Efficient diagnosis of behavioral disorders, developmental delays, and neurological disorders

Abstract

Described herein is software used to evaluate individuals, such as children, for behavioral disorders, developmental delays, and neurological disorders. Specifically, described herein is software configured for use with methods, devices, systems, and platforms used to analyze to aid in the positive or negative diagnosis of an individual for one or more behavioral disorders, developmental delays, and neurological disorders.

Description

[Technical Field]

[0001] cross reference This application claims the benefit of U.S. Provisional Patent Application No. 62 / 908,478, filed September 30, 2019, the entire disclosure of which is incorporated herein by reference. [Background technology]

[0002] Many individuals, including children, suffer from behavioral disorders, developmental delays, and neurological disorders. Examples of these conditions include attention deficit hyperactivity disorder ("ADHD"), autism (including autism spectrum disorders), and speech disorders.

[0003] Healthcare providers typically use traditional observational techniques, such as questionnaires and clinician interviews, to assess behavioral disorders, developmental delays, and neurological disorders. Summary of the Invention

[0004] Described herein are methods, devices, systems, software, and platforms used to evaluate individuals, such as children, for behavioral disorders, developmental delays, and neurological disorders. Specifically, described herein are methods, devices, systems, software, and platforms used to increase the accuracy and efficiency of diagnosing individuals with one or more behavioral disorders, developmental delays, and neurological disorders. Compared to conventional techniques for evaluating individuals for one or more behavioral disorders, developmental delays, and neurological disorders, the methods, devices, systems, software, and platforms described herein evaluate individual-specific input data and reduce the number of interviews to achieve comparable diagnosis accuracy. The inventive methods, devices, systems, software, and platforms described herein are designed, at least in part, to provide treatment for individuals suffering from mental health conditions, including behavioral disorders, developmental delays, and neurological disorders.

[0005] Traditionally, questionnaires and clinician interviews are used to diagnose patients with behavioral disorders, developmental delays, and neurological disorders. Clinician interviews are expensive in terms of time and resources, and multiple interviews are often required. Survey data can be similarly problematic, as the quality of the derived data depends on the subject's attention span and willingness to participate. As a result, survey data can be incomplete or of low quality.

[0006] Traditionally, behavioral disorders, developmental delays, and neurological disorders have been difficult to assess, and the relatedness of these disease types makes them particularly difficult to assess accurately and efficiently. That is, each disease type category (i.e., behavioral disorders, developmental delays, and neurological disorders) contains multiple disease types, and disease types are typically associated within the same disease type category and across different disease type categories, resulting in disease types having one or more overlapping symptoms or other identifiers. That is, certain behavioral disorders, developmental delays, and neurological disorders typically have overlapping symptoms that make them difficult to distinguish. For example, the behavioral disorder ADHD has overlapping symptoms with the developmental disorder of language delay.

[0007] Disorders within each single disease-type category (i.e., behavioral disorders, developmental delays, and neurological disorders) tend to be related such that they have one or more overlapping symptoms or other identifiers. For example, a primary developmental delay, such as autism, overlaps with a secondary developmental delay, such as language delay. As a result, autism can be difficult to differentiate from language delay using conventional techniques, resulting in the possibility of an individual receiving an incorrect diagnosis. Similarly, an individual with both developmental delays (i.e., autism and language delay) may be diagnosed with only one developmental delay but not both, because the presence of one developmental delay may cause the other developmental delay to be overlooked (i.e., an individual diagnosed with autism may have a missed language delay, and vice versa).

[0008] Similarly, disease types within a disease type category tend to be related such that they have one or more overlapping symptoms or other identifiers. For example, ADHD, a type of behavioral disorder, tends to overlap with autism, a type of developmental delay. As a result, ADHD can be difficult to differentiate from autism using conventional techniques, resulting in the possibility of an individual receiving an incorrect diagnosis. Similarly, an individual with both ADHD and autism may be diagnosed with only one but not both, because the presence of one developmental delay may cause the other developmental delay to be overlooked (i.e., an individual diagnosed with ADHD may be overlooked for autism, and vice versa).

[0009] Conventional techniques for assessing individuals with at least one disease type selected from the disease type categories of behavioral disorders, developmental delays, and neurological disorders typically involve repeated assessments of the individual, often involving the collection of multiple types of data, including various test findings. For example, conventional techniques may involve a relatively lengthy set of questions administered to the individual and / or their caregivers. Thus, in addition to inaccuracies due to the association of the assessed disease type (as described above), conventional techniques are typically time-consuming and inefficient.

[0010] Additionally, traditional approaches tend to be inefficient in many ways. For example, traditional instruments for diagnosing behavioral disorders, developmental delays, and neurological disorders typically involve asking many questions over long sessions, but many of the questions asked are often not useful from a diagnostic standpoint. That is, for an illustrative example, in a questionnaire containing 150 items for some patients, only a few items are diagnostic, while other questions are redundant or, in all cases, of minimal utility given the specific answers given to the previous questions.

[0011] In contrast to the prior art, described herein are methods, devices, systems, software, and platforms for accurately and efficiently assessing individuals for at least one disease type selected from the disease type categories of behavioral disorders, developmental delays, and neurological disorders. More specifically, described herein are methods, devices, systems, software, and platforms for reducing the length of observations, sessions, and / or questionnaires by reducing the number of questions (or other prompts) required to make an accurate diagnosis. Further described herein are methods, devices, systems, software, and platforms for increasing the accuracy of diagnosis of multi-symptom individuals and multi-symptom individuals with overlapping symptoms.

[0012] Described herein are computer-implemented methods for assessing an individual, the method including receiving inputs associated with a diagnostic device; generating a model of the individual's likelihood of having each of a plurality of diseases; identifying a next input that, upon receipt, reduces a measure of uncertainty in the model; and receiving a result of the next input. In some embodiments, the input is a specific question. In some embodiments, the input is a specific questionnaire. In some embodiments, the questionnaire is an abbreviated version of a full questionnaire. In some embodiments, the method includes determining a classification of the individual as having one of the plurality of diseases. In some embodiments, the classification is based on a subset of items from the diagnostic device. In some embodiments, the input includes responses provided by the individual's caregiver. In some embodiments, the input includes a video assessment, a video questionnaire, a written questionnaire, an audio recording of a questionnaire, or a non-video questionnaire. In some embodiments, the plurality of diseases includes neurological typical and inconclusive. In some embodiments, the model is generated using a Monte Carlo method. In some embodiments, the model is generated using a machine learning model. In some embodiments, the machine learning model includes a classifier. In some embodiments, the model is generated using at least one question asked to a plurality of individuals with a known positive or negative diagnosis of a behavioral disorder, developmental delay, or neurological disorder. In some embodiments, the model is generated using responses received from individuals with a known positive or negative diagnosis of a behavioral disorder, developmental delay, or neurological disorder. In some embodiments, the method includes determining a classification of the individual with one of the plurality of diseases. In some embodiments, the method includes determining whether the classification should be output or whether additional input is required. In some embodiments, the additional analysis is performed where the uncertainty of the classification is considered relative to the cost of performing the additional analysis. In some embodiments, the method includes determining a penalty score for each of the diseases.In some embodiments, the individual's classification including one of the plurality of diseases is output only if the penalty score is within a penalty gate. In some embodiments, the method includes determining the individual's classification including one of the plurality of diseases and treating the individual based on the classification by providing a drug treatment to the individual. In some embodiments, the method includes determining the individual's classification including one of the plurality of diseases and treating the individual based on the classification by providing a digital therapeutic to the individual. In some embodiments, the plurality of diseases comprises two or more of: Pervasive Developmental Disorder (PDD), Autism Spectrum Disorder (ASD), Social Communication Disorder, Restricted Repetitive Behaviors, Interests, and Activities (RRB), Autism ("Classic Autism"), Asperger's Syndrome ("High-Functioning Autism"), PDD Not Otherwise Specified (PDD-NOS, "Atypical Autism"), Attention Deficit Disorder (ADD), Attention Deficit Hyperactivity Disorder (ADHD), Speech and Language Delay, Obsessive-Compulsive Disorder (OCD), Depression, Schizophrenia, Alzheimer's Disease, Dementia, Intellectual Disability, or Learning Disability. In some embodiments, the plurality of diseases comprises Autism Spectrum Disorder.

[0013] Described herein is a system for assessing an individual, the system including a processor and a non-transitory computer-readable medium including software configured to cause the processor to receive inputs associated with a diagnostic device, generate a model of the individual's likelihood of having each of a plurality of diseases, identify a next input that, upon receipt, reduces the uncertainty of the model, and receive the next input. In some embodiments, the inputs are responses to a questionnaire. In some embodiments, the questionnaire is an abbreviated version of a full questionnaire. In some embodiments, the software further causes the processor to determine a classification of the individual as having one of the plurality of diseases. In some embodiments, the classification is based on a subset of items from the diagnostic device. In some embodiments, the input includes responses provided by the individual's caregiver. In some embodiments, the input includes a video assessment, a video questionnaire, a written questionnaire, an audio recording of a questionnaire, or a non-video questionnaire. In some embodiments, the plurality of diseases includes neurological typical and inconclusive. In some embodiments, the next required input is determined using a Monte Carlo method. In some embodiments, the model is generated using a machine learning model. In some embodiments, the machine learning model includes a classifier. In some embodiments, the model is generated using at least one question asked of a plurality of individuals with a known positive or negative diagnosis of a behavioral disorder, developmental delay, or neurological disorder. In some embodiments, the model is generated using responses received from individuals with a known positive or negative diagnosis of a behavioral disorder, developmental delay, or neurological disorder. In some embodiments, the software further causes the processor to determine a classification of the individual with one of the plurality of disorders. In some embodiments, the software further causes the processor to determine whether the classification should be output or whether additional input is required. In some embodiments, the additional input is required if the uncertainty of the classification is considered relative to the cost of collecting additional input.In some embodiments, the software further causes the processor to determine a penalty score for each of the diseases. In some embodiments, a classification of the individual including one of the plurality of diseases is output only if the penalty score is less than a penalty gate. In some embodiments, the software further causes the processor to determine a classification of the individual including one of the plurality of diseases and treat the individual based on the classification by providing a drug therapy to the individual. In some embodiments, the software further includes causing the processor to determine a classification of the individual including one of the plurality of diseases and treat the individual based on the classification by providing a digital therapeutic to the individual. In some embodiments, the plurality of diseases comprises two or more of: Pervasive Developmental Disorder (PDD), Autism Spectrum Disorder (ASD), Social Communication Disorder, Restricted Repetitive Behaviors, Interests, and Activities (RRB), Autism ("Classic Autism"), Asperger's Syndrome ("High-Functioning Autism"), PDD Not Otherwise Specified (PDD-NOS, "Atypical Autism"), Attention Deficit Disorder (ADD), Attention Deficit Hyperactivity Disorder (ADHD), Speech and Language Delay, Obsessive-Compulsive Disorder (OCD), Depression, Schizophrenia, Alzheimer's Disease, Dementia, Intellectual Disability, or Learning Disability. In some embodiments, the plurality of diseases comprises Autism Spectrum Disorder. [Brief explanation of the drawings]

[0014] The novel features of the present disclosure are set forth with particularity in the appended claims. A better understanding of the features and advantages of the present disclosure will be obtained by reference to the following detailed description that sets forth illustrative embodiments, in which the principles of the disclosure are utilized, and the accompanying drawings.

[0015] [Figure 1] 10 shows exemplary histograms of different exemplary classification predictions. [Figure 2] An exemplary overview of how the advisory module may be utilized in real time to determine the most predictive (or optimal) input to acquire next, given the degree of uncertainty in a particular classification, is provided. [Figure 3] 1 is a diagram illustrating, in matrix form, an analysis of the degree of severity of making a wrong prediction (e.g., due to a relatively high degree of uncertainty). [Figure 4] 10 shows a schematic diagram of an exemplary algorithm executed by the advisory module to determine whether a classification can be output by the software. [Figure 5] Another example overview of the algorithm as implemented by the advisory module is given below: In a first step, the user is screened by being asked a question. [Figure 6] Provides an example overview of a dynamic module that applies advisory modules to capture business logic [Figure 7] 1 illustrates a computing device suitable for use with the software described herein. DETAILED DESCRIPTION OF THE INVENTION

[0016] Described herein is software used to assess individuals, including children, for behavioral disorders, developmental delays, and neurological disorders. In various embodiments, the software described herein is configured to run on one or more computing devices, one or more computing systems, or one or more platforms. In some embodiments, input data is analyzed by the software to determine the next input to provide to the assessed individual to most likely reduce the uncertainty of a positive or negative classification of a particular behavioral disorder, developmental delay, or neurological disorder. In some embodiments, classification assessment is weighed against the risk or cost of making an incorrect classification. In some embodiments, the value of additional analysis in terms of reducing uncertainty is weighed against the cost of additional analysis and / or the impact of an error in classification.

[0017] definition As used herein, the term "diagnostic instrument" refers to a tool used to assess an individual for behavioral disorders, developmental delays, and / or neurological disorders. Non-limiting examples of diagnostic instruments include a set of questions designed to assess an individual, a set of tasks designed to assess an individual, a video or audio recording of the individual used to assess the individual, or a combination thereof.

[0018] As used herein, the term "input" or "input data" means data that is or can be received by the software described herein. Non-limiting examples of input include questions (or other prompts), responses provided by the individual being assessed, responses provided by the individual being assessed's caregiver or healthcare provider, audio recordings, video recordings, or combinations thereof. Input can be actually received by the software described herein or potentially received, such as responses that are sought but not yet provided.

[0019] As used herein, the term "classification" refers to the output of the software described herein. Non-limiting examples of classification include a diagnosis, an indication of the likelihood of a diagnosis, and the likelihood of multiple diagnoses. Generally, a diagnosis is either a disease or a type of disease, or both.

[0020] Unless otherwise defined, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.

[0021] As used herein, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Any reference to "or" is intended to include "and / or" unless otherwise specified.

[0022] Overview Diagnostic instruments used to assess individuals for behavioral disorders, developmental delays, and neurological disorders are generally configured to elicit responses in the assessed individual and / or responses in the individual's caregivers, which responses are intended (among other responses) to aid in the diagnosis or assessment of the individual.

[0023] The diagnostic device may include one or more prompts to elicit a response. Non-limiting examples of prompts include questions asked of the individual, their caregiver, and / or their therapist, images or videos displayed for the individual, their caregiver, and / or their therapist, and audio played for the individual, their caregiver, and / or their therapist. Non-limiting examples of responses include answers and actions.

[0024] Some of the prompts used in traditional methods are not useful or are minimally useful for some individuals. In part, because every individual is different, a prompt designed to elicit a certain response in one individual may be useful in assessing that individual, but not useful (or minimally useful) in assessing a different individual. Thus, there is one prompt or multiple prompts for each individual that elicit the response that is most useful in assessing that individual.

[0025] The innovative software described herein is configured to identify the most useful prompt for a particular individual being assessed. Identifying the most useful prompt provides a technique for assessing individuals with behavioral disorders, developmental delays, or neurological disorders more quickly than traditional methods. The software described herein can accurately classify individuals using fewer prompts than traditional methods require. Because the software described herein can (1) identify the next most useful prompt to provide to an individual (or the most useful response to elicit), and (2) accurately classify individuals using fewer prompts, the innovative software described herein eliminates the need to provide unhelpful or minimally useful prompts to the individual being assessed. This results in time savings, which in itself leads to improved accuracy.

[0026] Accuracy is improved by eliminating, for example, inaccurate responses, errors, or administrator bias due to fatigue or attention loss that traditionally results from time-consuming techniques. In some embodiments, the most useful prompt or prompts are defined as those that lead to the most accurate assessment of an individual. In some embodiments, the most useful prompt or prompts are defined as those that lead to the most accurate and efficient assessment of an individual. In some of these embodiments, efficiency is in terms of time saved to complete the assessment. In some of these embodiments, efficiency is in terms of cost saved to complete the assessment.

[0027] In some embodiments, the uncertainty of the usefulness of a particular prompt or prompts is evaluated, and the one determined to have less uncertainty in their usefulness is selected. In some embodiments, the determination is real-time, and these prompts of the methods, devices, systems, software, and platforms described herein are immediately provided to the user. In some embodiments, the user provides a response to the prompt, and the response is incorporated into the input data. In this manner, additional input data is iteratively acquired and processed until a diagnosis is efficiently reached by reducing time spent, cost, or both.

[0028] It would be beneficial to be able to take a subset of all prompts available in a diagnostic device and determine in real time if responses to the subset of all prompts are sufficient (i.e., less than the full amount of responses) to classify an individual as having a particular condition type based on the responses that are available. That is, it would be beneficial to have software, as described herein, configured to determine whether an individual can be accurately and efficiently classified based on incomplete input data to the software. In some of these embodiments, efficiency is in terms of time saved to complete the assessment. In some of these embodiments, efficiency is in terms of cost saved to complete the assessment.

[0029] Input data In some embodiments, software as described herein receives input data corresponding to characteristics associated with assessing an individual for behavioral disorders, developmental delay, or neurological disorders. The characteristics, in some embodiments, include responses provided by the assessed individual, their caregiver, or their therapist. In some embodiments, the characteristics include observations of the assessed individual, such as observations of video or audio recordings of the individual.

[0030] In some embodiments, the input data includes questions asked of the individual, questions asked of the individual's caregiver about the individual, and questions asked of the individual's clinician about the individual. In some embodiments, some questions are missing or improperly completed. In some embodiments, the input data is incomplete, e.g., includes questions that are not answered or does not otherwise include answers to a complete instrument (e.g., because they were not asked of the individual).

[0031] In some embodiments, the input data is provided by a caregiver of the individual. In some embodiments, the input data is provided by a clinician evaluating the individual. In some embodiments, the input data is provided by the individual.

[0032] In some embodiments, the input data is received by or transferred to a digital computing device.

[0033] In some embodiments, the input data includes a video assessment, a video questionnaire, a written questionnaire, an audio recording of a questionnaire, or a non-video questionnaire.

[0034] Analysis Software Module In some embodiments, the software described herein includes an advisory module and a dynamic module. In some embodiments, the software described herein includes only an advisory module. In some embodiments, the software described herein includes only a dynamic module.

[0035] The advisory module is generally configured to determine the optimal next prompt to provide to the individual being evaluated and to provide an accurate and efficient classification based on incomplete input.

[0036] Typically, the advisory module makes this determination without all information about the individual being evaluated being available. For example, in some embodiments, the advisory module determines the optimal next prompt to provide to the individual based on only a few responses from the individual. For example, the advisory module provides a classification of the individual based on incomplete input.

[0037] The dynamic module is generally configured to apply the advisory module in an efficient manner so that, for example, individuals with the most uncertainty in their assessment and / or individuals who would be most severely affected by an inaccurate classification are subject to additional assessment, while individuals assessed with little or no uncertainty and / or risk are not further assessed. In some embodiments, the dynamic module also performs a cost analysis with respect to reducing the uncertainty in the analysis results, which is weighed against the benefits of doing so.

[0038] In some embodiments, the software modules as described herein include only advisory modules. In some embodiments, the software modules as described herein include only dynamic modules. In some embodiments, the software modules as described herein include both advisory and dynamic modules.

[0039] Advice Module Advisory modules as described herein typically provide predictions based on incomplete input data (i.e., missed inputs). The predictions, in some embodiments, include the most useful inputs available from the individual. The predictions, in some embodiments, include determining the best classification for the individual.

[0040] In some embodiments, the degree of uncertainty regarding an individual's assessment due to incomplete input data is weighed by the advisory module against clinically driven asymmetries of different types of classification errors. In some embodiments, the advisory module is configured to make case-by-case decisions about when the available data result in acceptable prediction uncertainty (when weighed against clinically driven risk assessments of different types of classification errors) and consequently provide an overall efficient prediction system.

[0041] In some embodiments, the advisory module is configured to output a classification for the individual, the classification identifying the individual as likely to have one or more disease types. The disease types may include, for example, autism, autism spectrum disorder, ADHD, and neurotypical. For example, the individual may be classified as having autism spectrum disorder, ADHD, or as neurotypical, or as having both autism and ADHD. In some embodiments, the classification also includes identifying the individual at risk for developing a particular disease type. In some embodiments, the classification also includes identifying an individual for whom the classification is indeterminate.

[0042] The clinically driven asymmetry in classification errors arises, at least in part, from deficiencies in traditional diagnostic methods. There are currently no laboratory or radiological tests that identify behavioral disorders, developmental delays, or neurological disorders. Rather, traditional diagnostic methods tend to be subjective and can be biased by various errors. Additionally, behavioral disorders, developmental delays, or neurological disorders typically have significant overlap in terms of symptomatology, meaning accurate diagnosis is difficult and errors are common. Therefore, behavioral disorders, developmental delays, or neurological disorders typically have some degree of clinical classification error. Therefore, it is quite common for individuals to be misclassified, and in some embodiments, the degree of classification accuracy that the advisory module is configured to achieve is considered within that context. For example, if traditional methods typically achieve 90% accuracy for classifying individuals as having a particular behavioral disorder, the advisory module, in some embodiments, is configured to output a classification of that particular behavioral disorder when it predicts that it has achieved 90% or greater accuracy.

[0043] The advisory module is generally configured to (1) provide a prediction regarding an individual's classification, including situations where the available data for making a decision is incomplete, (2) quantify the specific uncertainty in the classification prediction made, and (3) compare the acceptability of that uncertainty within the context of traditional clinical uncertainty and / or error.

[0044] 1 shows an exemplary histogram of different exemplary classification predictions. As used herein, in FIG. 1, exemplary classifications available in the advisory module are neurotypical, inconclusive, at risk for / has another disorder (other than autism spectrum disorder), and positive for autism spectrum disorder. It should be understood that the four classification types shown are merely exemplary, and other embodiments of the software described herein may generate different, more, or fewer classification types.

[0045] As will be explained, the advisory module is configured to determine a classification likelihood, referred to herein as a classification value, for the individual. As shown in Figure 1, in this example, the advisory module predicts that, based on the data inputted to it, the individual will most likely be classified as at risk for / having another disorder other than autism spectrum disorder.

[0046] The input data used by the advice module typically takes the form of responses to prompts as described herein. Additionally, as described, the advice module is configured to provide classification predictions using incomplete input (such as that shown in the exemplary overview of FIG. 1). A non-limiting example of incomplete data includes responses provided to a subset of prompts from a diagnostic instrument (as opposed to the entire set of responses).

[0047] Typically, data models are configured to produce a single classification (e.g., yes or no); in contrast, the advisory module described herein is configured to determine classification values ​​for multiple different classification types, as shown in FIG. 1 (i.e., neurotypical, inconclusive, at risk for / has another disorder (other than autism spectrum disorder), and autism spectrum disorder).

[0048] In some embodiments, the advisory module uses Monte Carlo methods to make classification predictions. Monte Carlo methods use repeated random sampling to model uncertainty in one or more inputs to make numerical estimates of unknown parameters, resulting in the most likely classification. More specifically, Monte Carlo modeling applied to incomplete data provided to the advisory module is used to estimate the uncertainty associated with one or more inputs and model which inputs reduce the overall uncertainty given the data available to the advisory module. In other words, the Monte Carlo model is used to predict which classification of an individual is most likely to occur if all available data is provided as input. In some embodiments, any other statistical technique suitable for quantifying uncertainty empirically or formulaically can be used instead of Monte Carlo.

[0049] In some embodiments, the advisory module utilizes machine learning based on machine learning and modeling to make predictions using insufficient inputs. In some embodiments, machine learning is used in conjunction with Monte Carlo methods. In some embodiments, machine learning is used to generate a model based on population data including respective responses to diagnostic instruments and classifications of individuals within the population. In some embodiments, the machine learning model is used to generate a classifier. The data used to generate the machine learning model, in some embodiments, includes one or more questions asked to multiple individuals with known positive or negative diagnoses of behavioral disorders, developmental delays, or neurological disorders. One or more types of responses that may be used to build the model may include the most common answers to multiple individuals with known positive or negative diagnoses of behavioral disorders, developmental delays, or neurological disorders.

[0050] As shown in FIG. 1, it should be understood that different types of values ​​are suitable for use in quantifying classification values ​​within multiple classification categories. The classification value attributed to a particular classification type may represent, for example, the likelihood that an individual will be classified within that respective category, or, for example, the degree of uncertainty associated with an individual being classified within that respective classification category. Generally, having a relatively high likelihood of being classified into multiple classification categories is considered more uncertain than having a relatively high likelihood of being classified into two or fewer classification categories. As an illustrative example, individual A may have 80% certainty of being classified as ASD, 15% certainty of being classified as ADHD, and 5% certainty of being classified as neurotypical, while individual B has 45% certainty of being classified as ASD, 35% certainty of being classified as ADHD, and 20% certainty of being classified as neurotypical, which may determine that there is a greater overall certainty about individual A's illness than about individual B's illness.

[0051] In some embodiments, the advice module considers all unprovided prompts (e.g., all unasked questions) from a set of prompts and simulates many possible responses to the remaining unprovided prompts. The advice module then generates a "spread," represented schematically by the histogram in FIG. 1 , where the height of each column represents the estimate of obtaining each possible response. In some embodiments, the model threshold is further used to divide the "spread" into specific taxonomic types (i.e., divide the data into buckets of different types).

[0052] FIG. 2 provides an exemplary overview of how the advisory module is utilized in real time to determine what the next most predictive (or optimal) input is to obtain, given the degree of uncertainty in a particular classification. In these embodiments, the advisory module considers which prompt (in this example, a question) provides the greatest reduction in classification uncertainty. As shown, in FIG. 2 , adding responses from Question A as input to the advisory module leads to a classification histogram in which three classification values ​​for a particular disease are spread across four different classification types, while responses from Question B reduces the overall uncertainty by substantially eliminating classification values ​​for two classification types (i.e., only the current two classification types are considered likely). It should be understood that uncertainty can be reduced in many ways. In this embodiment, the advisory module is configured to be used in real time to suggest that Question B (i.e., the question predicted to reduce the overall uncertainty) be provided to the individual being evaluated. It should be understood that, in general, the advisory module is not limited to analyzing only questions. Any input that can be provided to the advisory module can be analyzed in the same manner to determine which next input will reduce the uncertainty in the classification prediction. Additionally, in some embodiments, the advice module provides suggestions to obtain input from someone other than the individual being assessed to provide the greatest reduction in the uncertainty of the classification prediction. For example, the advice module may suggest that the next input be provided by the caregiver or therapist of the individual being assessed. In general, particular inputs may also be suggested in response to various types of changes in the uncertainty determined by the advice module.

[0053] In some embodiments, obtaining a particular input as the next input is suggested if the classification value changes in one or more classification types. That is, when multiple classification types are considered, each classification category is assigned a value to the individual being evaluated for each input received by the advisory module. In some embodiments, obtaining a particular input as the next input is suggested if the classification value of the inconclusive classification category decreases. In some embodiments, obtaining a particular input as the next input is suggested if the classification value of the neurologically typical classification category or the atypical classification category increases and the classification value of the inconclusive classification category decreases. In some embodiments, obtaining a particular input as the next input is suggested if the classification value of the neurologically typical classification category and the atypical classification category increases and the classification value of the inconclusive classification category decreases. In some embodiments, obtaining a particular input as the next input is suggested if the classification value of the neurologically typical classification category or the atypical classification category maximizes and the classification value of the inconclusive classification category minimizes. In some embodiments, obtaining a particular input as the next input is suggested when the classification values ​​of the typical and atypical classification categories are maximized and the classification values ​​of the inconclusive classification categories are minimized. In some embodiments, obtaining a particular input as the next input is suggested when a threshold is applied to one or more classification types and classification values ​​that exceed the threshold.

[0054] In some embodiments, a model response value correlated with the classification outcome is determined, a measure of the variability of this response is estimated based on potentially unknown input values, and the next input is suggested if it reduces this variability by the greatest amount. In some embodiments, one or more of these techniques are evaluated for multiple diseases being predicted, and a combined value across diseases is intended to suggest the next input.

[0055] The advisory module is configured to determine an acceptable degree of uncertainty given the uncertainty of a typical clinical diagnosis. In some embodiments, a risk analysis is performed as depicted generally in FIG.

[0056] FIG. 3 is a schematic diagram analyzing, in matrix form, the degree of severity of making an incorrect prediction (e.g., due to a relatively high degree of uncertainty). Generally, a false-positive diagnosis, in which an individual with autism spectrum disorder is mistakenly classified as a neurotypical individual, is considered worse than a false-positive classification of an individual with autism spectrum disorder as high-risk or inconclusive for the disorder (autism spectrum disorder). The summary matrix shows the values ​​attributed to the advisory module for certain types of errors. For example, if an individual who truly tests positive for ASD is classified by the algorithm as high-risk, the penalty for that classification according to the matrix in FIG. 3 is 0.5, whereas if the same individual were instead classified by the algorithm as neurotypical, the penalty for that classification would be higher at 1.0.

[0057] The value attributable to a particular error can also be referred to as a penalty score. In some embodiments, the penalty score is expressed as a floating point number between 0 and 1, inclusive. More specifically, in some embodiments, the penalty score is a floating point number measuring the predicted adverse state / risk of issuing a particular classification and is calculated by interpreting a spread through a penalty matrix. In some embodiments, the penalty gate is a float value representing the maximum allowable penalty score. Generally, if the penalty score of a particular classification prediction is less than the penalty gate associated with that classification, the classification is issued. In some embodiments, the penalty gate value is preset by validating the impact of various choices on overall performance against retained validation data.

[0058]

[0023] Figure 4 shows a schematic diagram of an exemplary algorithm executed by the advisory module to determine whether a classification can be output by the software. Figure 4 shows that, as described above, in the first stage, a spread is determined. In the example of Figure 4, as described above, the advisory module determines a classification value for an individual based on one or more inputs within the classification types of autism spectrum disorder, inconclusive, neurotypical, and risk (generated by applying a threshold to the spread). In some embodiments, various inputs are suggested as next-best inputs based on their predicted impact on uncertainty, as described above.

[0059] Next, a penalty score is determined for each classification relative to each of the three other classification types. For example, if there is a true classification value for the classification of autism spectrum disorder, penalty scores are determined for errors where the predicted classification is inconclusive, errors where the predicted classification is neurotypical, and errors where the predicted classification is risk. The penalty score is then compared to a penalty gate. In this example, if the classification value is high and the penalty score is below the penalty limit, a classification of autism spectrum disorder is given. That is, for each classification value, the classification value is considered against the penalty score for the error and the penalty gate. In this embodiment, achieving a high classification value with a relatively low (as defined) risk associated with the error results in a particular classification being output. This results in efficient classification while taking into account the risk of delivering an incorrect classification.

[0060] FIG. 5 shows another example overview of the algorithm as executed by the advisory module. In the first stage, the user is screened by being asked a question. In the next step, a spread is established based on a simulation of many possible ways in which the remaining questions may be answered. In the next step, a threshold is applied along the spread to create many classification types (e.g., autism spectrum disorder, ADHD, neurotypical, etc.). In the next step, a penalty score is applied as described above and compared to the penalty gate. At that point, if the penalty score is less than the penalty gate, a classification is output (as in FIG. 4). If the penalty score is greater than or equal to the penalty gate, the advisory module determines whether there are additional questions to ask; if not, an inconclusive classification is output.

[0061] In some embodiments, more than one classification has a penalty score below the penalty gate. For example, one or more classification types have a penalty score above the penalty gate as determined by a threshold, and one or more classification types do not have a penalty score above the penalty gate. In some of these embodiments, the advisory module makes further decisions to determine which classification to output. Further decisions made by the advisory module to determine which classification to output when more than one classification has a penalty score below the penalty gate may include determining how close the penalty scores for each classification are. Further decisions made by the advisory module to determine which classification to output when more than one classification has a penalty score below the penalty gate may include determining the next question to present to the individual being evaluated, where the question is determined to reduce the uncertainty of one or more classifications. Further decisions made by the advisory module to determine which classification to output when more than one classification has a penalty score below the penalty gate may include determining a cost analysis of obtaining a particular input from the individual being evaluated (or providing a particular prompt to the individual) compared to the expected effect that the input will have on the uncertainty. For example, if obtaining a particular input has a high cost (as measured in terms of monetary cost and / or efficiency cost) and is expected to have only a small impact on uncertainty, in some embodiments, such input is not sought by the advisory module.

[0062] Dynamic Modules FIG. 6 shows an example overview of a dynamic module that applies advisory modules and incorporates business logic. In some embodiments, software as described herein includes a dynamic module that selectively applies advisory modules as described herein. In a first step, the dynamic module applies the advisory module to a diagnostic device containing a query. The output of the advisory module is then analyzed by the dynamic module for the cost of improving the accuracy of the output. If the classification is output as non-neurotypical and the cost analysis indicates that further analysis is warranted, a new diagnostic device is applied, which in this example is a video recording of the individual being evaluated, and the video recording is provided as input to the advisory module. The output of the video recording analysis is combined with the initial output, and a classification is determined based on that result. On the other hand, if the initial advisory module classification result is neurotypical and the cost analysis indicates that additional testing is not cost-effective, given the uncertainty of the classification and the cost of conducting additional analysis, a neurotypical classification is output.

[0063] In some embodiments, the dynamic module is configured to perform the analysis illustrated in the diagram of Figure 3 or to otherwise receive as input the analysis. For example, a penalty score is determined, and based on the determined penalty score, the dynamic module determines whether obtaining additional input is warranted, for example, through additional evaluation of the individual.

[0064] In some embodiments, the penalty score associated with the classification is at least one metric used to evaluate whether a certain degree of uncertainty is acceptable. For example, a very low level of uncertainty for a classification with a relatively high penalty score may be considered unacceptable and may require further analysis of the individual (e.g., through additional testing). However, if a classification is output with a relatively low penalty score and associated uncertainty, the same or similar uncertainty as in the previous example may be considered acceptable.

[0065] Methods for assessing behavioral disorders, developmental delays, or neurological disorders In some embodiments, individuals are assessed by a series of prompts in the form of questions displayed on the screen of a computing device.

[0066] In some embodiments, individuals are assessed by recording video and / or audio data of the individual interacting with other people, performing tasks, and / or answering questions. In some embodiments, individuals are recorded answering questions asked by a human interrogator or caregiver.

[0067] In some embodiments, the questionnaire is completed by the subject, caregiver, or clinician on a mobile or stationary computing device. In some embodiments, the video and / or audio recording is obtained on a mobile device. In some embodiments, the mobile device is a smartphone, tablet, smartwatch, or any device with a mobile camera or recording capabilities. In some embodiments, the video and / or audio recording is taken with a stationary camera and / or microphone. For example, individuals may be questioned in a clinician's office and their responses recorded with a camera on a tripod with an attached microphone.

[0068] The software described herein, in some embodiments, is located on a computing device used to receive input for the software. In some embodiments, the software as described herein is located on a server that is communicatively coupled to a computing device used by the individual being assessed.

[0069] In some embodiments, the methods disclosed herein are used to aid in the diagnosis of behavioral disorders, developmental delays, or neurological disorders.

[0070] Non-limiting examples of illnesses classified as behavioral disorders include attention deficit hyperactivity disorder (ADHD), oppositional defiant disorder (ODD), autism spectrum disorder (ASD), anxiety disorder, depression, bipolar disorder, learning or performance disorder, or conduct disorder. In some embodiments, attention deficit hyperactivity disorder includes predominantly inattentive ADHD, predominantly hyperactive-impulsive ADHD, or combined hyperactive-impulsive and inattentive ADHD. In some embodiments, autism spectrum disorder includes autistic disorder (classic autism), Asperger's syndrome, pervasive developmental disorder (atypical autism), or childhood disintegrative disorder. In some embodiments, anxiety disorders include panic disorder, phobias, social anxiety disorder, obsessive-compulsive disorder, separation anxiety disorder, illness anxiety disorder (hypochondriasis), or post-traumatic stress disorder. In some embodiments, depression includes major depression, persistent depressive disorder, bipolar disorder, seasonal affective disorder, psychotic depression, perinatal (postpartum) depression, premenstrual dysphoric disorder, "adjustment" disorder, or atypical depression. In some embodiments, bipolar disorder includes bipolar I disorder, bipolar II disorder, cyclothymic disorder, or bipolar disorder due to another medical or substance abuse disorder. In some embodiments, learning disorders include dyslexia, dyscalculia, dysgraphia, dyspraxia (sensory integration disorder), language disorder / aphasia, auditory processing disorder, or visual processing disorder. In some embodiments, behavioral disorders are disorders defined in any edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM).

[0071] Non-limiting examples of conditions classified as developmental delay include autism spectrum disorder, mental retardation, cerebral palsy, Down syndrome, failure to thrive, muscular dystrophy, hydrocephalus, developmental coordination disorder, cystic fibrosis, fetal alcohol syndrome, homocystinuria, tuberous sclerosis, abetalipoproteinemia, phenylketonuria, Arthritis syndrome, speech delay, gross motor delay, fine motor delay, social delay, emotional delay, behavioral delay, or cognitive delay. In some embodiments, mental retardation includes adrenoleukodystrophy, Ito syndrome, acroostosis imperfecta, Huntington's disease, Arskog syndrome, Aicardi syndrome, or Tay-Sachs disease. In some embodiments, cerebral palsy includes spastic cerebral palsy, dyskinetic cerebral palsy, hypotonic cerebral palsy, ataxic cerebral palsy, or mixed cerebral palsy. In some embodiments, the autism spectrum disorder comprises autistic disorder (classic autism), Asperger's syndrome, pervasive developmental disorder (atypical autism), or childhood disintegrative disorder. In some embodiments, the Down syndrome comprises trisomy 21, mosaicism, or a translocation. In some embodiments, the muscular dystrophy comprises Duchenne muscular dystrophy, Becker muscular dystrophy, congenital muscular dystrophy, myotonic dystrophy, facioscapulohumeral muscular dystrophy, oculopharyngeal muscular dystrophy, distal muscular dystrophy, or Emery-Dreifuss muscular dystrophy.

[0072] Non-limiting examples of diseases classified as neurological disorders include amyotrophic lateral sclerosis, arteriovenous malformation, cerebral aneurysm, brain tumor, dural arteriovenous fistula, epilepsy, headache, memory loss, multiple sclerosis, Parkinson's disease, peripheral neuropathy, postherpetic neuralgia, spinal cord tumor, stroke, Alzheimer's disease, corticobasal degeneration, Creutzfeldt-Jakob disease, frontotemporal dementia, Lewy body disease, mild cognitive impairment, progressive supranuclear palsy, or vascular dementia.

[0073] In some embodiments, the methods described herein are used in conjunction with known techniques for diagnosing behavioral disorders, developmental delays, or neurological disorders. In some embodiments, the methods described herein increase the accuracy of known methods of diagnosis or reduce the time or resources required for an accurate diagnosis.

[0074] Machine Learning Software Module As noted above, in some embodiments of the methods, devices, systems, software, and platforms described herein, a machine learning software module is utilized to identify questions and responses associated with the particular disease present in the individual being evaluated. In some embodiments, the machine learning algorithm utilizes input data and models the input data to determine questions most likely to reduce diagnostic uncertainty. The machine learning software module, in some embodiments, includes a machine learning model (or data model). It should be understood that machine learning encompasses numerous constructs and arrangements of data, and that the teachings herein are not limited to any single type of machine learning.

[0075] The machine learning software modules described herein are generally trained using a database of questionnaires from individuals with known positive or negative diagnoses of one or more behavioral disorders, developmental delays, or neurological disorders.

[0076] In some embodiments, the trained machine learning software module analyzes input data not previously associated with a particular behavioral disorder, developmental delay, or neurological disorder. In some embodiments, the machine learning algorithm generates recommended predictive input data, which is then acquired by asking recommended questions to an individual via the use of a digital questionnaire. A user (e.g., a clinician, caregiver, or subject) provides additional input data in response to the questions, and the machine learning algorithm analyzes the collected additional input data and provides a diagnostic probability that one or more behavioral disorders, developmental delays, or neurological disorders are present in the individual. The machine learning algorithm generates the recommended predictive input data and acquires additional input data via user responses until the estimated benefit of the uncertainty of acquiring the additional input data is less than the cost of acquiring the additional input data.

[0077] In some embodiments, the machine learning software module is a supervised learning algorithm, hi some embodiments, the machine learning software module is selected from nearest neighbor, naive Bayes, decision tree, linear regression, support vector machine, or neural network.

[0078] In some embodiments, the machine learning software module provides a diagnostic probability without considering contextual indicators. In some embodiments, the machine learning software module provides a diagnostic probability solely by analyzing questionnaire data. In some embodiments, the machine learning software module provides a diagnostic probability by analyzing contextual indicators provided by a clinician, caregiver, or subject. For example, a user provides questionnaire data and contextual data (e.g., a 5-year-old boy) of an individual responding to questions designed to assess for autism. In one embodiment, the machine learning software module analyzes the questionnaire data, including user-entered data related to contextual indicators such as the child's age, gender, and suspected diagnosis. In another embodiment, the machine learning software module analyzes the questionnaire data without the contextual indicators illustrated above.

[0079] Systems and Equipment The present disclosure provides a computerized device programmed to implement the methods of the present disclosure. Figure 7 shows a computerized device (701) suitable for use with the software described herein. The computerized device (701) can process various aspects of the information of the present disclosure, such as questions and answers, reactions, statistical analysis, etc. The computerized device (701) can be a user's electronic device or a computerized device located remotely relative to the electronic device. The electronic device can also be a mobile electronic device.

[0080] The computing device (701) includes a central processing unit (CPU, also referred to herein as "processor" and "computer processor") (705), which may be a single-core or multi-core processor, or multiple processors for parallel processing. The computing device (701) also includes memory or memory locations (710) (e.g., random access memory, read-only memory, flash memory), electronic storage (715) (e.g., hard disk), communication interfaces (720) (e.g., network adapters) for communicating with one or more other devices, and peripheral devices (725), such as cache, other memory, data storage devices, and / or electronic display adapters. The memory (710), storage unit (715), interface (720), and peripheral devices (725) are in communication with the CPU (705) through a communication bus (solid lines), such as a motherboard. The storage unit (715) may be a data storage unit (or data repository) for storing data. The computing device (701) can be operatively coupled to a computer network ("network") (730) with the aid of a communication interface (720). The network (730) can be the Internet, an Internet and / or extranet, an intranet and / or extranet in communication with the Internet. In some cases, the network (730) is a telecommunications and / or data network. The network (730) can include one or more computer servers, which can enable distributed computing, such as cloud computing. The network (730), in some cases, with the aid of the computing device (701), can implement a peer-to-peer network, which can enable devices coupled to the computing device (701) to act as clients or servers.

[0081] The CPU (705) can execute a series of machine-readable instructions, which may be embodied in a program or software. The instructions may be stored in a memory location, such as the memory (710). The instructions may be directed to the CPU (705), which can then program or configure the CPU (705) to implement the methods of the present disclosure. Examples of operations performed by the CPU (705) may include fetch, decode, execute, and writeback.

[0082] The CPU 705 may be part of a circuit, such as an integrated circuit. One or more other components of the device 701 may be included in the circuit. In some cases, the circuit is an application-specific integrated circuit (ASIC).

[0083] The storage unit (715) can store files such as drivers, libraries, and saved programs. The storage unit (715) can store user data, such as user preferences and user programs. The computing device (701) can optionally include one or more additional data storage units external to the computing device (701), such as located on a remote server in communication with the computing device (701) over an intranet or the Internet.

[0084] The computing device (701) can communicate with one or more remote computing devices through the network (730). For example, the computing device (701) can communicate with a remote computing device of a user (e.g., a mother). Examples of remote computing devices and mobile communication devices include a personal computer (e.g., a portable PC), a slate or tablet PC (e.g., an Apple® iPad, a Samsung® Galaxy Tab), a telephone, a smartphone (e.g., an Apple® iPhone, an Android-enabled device, a Blackberry®), or a personal digital assistant. A user can access the computing device (701) through the network (730).

[0085] Methods as described herein can be implemented by machine (e.g., computer processor) executable code stored in electronic storage locations of the computing device (701), such as, for example, on memory (710) or electronic storage unit (715). The machine-executable or machine-readable code can be provided in the form of software. During use, the code can be executed by the processor (705). In some cases, the code can be retrieved from the storage unit (715) and stored in memory (710) for immediate access by the processor (705). In some situations, the electronic storage unit (715) can be eliminated, and the machine-executable instructions are stored in memory (710).

[0086] The code may be pre-compiled and configured for use with a machine having a suitable processor to execute the code, or it may be compiled at run time. The code may be provided in a programming language that can be selected to render the code executable in a pre-compiled or as-compiled fashion.

[0087] Aspects of the apparatus and methods provided herein, such as the computing device (701), can be integrated into programming. Various aspects of the technology may be considered as "products" or "articles of manufacture," typically in the form of machine- (or processor-) executable code and / or associated data carried on or embedded in a type of machine-readable medium. The machine-executable code may be stored in an electronic storage unit, such as memory (e.g., read-only memory, random-access memory, flash memory) or a hard disk. "Storage" type media may include any or all of the tangible memory of a computer or processor, or its associated modules, such as various semiconductor memories, tape drives, disk drives, etc., which may provide non-transitory recording media at any time for programming the software. All or portions of the software are sometimes communicated via the Internet or various other telecommunications networks. Such communication may enable, for example, loading of the software from one computer or processor to another, e.g., from a management server or host computer to an application server computer platform. Thus, other types of media that may bear software elements include light waves, radio waves, and electromagnetic waves, such as those used across physical interfaces between local devices, through wired and optical landline networks, and on various air-links. Physical elements that carry such waves, such as wired or wireless links, optical links, etc., may also be considered software-bearing media. As used herein, unless limited to non-transitory, tangible "storage" media, terms such as computer or machine "readable medium" refer to media that participate in providing instructions to a processor for execution.

[0088] Thus, a machine-readable medium such as a computer-executable code may take many forms, including, but not limited to, a tangible storage medium, a carrier wave medium, or a physical transmission medium. Non-volatile storage media include, for example, optical or magnetic disks, any of the storage devices in a computer, such as those that may be used to implement the databases shown in the figures. Volatile storage media include dynamic memory, such as the main memory of such a computer platform. Tangible transmission media include coaxial cables, copper wire and fiber optics, including the wires that comprise a bus within a computing device. Carrier wave transmission media may take the form of electric or electromagnetic signals, or acoustic or light waves, such as those generated during radio frequency (RF) and infrared (IR) data communications. Thus, common forms of computer-readable media include, for example, floppy disks, flexible disks, hard disks, magnetic tape, other magnetic media, CD-ROMs, DVDs or DVD-ROMs, other optical media, punch cards, paper tape, other physical storage media with patterns of holes, RAM, ROM, PROMs and EPROMs, FLASH-EPROMs, other memory chips or cartridges, carrier waves carrying data or instructions, cables or links which transmit such carrier waves, or other media from which a computer can read programming code and / or data. Many of these forms of computer-readable media may be involved in carrying one or more sequences of one or more instructions to a processor for execution.

[0089] The computing device (701) may include or be in communication with an electronic display (735) that includes a user interface (UI) for providing, for example, questions and answers, analysis results, and recommendations. Examples of UIs include, but are not limited to, graphical user interfaces (GUIs) and web-based user interfaces.

[0090] The disclosed methods and apparatus may be implemented as one or more algorithms and using instructions provided to one or more processors as disclosed herein. The algorithms may be implemented by software after execution by a central processing unit (705). The algorithms may be, for example, random forests, graphical models, support vector machines, or others.

[0091] While the above steps illustrate the method of the device according to the example, one skilled in the art will recognize many variations based on the teachings described herein. Steps may be completed in a different order. Steps may be added or removed. Some of the steps may include sub-steps. Many steps may be repeated as many times as is beneficial to the platform.

[0092] Each of the examples as described herein may be combined with one or more other examples. Additionally, one or more components of one or more examples may be combined with other examples.

[0093] Combination with drug treatment In some embodiments, after an individual is evaluated using the software described herein, one or more medications are provided to the individual based on the individual's classification generated by the software.

[0094] The classification may include autism or autism spectrum disorder, and the drug may be selected from the group consisting of risperidone, quetiapine, amphetamine, dextroamphetamine, methylphenidate, methamphetamine, dextroamphetamine, dexmethylphenidate, guanfacine, atomoxetine, lisdexamfetamine, clonidine, aripiprazolecomprise, vasopressin, and oxytocin.

[0095] The classification may include attention deficit disorder (ADD) and the drug may be selected from the group consisting of amphetamine, dextroamphetamine, methylphenidate, methamphetamine, dextroamphetamine, dexmethylphenidate, guanfacine, atomoxetine, lisdexamfetamine, clonidine, and modafinil.

[0096] The classification may include obsessive-compulsive disorder and the drug may be selected from the group consisting of buspirone, sertraline, escitalopram, citalopram, fluoxetine, paroxetine, venlafaxine, clomipramine, and fluvoxamine.

[0097] The classification may include acute stress disorder and the medication may be selected from the group consisting of propranolol, citalopram, escitalopram, sertraline, paroxetine, fluoxetine, venlafaxine, mirtazapine, nefazodone, carbamazepine, divalproex, lamotrigine, topiramate, prazosin, phenelzine, imipramine, diazepam, clonazepam, lorazepam, and alprazolam, or the behavioral disorder, developmental delay, or neurological disorder may include adjustment disorder and the medication may be selected from the group consisting of buspirone, escitalopram, sertraline, paroxetine, fluoxetine, diazepam, clonazepam, lorazepam, and alprazolam.

[0098] The classification may include agoraphobia and the drug may be selected from the group consisting of diazepam, clonazepam, lorazepam, alprazolam, citalopram, escitalopram, sertraline, paroxetine, fluoextine, and buspirone.

[0099] The classification may include Alzheimer's disease and the drug may be selected from the group consisting of donepezil, galantamine, memantine, and rivastigmine, or the behavioral disorder, developmental delay, or neurological disorder may include anorexia nervosa and the drug may be selected from the group consisting of olanzapine, citalopram, escitalopram, sertraline, paroxetine, and fluoxetine.

[0100] The classification may include anxiety disorders and the medication may be selected from the group consisting of sertraline, escitalopram, citalopram, fluoxetine, diazepam, buspirone, venlafaxine, duloxetine, imipramine, desipramine, clomipramine, lorazepam, clonazepam, and pregabalin, or the behavioral disorder, developmental delay, or neurological disorder may include bereavement and the medication may be selected from the group consisting of citalopram, duloxetine, and doxepin.

[0101] The classification may include binge eating disorder and the drug may be selected from the group consisting of lisdexamfetamine.

[0102] The classification may include bipolar disorder and the drug may be selected from the group consisting of topiramate, lamotrigine, oxcarbazepine, haloperidol, risperidone, quetiapine, olanzapine, aripiprazole, and fluoxetine.

[0103] The classification may include body dysmorphic disorder and the drug may be selected from the group consisting of sertraline, escitalopram, and citalopram.

[0104] The classification may include brief psychotic disorder and the drug may be selected from the group consisting of clozapine, asenapine, olanzapine, and quetiapine.

[0105] The classification may include bulimia nervosa and the drug may be selected from the group consisting of sertraline and fluoxetine.

[0106] The classification may include conduct disorder and the drug may be selected from the group consisting of lorazepam, diazepam, and clobazam.

[0107] The classification may include delusional disorder and the drug may be selected from the group consisting of clozapine, asenapine, risperidone, venlafaxine, bupropion, and buspirone.

[0108] The classification may include depersonalization disorder and the drug may be selected from the group consisting of sertraline, fluoxetine, alprazolam, diazepam, and citalopram.

[0109] The classification may include depression and the drug may be selected from the group consisting of sertraline, fluoxetine, citalopram, bupropion, escitalopram, venlafaxine, aripiprazole, buspirone, vortioxetine, and vilazodone.

[0110] The classification can include severe mood dysregulation disorder and the drug can be selected from the group consisting of quetiapine, clozapine, asenapine, and pimavanserin.

[0111] The classification may include dissociative amnesia and the drug may be selected from the group consisting of alprazolam, diazepam, lorazepam, and chlordiazepoxide.

[0112] The classification may include dissociative disorders and the drug may be selected from the group consisting of bupropion, vortioxetine, and vilazodone.

[0113] The classification may include dissociative fugue and the drug may be selected from the group consisting of amobarbital, aprobarbital, butabarbital and methohexitlal.

[0114] The class may be selected from the group consisting of bupropion, venlafaxine, sertraline, and citalopram.

[0115] The classification may include eating disorders and the drug may be selected from the group consisting of olanzapine, citalopram, escitalopram, sertraline, paroxetine, and fluoxetine.

[0116] The class may be selected from the group consisting of estrogen, prostogen, and testosterone.

[0117] The classification may include generalized anxiety disorder and the drug may be selected from the group consisting of venlafaxine, duloxetine, buspirone, sertraline, and fluoxetine.

[0118] The category may include hoarding disorder and the drug may be selected from the group consisting of buspirone, sertraline, escitalopram, citalopram, fluoxetine, paroxetine, venlafaxine, and clomipramine.

[0119] The classification can include intermittent explosive disorder and the drug can be selected from the group consisting of asenapine, clozapine, olanzapine, and pimavanserin.

[0120] The classification may include kleptomania and the drug may be selected from the group consisting of escitalopram, fluvoxamine, fluoxetine, and paroxetine.

[0121] The classification may include panic disorder and the drug may be selected from the group consisting of bupropion, vilazodone, and vortioxetine.

[0122] The classification may include Parkinson's disease and the drug may be selected from the group consisting of rivastigmine, selegiline, rasagiline, bromocriptine, amantadine, cabergoline, and benztropine.

[0123] The classification may include gambling addiction and the drug may be selected from the group consisting of bupropion, vilazodone, and vortioxetine.

[0124] The classification may include postpartum depression and the drug may be selected from the group consisting of sertraline, fluoxetine, citalopram, bupropion, escitalopram, venlafaxine, aripiprazole, buspirone, vortioxetine, and vilazodone.

[0125] The classification may include post-traumatic stress disorder and the drug may be selected from the group consisting of sertraline, fluoxetine, and paroxetine.

[0126] The classification may include premenstrual dysphoric disorder and the drug may be selected from the group consisting of estradiol, drospirenone, sertraline, citalopram, fluoxetine, and buspirone.

[0127] The classification may include affective dysregulation disorders and the drug may be selected from the group consisting of dextromethorphan hydrobromide and quinidine sulfate.

[0128] The classification may include pyromania, and the drug may be selected from the group consisting of clozapine, asenapine, olanzapine, paliperidone, and quetiapine.

[0129] The classification may include schizoaffective disorder and the drug may be selected from the group consisting of sertraline, carbamazepine, oxcarbazepine, valproate, haloperidol, olanzapine, and loxapine.

[0130] The classification may include schizophrenia and the drug may be selected from the group consisting of chlopromazine, haloperidol, fluphenazine, risperidone, quetiapine, ziprasidone, olanzapine, perphenazine, aripiprazole, and prochlorperazine.

[0131] The classification may include schizophreniform disorder and the drug may be selected from the group consisting of paliperidone, clozapine, and risperidone.

[0132] The classification may include seasonal affective disorder and the drug may be selected from the group consisting of sertraline and fluoxetine.

[0133] The classification can include shared psychotic disorders and the drug can be selected from the group consisting of clozapine, pimavanserin, risperidone, and lurasidone.

[0134] The classification may include social anxiety phobia and the drug may be selected from the group consisting of amitriptyline, bupropion, citalopram, fluoxetine, sertraline, and venlafaxine.

[0135] The classification may include specific phobias and the drug may be selected from the group consisting of diazepam, estazolam, quazepam, and alprazolam.

[0136] The classification may include stereotypic movement disorder and the drug may be selected from the group consisting of risperidone and clozapine.

[0137] The classification may include Tourette's syndrome and the drug may be selected from the group consisting of haloperidol, fluphenazine, risperidone, ziprasidone, pimozide, perphenazine, and aripiprazole.

[0138] The classification may include transient tic disorders and the drug may be selected from the group consisting of guanfacine, clonidine, pimozide, risperidone, citalopram, escitalopram, sertraline, paroxetine, and fluoxetine.

[0139] The classification may include trichotillomania, and the drug may be selected from the group consisting of sertraline, fluoxetine, paroxetine, desipramine, and clomipramine.

[0140] Combination with drug treatment In some embodiments, after assessing an individual using the software described herein, one or more digital therapeutics are provided to the individual based on the individual's classification generated by the software. Digital therapeutics can include single or multiple therapeutic activities or interventions that can be performed by the patient or caregiver. Digital therapeutics can include predefined interactions with third-party devices, such as sensors, computers, medical devices, and therapy delivery systems. Digital therapeutics can support FDA-cleared medical claims, a range of diagnostic codes, or a single diagnostic code. Digital therapeutics can include instructions, feedback, activities, or interactions provided to the subject or caregiver. In some embodiments, digital therapeutics include an individual's therapeutic treatment plan. The individual's therapeutic treatment plan can include a schedule for the frequency, amount / quantity, or duration of the digital therapy. As an illustrative example, an individual's therapeutic treatment plan for a digital therapeutic may specify receiving a digital therapy (e.g., implemented via a software module providing speech / language activities) once per day (frequency), for at least a minimum duration, such as 20 minutes (quantity or amount), for a duration, such as three months (duration).

[0141] The systems, software, and methods disclosed herein can include a software module configured to generate an individualized therapeutic treatment plan. The software module can be configured to determine the optimal frequency, amount, and / or duration of digital therapy for the individualized therapeutic treatment plan. The treatment plan can be generated, at least in part, using a machine learning model or classifier trained on training data to predict the effectiveness of a therapeutic outcome. Multiple potential treatment plans can be evaluated to determine the optimal treatment plan for a particular individual based on relevant features (e.g., diagnostic features used to identify or diagnose one or more disorders, such as autism / ASD).

[0142] The systems and methods described herein provide digital diagnostics and digital therapeutics to patients. Digital personalized medicine systems can use digital data to assess or diagnose patient conditions in ways that inform personalized or more appropriate therapeutic interventions and improved diagnoses.

[0143] In one aspect, a digital personalized medicine system can include a digital device having a processor and associated software that can be configured to capture interaction and feedback data and to perform data analysis that identifies relative levels of efficacy, compliance, and response as a result of a therapeutic intervention. Such data analysis can include, for example, artificial intelligence, including machine learning, and / or statistical models that evaluate user data and user profiles to further personalize, improve, or evaluate the effectiveness of the therapeutic intervention.

[0144] In some examples, the system can be configured to use digital diagnostics and digital therapeutics. Digital diagnostics and digital therapeutics can include systems or methods for digitally collecting information and processing and evaluating the provided data to improve an individual's medical, psychological, or physiological condition. Digital therapeutic systems apply software-based learning to evaluate user data and monitor and improve diagnostics and therapeutic interventions provided by the system.

[0145] Additionally, the systems and methods described herein can provide digital diagnostics and digital therapeutics to patients. Digital personalized medicine systems can use digital data to assess or diagnose patient conditions in ways that inform personalized or more appropriate therapeutic interventions and improved diagnoses.

[0146] In one aspect, a digital personalized medicine system can include a digital device having a processor and associated software that can be configured to use the data to evaluate and diagnose patients, capture interaction and feedback data that identifies relative levels of efficacy, compliance, and response as a result of a therapeutic intervention, and perform data analysis. Such data analysis can include, for example, artificial intelligence, including machine learning, and / or statistical models that evaluate user data and user profiles to further personalize, improve, or evaluate the effectiveness of the therapeutic intervention.

[0147] In some examples, the system can be configured to use digital diagnostics and digital therapeutics. Digital diagnostics and digital therapeutics can include systems or methods for digitally collecting information and processing and evaluating the provided data to improve an individual's medical, psychological, or physiological condition. Digital therapeutic systems apply software-based learning to evaluate user data and monitor and improve diagnostics and therapeutic interventions provided by the system.

[0148] Additionally, the digital personalized medicine systems and methods described herein can provide digital diagnoses and digital therapeutics to patients. Digital personalized medicine systems can use digital data to assess or diagnose patient conditions in a manner that informs personalized or more appropriate therapeutic interventions and improved diagnoses.

[0149] In one aspect, a digital personalized medicine system can include a digital device having a processor and associated software that can be configured to use the data to evaluate and diagnose patients, capture interaction and feedback data that identifies relative levels of efficacy, compliance, and response as a result of a therapeutic intervention, and perform data analysis. Such data analysis can include, for example, artificial intelligence, including machine learning, and / or statistical models that evaluate user data and user profiles to further personalize, improve, or evaluate the effectiveness of the therapeutic intervention.

[0150] In some examples, the system can be configured to use digital diagnostics and digital therapeutics. Digital diagnostics and digital therapeutics can include systems or methods for digitally collecting information and processing and evaluating the provided data to improve an individual's medical, psychological, or physiological condition. Digital therapeutic systems apply software-based learning to evaluate user data and monitor and improve diagnostics and therapeutic interventions provided by the system.

[0151] Apparatus and system for assessing behavioral disorders, developmental delays, or neurological disorders In some embodiments, assessment of an individual using the software described herein utilizes a mobile or stationary computing device. In some embodiments, the mobile device is a smartphone, tablet, or laptop computer. In some embodiments, a mobile application on the mobile or stationary device is used to display the questions used in the assessment and provide an interface for responding to the displayed questions.

[0152] In some embodiments, the systems and devices disclosed herein include a recording device. In some embodiments, the video and / or audio recording is taken on a mobile device. In some embodiments, the mobile device is a smartphone, tablet, smartwatch, or any device with mobile camera or recording capabilities. In some embodiments, the video and / or audio recording is taken using a stationary camera and / or microphone.

[0153] Digital Processing Unit In some embodiments, software as described herein is located in a digital processing device and / or configured to cause a processor of the digital processing device to perform certain tasks. In further embodiments, the digital processing device includes one or more hardware central processing units (CPUs) or general-purpose graphics processing units (GPGPUs) that perform the device's functions. In still further embodiments, the digital processing device further includes an operating system configured to execute the executable instructions. In some embodiments, the digital processing device is optionally connected to a computer network. In further embodiments, the digital processing device is optionally connected to the Internet to access the World Wide Web. In still further embodiments, the digital processing device is optionally connected to a cloud computing infrastructure. In other embodiments, the digital processing device is optionally connected to an intranet. In other embodiments, the digital processing device is optionally connected to a data storage device.

[0154] In accordance with the description herein, suitable digital processing devices include, by way of non-limiting example, server computers, desktop computers, laptop computers, notebook computers, subnotebook computers, netbook computers, netpad computers, set-top computers, media streaming devices, handheld computers, internet appliances, mobile smartphones, tablet computers, personal digital assistants, video game consoles, and vehicles. Those skilled in the art will recognize that many smartphones are suitable for use with the systems described herein. Those skilled in the art will recognize that selected televisions, video players, and digital music players with optional computer network connectivity are suitable for use with the systems described herein. Suitable tablet computers include those with booklet, slate, and convertible configurations known to those skilled in the art.

[0155] In some embodiments, the digital processing device includes an operating system configured to execute executable instructions. An operating system is software, including programs and data, that controls the device's hardware and provides services for the execution of applications, for example. Those skilled in the art will recognize that suitable server operating systems include, by way of non-limiting example, FreeBSD, OpenBSD, NetBSD®, Linux, Apple® Mac OS X Server®, Oracle® Solaris®, Windows Server®, and Novell® NetWare®. Those skilled in the art will recognize that suitable personal computer operating systems include, by way of non-limiting example, Microsoft® Windows®, Apple® Mac OS X®, UNIX®, and UNIX-like operating systems such as GNU / Linux®. In some embodiments, the operating system is provided by cloud computing. Those skilled in the art will also recognize that suitable mobile smartphone operating systems include, by way of non-limiting example, Nokia® Symbian® OS, Apple® iOS®, Research In Motion® BlackBerry® OS®, Google® Android®, Microsoft® Windows Phone® OS, Microsoft® Windows Mobile® OS, Linux®, and Palm® WebOS®.Those skilled in the art will also recognize that suitable media streaming device operating systems include, by way of non-limiting example, Apple TV®, Roku®, Boxee®, Google TV®, Google Chromecast®, Amazon Fire®, and Samsung® HomeSync®. Those skilled in the art will also recognize that suitable video game console operating systems include, by way of non-limiting example, Sony® PS3®, Sony® PS4®, Microsoft® Xbox 360®, Microsoft Xbox One, Nintendo® Wii®, Nintendo® Wii U®, and Ouya®.

[0156] In some embodiments, the device includes a storage device and / or memory device. A storage device and / or memory device is one or more physical devices used to temporarily or permanently store data or programs. In some embodiments, the device is volatile memory, requiring power to maintain stored information. In some embodiments, the device is nonvolatile memory, retaining stored information when power is not applied to the digital processing device. In further embodiments, the nonvolatile memory includes flash memory. In some embodiments, the nonvolatile memory includes dynamic random access memory (DRAM). In some embodiments, the nonvolatile memory includes ferroelectric random access memory (FRAM). In some embodiments, the nonvolatile memory includes phase change random access memory (PRAM). In other embodiments, the device is a storage device, including, by way of non-limiting examples, CD-ROMs, DVDs, flash memory devices, magnetic disk drives, magnetic tape drives, optical disk drives, and cloud computing-based storage devices. In further embodiments, the storage device and / or memory device is a combination of devices such as those disclosed herein.

[0157] In some embodiments, the digital processing device includes a display for conveying visual information to a user. In some embodiments, the display is a liquid crystal display (LCD). In further embodiments, the display is a thin film transistor liquid crystal display (TFT-LCD). In some embodiments, the display is an organic light emitting diode (OLED) display. In various further embodiments, the OLED display is a passive-matrix OLED (PMOLED) or active-matrix OLED (AMOLED) display. In some embodiments, the display is a plasma display. In other embodiments, the display is a video projector. In still other embodiments, the display is a head-mounted display in communication with the digital processing device, such as a VR headset. In further embodiments, suitable VR headsets include, by way of non-limiting example, HTC Vive, Oculus Rift, Samsung Gear VR, Microsoft HoloLens, Razer OSVR, FOVE VR, Zeiss VR One, Avegant Glyph, Freefly VR headsets, and the like. In still further embodiments, the display is a combination of devices, such as those disclosed herein.

[0158] In some embodiments, the digital processing device includes an input device for receiving information from a user. In some embodiments, the input device is a keyboard. In some embodiments, the input device is a pointing device, including, by way of non-limiting example, a mouse, trackball, trackpad, joystick, game controller, or stylus. In some embodiments, the input device is a touchscreen or multi-touchscreen. In other embodiments, the input device is a microphone for capturing voice or other sound input. In other embodiments, the input device is a video camera or other sensor for capturing motion or visual input. In further embodiments, the input device is a Kinect, Leap Motion, or the like. In still further embodiments, the input device is a combination of devices, such as those disclosed herein.

[0159] Non-transitory computer-readable storage medium In some embodiments, the computing device used with the software described herein further includes one or more non-transitory computer-readable storage media encoded with a program including instructions executable by an operating system of an optionally networked digital processing device. In further embodiments, the computer-readable storage medium is a tangible component of the digital processing device. In still further embodiments, the computer-readable storage medium is optionally removable from the digital processing device. In some embodiments, computer-readable storage media include, by way of non-limiting example, CD-ROMs, DVDs, flash memory devices, solid-state storage devices, magnetic disk drives, magnetic tape drives, optical disk drives, cloud computing systems and services, and the like. In some cases, the program and instructions are encoded on the medium permanently, substantially permanently, semi-permanently, or non-transitoryly.

[0160] computer program In some embodiments, software as described herein comprises a sequence of instructions executable by a processor, such as a CPU of a digital processing device, written to perform specified tasks. The computer-readable instructions may be implemented as program modules, such as functions, objects, application programming interfaces (APIs), data structures, etc., that perform particular tasks or implement particular abstract data types. In light of the disclosure provided herein, those skilled in the art will recognize that computer programs may be written in a variety of languages ​​and versions.

[0161] The functionality of the computer-readable instructions may be combined or distributed as desired in various environments. In some embodiments, a computer program includes one sequence of instructions. In some embodiments, a computer program includes multiple sequences of instructions. In some embodiments, a computer program is provided from one location. In other embodiments, a computer program is provided from multiple locations. In various embodiments, a computer program includes one or more software modules. In various embodiments, a computer program, in part or in whole, includes one or more web applications, one or more mobile applications, one or more standalone applications, one or more web browser plug-ins, extensions, add-ins, or add-ons, or any combination thereof.

[0162] Web Applications In some embodiments, the software described herein includes a web application. In light of the disclosure provided herein, those skilled in the art will recognize that web applications, in various embodiments, utilize one or more software frameworks and one or more database systems. In some embodiments, the web application is created on a software framework such as Microsoft® .NET or Ruby on Rails (RoR). In some embodiments, the web application utilizes one or more database systems, including, by way of non-limiting example, relational, non-relational, object-oriented, associative, and XML database systems. In further embodiments, suitable relational database systems include, by way of non-limiting example, Microsoft® SQL Server, mySQL™, and Oracle®. Those skilled in the art will also recognize that web applications, in various embodiments, are written in one or more versions of one or more languages. Web applications may be written in one or more markup languages, presentation definition languages, client-side scripting languages, server-side coding languages, database query languages, or combinations thereof. In some embodiments, a web application is written in part in a markup language such as Hypertext Markup Language (HTML), Extensible Hypertext Markup Language (XHTML), or Extensible Markup Language (XML). In some embodiments, a web application is written in part in a presentation definition language such as Cascading Style Sheets (CSS). In some embodiments, a web application is written in part in client-side scripting such as Asynchronous Javascript and XML (AJAX), Flash® Actionscript, Javascript, or Silverlight®.In some embodiments, the web application is written in part in a server-side coding language such as Active Server Pages (ASP), ColdFusion®, Perl, Java™, JavaServer Pages (JSP), Hypertext Preprocessor (PHP), Python™, Ruby, Tcl, Smalltalk, WebDNA®, or Groovy. In some embodiments, the web application is written in part in a database query language such as Structured Query Language (SQL). In some embodiments, the web application integrates with enterprise server products such as IBM® Lotus Domino®. In some embodiments, the web application includes a media player element. In various further embodiments, the media player element utilizes one or more of a number of suitable multimedia technologies, including, by way of non-limiting example, Adobe® Flash®, HTML 5, Apple® QuickTime®, Microsoft® Silverlight®, Java™, and Unity®.

[0163] Mobile Applications In some embodiments, the software described herein comprises a mobile application provided to the mobile digital processing device. In some embodiments, the mobile application is provided to the mobile digital processing device at the time of manufacture. In other embodiments, the mobile application is provided to the mobile digital processing device by a computer network described herein.

[0164] Given the disclosure provided herein, mobile applications are created using hardware, languages, and development environments known in the art and techniques known to those skilled in the art. Those skilled in the art will recognize that mobile applications may be written in multiple languages. Suitable programming languages ​​include, by way of non-limiting example, C, C++, C#, Objective-C, Java™, Javascript, Pascal, Object Pascal, Python™, Ruby, VB.NET, WML, and XHTML / HTML with or without CSS, or combinations thereof.

[0165] Suitable mobile application development environments are available from several sources. Commercially available development environments include, but are not limited to, Airplay SDK, alcheMo, Appcelerator®, Celsius, Bedrock, Flash Lite, .NET Compact Framework, Rhomobile, and WorkLight Mobile Platform. Other development environments are available without cost and include, but are not limited to, Lazarus, MobiFlex, MoSync, and Phonegap. Mobile device manufacturers also distribute software development kits, including, but not limited to, the iPhone and iPad (iOS) SDK, Android™ SDK, BlackBerry® SDK, BREW SDK, Palm® OS SDK, Symbian SDK, webOS SDK, and Windows Mobile SDK.

[0166] Those skilled in the art will recognize that various commercial forums are available for the distribution of mobile applications, including, by way of non-limiting example, the Apple® App Store, Google® Play, Chrome Web Store, BlackBerry® App World, the App Store for Palm devices, the App Catalog for webOS, the Windows® Marketplace for Mobile, the Ovi Store for Nokia® devices, Samsung® Apps, and the Nintendo® DSi Shop.

[0167] Standalone Applications In some embodiments, the software described herein includes a standalone application, which runs as an independent computer process and is not an add-on to an existing process, e.g., not a plug-in. Those skilled in the art will recognize that standalone applications are often compiled. A compiler is a computer program that converts source code written in a programming language into binary object code, such as assembly language or machine code. Suitable compiled programming languages ​​include, by way of non-limiting example, C, C++, Objective-C, COBOL, Delphi, Eiffel, Java™, Lisp, Python™, Visual Basic, and VB.NET, or a combination thereof. Compilation is often performed at least in part to create an executable program. In some embodiments, a computer program includes one or more executable compiled applications.

[0168] Web browser plugin In some embodiments, the software described herein includes or works in conjunction with a web browser plug-in (e.g., decompressor). In computing, a plug-in is one or more software components that add specific functionality to a larger software application. Software application manufacturers support plug-ins to create the ability for third-party developers to extend the application, easily support adding new features, and reduce the application's size. When supported, plug-ins allow for customization of the software application's functionality. For example, plug-ins are commonly used in web browsers to play video, create interactivity, scan for viruses, and display specific file types. Those skilled in the art are familiar with various web browser plug-ins, including Adobe® Flash® Player, Microsoft® Silverlight®, and Apple® QuickTime®.

[0169] Given the disclosure provided herein, one of ordinary skill in the art will recognize that a variety of plug-in frameworks are available that allow for the development of plug-ins in a variety of programming languages, including, by way of non-limiting example, C++, Delphi, Java™, PHP, Python™, and VB .NET, or combinations thereof.

[0170] A web browser (also called an Internet browser) is a software application designed for use with networked digital processing devices for searching, viewing, and traversing information resources on the World Wide Web. Suitable web browsers include, by way of non-limiting example, Microsoft® Internet Explorer®, Mozilla® Firefox®, Google® Chrome, Apple® Safari®, Opera Software® Opera®, and KDE Konqueror. In some embodiments, the web browser is a mobile web browser. Mobile web browsers (also called microbrowsers, minibrowsers, and wireless browsers) are designed for use with mobile digital processing devices, including, by way of non-limiting example, handheld computers, tablet computers, netbook computers, subnotebook computers, smartphones, music players, personal digital assistants (PDAs), and handheld video game systems. Suitable mobile web browsers include, by way of non-limiting example, Google® Android® browser, RIM BlackBerry® browser, Apple® Safari®, Palm® Blazer, Palm® WebOS® Browser, Mozilla® Firefox® for mobile, Microsoft® Internet Explorer® Mobile, Amazon® Kindle® Basic Web, Nokia® browser, Opera Software® Opera® Mobile, and Sony® PSP™ browser.

[0171] Software Module In some embodiments, the software described herein includes modules, or uses thereof. In light of the disclosure provided herein, software modules are created by techniques known to those skilled in the art using machines, software, and languages ​​known in the art. The software modules disclosed herein are implemented in many ways. In various embodiments, a software module includes a file, a section of code, a programming object, a programming structure, or a combination thereof. In further various embodiments, a software module includes multiple files, multiple sections of code, multiple programming objects, multiple programming structures, or a combination thereof. In various embodiments, one or more software modules include, by way of non-limiting examples, a web application, a mobile application, and a standalone application. In some embodiments, a software module is in one computer program or application. In other embodiments, a software module is in more than one computer program or application. In some embodiments, a software module is hosted on one machine. In other embodiments, a software module is hosted on more than one machine. In further embodiments, a software module is hosted on a cloud computing platform. In some embodiments, a software module is hosted on one or more machines in a single location. In other embodiments, the software modules are hosted on one or more machines in more than one location.

[0172] Database In some embodiments, the software described herein operates in conjunction with or using one or more databases. In various embodiments, suitable databases include, by way of non-limiting example, relational databases, non-relational databases, object-oriented databases, object databases, entity-relationship model databases, associative databases, and XML databases. Further non-limiting examples include SQL, PostgreSQL, MySQL, Oracle, DB2, and Sybase. In some embodiments, the database is internet-based. In further embodiments, the database is web-based. In still further embodiments, the database is cloud computing-based. In other embodiments, the database utilizes one or more local computer memory devices.

[0173] A platform for assessing behavioral disorders, developmental delays, and neurological disorders In some embodiments, the software described herein is configured for use on one or more platforms for assessing behavioral disorders, developmental delays, and neurological disorders, each including one or more computing devices with applications that enable communication and / or data sharing between the one or more computing devices. In some embodiments, the applications provide users with specialized portals, such as, for example, a healthcare provider portal and a patient portal. Features provided by the applications on the platforms described herein include recording individuals and assessing them using the techniques described herein.

[0174] In some embodiments, a user provides personal input data that is assessed through the use of a questionnaire for a first user application on a first computing device, in some embodiments, the user application provides questions one at a time and actively generates questions in the manner described above.

[0175] In some embodiments, the input data is analyzed by a machine learning software module that provides a probabilistic diagnostic score for each possible diagnosis and classification value associated with each symptom classification category. In some embodiments, the analysis is provided to a clinician through use of a clinician application. In some embodiments, the probabilistic diagnostic score must exceed a numerical threshold to be displayed in the clinician application. In some embodiments, probabilistic diagnostic scores below a certain threshold are displayed in a separate tab or screen in the clinician application. In some embodiments, the clinician reviews the results of the analysis and requests additional data through the clinician application. For example, the clinician may receive results indicating that a child has a 35% probability diagnostic score for autism type, a 48% probability diagnostic score for mental retardation type, and a 10% probability diagnostic score for language delay. The probability score threshold is set at 25%, and the clinician reviews the scores for autism and mental retardation. The clinician orders behavioral testing through the application and requests additional footage of tasks performed by a child exhibiting one or both symptoms. In some embodiments, the clinician diagnoses an individual with the aid of the results provided by the machine learning algorithm. In some embodiments, a clinician enters a diagnosis into the application and the data and diagnosis are available to a healthcare provider.

[0176] In some embodiments, the healthcare provider can coordinate the individual's treatment and provide treatment recommendations to the user and the individual. In some embodiments, the individual's input data is accessible to clinicians treating the individual within the healthcare provider's network.

Claims

1. 1. A computer-implemented method for assessing an individual, the method comprising: (a) receiving input associated with an evaluation device; (b) using a model to generate a plurality of likelihoods based at least on the input, each likelihood comprising a likelihood that the individual has one of a plurality of diseases, wherein the likelihood that the individual has one of the plurality of diseases is based at least in part on a penalty score, the penalty score being a measure of the severity of the individual being misclassified as having the one of the diseases; (c) identifying next inputs that reduce the uncertainty of the model; and (d) receiving the next input associated with the evaluation device.

2. The method of claim 1 , wherein the input is a response to a survey.

3. The method of claim 2 , wherein the questionnaire is a shortened version of the full questionnaire.

4. The method of claim 1 , comprising determining a classification of the individual as having one of the plurality of diseases based at least on the plurality of likelihoods.

5. The method of claim 4 , wherein the classification is based on a subset of items from the assessment instrument.

6. The method of claim 1 , wherein the input comprises a response provided by a caregiver of the individual.

7. The method of claim 1 , wherein the input comprises a video assessment, a video questionnaire, a written questionnaire, or an audio recording of a questionnaire.

8. 10. The method of claim 1, wherein the plurality of diseases includes neurological typical and inconclusive.

9. The method of claim 1 , wherein the model is generated using a Monte Carlo method.

10. The method of claim 1 , wherein the model is generated using machine learning.

11. The method of claim 10 , wherein the model comprises a classifier.

12. 10. The method of claim 1, wherein the model is generated using at least one question asked of a plurality of individuals with a known positive or negative assessment of behavioral disorder, developmental delay, or neurological disorder.

13. 10. The method of claim 1, wherein the model is generated using the most common answers received from a plurality of individuals with known positive or negative assessments of behavioral disorders, developmental delays, or neurological disorders.

14. The method of claim 1 , comprising determining a classification of the individual with one of the plurality of diseases based at least on the plurality of likelihoods.

15. 15. The method of claim 14, comprising determining whether the classification should be output or whether additional analysis should be performed, wherein determining whether the classification should be output or whether additional analysis should be performed is based, at least in part, on the uncertainty in the model.

16. The method of claim 15 , wherein the additional analysis is performed when the uncertainty of the classification is considered relative to the cost of performing the additional analysis.

17. 2. The method of claim 1, comprising determining the penalty score for each of the plurality of diseases, the penalty score comprising a measure of risk for classifying the individual as having one of the plurality of diseases using the model.

18. 18. The method of claim 17, wherein a classification of the individual including one of the plurality of diseases is output only if the penalty score is less than a penalty gate.

19. 19. The method of any one of claims 1 to 18, wherein the plurality of diseases comprises two or more of Pervasive Developmental Disorder (PDD), Autism Spectrum Disorder (ASD), Social Communication Disorder, Restricted Repetitive Behaviors, Interests, and Activities (RRB), Autism ("Classic Autism"), Asperger's Syndrome ("High Functioning Autism"), PDD Not Otherwise Specified (PDD-NOS, "Atypical Autism"), Attention Deficit Disorder (ADD), Attention Deficit Hyperactivity Disorder (ADHD), Speech and Language Delay, Obsessive-Compulsive Disorder (OCD), Depression, Schizophrenia, Alzheimer's Disease, Dementia, Intellectual Disability, or Learning Disability.

20. The method of any one of claims 1 to 18, wherein the plurality of diseases includes autism spectrum disorder.

21. 1. A system for assessing an individual, the system comprising: (a) processor (b) the processor receiving inputs associated with the evaluation device; using a model to generate, based at least on the inputs, a plurality of likelihoods, each including a likelihood that the individual has one of a plurality of diseases, the likelihood that the individual has one of the plurality of diseases being based at least in part on a penalty score, the penalty score being a measure of the severity of the individual being misclassified as having the one of the diseases; Identifying a next input that, when received, reduces the uncertainty of the model; and A system including a non-transitory computer-readable medium including software configured to cause the system to receive the next input associated with the evaluation device.

22. 22. The system of claim 21, wherein the input is a response to a survey.

23. 23. The system of claim 22, wherein the questionnaire is an abbreviated version of the full questionnaire.

24. 22. The system of claim 21, wherein the software further causes the processor to determine a classification of the individual as having one of the plurality of diseases based at least on the plurality of likelihoods.

25. 25. The system of claim 24, wherein the classification is based on a subset of items from the assessment instrument.

26. 22. The system of claim 21, wherein the input comprises a response provided by a caregiver of the individual.

27. 22. The system of claim 21, wherein the input comprises a video assessment, a video questionnaire, a written questionnaire, or an audio recording of a questionnaire.

28. 22. The system of claim 21, wherein the plurality of diseases includes neurological typical and inconclusive.

29. The system of claim 21 , wherein the model is generated using a Monte Carlo method.

30. The system of claim 21 , wherein the model is generated using machine learning.

31. The system of claim 30 , wherein the model comprises a classifier.

32. 22. The system of claim 21, wherein the model is generated using at least one question asked of a plurality of individuals with a known positive or negative assessment of behavioral disorder, developmental delay, or neurological disorder.

33. 22. The system of claim 21, wherein the model is generated using the most common answers received from a plurality of individuals with known positive or negative assessments of behavioral disorders, developmental delays, or neurological disorders.

34. 22. The system of claim 21, wherein the software further causes the processor to determine a classification of the individual with one of the plurality of diseases based at least on the plurality of likelihoods.

35. 35. The system of claim 34, wherein the software further causes the processor to determine whether the classification should be output or whether additional analysis should be performed, where the classification should be output or whether additional analysis should be performed is based, at least in part, on the uncertainty in the model.

36. 36. The system of claim 35, wherein the additional analysis is performed when the uncertainty of the classification is considered relative to the cost of performing the additional analysis.

37. 22. The system of claim 21, wherein the software further causes the processor to determine a penalty score for each of the plurality of diseases, the penalty score comprising a measure of risk for classifying the individual as having one of the plurality of diseases using the model.

38. 38. The system of claim 37, wherein a classification of the individual including one of the plurality of diseases is output only if the penalty score is less than a penalty gate.

39. 39. The system of any one of claims 21 to 38, wherein the plurality of diseases comprises two or more of Pervasive Developmental Disorder (PDD), Autism Spectrum Disorder (ASD), Social Communication Disorder, Restricted Repetitive Behaviors, Interests, and Activities (RRB), Autism ("Classic Autism"), Asperger's Syndrome ("High-Functioning Autism"), PDD Not Otherwise Specified (PDD-NOS, "Atypical Autism"), Attention Deficit Disorder (ADD), Attention Deficit Hyperactivity Disorder (ADHD), Speech and Language Delay, Obsessive-Compulsive Disorder (OCD), Depression, Schizophrenia, Alzheimer's Disease, Dementia, Intellectual Disability, or Learning Disability.

40. 40. The system of any one of claims 21 to 39, wherein the plurality of diseases includes autism spectrum disorder.

Images