Predicting response to psilocybin therapy for treatment-resistant depression

Abstract

[0006] Techniques for predicting response to an administered therapy are provided. One or more audio recordings associated with the administered therapy may be transcribed into one or more transcripts. The transcripts may be parsed into utterances. A speech sentiment may be determined for each utterance, and response to the administered therapy may be predicted based at least in part on the speech sentiment.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] [1] This application claims priority to and benefit of U.S. Provisional Application No. 63 / 392,451, filed July 26, 2022, entitled "PSILOCYBIN THERAPY FOR TREATMENT RESISTANT DEPRESSION," and U.S. Provisional Application No. 63 / 414,769, filed October 10, 2022, entitled "PSILOCYBIN THERAPY FOR TREATMENT RESISTANT DEPRESSION," the entire disclosures of which are incorporated herein by reference in their entirety for all purposes. [Background technology]

[0002] [2] Therapeutic administration of psychedelic drugs has shown significant potential in both historical reports and recent clinical trials for the treatment of depression and other mood disorders. For example, recent studies have shown promising results when using psilocybin formulations in patients with treatment-resistant depression (TRD). However, while promising, such treatments may only work for a portion of the population, and early prediction of outcome is an important goal of treatment.

[0003] [3] Various embodiments according to the present disclosure are described with reference to the following drawings: [Brief explanation of the drawings]

[0004] [Figure 1] [4] illustrates an example sentiment plot that can be utilized in accordance with various embodiments. [Figure 2] [5] illustrates example methods that can be utilized to implement one or more aspects of various embodiments. [Figure 3] [6] illustrates example methods that can be utilized to implement one or more aspects of various embodiments. [Figure 4][7] illustrates components of an exemplary computing device that can be utilized in accordance with various embodiments. [Figure 5] [8] illustrates an example environment for implementing aspects according to various embodiments. [Figure 6] [9] illustrates components of another illustrative environment in which aspects of various embodiments may be implemented. DETAILED DESCRIPTION OF THE INVENTION

[0005]

[10] Various factors may be considered when predicting a patient's potential response to therapy. For example, when combining the patient's and therapist's average linguistic sentiment scores during post-medication psychological support or integration sessions, a machine learning model may be adapted to predict with high fidelity therapeutic response for participants at both future and future time points. These techniques 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 psychedelic therapy.

[0006]

[11] In the following description, various embodiments are described. For purposes of explanation, specific configurations and details are set forth to provide a thorough understanding of the embodiments. However, it will be apparent to one skilled in the art that the embodiments may be practiced without the specific details. Additionally, well-known features may be omitted or simplified so as not to obscure the described embodiments.

[0007]

[12] Systems and methods are provided for predicting response to an administered therapy. One or more scores corresponding to an individual's reported outcomes associated with the administered therapy may be received. One or more audio recordings associated with the administered therapy may be transcribed into one or more transcripts. The transcripts may be parsed into speech. A speech sentiment may be determined for each utterance, and a response to the administered therapy may be predicted based at least in part on the score and the speech sentiment.

[0008]

[13] Major depressive disorder (MDD) is a debilitating illness that may affect one in six adults in their lifetime. MDD may be characterized by at least one depressive episode lasting at least two weeks and accompanied by significant changes in mood, cognition, and the ability to experience pleasure. While MDD can be effectively managed using psychotherapy and / or pharmacological treatment, some MDD patients may fail to respond to treatment despite multiple attempts. Such individuals may be referred to as patients with treatment-resistant depression (TRD). While various treatment options exist, they are often deemed inadequate. Therefore, there is a need for the development of alternative therapeutic options for TRD patients with improved efficacy. Additionally, acceptability of the condition or treatment may remain a significant challenge for such patients.

[0009]

[14] Psilocybin is a tryptamine alkaloid, and its potential as an effective antidepressant has been preliminarily studied in patients with life-threatening cancer, MDD, and TRD. In at least one psilocybin study using a 25 mg dose of COMP360, a set of participants experienced a reduction in depressive symptoms for as long as 12 weeks. While very promising, these results indicate that durable psilocybin responses occur in only a fraction of the TRD population. Weeks can pass during which potential opportunities for additional treatment are potentially wasted.

[0010]

[15] Figure 1 illustrates an example sentiment plot 100 that can be utilized in accordance with 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 consider various factors, including patient and therapist sentiment scores, the participant's or patient's treatment arm (dosage), and a measure of the participant's or patient's and therapist's average linguistic sentiment during an integrated session at least one day after dosing.

[0011]

[16] In some embodiments, predictive models may be utilized to predict which participants will be responders, sustained responders, and relaxed sustained responders using information available immediately after treatment. Machine learning models may be utilized to help predict patient response. In illustrative embodiments, the machine learning models may consider additional exogenous variables, including, but not limited to, values ​​summarizing the participant's or patient's sentiment during the integrated session and values ​​summarizing the therapist's sentiment during the integrated session.

[0012]

[17] At least one day after the first psilocybin dose, the patient or participant may have an integrated session with the therapist to discuss their initial response to treatment. Audio recordings of the integrated session may be collected and transcribed into dialogue text, either manually or through the use of natural language processing (NLP) techniques. The transcript may then be parsed into individual “utterances” that are used to estimate session sentiment for the therapist and patient or participant using a sentiment model. Such a model may generate valence and arousal scores for each utterance. As shown in FIG. 1, arousal scores 110 and valence scores 120 may be represented on a sentiment plot 100. Individual circles, such as circle 130, may represent utterances from the session, and the size of the circles may reflect the relative length of the utterances. Circled “Xs,” such as element 140, may mark the average sentiment value of all utterances during the session. Sentiment plots may be specific to a patient or therapist. The valence score may correspond to the positive or negative score used in sentiment analysis. The arousal score may characterize where the utterance falls on a spectrum, such as bored or calm, tense, alert, or excited. The score may indicate the average sentiment of the utterances spoken by the patient or participant and therapist during the integration session.

[0013]

[18] In at least some embodiments, audio may be parsed and tagged into utterances. The audio may be processed using a model to predict the patient's tone of voice. In some embodiments, the audio may be correlated with a score indicative of the patient's tone of voice. The audio score may be compared to valence and arousal scores, or the audio score may be considered together with the valence and arousal scores. A classifier built on a Bidirectional AutoRegressive Transformer (BART) autoencoder and a Multi-Genre Natural Language Inference (MNLI) dataset may be used to calculate sentiment valence and arousal scores.

[0014]

[19] Figure 2 illustrates an example method 200 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 integrated session between a patient or participant and a healthcare 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 a set of utterances 220. A sentiment score can be assigned or determined for each utterance in the set 230. A session average of the sentiment scores can be calculated. The averaged sentiment score can be utilized to predict the patient's response to treatment.

[0015]

[20] Prior to a psychological support session with a therapist or healthcare provider, the patient or participant may provide written consent indicating consent to being recorded during the session. The session may be recorded using any device equipped with a microphone. In some embodiments, the recording device may be pre-configured with a secure cloud storage account. Once recordings are completed, they may be automatically uploaded to the configured storage account. Quality assurance checks may be performed to ensure that metadata about each recording is accurate, and the recordings may be made available for transcription.

[0016]

[21] 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 mentioned, transcripts may be reviewed for quality assurance prior to analysis. After converting the audio recordings to text, individual transcripts may be parsed into utterances. In some embodiments, punctuation in the transcripts may be used as a guide. According to one or more embodiments, a trained large-scale language model may be used to help score the utterances. For example, the model may analyze individual sentences parsed and constructed with text that may be recognizable by the model to generate a score.

[0017]

[22] In NLP, an "utterance" may be defined as a group of spoken words preceded and followed by a pause. In contrast, a "sentence" may refer to a group of words that express a complete thought. According to one or more embodiments described herein, an "utterance" may be an amalgamation of the two. For example, if a sentence occurs across several utterances, the utterances may be combined to form a single utterance. Alternatively, if an utterance includes several sentences, each sentence may be extracted and treated as an independent utterance.

[0018]

[23] Additional processing steps may occur after transcription. For example, Unicode characters may be converted to ASCII characters. Organized information such as names may be replaced with non-personally identifiable substitutes (e.g., Jane / John Doe). According to another illustrative embodiment, transcription comments may be replaced with text familiar to the model. For example, the transcription note "[LAUGHING]" may be replaced with "haha" so that the model can better recognize the term and use it in generating a score.

[0019]

[24] Sentiment analysis of a text fragment can involve scoring the text as positive or negative. Text can be scored on two dimensions: emotional valence (e.g., positivity) and arousal (e.g., energy or activation). In this way, sentiment can capture intensity rather than simply positivity or negativity. Sentiment scores of text fragments can be distinguishable from attempts to infer a speaker's emotional state. For example, text stating "I love broccoli" can be scored as positive by a traditional sentiment model. However, if spoken harshly, the text may suggest a negative attitude toward broccoli. Additionally, text stating "I love broccoli" can be ranked as 97% positive in one model, while text stating "I like broccoli" can be ranked as 98% positive in the same model. The similarity in positivity scores may be a result of treating the sentiment analysis problem as a classification problem and not considering intensity, in which case the model may only care about whether the "positive" or "negative" label is correct.

[0020]

[25] A two-dimensional emotion model may plot emotions in an x-y plane, where the x value represents valence (e.g., positivity) and the y value represents arousal (e.g., energy or activation). Examples of high-valence emotions, according to illustrative embodiments, may include "giddy," "happy," "content," and "serene." Examples of low-valence emotions, according to illustrative embodiments, may include "fear," "nervousness," "sadness," and "boredom." Examples of high-arousal emotions, according to illustrative embodiments, may include "tense," "alarmed," "astonished," and "excited." Examples of low-arousal emotions, according to illustrative embodiments, may include "bored," "droopy," "tired," and "sleepy."

[0021]

[26] In some illustrative embodiments, a classifier may be utilized to calculate sentiment valence and arousal scores. Such a classifier may be built on the BART autoencoder and the MNLI (Multi-Genre Natural Language Inference) dataset. The use of a model built on a larger model may enable the use of nearly unlimited freely available data for smaller data tasks. BART is a deep learning model designed to reconstruct corrupted text. It was trained on a large corpus of books and online content. Fine-tuning BART on the MNLI dataset may result in a classifier for any given class. For example, a user can specify a list of classes and submit a fragment of text to be classified. Text stating "I love broccoli" may be submitted to be classified into the classes "food" and "politics," where the model may indicate, for example, that there is a 99.8% probability that this text is about food and a 0.2% probability that this text is about politics.

[0022]

[27] According to one or more embodiments described herein, for each utterance, the model may be used to score the likelihood that the utterance will belong to one of four classes: "happy," "angry," "gloomy," and "calm." This example utilizes the aforementioned classes, but other classes indicative of sentiment may be utilized. For a given utterance, the model may provide scores for each class. The scores, in an illustrative embodiment, may be positive numbers that sum to 1. Valence-arousal score pairs may be assigned to the classes, and the scores may then be utilized to plot points in a two-dimensional emotional plane.

[0023]

[28] For example, for a given set of classes (class 1, class 2, class 3, class 4), the model may determine a score for class 1 as (1,1), a score for class 2 as (-1,1), a score for class 3 as (-1,-1), and a score for class 4 as (1,-1). In some embodiments, classes 1 and 2 may be paired with respect to sentiment (e.g., "happy" and "angry"), and classes 3 and 4 may be paired (e.g., "depressed" and "calm"). The point (emotional valence (utterance), arousal (utterance)) for a given utterance u may then be defined as a convex combination of the points (1,1), (-1,1), (1,-1), and (1,1): (Emotional valence (utterance), arousal level (utterance)) = P u (Class 1)(1,1)+P u (Class 2)(-1,1)+P u (Class 3)(-1,-1)+P u (Class 4)(1,-1) (Equation 1) Similarly, Emotional valence (u) = P u (Class 1)-P u (Class 2)-P u (Class 3)+P u (Class 4) (Formula 2) and, Arousal level (u) = P u (Class 1)+Pu (Class 2)-P u (Class 3)-P u (Class 4) (Formula 3)

[0024]

[29] These equations may result in points lying within a two-dimensional square with corners at (±1, ±1). In an illustrative embodiment, one or more points may be plotted within a two-dimensional square such as that shown in FIG.

[0025]

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

[0026]

[31] To determine a session sentiment score, a 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.) can be assigned a probability scale, where the scale for a given utterance is proportional to the number of words in the utterance. From this, an average valence score and an arousal score can be obtained.

[0027] Response to the administered therapy may be predicted based at least in part on the EBI summary score and the determined value. 250 In some embodiments, a machine learning model may be utilized to predict whether a participant or patient will be a responder, a relaxed sustained responder, or a sustained responder to a treatment or therapy. In some illustrative embodiments, treatment or therapy may refer to administration of psilocybin. In some illustrative embodiments, a responder may be defined as a patient whose primary outcome measure score 3 weeks after the date of therapy administration is reduced by at least 50% compared to the 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., weeks 3, 6, 9, and 12). A relaxed 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., weeks 3 and 12) and one of the weeks in between (e.g., week 6 or week 9). This definition of "responder" is not intended to be limiting, and other definitions of "responder" may be utilized.

[0028]

[33] The machine learning model may utilize the patient's or participant's EBI score, treatment dosage, and sentiment metrics from the transcript of the first integrated session the day after treatment. The machine learning model may be fitted to the full dataset to ensure that the selected model provides an adequate fit. Leave-one-out (LOO) cross-validation may be performed to evaluate the predictive power of the machine learning model. For example, a model may be fitted to all participants or patients except one, and the model may be used to predict the responder status of the excluded participant. In some illustrative embodiments, the model may be trained on existing data and used to predict the responder status of new patients.

[0029]

[34] In some illustrative 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, therapy session sentiment scores may be normalized to have a mean of zero and a standard deviation of 1.

[0030]

[35] For any process herein, unless otherwise specified, it should be understood that there may be additional, fewer, or alternative steps performed in a similar or alternative order, or in parallel, within various embodiments.

[0031]

[36] Figure 3 illustrates an example method 300 that can be utilized to implement one or more aspects of various embodiments. An audio recording of an initial integrated session between a patient and a healthcare provider may be generated and received (310). Using one or more NLP techniques, the recording may be transcribed into text 320, and the text may be parsed to generate a set of utterances 330. A sentiment score may be assigned or determined for each utterance in the set 340. A session average of the sentiment scores may be calculated 350. The averaged sentiment score may be utilized to predict the patient's response to treatment.

[0032]

[37] 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 mentioned, transcripts may be reviewed for quality assurance prior to analysis. After converting the audio recordings to text, individual transcripts may be parsed into utterances. In some embodiments, punctuation in the transcripts may be used as a guide. According to one or more embodiments, a trained large-scale language model may be used to help score the utterances.

[0033]

[38] In NLP, an "utterance" may be defined as a group of spoken words preceded and followed by a pause. In contrast, a "sentence" may refer to a group of words that express a complete thought. According to one or more embodiments described herein, an "utterance" may be an amalgamation of the two. For example, if a sentence occurs across several utterances, the utterances may be combined to form a single utterance. Alternatively, if an utterance includes several sentences, each sentence may be extracted and treated as an independent utterance.

[0034]

[39] Additional processing steps may occur after transcription. For example, Unicode characters may be converted to ASCII characters. Organized information such as names may be replaced with non-personally identifiable substitutes (e.g., Jane / John Doe). According to another illustrative embodiment, transcription comments may be replaced with text familiar to the model. For example, the transcription note “[laughing]” may be replaced with “haha” so that the model can better recognize the term and use it in generating a score.

[0035]

[40] Sentiment analysis of a text fragment can involve 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 simply positivity or negativity. Sentiment scores of text fragments can be distinguishable from attempts to infer a speaker's emotional state. For example, text stating "I love broccoli" can be scored as positive by a traditional sentiment model. However, if spoken harshly, the text may suggest a negative attitude toward broccoli. Additionally, text stating "I love broccoli" can be ranked as 97% positive in one model, while text stating "I like broccoli" can be ranked as 98% positive in the same model. The similarity in positivity scores can be a result of the sentiment analysis problem being treated as a classification problem and not considering intensity. In such cases, the model may only care about whether the "positive" or "negative" label is correct.

[0036]

[41] A two-dimensional emotion model may plot emotions in an x-y plane, where the x value represents valence (e.g., positivity) and the y value represents arousal (e.g., energy or activation). Examples of high-valence emotions, according to illustrative embodiments, may include "ecstatic," "happy," "contented," and "calm." Examples of low-valence emotions, according to illustrative embodiments, may include "fearful," "nervous," "sad," and "bored." Examples of high-arousal emotions, according to illustrative embodiments, may include "tense," "alert," "startled," and "excited." Examples of low-arousal emotions, according to illustrative embodiments, may include "disgusted," "depressed," "fatigued," and "sleepy."

[0037]

[42] In some illustrative embodiments, a classifier may be utilized to calculate sentiment valence and arousal scores. Such a classifier may be built on the BART autoencoder and the MNLI (Multi-Genre Natural Language Inference) dataset. The use of a model built on a larger model may enable the use of nearly unlimited freely available data for smaller data tasks. BART is a deep learning model designed to reconstruct corrupted text. BART was trained on a large corpus of books and online content. Fine-tuning BART on the MNLI dataset may result in a classifier for any given class. For example, a user can specify a list of classes and submit a fragment of text to be classified. Text stating "I love broccoli" may be submitted to be classified into the classes "food" and "politics," where the model may indicate, for example, that there is a 99.8% probability that this text is about food and a 0.2% probability that this text is about politics.

[0038]

[43] According to one or more embodiments described herein, for each utterance, the model may be used to score the likelihood that the utterance will belong to one of four classes: "happy," "angry," "depressed," or "calm." This example utilizes the aforementioned classes, but other classes indicative of sentiment may be utilized. For a given utterance, the model may provide scores for each class. The scores, in an illustrative embodiment, may be positive numbers that sum to 1. Valence-arousal score pairs may be assigned to the classes, and the scores may then be utilized to plot points in a two-dimensional emotional plane.

[0039] 44 Computing resources, such as servers, that can have software and / or firmware updated in such a manner typically include at least a set of standard components configured for general-purpose operation, although various proprietary components and configurations can also be used within the scope of various embodiments. FIG. 4 illustrates components of an exemplary computing device 400 that can be utilized in accordance with various embodiments. As is known for computing devices, a computer will have one or more processors 402, such as a central processing unit (CPU), graphics processing unit (GPU), and the like, electronically and / or communicatively coupled to various components using various buses, traces, and other such mechanisms. The processor 402 can include memory registers 406 and cache memory 404 for holding instructions, data, and the like. In this example, a chipset 414, which in some embodiments can include a northbridge and a southbridge, in cooperation with various system buses, can connect the processor 402 to components such as system memory 416 in the form of physical RAM or ROM, which can include code for an operating system and various other instructions and data utilized for operation of the computing device. The computing device may also include or communicate with one or more storage devices 420, such as a hard drive, flash drive, optical storage, and the like, for persisting data and instructions similar to or in addition to those 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.), where those components may include a communication device 424, such as a cellular modem or network card, media components 426, such as a graphics card and audio components, and a peripheral interface 430 for connecting peripheral devices such as printers, keyboards, and the like.At least one cooling fan 432 or other such temperature regulation or temperature reduction component may also be included, which may be driven by the processor or may be triggered by various other sensors or components on the device or remote from the device. Various other or alternative components and configurations may be utilized as well as those known in the art for computing devices.

[0040]

[45] At least one processor 402, in some embodiments, can retrieve data from physical memory 416, such as dynamic random access memory (DRAM) modules, via a coherency fabric. It should be understood that various architectures, including various selections, numbers, and arrangements of buses and bridges, can be utilized for such computing devices within the scope of various embodiments. Data in memory can be managed and accessed by a memory controller, such as a DDR controller, through the coherency fabric. Data can, in at least some embodiments, be temporarily stored in 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 can be an I / O controller for each type of I / O device, such as a universal serial bus (USB) device, data storage (e.g., flash or disk storage), a network card, a peripheral component interconnect express (PCIe) card or interface 430, a communications device 424, a graphics or audio card 426, and a direct memory access (DMA) card, among other such options. In some embodiments, components such as a processor, controller, and cache may be configured on a single card, board, or chip (i.e., a system-on-chip implementation), while in other embodiments, at least some of the components may be located in different locations, etc.

[0041]

[46] An operating system (OS) running on the processor 402 can help manage various devices that may be utilized to provide input to be processed. This may include, for example, utilizing associated device drivers to enable interaction with various I / O devices, where those devices may be related to data storage, device communications, user interfaces, and the like. The various I / O devices will typically connect via various device ports and communicate with the processor and other device components through one or more buses. There may be specific types of buses that provide communications according to specific protocols, such as Peripheral Component Interconnect (PCI) or Small Computer System Interface (SCSI) communications, among other such options. Communication may occur using registers associated with each port, including registers such as data-in and data-out registers. Communication may also occur using memory-mapped I / O, where a portion of the processor's address space is mapped to a particular device and data is written directly to and from that portion of the address space.

[0042]

[47] Such devices may be used, for example, as servers in a server farm or data warehouse. Server computers often need to perform tasks outside the environment of the CPU and main memory (i.e., RAM). For example, a server may need to communicate with external entities (e.g., other servers) or process data using an external processor (e.g., a general-purpose graphical processing unit (GPGPU)). In such cases, the CPU may interface with one or more I / O devices. In some cases, these I / O devices may be dedicated hardware designed to fulfill a specific role. For example, an Ethernet network interface controller (NIC) may be implemented as an application-specific integrated circuit (ASIC) comprising digital logic operable to send and receive packets.

[0043] In an exemplary embodiment, a host computing device is associated with various hardware and software components and their respective configurations that facilitate the execution of I / O requests. One such component is an I / O adapter, which 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 emulated components and communication channels. In another aspect, the I / O adapter device can include an embedded microprocessor to enable the I / O adapter device to execute computer-executable instructions related to implementing management functions or managing one or more such management functions, or 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 components in the host device other than the I / O adapter device. In some embodiments, the I / O adapter device is attached external to the host device. In some embodiments, the I / O adapter device is internally integrated into the host device. Also in communication with the I / O adapter device may be an external communication port component for establishing a communication channel between the host device and one or more network-based services or other network-attached or direct-attached computing devices. Illustratively, the external communication port component may correspond to a network switch, sometimes known 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 the host device and one or more services, such as health check services, financial services, and the like.

[0044]

[49] The I / O adapter device may also communicate with a basic input / output system (BIOS) component. The BIOS component may include non-transitory executable code, often referred to as firmware, that can be executed by one or more processors and used to cause components of the host device to initialize and identify system devices such as a video display card, keyboard and mouse, hard disk drive, optical disk drive, and other hardware. The BIOS component may also include or host boot loader software utilized to boot the host device. For example, in one embodiment, the BIOS component may include executable code that, when executed by a processor, causes the host device to attempt to host pre-boot execution environment (PXE) boot software. Additionally, the BIOS component may include or benefit from hardware latches electrically controlled by the I / O adapter device. The hardware latches may restrict access to one or more aspects of the BIOS component, such as controlling modification or configuration of executable code maintained in the BIOS component. The BIOS component may be connected to (or communicate with) several additional computing device resource components, such as a processor, memory, and the like. In one embodiment, resource components of such a computing device may be physical computing device resources that communicate with other components via communication channels. The communication channels may correspond to one or more communication buses over which 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 PCI Express bus, etc. Other types of communication channels, media, buses, or protocols (e.g., an Ethernet communication protocol) may also be utilized.Additionally, in other embodiments, one or more of the resource components of the computing device may be virtualized hardware components emulated by the host device. In such embodiments, 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 criteria. The resource components of the computing device may communicate with the I / O adapter device through a communication channel. In addition, the communication channel may connect the PCI Express device to the CPU through a northbridge or host bridge, among other such options.

[0045] Communicating with the I / O adapter device via 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. Like a BIOS component, the controller component may include or benefit from hardware latches that are electronically controlled by the I / O adapter device. The hardware latches may restrict access to one or more aspects of the controller component. Illustratively, the hardware latches may be controlled together or independently. For example, an I / O adapter device may selectively close hardware latches for one or more components based on a trust level associated with a particular user. In another example, an I / O adapter device may selectively close hardware latches for one or more components based on a trust level associated with a creator or distributor of executable code to be executed by the I / O adapter device. In a further example, an I / O adapter device may selectively close hardware latches for one or more components based on a trust level associated with the component itself. A host device may also include additional components that communicate with one or more of the illustrative components associated with the host device. Such components may include devices such as one or more controllers combined with one or more peripheral devices, such as hard disks or other storage devices. Additionally, 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 component. As mentioned above, in one embodiment, the hardware latches may be controlled together or independently.

[0046] As discussed, different approaches can be implemented in various environments according to the described embodiments. For example, FIG. 5 illustrates an example environment 500 for implementing aspects according to various embodiments. As will be appreciated, while a web-based environment is used for illustrative purposes, different environments may be used to implement various embodiments, as appropriate. The system includes an electronic client device 502, which may include any suitable device operable to send and receive requests, messages, or information over a suitable network 504 and return information to a user of the device. Examples of such client devices include personal computers, mobile phones, handheld messaging devices, laptop computers, set-top boxes, personal digital assistants, e-book readers, and the like. Examples of such recipients or users may include healthcare providers, including therapists, or patients. The network may include any suitable network, including an intranet, the Internet, a cellular network, a local area network, or any other such network, or combinations thereof. The components used in such a system may depend at least in part on the type of network and / or environment selected. Protocols and components for communicating over such networks are well known and will not be discussed in detail herein. Communication over the network can be enabled via wired or wireless connections, and combinations thereof. In this example, the network includes the Internet and the environment includes a web server 506 for receiving requests and providing content in response thereto, although in other networks, alternative devices that serve similar purposes can be used, as will be apparent to those skilled in the art.

[0047]

[52] The exemplary environment includes at least one application server 508 and a data store 510. It should be understood that there may be several application servers, layers, or other elements, processes, or components, which may be chained or otherwise configured, that can interact to perform tasks, such as retrieving data from an appropriate data store. As used herein, the term "data store" 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 integrate with the data store 510 as needed to run aspects of one or more applications for client devices and may include any suitable hardware and software for handling much of the data access and business logic for the applications. The application server may cooperate with the data store to provide access control services and generate content, such as text, graphics, audio, and / or video, to be transmitted to users, which in this example may be served to users by the web server 506 in the form of HTML, XML, or another suitable structured language. Handling of all requests and responses, as well as delivery of content between client device 502 and application server 508, can be handled by web server 506. It should be understood that the structured code discussed herein can be executed on any suitable device or host machine, as discussed elsewhere herein, and thus a web server and application server are not required and are merely illustrative components.

[0048]

[53] The data store 510 may include several separate data tables, databases, or other data storage mechanisms and media for storing data related to particular aspects. For example, the illustrated data store includes mechanisms for storing biomarker data (e.g., production data) 512 and user information 516, which can be used to serve content to the production side. The data store is also shown to include mechanisms for storing log or session data 514. It should be understood that there may be many other aspects that may need to be stored in the data store, 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 store 510, as appropriate. The data store 510, through its associated logic, is operable to receive instructions from the application server 508 and, in response, retrieve, update, or otherwise process data. In one example, a user may submit a search request for a particular type of item. In this case, the data store may access the user information to verify the user's identity and may access catalog details to obtain information about that type of item. The information can then be returned to the user, such as through a patient or therapist portal containing biomarker and diagnostic data accessible through web pages that the user can view via a browser on the user device 502. Information about particular items of interest can be viewed in dedicated pages or windows in the browser.

[0049]

[54] 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 that stores instructions that, when executed by the server's processor, enable the server to perform its intended functions. Suitable implementations for server operating systems and general functions are known or commercially available, and will be readily implemented by those of skill in the art, especially in light of the disclosure herein.

[0050]

[55] In one embodiment, the environment is a distributed computing environment utilizing several computer systems and components interconnected through communications links, using one or more computer networks or direct connections. However, those skilled in the art will recognize that such a system may operate equally well in a system having fewer or more components than illustrated in Figure 5. For this reason, the illustration of system 500 in Figure 5 should be construed as being exemplary in nature and not limiting on the scope of the present disclosure.

[0051]

[56] Figure 6 illustrates an example environment 600 in which aspects of various embodiments can be implemented. In this example, a user can utilize a client device 602 to submit requests to a multi-tenant resource provider environment 606 over at least one network 604. A client device can include any suitable electronic device operable to send and receive requests, messages, or other such information over an appropriate network and return information to a user of the device. Examples of such client devices include personal computers, tablet computers, smartphones, notebook computers, and the like. The at least one network 604 can include any suitable network, including an intranet, the Internet, a cellular network, a local area network (LAN), or any other such network or combination, and communication through the network can be enabled via wired and / or wireless connections. The resource provider environment 606 can include any suitable components for receiving requests and returning information or performing actions in response to those requests. By way of example, the provider environment may include web servers and / or application servers for receiving and processing requests and then returning data, web pages, video, audio, or other such content or information in response to the request.

[0052]

[57] In various embodiments, a provider environment may include various types of resources that can be utilized by multiple users for a variety of different purposes. As used herein, computing resources 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, and the like, which may perform tasks such as receiving, transmitting, and / or processing data and / or executable instructions. In at least some embodiments, all or a portion of a given resource or set of resources may be allocated to a particular user or allocated for a particular task, at least for a determined period of time. The sharing of these multi-tenant resources from a provider environment is often referred to as resource sharing, web services, or “cloud computing,” among other such terms, depending on the particular 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, application servers operable to process instructions provided by users or database servers operable to process data stored in one or more data stores 616 in response to user requests. As is known for such purposes, users may also reserve at least a portion of the data storage in a given data store. Methods for enabling users to reserve various resources and resource instances are well known in the art, and as such, a detailed description of the entire process, and a description of all possible components, will not be discussed in detail herein.

[0053]

[58] In at least some embodiments, a user desiring to utilize a portion of a resource 614 can submit a request that is received at an interface layer 608 of the provider environment 606. The interface layer may include an application programming interface (API) or other exposed interface that allows 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, routing component, load balancer, and the like. When a request to provision a resource is received at the interface layer 608, information about the request may be directed to a service manager 610 or other such system, service, or component configured to manage user accounts and information, resource provisioning and usage, and other such aspects. The service manager 610 that receives the request may perform tasks such as authenticating the identity of the user submitting the request and determining whether the user has an existing account with the resource provider, where the account data may be stored in at least one account data store 612 in the provider environment. The user may provide any of various types of credentials to authenticate the user's identity 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 can verify this information against information stored for the user. If the user has an account with the appropriate permissions, status, etc., the resource manager can determine whether there are sufficient resources available to meet the user's request, and if so, can provision resources for the user's use in the amount specified by the request, or otherwise grant access to the corresponding portion of those resources.This amount may include, for example, a capacity to process a single request or perform a single task, a specified time period, or a repeatable / renewable period, among other such values. If the user does not have a valid account with the provider, the user account does not allow access to the type of resource specified in the request, or another such reason prevents the user from gaining access to such resource, a communication may be sent to the user to enable the user to create or modify an account or change the resource specified in the request, among other such options.

[0054]

[59] Once a user is authenticated, their account is verified, and resources are allocated, the user can utilize the allocated resource(s) for a specified capacity, data transfer amount, time period, or other such value. In at least some embodiments, the user may provide a session token or other such credential with subsequent requests to enable those requests to be processed on that user session. The user may receive a resource identifier, specific address, or other such information that can enable the client device 602 to communicate with the allocated resource without having to communicate with the service manager 610, at least until such time as relevant aspects of the user account change, the user is no longer authorized to access the resource, or another such aspect changes.

[0055]

[60] The service manager 610 in this example (or another such system or service) can also function as a virtual layer of hardware and software components that handles control functions in addition to management actions, such as may include provisioning, scaling, replication, etc. The resource manager can utilize dedicated APIs in the interface layer 608, where each API can be provided to receive requests for at least one specific action to be performed with respect to the data environment, such as provisioning, scaling, cloning, or hibernating an instance. Upon receiving a request for one of the APIs, the web services portion of the interface layer can parse or otherwise analyze the request to determine the steps or actions needed to act on or process the call. For example, a web services call can be received that includes a request to create a data repository.

[0056]

[61] The interface layer 608 in at least one embodiment includes a scalable set of user-facing servers that can offer various APIs and return appropriate responses based on the API specifications. The interface layer, in one embodiment, can also include at least one API services layer, consisting of stateless replicated servers that handle external-facing user APIs. The interface layer can be responsible for web service front-end functions such as authenticating users based on credentials, authorizing users, throttling user requests to the API server, validating user input, and marshalling or unmarshalling requests and responses. The API layer can also be responsible for writing / reading database configuration data to / from a management data store in response to API calls. In many embodiments, the web services layer and / or API services layer will be the only externally visible components or the only components visible to and accessible by users of the control services. The servers in the web services layer are stateless and can be horizontally scaled as known in the art. The API servers and persistent data stores can be distributed across multiple data centers across a region, for example, so that the servers are resilient to a single data center failure.

[0057]

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

[0058]

[63] Most embodiments utilize at least one network known to those skilled in the art to support communications using any of a variety of commercially available protocols, such as TCP / IP, FTP, UPnP, NFS, and CIFS. The network may 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 may run any of a variety of server or middle-tier applications, including an HTTP server, an FTP server, a CGI server, a data server, a Java server, and a business application server. The server(s) may also be capable of executing programs or scripts in response to requests from user devices, such as by running one or more web applications, which may be implemented as one or more scripts or programs written in any programming language, such as Java, C, C#, or C++, or any scripting language, such as Perl, Python, or TCL, and combinations thereof. The server(s) may also include database servers, including, but not limited to, those commercially available from Oracle®, Microsoft®, Sybase®, and IBM®.

[0059]

[64] The environment may include a variety of data stores and other memory and storage media, as discussed above. These may reside in a variety of locations, such as on storage media local to (and / or resident within) one or more of the computers, or remote from any or all of the computers across a network. In a particular set of embodiments, information may reside in a storage area network (SAN) known to those skilled in the art. Similarly, any files necessary to perform functions attributed to a computer, server, or other network device may be stored locally and / or remotely, as appropriate. Where the system includes computerized devices, each such device may include hardware elements that may be electrically coupled via a bus, and the elements may include, for example, at least one central processing unit (CPU), at least one input device (e.g., a mouse, keyboard, controller, touch-sensitive 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), and removable media devices, memory cards, flash cards, etc. Such devices 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 working memory, as described above. A computer-readable storage medium reader may be connected to or configured to receive computer-readable storage media representing remote, local, fixed, and / or removable storage devices, as well as storage media for temporarily and / or more permanently containing, storing, transmitting, and retrieving computer-readable information.

[0060]

[65] The system and various devices will also typically include several software applications, modules, services, or other elements located within at least one working memory device, including an operating system and application programs such as client applications or web browsers. It should be recognized that alternative embodiments may have numerous variations from those described above. For example, customized hardware may also be used, and / or particular elements may be implemented in hardware, software (including portable software such as applets), or both. Additionally, connections to other computing devices, such as network input / output devices, may be used. Storage media and other non-transitory computer-readable media for containing code or portions of 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 implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data, including RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a system device. Based on the disclosure and teachings provided herein, one of ordinary skill in the art will recognize other ways and / or methods for implementing the various embodiments.

[0061]

[66] The specification and drawings are, therefore, 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. 1. A computer-implemented method comprising: transcribing one or more recordings of sessions associated with an administered therapy for the individual into one or more transcripts; parsing one or more of said transcripts into utterances; determining a speech sentiment for each utterance; predicting a response outcome of the individual to the administered therapy based at least in part on the speech sentiment; and 1. A computer-implemented method comprising:

2. calculating a sentiment score for the utterance sentiment; 2. The computer-implemented method of claim 1, further comprising: wherein the sentiment score indicates the individual's response to the administered therapy.

3. The computer-implemented method of claim 1 , wherein the response to the administered therapy is predicted for treatment-resistant depression.

4. generating one or more of said recordings; assigning sentiment scores to each utterance to determine the utterance sentiment; calculating a session average of the sentiment score; The computer-implemented method of claim 1 further comprising:

5. The computer-implemented method of claim 4 , wherein the sentiment scores include an arousal score and a valence score associated with each utterance.

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

7. 1. A computing system comprising: a computing device processor; a memory device containing instructions; wherein the instructions, when executed by the computing device processor, cause the computing system to: transcribing one or more recordings of sessions associated with an administered therapy for the individual into one or more transcripts; parsing one or more of said transcripts into utterances; determining a speech sentiment for each utterance; using a machine learning model to predict a response outcome of the individual to the administered therapy based at least in part on the speech sentiment; A computing system that enables

8. The instructions, when executed by the computing device processor, further cause the computing system to: The computing system of claim 7 , further comprising: determining a sentiment score for the utterance sentiment, the sentiment score indicating the individual's response to the administered therapy.

9. The computing system of claim 7 , wherein the individual's response to the administered therapy is predicted for treatment-resistant depression.

10. The instructions, when executed by the computing device processor, further cause the computing system to: generating one or more of said recordings; assigning sentiment scores to each utterance to determine the utterance sentiment; calculating a session average of the sentiment score; The computing system of claim 7 , wherein the computing system is capable of performing the following:

11. The computing system of claim 10 , wherein the sentiment scores include an arousal score and a valence score associated with each utterance.

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

13. The computing system of claim 7 , wherein the utterance sentiment is determined utilizing a classifier built on a large-scale 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 sessions associated with an administered therapy for the individual into one or more transcripts; parsing one or more of said transcripts into utterances; determining a speech sentiment for each utterance; predicting the individual's response to the administered therapy based at least in part on the speech sentiment; and A non-transitory computer-readable medium for causing

15. The instructions, when executed by at least one of the processors, further cause the at least one processor to:

15. The non-transitory computer-readable medium of claim 14, further comprising determining a sentiment score for the utterance sentiment, the sentiment score indicating a response of the individual to the administered therapy.

16. 15. The non-transitory computer-readable medium of claim 14, wherein the individual's response to the administered therapy is predicted for treatment-resistant depression.

17. The instructions, when executed by at least one of the processors, further cause the at least one processor to: generating one or more of said recordings; assigning sentiment scores to each utterance to determine the utterance sentiment; calculating a session average of the sentiment score; 15. The non-transitory computer-readable medium of claim 14,

18. 20. The non-transitory computer-readable medium of claim 17, wherein the sentiment scores include an arousal score and a valence score associated with each utterance.

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

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

Images