, diadochokinesis, reading speech, spontaneous speech, spirometry, picture description, and emotion elicitation. Metrics from evaluation of the responding person's performance are advantageously produced automatically, and are presented in spreadsheet format.

Abstract: A computer-generated dialog session is customized for a user having a pathology characterized at least in part by a speech pathology. The user's speech is analyzed for spans of speech in which the starts and ends of the spans satisfy predetermined thresholds of time. Customization occurs by altering at least one of the following configurable parameters: (a) a threshold minimum signal strength of speech (dB) to consider as the start of the span of speech; (b) an adjustment factor by which signal strengths of background noise increases between consecutive spans of speech; (c) a threshold between signal strength during the span of speech and signal strength during the span of non-speech; (d) a start speech time threshold; and (e) an end speech time threshold.