Predicting response to nummulin therapy for refractory depression

Abstract

Methods for predicting response to administration therapy are provided. One or more records of a session associated with administration of a therapy may be transcribed into one or more transcripts. The transcript may be parsed into an utterance. An utterance emotion for a single utterance may be determined, and a response to the administration therapy may be predicted based at least in part on the utterance emotion.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of U.S. Provisional Application Serial No. 63 / 392,451, filed on July 26, 2022, entitled “PSILOCYBIN THERAPY FOR TREATMENT RESISTANT DEPRESSION,” and U.S. Provisional Application Serial No. 63 / 414,769, filed on October 10, 2022, entitled “PSILOCYBIN THERAPY FOR TREATMENT RESISTANT DEPRESSION,” the entire disclosures of which are incorporated herein by reference for all purposes. Background Art

[0003] The therapeutic administration of psychedelic drugs has shown significant potential both historically and in recent clinical trials for the treatment of depression and other mood disorders. For example, recent studies have shown promising results when using psilocybin preparations to treat patients with treatment-resistant depression (TRD). However, while promising, this treatment may only be effective for a subset of the population, and early prediction of outcomes is a key goal of treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0004] Various embodiments according to the present disclosure will be described with reference to the accompanying drawings, in which:

[0005] Figure 1 Exemplary emotion graphs are shown that may be utilized in accordance with various implementations.

[0006] Figure 2 Exemplary methods are presented that may be utilized to implement one or more aspects of various embodiments.

[0007] Figure 3 Exemplary methods are presented that may be utilized to implement one or more aspects of various embodiments.

[0008] Figure 4 Components of an exemplary computing device are shown that can be utilized in accordance with various implementations.

[0009] Figure 5 Examples of environments for implementing aspects according to various implementations are presented.

[0010] Figure 6 Components of another exemplary environment are shown in which aspects of various embodiments may be implemented. DETAILED DESCRIPTION

[0011] When predicting a patient's potential response to a therapy, various factors may be considered. For example, when combined with the patient and therapist's average verbal emotion scores during a post-drug support session or integration session, a machine learning model may be adapted to predict with high fidelity the participant's therapeutic response at upcoming and future time points. These methods may be utilized in accordance with one or more embodiments to help predict at least a portion of a participant's or patient's response to a hallucinogenic therapy.

[0012] In the following description, various embodiments will be described. For the purpose of explanation, specific configurations and details are set forth to provide a thorough understanding of the embodiments. However, those skilled in the art will also appreciate that the embodiments may be practiced without the specific details. In addition, well-known features may be omitted or simplified to avoid obscuring the described embodiments.

[0013] A system and method for predicting a response to an administered therapy is provided. One or more scores corresponding to individual reported results associated with the administered therapy may be received. One or more records of a conversation associated with the administered therapy may be transcribed into one or more transcripts. The transcripts may be parsed into utterances. The utterance sentiment of a single utterance may be determined, and the response to the administered therapy may be predicted based at least in part on the scores and the utterance sentiment.

[0014] Major depressive disorder (MDD) is a debilitating disease and can affect one in six adults in their lifetime. MDD can be characterized by at least one depressive episode, which lasts for at least two weeks and involves significant changes in mood, cognition, and the ability to experience happiness. Although MDD can be effectively controlled by psychotherapy and / or medication, some MDD patients may still be unresponsive to treatment despite multiple attempts at treatment. Such individuals may be referred to as patients with refractory depression (TRD). There are a variety of existing treatment options, but these options are often determined to be unsatisfactory. Therefore, it is necessary to develop alternative therapeutic options with improved efficacy for TRD patients. Additionally, for such patients, the acceptability of the condition or treatment may still be an important challenge.

[0015] Psilocybin is a tryptamine alkaloid whose potential as an effective antidepressant has been investigated in preliminary studies in patients with life-threatening cancers, MDD, and TRD. In at least one psilocybin study using a 25mg dose of COMP360, a group of participants experienced a reduction in depressive symptoms for up to 12 weeks. While promising, these results suggest that lasting psilocybin responses occur only in a subset of the TRD population. Weeks may pass, and potential opportunities for additional treatment may be wasted.

[0016] Figure 1 An exemplary mood map 100 is shown that can be utilized according to various embodiments. In at least some embodiments, a model can be utilized to help predict whether a participant will respond in a particular week in their treatment timeline. The model can take into account various factors, including the patient's and therapist's mood scores, the participant's or patient's treatment group (dose), and a measure of the participant's or patient's and therapist's average verbal mood during an integration session for at least one day after dosing.

[0017] In some embodiments, a predictive model can be utilized using information available immediately after treatment to predict which participants will be responders, sustained responders, and relaxed sustained responders. A machine learning model can be utilized to help predict patient responses. In an exemplary embodiment, the machine learning model can take into account additional exogenous variables, including but not limited to values ​​summarizing participant or patient emotions during the integration session, and values ​​summarizing therapist emotions during the integration session.

[0018] At least one day after the initial administration of psilocybin, the patient or participant can have an integration session with the therapist to discuss their initial response to treatment. Audio recordings of the integration sessions can be collected and transcribed into text of the conversations, either manually or through the use of natural language processing (NLP) techniques. The transcripts can then be parsed into individual "utterances" that are used to assess the emotion of the session for both the therapist and the patient or participant using a sentiment model. Such a model can produce a valence score and an arousal score for each utterance. Figure 1 As shown, arousal scores 110 and valence scores 120 can be presented on a mood map 100. A single circle, such as circle 130, can represent an utterance from a session, and the size of the circle can reflect the relative length of the utterance. A circled "X" such as element 140 can mark the average emotional value of all utterances during the session. The mood map can be patient or therapist specific. The valence score can correspond to a positive or negative score used in sentiment analysis. The arousal score can characterize where the utterance falls on the spectrum, such as bored or calm to nervous, alert, or excited. The score can indicate the average emotion of the utterances spoken by the patient or participant and therapist during the integration session.

[0019] In at least some embodiments, the audio can be parsed and labeled as utterances. The audio can be processed using a model to predict the patient's tone. In some embodiments, the audio can be associated with a score indicating the patient's tone. The audio score can be compared to the valence score and the arousal score, or the audio score can be explained by the valence score and the arousal score. A classifier built based on a bidirectional autoregressive transformer (BART) autoencoder and a multi-type natural language inference (MNLI) dataset can be used to calculate the emotional valence score and the arousal score.

[0020] Figure 2 An exemplary method 200 is shown that can be utilized to implement one or more aspects of various embodiments. An audio recording can be generated at the time of an initial integration session between a patient or participant and a medical provider, such as a therapist. Using one or more NLP techniques, the recording can be transcribed into text 210, and the text can be parsed to generate groups of utterances 220. Emotion scores can be assigned or determined for individual utterances in the group 230. An interview average of the emotion scores can be calculated. The average emotion score can be used to predict the patient's response to treatment.

[0021] Prior to a psychological support session with a therapist or healthcare provider, a patient or participant may provide written consent to be audio recorded during the session. Any device that includes a microphone may be used to record the session. In some embodiments, the recording device may be pre-configured with a secure cloud storage account. Once recordings are complete, they may be automatically uploaded to the configured storage account. Quality assurance checks may be performed to ensure that the metadata of individual recordings is accurate, and the recordings may be made available for transcription.

[0022] The audio recordings may be transcribed manually or automatically. Identifiable information of both the patient or participant and the health care provider may be removed to anonymize the transcripts. As described above, the transcripts may be reviewed for quality assurance prior to analysis. After the audio recordings are converted to text, the individual transcripts may be parsed into utterances. In some embodiments, transcript punctuation may be used as a guide. According to one or more embodiments, training of a large language model may be utilized to help score utterances. For example, the model may analyze a single sentence that has been parsed and constructed with text that can be recognized by the model to generate a score.

[0023] In NLP, an "utterance" may be defined as a group of spoken words with pauses before and after. In contrast, a "sentence" may refer to a group of words that expresses a complete thought. According to one or more embodiments described herein, an "utterance" may be a fusion of the two. For example, if a sentence appears in several utterances, the utterances may be combined to form a single utterance. Alternatively, if an utterance contains several sentences, each sentence may be extracted and treated as an independent utterance.

[0024] Additional processing steps may be taken after transcription. For example, Unicode characters may be converted to ASCII characters. Redacted information such as names may be replaced with non-personally identifiable substitutes (e.g., Jane / John Doe). According to another exemplary embodiment, transcriptionist annotations may be replaced with text that is familiar to the model. For example, the transcription annotation "[LAUGHING]" may be replaced with "haha" so that the model can better recognize the term and use it when generating a score.

[0025] Sentiment analysis of a piece of text can include scoring the text as positive or negative. Text can be scored on two dimensions: valence (e.g., positivity) and arousal (e.g., energy or activation). In this way, sentiment can capture intensity, rather than just positivity or negativity. The sentiment scoring of a piece of text can be different from trying to infer the speaker's emotional state. For example, a traditional sentiment model might score a text that states "I love broccoli" as positive. However, if said in a sarcastic manner, the text would signal a negative attitude toward broccoli. Furthermore, a text that states "I love broccoli" might be scored as 97% positive in one model, and a text that states "I like broccoli" might be scored as 98% positive in the same model. The similarity in positivity scores may be due to the sentiment analysis problem being treated as a classification problem, without regard to intensity. In this case, the model may only care whether the "positive" or "negative" label is correct.

[0026] The two-dimensional emotion model can plot emotions on an xy plane, where the x value represents valence (e.g., positivity) and the y value represents arousal (e.g., energy or activation). According to an exemplary embodiment, examples of high-valence emotions can include "excited", "happy", "contented", and "serene". According to an exemplary embodiment, low-valence emotions can include "fear", "nervous", "sad", and "bored". According to an exemplary embodiment, high-arousal emotions can include "anxious", "panic", "surprised", and "excited". According to an exemplary embodiment, low-arousal emotions can include "bored", "listless", "tired", and "sleepy".

[0027] In some exemplary embodiments, a classifier may be used to calculate emotional valence scores and arousal scores. Such a classifier may be built on the BART autoencoder and the Multi-Type Natural Language Inference (MNLI) dataset. Using a model built on top of a larger model allows almost unlimited free and available data to be used for smaller data tasks. BART is a deep learning model designed to reconstruct damaged text. It is trained on a large corpus of books and online content. Fine-tuning BART on the MNLI dataset may produce a classifier for any given category. For example, a user can specify a list of categories and submit a piece of text to be classified. A text stating "I love broccoli" may be submitted to be classified into the categories of "food" and "political views", where the model may indicate, for example, that the text is 99.8% likely to be related to food and 0.2% likely to be related to political views.

[0028] According to one or more embodiments described herein, for a single utterance, a model may be used to score the likelihood that the utterance should belong to one of four categories: "happy," "angry," "gloomy," and "calm." While this example utilizes the above categories, other categories representing emotions may also be utilized. For a given utterance, the model may provide a score for a single category. In an exemplary embodiment, the score may be a positive number that sums to one. Valence-arousal score pairs may be assigned to the categories so that the scores may be used to plot points on a two-dimensional affective plane.

[0029] For example, for a given set of categories (category 1, category 2, category 3, category 4), the model may determine that category 1 has a score of (1, 1), category 2 has a score of (-1, 1), category 3 has a score of (-1, -1), and category 4 has a score of (1, -1). In some embodiments, category 1 and category 2 may be a pair of emotions (e.g., "happy" and "angry"), and category 3 and category 4 may be a pair (e.g., "gloomy" and "calm"). Then, the point (valence (utterance), arousal (utterance)) for a given utterance u may be defined as a convex combination of the points (1, 1), (-1, 1), (1, -1), and (1, 1):

[0030] (Valence(words), Arousal(words)) = P u (Category 1)(1,1)+P u (Category 2)(-1, 1)+P u (Category 3)(-1,-1)+P u (Category 4) (1, -1) (Eq. 1)

[0031] Equivalently,

[0032] Potency (u) = P u (Category 1)-Pu (Category 2)-P u (Category 3)+P u (Category 4) (Eq.2)

[0033] as well as

[0034] Wake-up (u) = P u (Category 1)+P u (Category 2)-P u (Category 3)-P u (Category 4) (Eq.3)

[0035] These equations can yield points that fall within a two-dimensional square with corner points at (±1, ±1). In an exemplary embodiment, one or more points can be plotted within the two-dimensional square, such as Figure 1 shown.

[0036] One or more machine learning models can be utilized to help predict the probability of class membership for each subject, such as responder versus non-responder. In at least some embodiments, the predictions can be cross-validated to check the accuracy of the model. Valence and arousal scores can be extracted using categories such as "positive," "negative," "arousal," or "unarousal," but these categories may not be effectively extracted because the categories may be too broad to accurately capture the patient's emotions.

[0037] To determine the initial emotion score, a probability measure can be given to the set of utterances of a given speaker (e.g., participant or patient, therapist, etc.) during a single visit (e.g., first preparation, first integration, etc.), where the measure for a given utterance is proportional to the number of words in the utterance. From this, an average valence score and arousal score can be obtained.

[0038] The response to the administered therapy can be predicted based at least in part on the EBI summary score and the determined value 250. In some embodiments, a machine learning model can be used to predict whether a participant or patient is a responder to the treatment or therapy, a sustained responder to relaxation, or a sustained responder. In some exemplary embodiments, the treatment or therapy may refer to the administration of psilocybin. In some exemplary embodiments, a responder may be defined as a patient whose primary outcome measure score three weeks after the date of therapy administration is reduced by at least 50% relative to his baseline score. A sustained responder may be defined as a participant or patient whose score is reduced by at least 50% at each determined time point (e.g., the third, sixth, ninth, and twelfth week). A sustained responder to relaxation may be defined as a participant or patient whose score is reduced by at least 50% at a determined time point (e.g., the third and twelfth week) and a week in between (e.g., the sixth or ninth week). This definition of "responder" is not intended to be limiting, and other definitions of "responders" may be used.

[0039] The machine learning model can utilize the patient's or participant's EBI score, treatment dose, and mood measure from the transcript of the first integration session on the second day after treatment. The machine learning model can be fit to the complete data set to ensure that the selected model produces an adequate fit. A leave-one-out (LOO) cross-validation can be performed to evaluate the predictive power of the machine learning model. For example, the model can be fit to all participants or patients except one participant or patient, and the model can be used to predict the responder status of the excluded participant. In some exemplary embodiments, the model can be trained based on existing data and used to predict the responder status of new patients.

[0040] In some exemplary embodiments, treatment may be coded as a categorical variable with values ​​of 0, 1, and 2 for the 1 mg, 10 mg, and 25 mg treatment groups, respectively. Additionally, the therapy session mood scores may be normalized to have a mean of zero and a standard deviation of one.

[0041] It should be understood that for any process herein, additional, fewer, or alternative steps may be performed in similar or alternative sequences, or in parallel, within the scope of the various embodiments, unless expressly stated otherwise.

[0042] Figure 3 An exemplary method 300 is shown that can be utilized to implement one or more aspects of various embodiments. An audio recording of an initial integration session between a patient and a medical provider can be generated and received 310. Using one or more NLP techniques, the recording can be transcribed into text 320, and the text can be parsed to generate groups of utterances 330. A sentiment score can be assigned or determined for individual utterances in the group 340. A session average of the sentiment scores can be calculated 350. The average sentiment score can be utilized to predict the patient's response to treatment.

[0043] The audio recordings may be transcribed manually or automatically. Identifiable information of both the patient or participant and the healthcare provider may be removed to anonymize the transcripts. As described above, the transcripts may be reviewed for quality assurance prior to analysis. After the audio recordings are converted to text, the individual transcripts may be parsed into utterances. In some embodiments, transcript punctuation may be used as a guide. According to one or more embodiments, training of large language models may be utilized to assist in scoring utterances.

[0044] In NLP, an "utterance" may be defined as a group of spoken words with pauses before and after. In contrast, a "sentence" may refer to a group of words that expresses a complete thought. According to one or more embodiments described herein, an "utterance" may be a fusion of the two. For example, if a sentence appears in several utterances, the utterances may be combined to form a single utterance. Alternatively, if an utterance contains several sentences, each sentence may be extracted and treated as an independent utterance.

[0045] Additional processing steps may be taken after transcription. For example, Unicode characters may be converted to ASCII characters. Redacted information such as names may be replaced with non-personally identifiable substitutes (e.g., Jane / John Doe). According to another exemplary embodiment, transcriptionist annotations may be replaced with text that is familiar to the model. For example, the transcription annotation "[LAUGHING]" may be replaced with "haha" so that the model can better recognize the term and use it when generating a score.

[0046] Sentiment analysis of a piece of text can include scoring the text as positive or negative. Text can be scored on two dimensions: valence (e.g., positivity) and arousal (e.g., energy or activation). In this way, sentiment can capture intensity, rather than just positivity or negativity. The sentiment scoring of a piece of text can be different from trying to infer the speaker's emotional state. For example, a traditional sentiment model might score a text that states "I love broccoli" as positive. However, if said in a sarcastic manner, the text would signal a negative attitude toward broccoli. Furthermore, a text that states "I love broccoli" might be scored as 97% positive in one model, and a text that states "I like broccoli" might be scored as 98% positive in the same model. The similarity in positivity scores may be due to the sentiment analysis problem being treated as a classification problem, without regard to intensity. In this case, the model may only care whether the "positive" or "negative" label is correct.

[0047] The two-dimensional emotion model can plot emotions on an xy plane, where the x value represents valence (e.g., positivity) and the y value represents arousal (e.g., energy or activation). According to an exemplary embodiment, examples of high-valence emotions can include "excited", "happy", "contented", and "serene". According to an exemplary embodiment, low-valence emotions can include "fear", "nervous", "sad", and "bored". According to an exemplary embodiment, high-arousal emotions can include "anxious", "panic", "surprised", and "excited". According to an exemplary embodiment, low-arousal emotions can include "bored", "listless", "tired", and "sleepy".

[0048] In some exemplary embodiments, a classifier may be used to calculate emotional valence and arousal scores. Such a classifier may be built on the BART autoencoder and the Multi-Type Natural Language Inference (MNLI) dataset. Using a model built on top of a larger model enables almost unlimited free and available data to be used for smaller data tasks. BART is a deep learning model designed to reconstruct damaged text. BART is trained on a large corpus of books and online content. Fine-tuning BART on the MNLI dataset may produce a classifier for any given category. For example, a user can specify a list of categories and submit a piece of text to be classified. A text stating "I love broccoli" may be submitted to be classified into the categories of "food" and "political views", where the model may indicate, for example, that the text is 99.8% likely to be related to food and 0.2% likely to be related to political views.

[0049] According to one or more embodiments described herein, for a single utterance, a model may be used to score the likelihood that the utterance should belong to one of four categories: "happy," "angry," "gloomy," and "calm." While this example utilizes the above categories, other categories representing emotions may also be utilized. For a given utterance, the model may provide a score for a single category. In an exemplary embodiment, the score may be a positive number that sums to one. Valence-arousal score pairs may be assigned to the categories so that the scores may be used to plot points on a two-dimensional affective plane.

[0050] Computing resources such as servers that can update software and / or firmware in this manner will generally include at least a set of standard components configured for general operation, although various proprietary components and configurations may also be used within the scope of various embodiments. Figure 4Components of an exemplary computing device 400 that can be utilized according to various embodiments are shown. As is known for computing devices, a computer will have one or more processors 402, such as a central processing unit (CPU), a graphics processing unit (GPU), etc., which are electronically and / or communicatively coupled to various components using various buses, traces, and other such mechanisms. The processor 402 may include memory registers 406 and cache memory 404 for storing instructions, data, etc. In this example, a chipset 414, which may include a north bridge and a south bridge in some embodiments, may work with various system buses to connect the processor 402 to components such as a system memory 416 in the form of physical RAM or ROM, which may include code for an operating system and various other instructions and data for the operation of the computing device. The computing device may also include one or more storage devices 420, such as a hard drive, a flash drive, an optical storage device, etc., or communicate with the one or more storage devices 420 to store data and instructions similar to or in addition to the data and instructions stored in the processor and memory. The processor 402 may also communicate with various other components via a chipset 414 and an interface bus (or graphics bus, etc.), which may include a communication device 424, such as a cellular modem or network card, a media component 426, such as a graphics card and an audio component, and a peripheral interface 430 for connecting peripheral devices, such as a printer, a keyboard, etc. At least one cooling fan 432 or other such temperature regulating or reducing component may also be included, which may be driven by the processor or triggered by various other sensors or components on the device or remote from the device. Various other or alternative components and configurations for computing devices known in the art may be utilized.

[0051] In some embodiments, at least one processor 402 can obtain data from a physical memory 416 such as a dynamic random access memory (DRAM) module through a consistency architecture. It should be understood that for such a computing device, various architectures can be utilized, which may include different selections, quantities, and parameters of buses and bridges within the scope of various embodiments. Data in the memory can be managed and accessed by a memory controller, such as a DDR controller, through a consistency architecture. In at least some embodiments, data can be temporarily stored in a processor cache 404. The computing device 400 can also support multiple I / O devices using a set of I / O controllers connected via an I / O bus. There may be an I / O controller to support various types of I / O devices, such as a universal serial bus (USB) device, a data storage device (e.g., a flash memory device or a disk storage device), a network card, a high-speed peripheral component interconnect standard (PCIe, peripheral component interconnect express) card or interface 430, a communication device 424, a graphics or audio card 426, and a direct memory access (DMA) card, and options such as these. In some embodiments, components such as a processor, controller, and cache may be configured on a single card, board, or chip (ie, a system-on-chip implementation), while in other embodiments at least some components may be located in different locations, etc.

[0052] An operating system (OS) running on the processor 402 can help manage various devices that can be utilized to provide input to be processed. This can include, for example, utilizing associated device drivers to implement interactions with various I / O devices, which may be related to data storage, device communication, user interface, etc. Various I / O devices will typically be connected through various device ports and communicate with the processor and other device components through one or more buses. There may be a specific type of bus that provides communication according to a specific protocol, such as may include peripheral component interconnect standard (PCI) or small computer system interface (SCSI) communication, and options such as these. Registers associated with corresponding ports may be used for communication, including registers such as data input and data output registers. Memory mapped I / O may also be used for communication, in which a portion of the processor's address space is mapped to a specific device, and data is written directly to or from the portion of the address space.

[0053] Such a device can be used as a server in a server farm or data warehouse, for example. Server computers typically have the need to perform tasks outside the CPU and main memory (i.e., RAM) environment. For example, a server may need to communicate with an external entity (e.g., other servers) or use an external processor (e.g., a general purpose graphics processing unit (GPGPU)) to process data. In such a case, the CPU can be docked with one or more I / O devices. In some cases, these I / O devices can be dedicated hardware designed to perform specific roles. For example, an Ethernet network interface controller (NIC) can be implemented as an application specific integrated circuit (ASIC), which includes digital logic that can be operated to send and receive data packets.

[0054] In an illustrative embodiment, the host computing device is associated with various hardware components, software components, and respective configurations that facilitate the execution of I / O requests. One such component is an I / O adapter that inputs and / or outputs data along a communication channel. In one aspect, the I / O adapter device can communicate as a standard bridge component to facilitate access between various physical and simulated components and the communication channel. On the other hand, the I / O adapter device may include an embedded microprocessor to allow the I / O adapter device to execute computer executable instructions related to the implementation of management functions or the management of one or more such management functions, or to execute other computer executable instructions related to the implementation of the I / O adapter device. In some embodiments, the I / O adapter device can be implemented using multiple discrete hardware elements, such as multiple cards or other devices. The management controller can be configured to be electrically isolated from any other component in the host device except the I / O adapter device. In some embodiments, the I / O adapter device is externally attached to the host device. In some embodiments, the I / O adapter device is internally integrated into the host device. An external communication port component can also be communicated with the I / O adapter device, which is used to establish a communication channel between the host device and one or more network-based services or other network-connected or directly connected computing devices. Illustratively, the external communication port component may correspond to a network switch, sometimes referred to as a top-of-rack ("TOR") switch. The I / O adapter device may utilize the external communication port component to maintain a communication channel between one or more services and the host device, such as a health check service, a financial service, etc.

[0055] The I / O adapter device can also communicate with a basic input / output system (BIOS) component. The BIOS component can include non-transient executable code, commonly referred to as firmware, which can be executed by one or more processors and used to initialize and identify system devices such as video display cards, keyboards and mice, hard drives, optical drives, and other hardware of the host device. The BIOS component can also include or locate the boot loader software that will be used to boot the host device. For example, in one embodiment, the BIOS component can include executable code that, when executed by the processor, causes the host device to attempt to locate the pre-boot execution environment (PXE) boot software. In addition, the BIOS component can include or utilize a hardware latch electrically controlled by the I / O adapter device. The hardware latch can limit access to one or more aspects of the BIOS component, such as controlling the modification or configuration of the executable code maintained in the BIOS component. The BIOS component can be connected to many additional computing device resource components, such as (or communicate with) a processor, a memory, etc. In one embodiment, such a computing device resource component can be a physical computing device resource that communicates with other components through a communication channel. The communication channel may correspond to one or more communication buses in which the components of the bare metal host device communicate, such as a shared bus (e.g., a processor bus, a memory bus), a point-to-point bus such as a PCI or a high-speed PCI bus, etc. Other types of communication channels, communication media, communication buses, or communication protocols (e.g., an Ethernet communication protocol) may also be utilized. In addition, in other embodiments, one or more of the computing device resource components may be virtualized hardware components emulated by the host device. In such an embodiment, the I / O adapter device may implement a management process in which the host device is configured with physical or emulated hardware components based on various standards. The computing device resource component may communicate with the I / O adapter device via the communication channel. In addition, the communication channel may connect a high-speed PCI device to the CPU via a north bridge or a host bridge, and options such as these.

[0056] Communicating with the I / O adapter device through the communication channel may be one or more controller components for managing a hard drive or other form of memory. An example of a controller component may be a SATA hard drive controller. Similar to the BIOS component, the controller component may include or utilize a hardware latch electrically controlled by the I / O adapter device. The hardware latch may limit access to one or more aspects of the controller component. As an illustration, the hardware latches may be controlled together or independently. For example, the I / O adapter device may selectively close the hardware latch for one or more components based on a trust level associated with a particular user. In another example, the I / O adapter device may selectively close the hardware latch for one or more components based on a trust level associated with the author or publisher of the executable code to be executed by the I / O adapter device. In other examples, the I / O adapter device may selectively close the hardware latch for one or more components based on a trust level associated with the component itself. The host device may also include additional components that communicate with one or more illustrative components associated with the host device. Such components may include devices, such as one or more controllers in combination with one or more peripheral devices, such as hard disks or other storage devices. In addition, additional components of the host device may include another set of peripheral devices, such as a graphics processing unit ("GPU"). The peripheral devices may also be associated with hardware latches to restrict access to one or more aspects of the components. As described above, in one embodiment, the hardware latches may be controlled together or independently.

[0057] As discussed, different methods may be implemented in various environments depending on the implementation. For example, Figure 5An example of an environment 500 for implementing aspects according to various embodiments is shown. It should be understood that, although a Web-based environment is used for explanation purposes, various embodiments may be implemented using different environments as appropriate. The system includes an electronic client device 502, which may include any appropriate device operable to send and receive requests, messages or information through an appropriate network 504 and convey information back to the user of the device. Examples of such client devices include personal computers, mobile phones, handheld messaging devices, laptops, set-top boxes, personal data assistants, e-book readers, etc. Examples of such recipients or users may include medical providers (including therapists) or patients. The network may include any appropriate network, including an intranet, the Internet, a cellular network, a local area network, or any other such network or combination thereof. The components used for such a system may depend at least in part on the type of selected network and / or environment. The protocols and components used to communicate through such a network are well known and will not be discussed in detail herein. Communication on the network may be achieved through wired or wireless connections and combinations thereof. In this example, the network includes the Internet, as the environment includes a Web server 506 for receiving requests and providing content in response thereto, although it will be apparent to one of ordinary skill in the art that alternative devices for similar purposes may be used for other networks.

[0058] The illustrative environment includes at least one application server 508 and a data repository 510. It should be understood that there may be several application servers, layers or other elements, processes or components, which may be linked or otherwise configured, and which may interact to perform tasks such as obtaining data from an appropriate data repository. As used herein, the term "data repository" refers to any device or combination of devices capable of storing, accessing and retrieving data, which may include any combination and number of data servers, databases, data storage devices and data storage media in any standard, distributed or clustered environment. The application server 508 may include any appropriate hardware and software for integrating with the data repository 510 as needed to perform aspects of one or more applications for client devices, and processing most of the data access and business logic for applications. The application server collaborates with the data repository to provide access control services, and is capable of generating content such as text, graphics, audio and / or video to be transmitted to the user, which may be provided to the user by the Web server 506 in the form of HTML, XML or other appropriate structured languages ​​in this example. The processing of all requests and responses and the content delivery between the client device 502 and the application server 508 may be handled by the Web server 506. It should be understood that the web and application servers are not required and are merely exemplary components, as the structured code discussed herein can be executed on any appropriate device or host machine, as discussed elsewhere herein.

[0059] The data repository 510 may include several separate data tables, databases, or other data storage mechanisms and media for storing data related to a particular aspect. For example, the data repository shown includes mechanisms for storing biomarker data (e.g., production data) 512 and user information 516, which can be used to provide content to the production side. The data repository is also shown as including mechanisms for storing log or period data 514. It should be understood that there may be many other aspects that may need to be stored in the data repository, such as page image information and access rights information, which may be stored in any of the mechanisms listed above or in additional mechanisms in the data repository 510 as appropriate. The data repository 510 may be operated by logic associated therewith to receive instructions from the application server 508 and obtain, update, or otherwise process data in response thereto. In one example, a user may submit a search request for a certain type of item. In this case, the data repository may access the user information to verify the user's identity and may access the catalog details to obtain information about that type of item. Information can then be returned to the user, such as through a patient or therapist portal, including biomarker and diagnostic data accessible through a web page that the user can view through a browser on the user device 502. Information for specific items of interest can be viewed in a dedicated page or window in the browser.

[0060] Each server will typically include an operating system that provides executable program instructions for the general management and operation of the server, and will typically include a computer-readable medium storing instructions that, when executed by a processor of the server, allow the server to perform its intended functions. Suitable implementations of operating systems and general functionality for the servers are known or commercially available and are readily implemented by those of ordinary skill in the art, particularly in light of the disclosure herein.

[0061] In one embodiment, the environment is a distributed computing environment utilizing several computer systems and components that are interconnected via communication links, using one or more computer networks or direct connections. However, one of ordinary skill in the art will appreciate that such a system may be implemented in environments with more than Figure 5 The system may operate equally well with fewer or greater numbers of components as shown. Figure 5 The description of system 500 should be regarded as illustrative in nature and not limiting the scope of the present disclosure.

[0062] Figure 6An exemplary environment 600 in which aspects of various embodiments can be implemented is shown. In this example, a user can submit a request to a multi-tenant resource provider environment 606 using a client device 602 through at least one network 604. The client device may include any appropriate electronic device operable to send and receive requests, messages, or other such information through an appropriate network and convey the information back to the user of the device. Examples of such client devices include personal computers, tablet computers, smart phones, laptops, etc. At least one network 604 may include any appropriate network, including an intranet, the Internet, a cellular network, a local area network (LAN), or any other such network or combination, and communication on the network may be achieved through wired and / or wireless connections. The resource provider environment 606 may include any appropriate components for receiving requests and returning information or performing actions in response to these requests. As an example, the provider environment may include a Web server and / or an application server for receiving and processing requests, and then returning data, web pages, videos, audio, or other such content or information in response to the request.

[0063] In various embodiments, the provider environment may include various types of resources that can be utilized by multiple users for various purposes. As used herein, computing and other electronic resources utilized in a network environment may be referred to as "network resources". These may include, for example, servers, databases, load balancers, routers, etc., which may perform tasks such as receiving, transmitting and / or processing data and / or executable instructions. In at least some embodiments, all or part of a given resource or resource set may be allocated to a specific user or to a specific task for at least a continuous determined period of time. Sharing these multi-tenant resources from the provider environment is generally referred to as resource sharing, Web services or "cloud computing", and terms such as these, and depends on the specific environment and / or implementation. In this example, the provider environment includes multiple resources 614 of one or more types. These types may include, for example, an application server operable to process instructions provided by a user or a database server operable to process data stored in one or more data repositories 616 in response to a user request. As known for such purposes, a user may also retain at least a portion of the data storage in a given data repository. Methods for enabling users to retain various resources and resource instances are well known in the art, so a detailed description of the entire process and an explanation of all possible components will not be discussed in detail herein.

[0064] In at least some embodiments, a user who wants to utilize a portion of a resource 614 may submit a request that is received by an interface layer 608 of a provider environment 606. The interface layer may include an application programming interface (API) or other exposed interface that enables a user to submit a request to the provider environment. The interface layer 608 in this example may also include other components, such as at least one web server, a routing component, a load balancer, etc. When the interface layer 608 receives a request to provide a resource, information for the request may be directed to a service manager 610 or other such systems, services, or components that are configured to manage user accounts and information, resource provisioning and use, and other such aspects. The service manager 610 that receives the request may perform tasks such as verifying the identity of the user submitting the request, and determining whether the user has an existing account at a resource provider, where the account data may be stored in at least one account data repository 612 in the provider environment. The user may provide various types of credentials to verify the identity of the user to the provider. These credentials may include, for example, a username and password pair, biometric data, a digital signature, or other such information. The provider may verify this information based on the information stored for the user. If the user has an account with appropriate permissions, status, etc., the resource manager can determine whether there are sufficient available resources to satisfy the user's request, and if so, can provide the resources or otherwise grant the user access to a corresponding portion of the resources for the amount specified by the request. The amount can include, for example, the ability to process a single request or perform a single task, a specified time period or a recurring / renewable time period, and the like. If the user does not have a valid account with the provider, the user's account does not allow access to the resource type specified in the request, or another such reason is preventing the user from obtaining access to such a resource, a communication can be sent to the user to enable the user to create or modify an account, or change the resources specified in the request, and the like.

[0065] Once the user is authenticated, the account is verified, and the resources are assigned, the user may utilize the assigned resources to obtain specified capabilities, data transfer amounts, time periods, or other such values. In at least some embodiments, the user may provide a session token or other such credentials in subsequent requests so that the requests can be processed in the user session. The user may receive a resource identifier, a specific address, or other such information that enables the client device 602 to communicate with the assigned resources without having to communicate with the service manager 610 at least until a change occurs in a relevant aspect of the user's account, the user is no longer granted access to the resources, or another such change occurs.

[0066] The service manager 610 (or another such system or service) in this example can also act as a virtual layer for hardware and software components, which, in addition to management actions, also handles control functions, such as provisioning, expansion, replication, etc. The resource manager can utilize dedicated APIs in the interface layer 608, each of which can be provided to receive a request for at least one specific action performed on the data environment, such as provisioning, expansion, cloning, or dormant instances. Upon receiving a request for one of the APIs, the Web service portion of the interface layer can parse or otherwise analyze the request to determine the steps or actions required to act on or process the call. For example, a Web service call can be received that includes a request to create a data repository.

[0067] The interface layer 608 in at least one embodiment includes a set of scalable user-oriented servers that can provide various APIs and return appropriate responses according to the API specifications. The interface layer can also include at least one API service layer, which in one embodiment is composed of stateless, replicated servers that handle external user APIs. The interface layer can be responsible for Web service front-end features, such as authenticating users based on credentials, authorizing users, limiting user requests to API servers, verifying user input, and marshaling or unmarshaling requests and responses. The API layer can also be responsible for responding to API calls, reading and writing database configuration data from the management data repository. In many embodiments, the Web service layer and / or the API service layer will be the only externally visible component, or the only component visible to and accessible to users of the control service. The servers of the Web service layer can be stateless and can be horizontally expanded, as is well known in the art. The API server and the persistent data repository can be spread across multiple data centers in a region, for example, so that the server can withstand single data center failures.

[0068] Various embodiments can also be implemented in a variety of operating environments, which in some cases can include one or more user computers or computing devices that can be used to operate any of many applications. User or client devices can include any of many general-purpose personal computers, such as desktops or laptops running standard operating systems, and cellular, wireless and handheld devices running mobile software and capable of supporting many network and messaging protocols. Such systems can also include many workstations running any of a variety of commercial operating systems and other known applications for purposes such as development and database management. These devices can also include other electronic devices, such as virtual terminals, thin clients, gaming systems and other devices capable of communicating over a network.

[0069] Most embodiments utilize at least one network familiar to those skilled in the art to support communications using a variety of commercially available protocols such as TCP / IP, FTP, UPnP, NFS, and CIFS. The network can be, for example, a local area network, a wide area network, a virtual private network, the Internet, an intranet, an extranet, a public switched telephone network, an infrared network, a wireless network, and any combination thereof. In embodiments utilizing a Web server, the Web server can run any of a variety of server or middle-tier applications, including HTTP servers, FTP servers, CGI servers, data servers, Java servers, and business application servers. One or more servers can also execute programs or scripts in response to requests from user devices, such as by executing one or more Web applications, which can be implemented as one or more scripts or programs, which can be written in any programming language, such as C, C# or C++ or any scripting language such as Perl, Python or TCL, and combinations thereof. The server may also include a database server, including but not limited to and Those commercially available database servers.

[0070] The environment may include various data repositories and other memories and storage media as discussed above. They may reside in various locations, such as on a storage medium local to one or more computers (and / or reside therein), or on a storage medium remote from any or all computers via a network. In a specific set of embodiments, information may reside in a storage area network (SAN) familiar to those skilled in the art. Similarly, any file required to perform functions attributed to a computer, server, or other network device may be stored locally and / or remotely as appropriate. When the system includes a computerized device, each such device may include hardware elements that may be electrically coupled via a bus, including, for example, at least one central processing unit (CPU), at least one input device (e.g., a mouse, keyboard, controller, touch display element, or keypad), and at least one output device (e.g., a display device, printer, or speaker). Such a system may also include one or more storage devices, such as disk drives, optical storage devices, and solid-state storage devices, such as random access memory (RAM) or read-only memory (ROM), as well as removable media devices, memory cards, flash memory cards, etc. Such a device may also include a computer-readable storage medium reader, a communication device (e.g., a modem, a network card (wireless or wired), an infrared communication device), and a working memory as described above. A computer-readable storage medium reader may be connected to a computer-readable storage medium, or configured to receive a computer-readable storage medium, which represents a remote, local, fixed and / or removable storage device and a storage medium for temporarily and / or more permanently containing, storing, transmitting, and retrieving computer-readable information.

[0071] The system and various devices will typically also include many software applications, modules, services or other elements located in at least one working memory device, including operating systems and applications, such as client applications or Web browsers. It should be understood that alternative embodiments may have many variations different from the above-mentioned embodiments. For example, custom hardware and / or specific elements may also be implemented in the form of hardware, software (including portable software, such as applets) or both. In addition, connections with other computing devices such as network input / output devices may be adopted. Storage media and other non-transitory computer-readable media for including code or part of the code may include any suitable media known or used in the art, such as but not limited to volatile and non-volatile, removable and non-removable media for storing information such as computer-readable instructions, data structures, program modules or other data implemented in any method or technology, including RAM, ROM, EEPROM, flash memory or other storage technologies, CD-ROM, digital versatile discs (DVD) or other optical storage, cassettes, tapes, disk storage devices or other magnetic storage devices or any other media that may be used to store required information and accessible by system devices. Based on the disclosure and teachings provided herein, those of ordinary skill in the art will understand other ways and / or methods for implementing various embodiments.

[0072] Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention as set forth in the claims.

Claims

1. A computer-implemented method comprising: transcribing one or more recordings of an interview related to administering a therapy to an individual into one or more transcripts; parsing the one or more transcripts into utterances; Determine the discourse sentiment of individual utterances; as well as Based at least in part on the utterance sentiment, an outcome of the individual's response to the administered therapy is predicted.

2. The computer-implemented method of claim 1 , further comprising: A sentiment score is calculated for the sentiment of the utterance, wherein the sentiment score is indicative of an individual's response to the administered therapy.

3. The computer-implemented method of claim 1 , wherein: For treatment-resistant depression, predicting a response to the administered therapy.

4. The computer-implemented method of claim 1 , further comprising: Generate one or more records; assigning a sentiment score to a single utterance to determine the sentiment of the utterance; and The session average of the sentiment scores was calculated.

5. The computer-implemented method of claim 4, wherein: The sentiment score includes an arousal score and a valence score associated with a single utterance.

6. The computer-implemented method of claim 1 , wherein: Based at least in part on one or more machine learning models, a response to the administered therapy is predicted.

7. A computing system comprising: computing device processor; and a memory device comprising instructions that, when executed by a processor of the computing device, enable the computing system to: transcribing one or more recordings of an interview related to administering a therapy to an individual into one or more transcripts; parsing the one or more transcripts into utterances; Determining the utterance sentiment of a single utterance; and Using a machine learning model, predict an outcome of an individual's response to the administered therapy based at least in part on the sentiment of the utterance.

8. The computing system of claim 7, wherein: When the instructions are executed by the computing device processor, the computing system is further capable of: An emotion score for the emotion of the utterance is determined, wherein the emotion score is indicative of an individual's response to the administered therapy.

9. The computing system of claim 7, wherein: For treatment-resistant depression, predicting an individual's response to the administered therapy.

10. The computing system of claim 7, wherein: When the instructions are executed by the computing device processor, the computing system is further capable of: Generate one or more records; assigning a sentiment score to a single utterance to determine the sentiment of the utterance; and The session average of the sentiment scores was calculated.

11. The computing system of claim 10, wherein: The sentiment score includes an arousal score and a valence score associated with a single utterance.

12. The computing system of claim 7, wherein: Based at least in part on one or more machine learning models, a response to the administered therapy is predicted.

13. The computing system of claim 7, wherein: The sentiment of the utterance is determined using a classifier built on a large language model.

14. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to: transcribing one or more recordings of an interview related to administering a therapy to an individual into one or more transcripts; parsing the one or more transcripts into utterances; Determine the discourse sentiment of individual utterances; as well as Based at least in part on the sentiment of the utterance, a response of the individual to the administered therapy is predicted.

15. The non-transitory computer readable medium of claim 14, wherein: When the instructions are executed by at least one processor, the instructions cause the at least one processor to further: An emotion score for the emotion of the utterance is determined, wherein the emotion score is indicative of an individual's response to the administered therapy.

16. The non-transitory computer readable medium of claim 14, wherein: For treatment-resistant depression, predicting an individual's response to the administered therapy.

17. The non-transitory computer readable medium of claim 14, wherein: When the instructions are executed by at least one processor, the instructions cause the at least one processor to further: Generate one or more records; assigning a sentiment score to a single utterance to determine the sentiment of the utterance; and The session average of the sentiment scores was calculated.

18. The non-transitory computer readable medium of claim 17, wherein: The sentiment score includes an arousal score and a valence score associated with a single utterance.

19. The non-transitory computer readable medium of claim 14, wherein: Based at least in part on one or more machine learning models, a response to the administered therapy is predicted.

20. The non-transitory computer readable medium of claim 14, wherein: The sentiment of the utterance is determined using a classifier built on a large language model.

Images