Systems and methods for using machine learning models to select weight loss medications to address obesity

Abstract

Systems and methods are provided herein for using a machine learning model to select a weight loss medication to address obesity. A computing system can receive physiological measurements of a user. The computing system can apply the measurements to a machine learning model. The machine learning model can be trained using a plurality of examples, each example including sample physiological measurements of a sample user and a corresponding sample weight loss medication administered to the sample user. The computing system can generate, for the user, a metric indicative of an expected outcome related to a weight loss medication based on applying the one or more physiological measurements to the machine learning model. The computing system can provide, to a user device associated with the user, a message indicative of the expected outcome related to the weight loss medication. The computing system can improve the effectiveness of medications in addressing obesity.

Description

[0001] Cross-references to related applications

[0002] This application claims priority and benefit to U.S. Patent Application No. 18 / 962,355, filed November 27, 2024, entitled "MACHINE LEARNING ARCHITECTURESTO DETERMINE USER RESPONSIVENESS BASED ON MULTI-MODAL MEASUREMENT DATA", the entire contents of which are incorporated herein by reference. Background Technology

[0003] Obesity is the excessive accumulation of fat associated with weight gain and health risks. This condition can be caused by a variety of underlying factors, such as lifestyle factors, genetics, environmental factors, or medical conditions. Specific potential factors that may contribute to obesity include lifestyle choices (e.g., poor diet, overeating, or lack of physical activity), genetics (e.g., genetic traits), psychological conditions (e.g., depression, stress, anxiety, or binge eating), medical conditions (e.g., hyperthyroidism), certain medications (e.g., steroids or antidepressants), or hormones (e.g., leptin resistance). At the molecular level, in individuals with obesity, the size or number of fat cells (called adipocytes) increases, causing them to store excess energy as fat. Furthermore, hormonal imbalances (such as leptin resistance, where the brain fails to respond effectively to signals about energy storage) may cause individuals to overeat despite high energy storage levels.

[0004] Obesity negatively impacts the mental health, physical health, and social well-being of affected individuals. Obese individuals are at higher risk of various physical health problems, such as cardiovascular diseases (e.g., high blood pressure or heart failure), cardiometabolic disorders (e.g., diabetes), respiratory diseases (e.g., sleep apnea or asthma), or cancers (e.g., kidney, liver, or pancreatic cancer). Obese individuals may also face a host of mental health issues, such as depression, anxiety, social isolation, or chronic stress. The quality of daily life for obese individuals is affected not only by health problems but also by accessibility (e.g., mobility impairments) and economic burden (e.g., medical expenses).

[0005] Certain obesity medications can be administered to individuals in an attempt to promote weight loss. However, even with these medications, side effects exist, making it difficult for users to adhere to their individual prescriptions and subsequently discontinue use. Furthermore, neglecting individual physiological measurements and other relevant information can lead to prescriptions producing a variety of side effects, resulting in user discontinuation of medication and minimal improvement in ultimate health outcomes. Additionally, some individuals may be physiologically more resistant to certain types of obesity medications than others. Administering equally ineffective medications to these individuals may also result in minimal clinical improvement. Medication adherence is a critical determinant of successful weight loss. However, when prescriptions cause a variety of side effects of varying severity, individuals may find it difficult to adhere to their prescriptions and achieve their weight loss goals.

[0006] One approach to addressing medication adherence involves a trial-and-error method. In this method, an individual is prescribed a weight-loss medication, and their response and any side effects are subsequently monitored. However, the trial-and-error method has several drawbacks. First, it involves having an individual start taking one medication, waiting to collect additional data to determine if the medication is effective, and then switching to another medication if the initial prescription is found to be ineffective or have side effects. This can lead to prolonged periods without treatment or suboptimal clinical outcomes for the individual. On the other hand, each new medication carries the potential to cause side effects or adverse events for the individual. Monitoring for side effects or other events adds complexity, requiring frequent checks and data collection. Furthermore, weight-loss medications present unique challenges. Due to differences in genetics, metabolism, baseline body composition, and underlying health conditions, responses to weight-loss medications vary significantly between individuals. This vast variability in individual responses may lead some individuals to discontinue medication use. Summary of the Invention

[0007] To address these and other technical challenges related to adherence to obesity medications, digital therapy applications can utilize machine learning models, as detailed in this paper, that leverage real-time multimodal data from individuals to output expected outcomes for various weight-loss medications, such as side effects, weight loss, and dropout rates. The digital therapy applications detailed in this paper offer several benefits to users. First, they can aggregate multimodal data from various sources in real time and apply it to machine learning models to personalize weight-loss medication selection. By analyzing user data using machine learning models, digital therapy applications can identify which obesity medications are likely to produce the highest weight-loss results for a particular user while minimizing side effects. The output can also include the precise type, dosage, frequency, and dosing regimen of the weight-loss medication. Compared to trial and error, machine learning models provide outputs for the most effective treatment and optimal clinical outcomes for a specific user.

[0008] On the other hand, digital therapy applications can use machine learning models to predict potential side effects based on user data. Side effect prediction is particularly valuable for weight-loss medications known to have a variety of potential adverse reactions. By identifying the risk of these side effects in advance, digital therapy applications can be used to adjust the administration of obesity medications (e.g., drug type, dosage, and frequency) to mitigate side effects before they occur. This proactive approach can minimize user discomfort, improve adherence, and ultimately contribute to more successful outcomes. Furthermore, machine learning models can be used to identify specific users at risk of discontinuing weight-loss medications. Using this model, digital therapy applications can identify the behavioral and physiological factors that typically lead to discontinuation for this type of user and can provide different medications or dosing parameters to avoid discontinuation. By providing personalized support, digital therapy applications can offer specific interventions to mitigate user side effects and the risk of discontinuation, thereby increasing the likelihood of medication adherence and thus achieving better clinical outcomes.

[0009] Furthermore, instances of machine learning models are created and tailored for specific users to take into account each user's unique characteristics. For example, multiple instances of a machine learning model can be created for different individuals under physician supervision, each instance being tailored to each individual's specific response profile and preferences. For an individual who has previously experienced side effects of a particular medication and is therefore susceptible to it, an instance of the machine learning model will be created for that individual to output a higher probability of side effects for that medication. For another individual who has no concerns about the same medication but has difficulty with medication adherence due to their work schedule, another instance of the machine learning model will be trained to take into account known factors that lead to low adherence (e.g., higher dosing frequency). Because each instance of the machine learning model is personalized for these individuals, they are able to generate different outputs even using the same or similar measurement data. This improves the accuracy and relevance of the machine learning model's outputs across different user profiles and characteristics.

[0010] Furthermore, digital therapy applications incorporate real-time physiological measurements of the user (such as blood glucose, heart rate, or blood pressure) to iteratively update side effect risks and weight loss predictions while the user adheres to their medication prescription. By continuously monitoring the user's measurements in real time throughout their weight loss journey, digital therapy applications can iteratively update the user's medication, dosage, and dosing parameters, as well as the user's dropout and side effect risks. Unlike other methods that do not incorporate real-world data, digital therapy applications use machine learning models to evaluate real-time data to account for all relevant factors that may influence a user's response to a specific weight loss medication. Using the digital therapy applications described herein enables the creation of highly personalized prescriptions while optimizing the integration of pharmacological and digital therapy interventions.

[0011] From a computer science perspective, machine learning models can efficiently process and analyze large datasets across various modalities. By using machine learning models, digital therapy applications can refine complex, high-dimensional data into embedded representations, thereby reducing computation time without compromising predictive accuracy. Compared to trial-and-error methods involving repeated trials, human monitoring, and follow-up, digital therapy applications can continuously monitor and provide recommendations, including the selection of weight-loss medications and optimized dosage, frequency, and timing of administration. By reducing reliance on human assessment and continuous trials, digital therapy applications can execute data-driven outputs more accurately and quickly.

[0012] Furthermore, digital therapy applications can offer various visualizations to promote medication adherence. These applications provide visual incentives to encourage adherence to medication prescriptions. They can generate simulations that represent the user's experience while taking medication. For example, based on physiological measurements, simulations can identify reasons for withdrawal, the probability of side effects, or predicted weight loss, and represent this information graphically over a period of time. These visualizations serve as persuasive tools to motivate users to adhere to medication prescriptions and prepare for predicted side effects. The likelihood of side effects and predicted weight loss are continuously updated to reflect real-time data received by the digital therapy application, ensuring that the information provided to users remains accurate and effective.

[0013] Therefore, digital therapeutics applications address the lack of accurate, personalized real-world data integration by providing models that dynamically predict individual responses to weight-loss medications. This application offers a precise and tailored weight-loss approach that matches each patient's physiological profile to enhance overall weight loss while minimizing side effects. By integrating digital and pharmacological solutions, the treatment of obesity has been significantly improved, leading to better outcomes and enhanced overall patient care.

[0014] This disclosure relates to a system and method for selecting a weight-loss drug for a user's obesity condition. One or more processors can receive one or more physiological measurements of the user. The one or more processors can apply the one or more physiological measurements to a machine learning model. Multiple examples can be used to train the machine learning model, each example including one or more sample physiological measurements of a sample user and a corresponding sample weight-loss drug administered to the sample user. The one or more processors can generate a metric indicating an expected outcome related to the weight-loss drug for the user based on applying the one or more physiological measurements to the machine learning model. The one or more processors can provide a message indicating at least one of the selection of a weight-loss drug to a user device associated with the user based on the metric indicating the expected outcome or the expected outcome related to the weight-loss drug.

[0015] In various embodiments, one or more processors select a weight-loss drug from a variety of weight-loss drugs based on multiple expected outcomes associated with the drug. In various embodiments, one or more physiological measurements include at least one of the following: body mass index, weight, blood pressure, heart rate, smoking status, glucose excretion, comprehensive metabolomics, complete blood cell count, lipase level, thyroid function, magnesium level, HgA1c, fasting blood glucose, energy expenditure, physical activity, hormone levels, weight, body fat percentage, genetic markers, gut microbiome assessment, or energy intake. The machine learning model includes one or more corresponding weights to generate one or more values, the weights including at least one of binary weights or continuous weights. One or more processors can then generate a metric based on the one or more values. The weight-loss drug can be selected from GLP-1 receptor agonists or GIP receptor agonists. GLP-1 receptor agonists can be selected from one or more of semaglutide, liraglutide, exenatide, and dulaglutide, and wherein GIP receptor agonists include tezepamide.

[0016] In various embodiments, the anticipated outcome also includes at least one administration parameter of the weight-loss drug, including at least one of the following: dosage of the weight-loss drug, time of administration, frequency of administration, route of administration, dose escalation regimen, and administration status, or any combination thereof. In various embodiments, the anticipated outcome also includes identifying at least one of treatment discontinuation, side effects, or treatment effectiveness. In various embodiments, side effects are selected from nausea, vomiting, diarrhea, early satiety, loss of appetite, anorexia, dizziness, tachycardia, indigestion, headache, hypoglycemia, kidney or ureteral stones, pancreatitis, diabetic retinopathy, depression, suicidal ideation or attempt, abdominal pain, acute kidney injury, muscle wasting and atrophy, constipation, or any combination thereof. To generate metrics, one or more processors may generate multiple metrics of multiple anticipated outcome parameters based on applying one or more physiological measurements to a machine learning model.

[0017] In various embodiments, the expected outcome further includes at least one expected outcome parameter, which includes at least one or any combination of termination time, termination reason, termination probability, and termination relief. In various embodiments, the expected outcome further includes at least one expected outcome parameter, which includes at least one or any combination of side effect onset time, side effect duration, side effect probability, and side effect relief. In various embodiments, the expected outcome further includes at least one expected outcome parameter, which includes at least one or any combination of side effect onset time, side effect duration, side effect probability, and side effect relief. In various embodiments, the expected outcome further includes at least one expected outcome parameter, which includes at least one or any combination of weight loss, fat reduction, fasting blood glucose, cholesterol level, hormone level, duration of fat reduction, risk of weight rebound, and change in body mass index.

[0018] In various embodiments, one or more processors generate simulations that identify multiple expected outcomes at corresponding points in time. The simulations may include representations of the multiple expected outcomes at corresponding points in time, wherein the representations include at least one of timelines, graphs, video, audio, or icons. In various embodiments, the simulations may identify multiple expected outcomes including at least one expected outcome parameter, such that the expected outcome parameter includes at least one of termination time, termination reason, termination probability, termination mitigation (also referred to herein as reduction, mitigation, minimization, or prevention, etc.), or any combination thereof. The simulations may identify multiple expected outcomes including at least one expected outcome parameter, such that the expected outcome parameter includes at least one of side effect onset time, side effect duration, side effect probability, side effect mitigation, or any combination thereof. The simulations may identify multiple expected outcomes including at least one of weight loss, fat loss, fasting blood glucose, cholesterol levels, hormone levels, duration of fat loss, risk of weight regain, and change in body mass index, or any combination thereof.

[0019] In various embodiments, the user has a BMI greater than 25, a body fat percentage greater than 20%, and suffers from type 1 diabetes, type 2 diabetes, or non-alcoholic steatohepatitis (NASH). One or more processors may provide messages to the user's device or the user's clinician. One or more processors may obtain one or more physiological measurements of the user through at least one of the user's device or instruments on the user's person. One or more processors may determine a metric based on at least one of the following: (i) the average of multiple samples, (ii) a weighted combination of multiple samples, or (iii) a comparison with a dataset consisting of multiple samples, to generate a metric indicating an expected outcome. In various embodiments, one or more processors to receive one or more physiological measurements may receive one or more physiological measurements from at least one of the user's device or instruments over a period of time. To apply a machine learning model, one or more processors may apply one or more physiological measurements to the machine learning model in response to the passage of time. To generate a metric, one or more processors may generate a metric indicating an expected outcome related to weight-loss medication in subsequent time periods.

[0020] In various embodiments, one or more processors receive one or more subsequent physiological measurements from a user. In response to the receipt of the one or more subsequent physiological measurements, the one or more processors may apply the one or more subsequent physiological measurements to a machine learning model. Based on the application of the one or more subsequent physiological measurements to the machine learning model, the one or more processors may generate a subsequent metric indicating a subsequent expected outcome related to the user's subsequent weight-loss medication. The one or more processors may provide a subsequent message to the user device within a defined time period relative to the receipt of the one or more subsequent physiological measurements, the subsequent message indicating at least one of the following: a) selection of a weight-loss medication or subsequent weight-loss medication based on the subsequent metric indicating the subsequent expected outcome, or b) a subsequent expected outcome related to the subsequent weight-loss medication. The defined time period ranges from 1 second to 1 hour. Attached Figure Description

[0021] The foregoing and other objects, aspects, features and advantages of this disclosure will become more apparent and better understood by referring to the following description taken in conjunction with the accompanying drawings, wherein:

[0022] Figure 1 A block diagram of a system for selecting a drug for a user, according to an illustrative embodiment, is depicted.

[0023] Figure 2 A block diagram depicts the process of receiving measurement values ​​from a user according to an illustrative embodiment.

[0024] Figure 3 A block diagram depicts the process of generating metrics using a machine learning (ML) model according to an illustrative embodiment.

[0025] Figure 4 A block diagram depicts providing a user with a simulated and selected drug according to an illustrative embodiment.

[0026] Figure 5A and 5B Screenshots depicting a set of example user interfaces for selecting a drug according to illustrative embodiments are shown.

[0027] Figure 6A and 6B Screenshots depicting a set of example user interfaces for selecting a drug according to illustrative embodiments are shown.

[0028] Figure 7 Screenshots depicting a set of example user interfaces for selecting a drug according to illustrative embodiments are shown.

[0029] Figure 8 Screenshots depicting a group of example user interfaces for notifying side effects according to an illustrative embodiment.

[0030] Figure 9 Screenshots depicting a group of example user interfaces for notifying side effects according to an illustrative embodiment.

[0031] Figure 10 Screenshots depicting a set of example user interfaces for illustrating expected results according to illustrative embodiments.

[0032] Figure 11 Screenshots depicting a set of example user interfaces for selecting a drug according to illustrative embodiments are shown.

[0033] Figure 12 A flowchart is depicted according to an illustrative embodiment of a method for selecting a drug for a user to address obesity.

[0034] Figure 13 This is a block diagram of a server system and a client computer system according to an illustrative embodiment. Detailed Implementation

[0035] To facilitate reading the following description of the various embodiments, the following enumeration of portions of this specification and their respective contents may be helpful:

[0036] Part A describes the systems and methods used to select medications to address a user's obesity condition.

[0037] Part B describes the network and computing environments that can be used to practice the embodiments described herein.

[0038] A. Systems and methods for selecting medications to address a user's obesity condition.

[0039] This paper presents a system and method for selecting weight-loss medications for users with obesity. The digital therapy application described herein receives physiological measurements from the user. These measurements may include user-inputted values, test results, or wearable technology data. Once received, the application can apply these measurements to a machine learning model to select weight-loss medications for the user based on expected outcomes. Expected outcomes may include results, effects, and effects, such as the onset time of side effects and the timing of administration of a specific weight-loss medication.

[0040] Machine learning models can be trained on training data derived from real-world data, including the effects of specific weight-loss drugs and prescriptions on individuals with various physiological measurements from sample subjects. As a result of training, the machine learning model can assign weights to each physiological measurement. These weights can be embedded into obvious patterns (or latent features) within the training data. Furthermore, applications can generate simulations based on physiological measurements to visualize the effects of weight-loss drugs on users, such as side effects and weight loss. As the application receives more data from sources such as wearable technology, predicted weight loss and other such factors can be updated to reflect real-time data.

[0041] By using machine learning models, the application can generate metrics that indicate expected outcomes associated with a weight-loss drug selected for the user. To select a weight-loss drug, the application can generate a set of expected outcomes and choose the drug with the fewest side effects and the most desirable health results. Expected outcomes may include, for example, the onset time of side effects, fat reduction, the duration of fat reduction, or cholesterol levels, blood sugar, insulin levels, etc. The application can consider physiological measurements to generate metrics based on the predicted outcomes and the impact of the selected weight-loss drug on the user. The application can then provide the user with a message indicating one of the weight-loss drug choices based on the metrics indicating the expected outcomes or the expected outcomes associated with the weight-loss drug. This message may also include visualizations of the expected outcomes, such as in the form of charts, icons, timelines, videos, or audio.

[0042] In this way, the application can leverage real-world data to identify the optimal weight-loss medication based on the user's physiological measurements to promote weight loss. By considering various physiological measurements, the application can select weight-loss medications and generate personalized expected outcomes based on the results of taking the medications. As the application receives subsequent physiological measurements, it can update the weight-loss medication and related expected outcomes. For example, as the user continues to lose weight, the application can adjust the dosage and frequency of the weight-loss medication, as well as the expected outcomes. The application can integrate pharmacological and digital treatment solutions to promote user weight loss while avoiding prescribing weight-loss medications based on trial and error.

[0043] Now for reference Figure 1 This diagram depicts a block diagram of a system 100 for presenting interactive sessions to address user obesity. Generally, system 100 may include at least one session management service 105, a group of user devices 110A-N (collectively referred to as user devices 110), and instrumentation devices 135 communicatively coupled to each other via at least one network 115. At least one user device 110 (e.g., the first user device 110A shown) may include at least one application 125. Application 125 may include or provide at least one user interface 130. Session management service 105 may include at least a data collector 140, a model applicator 145, a metric evaluator 150, a simulation processor 155, an output generator 160, and at least one machine learning (ML) model 165, etc. Session management service 105 may include or have access to at least one database 170. Database 170 may store, maintain, or otherwise include one or more user profiles 175A-N (collectively referred to as user profiles 175) and training datasets 180. The functionality of application 125 can be partially executed on session management service 105. Conversely, the functionality of application 125 can also be included in operations performed on session management service 105. In general, user device 110 and session management service 105 can be part of the computing system that provides application 125.

[0044] More specifically, session management service 105 (sometimes collectively referred to herein as a service) can be any computing device including one or more processors coupled with memory and software, and capable of performing the various processes and tasks described herein. Session management service 105 can communicate with one or more user devices 110 and database 170 via network 115. Session management service 105 may be located, situated, or otherwise associated with at least one server group. The server group may correspond to a data center, branch office, or site where one or more servers corresponding to session management service 105 reside. Session management service 105 may be located, situated, or otherwise associated with one or more user devices 110. Some components of session management service 105 may reside within the server group, and some components may reside within client devices. For example, session management service 105 may run or reside on user device 110, and ML model 165 may run or reside on the server group.

[0045] In session management service 105, data collector 140 can present the data to be input to the user on the corresponding user device 110 via application 125. Data collector 140 can then collect the user-provided data, and model applicator 145 can receive this data. Model applicator 145 can apply the data from the user to a machine learning model (e.g., ML model 165) to analyze the data to determine the metrics for the weight-loss drug. Simulation processor 155 can simulate various outcomes of the weight-loss drug for the user based on this data to provide the user with a visual output. Output generator 160 can select a drug based on the metrics and provide a message to the user along with the drug and the visual output.

[0046] ML Model 165 (sometimes referred to as a machine learning (ML) model in this paper) can be used to generate a set of expected results for a group of weight-loss drugs and select weight-loss drugs based on this set of expected results. The architecture of the machine learning model can include, for example, deep learning neural networks (such as convolutional neural network architectures, residual networks, or transformer-based architectures), regression models (such as linear or logistic regression models), random forests, gradient boosting, K-neighbor classifiers and / or regressors, support vector machines (SVMs), clustering algorithms (such as k-nearest neighbor algorithms), or Naive Bayes models, and can be supervised, unsupervised, or self-supervised.

[0047] Generally, an ML model 165 may have at least one input and one output. The input and output can be associated with a set of weights. The input may be data from the user, etc., while the output may include at least one or more drug choices, expected outcomes, and visualizations, etc. Visualizations may include timelines, charts, videos, audio, or icons. The ML model 165 can be trained using a training dataset 180. The training dataset 180 may include a set of examples representing subjects who have received weight-loss therapy. Each example may include inputs (e.g., weight-loss drugs, physiological measurements, selected drugs) and outcomes (e.g., weight loss, side effects, discontinuation). In some embodiments, the session management service 105 may maintain a set of ML models 165, each model for a specific user or a clinician examining the user.

[0048] User device 110 (sometimes referred to herein as an end-user computing device or client device) can be any computing device including one or more processors coupled to memory and software, and capable of performing the various processes and tasks described herein. In some embodiments, user device 110 may be associated with a user taking weight-loss medication. In some embodiments, user device 110 may be associated with an individual's clinician (e.g., prescribing weight-loss medication to the individual). User device 110 can communicate with session management service 105, instrumentation equipment 135, and database 170 via network 115. User device 110 can be a smartphone, other mobile phone, tablet, wearable device (e.g., smartwatch, glasses), or laptop. User device 110 can be used to access application 125. In some embodiments, application 125 may be downloaded and installed on user device 110 (e.g., via a digital distribution platform). In some embodiments, application 125 may be a web application with resources accessible via network 115.

[0049] Instrument 135 (sometimes referred to herein as wearable technology, wearable device, or device) can be any computing device capable of collecting measurements from a user. Instrument 135 may include health trackers, smartwatches, heart monitors, pedometers, or blood glucose monitors, etc. Instrument 135 may be worn by a user (e.g., attached to a user) to collect various data. Instrument data may be continuously provided to user device 110 (e.g., application 125 on user device 110) or data collector 140. Instrument 135 may communicate with session management service 105, user device 110, database 170, etc., via network 115.

[0050] Application 125 running on user device 110 may be a digital therapy application and may provide sessions (sometimes referred to herein as therapy sessions) to address obesity symptoms and related conditions. The user of application 125 may be diagnosed with or at risk of obesity-related conditions or disorders. For example, the user may have diabetes, high blood pressure, high cholesterol, fatigue, excess body fat, psychological problems, snoring, shortness of breath, or physical disabilities. Diseases or conditions may include any number of conditions that contribute to the user's obesity. The user's body mass index (BMI) may be greater than or equal to 25, greater than or equal to 30, greater than or equal to 32, or greater than or equal to 35. The user's body fat percentage may be greater than 20%, greater than 25%, or greater than 30%. The user may have type 1 diabetes, type 2 diabetes, non-alcoholic steatohepatitis (NASH), or non-alcoholic fatty liver disease (NAFLD). Causes of obesity may include genetic, behavioral, environmental, physiological, and psychological factors. For example, certain genetic traits, such as a slower metabolism and / or slower appetite regulation, can influence weight gain. A family history of obesity can also increase the likelihood of developing obesity based on lifestyle habits and shared genetic predispositions. In another example, metabolic disorders such as diabetes can lead to weight gain, for instance, due to increased appetite and calorie intake caused by higher blood sugar levels.

[0051] Obesity can lead to physical health, mental health, social and economic impacts, and it also affects the children of obese individuals. Physical health impacts may include cardiovascular diseases such as high blood pressure, heart disease, or stroke, or metabolic disorders such as diabetes or dyslipidemia. The condition can impair or hinder social skills, such as facing discrimination or humiliation in various social settings, including the workplace or healthcare facilities.

[0052] Application 125 can be used to select medications and provide users with expected outcomes related to those medications. Medications can be presented as results, such as user input data (e.g., physiological measurements), selected medications, or the generation of metrics (also referred to herein as measurements, indicators, parameters, or standards, etc.) that indicate expected outcomes. Medications can be presented along with visual outputs of expected outcomes, such as timelines showing the onset of side effects and weight loss over time. Providing users with digital therapies (e.g., interventions) through Application 125 can address the adverse effects of obesity.

[0053] Physiological measurements may include at least one or more of the following: body mass index, weight, blood pressure, heart rate, smoking status, glucose excretion, comprehensive metabolomics, complete blood cell count, lipase level, thyroid group, magnesium level, glycated hemoglobin (HgA1c), fasting blood glucose, energy expenditure, physical activity, hormone levels, weight, body fat percentage, genetic markers, gut microbiome assessment, or energy intake. Expected outcomes may include treatment discontinuation (e.g., withdrawal, discontinuation of medication), (e.g., drug side effects), or treatment efficacy (also referred to herein as effectiveness, performance, or success rate, etc.).

[0054] Users may receive treatment, at least partially concurrently with a medication prescription provided by application 125, to address a condition or its side effects. For example, a user may be receiving treatment for diabetes. The user may receive treatment, at least partially concurrently with a first, second, third, or any combination thereof. Treatment may include taking medication. Medications may be administered orally, intravenously, or topically. For example, for metabolic conditions (e.g., diabetes or hypothyroidism), a user may be taking diabetes medications (e.g., insulin, biguanides, sulfonylureas, or chloropicrin) or beta-blockers (e.g., propranolol or atenolol). Treatment may include blood tests, bariatric surgery, metabolic surgery, nutritional counseling, psychological counseling, or weight management programs.

[0055] To address obesity, medications such as glucagon-like peptide-1 receptor agonists (GLP-1 RAs) and / or gastrointestinal inhibitory peptides (GIPs) can be administered to users to promote weight loss. GLP-1 RAs mimic the action of the natural hormone GLP-1, which regulates blood glucose levels, insulin secretion, and appetite. GIP therapy is an analogue of the human GIP hormone that stimulates the pancreas to release insulin. Therefore, GLP-1 RAs and GIPs can increase insulin release, reduce glucagon release, and slow gastric emptying to reduce appetite and lower blood glucose levels, thereby promoting weight loss. Examples of GLP-1 RAs include semaglutide, liraglutide, exenatide, and dulaglutide. Examples of GIPs include tezepamide. In some respects, medications may include any analogues of GLP-1 RAs or GIPs. Medications may include functionally equivalent peptides or therapeutic agents. Furthermore, medications may include any medicine that has been shown to be effective in treating obesity and obesity-related conditions. For example, the drug may include agents that can stimulate GLP-1 or GIP, or drugs that can induce fat reduction and / or suppress the user's appetite.

[0056] Database 170 can store and maintain various resources and data related to session management service 105 and application 125. Database 170 may include a database management system (DBMS) to arrange and organize the data maintained thereon. Database 170 can communicate with session management service 105 and one or more user devices 110 via network 115. When performing various operations, session management service 105 and application 125 can access database 170 to retrieve identified data from it. Session management service 105 and application 125 can also write data to database 170 by performing such operations.

[0057] Such operations may include maintaining a user profile 175 (sometimes referred to herein as a subject profile). As described herein, the user profile 175 may include information related to the user's condition. For example, the user profile 175 may include information related to the severity of the condition, the occurrence of the condition (such as the occurrence of symptoms associated with a condition affecting the user's cognitive function), medications or treatments the user is taking for the condition, and / or the duration of the condition. The user profile 175 may be updated in response to schedules, periodically (e.g., daily, weekly), in response to changes in user information (e.g., input by the user through user interface 130 or obtained from user device 110), or in response to clinicians addressing the user's condition (e.g., doctors or nurses).

[0058] User profile 175 can store and maintain user-related information for application 125 via user device 110. Each user profile 175 can be associated with or correspond to a specific user of application 125. This guided approach reduces the need for multiple communications with the user, thereby reducing bandwidth and improving the efficiency of user-computer interaction. In some embodiments, user profile 175 may identify or include information about the treatment regimen taken by the user, such as treatment type (e.g., therapy, medication, or psychotherapy), duration (e.g., daily, weekly, or yearly), and frequency (e.g., daily, weekly, quarterly, annually). User profile 175 can be stored and maintained in database 170 using one or more files (e.g., Extensible Markup Language (XML), comma-separated value (CSV) delimited text files, or Structured Query Language (SQL) files). User profile 175 can be iteratively updated as the user provides responses, makes choices, and performs actions related to a session, data collector 140, or output generator 160. For example, user profile 175 can be updated with data collected by data collector 140.

[0059] Now for reference Figure 2This diagram depicts a block diagram of a process 200 in system 100 for collecting measurements from user 210 to select a medication. Process 200 may include or correspond to operations performed by system 100 for receiving and processing data from the user. Under process 200, a data collector 140, executing on session management service 105, may communicate with user device 110 or instrument device 135 associated with at least one user 210. User 210 may have a body mass index (BMI) greater than 25, a body fat percentage greater than 20%, type 1 diabetes, type 2 diabetes, or NASH, etc. User 210 may have obesity-related conditions such as diabetes, high blood pressure, or high cholesterol.

[0060] Data collector 140 may create, write, or otherwise generate one or more instructions 205 (collectively referred to as instructions 205) for at least user 210. Instructions 205 may be used to request measurements from user 210 (or application 125 or instrument 135). Instructions 205 may identify one or more measurement fields to be acquired by user device 110. One or more measurement fields may be associated with physiological measurements of user 210. Measurements may span multiple modalities, such as numerical values, time-series data, imaging, Boolean values, or free text. One or more measurement fields may include at least one of the following: body mass index (BMI) (e.g., calculated from the user's height and weight measurements), weight (e.g., the total mass of user 210), blood pressure (e.g., the force exerted by circulating blood on the arterial walls), heart rate (e.g., the number of heartbeats in 60 seconds), smoking status (e.g., an indication of whether user 210 smokes), glucose excretion, comprehensive metabolomics, complete blood cell count, lipase level, thyroid group, magnesium level, HgA1c, fasting blood glucose, energy expenditure, physical activity, hormone levels, weight, body fat percentage, genetic markers, gut microbiome assessment, or energy intake, etc.

[0061] In some embodiments, one or more measurement fields may also include at least one questionnaire. The questionnaire may be used by user 210 to indicate at least one of the following: impairment (e.g., physical injury affecting the user's ability to move; dizziness recently experienced by the user affecting the user's ability to tolerate nausea); side effects (e.g., negative reactions to a specific weight-loss drug or to other non-weight-loss drugs); or side effect preferences (e.g., a preference to limit nausea as a side effect because the user is a pilot and cannot tolerate nausea at work). For example, the questionnaire may ask user 210 about: (i) general side effects since the start of medication, (ii) identification of symptoms (e.g., nausea, vomiting, diarrhea, early satiety, loss of appetite, anorexia, dizziness, rapid heart rate, indigestion, headache, hypoglycemia, kidney or ureteral stones, pancreatitis, diabetic retinopathy, depression, suicidal ideation or attempt, abdominal pain, acute kidney injury, muscle wasting or atrophy), (iii) the start date of the side effects, (iv) the frequency of the side effects, or (v) their impact on daily life, etc. As another example, the measurement field may include questions that user 210 must answer regarding the side effects that user 210 can tolerate. The measurement field may also request user 210 to input information about recent injuries, such as knee or ankle injuries that affect user 210's physical mobility. A questionnaire may be generated based on questions identified in the user profile 175.

[0062] When generating instruction 205, data collector 140 may select or identify one or more physiological measurement fields based at least on user profile 175. For example, the physiological measurement values ​​identified in instruction 205 may depend on the user 210's medical condition. User profile 175 may contain the user's past and present medical conditions (e.g., type 1 diabetes), which can be used to select medications, and data collector 140 may identify blood glucose and other measurements in instruction 205. In some embodiments, instruction 205 may identify one or more measurement fields associated with a time period. For example, instruction 205 may specify the time period for which user 210 should input one or more measurement fields. The time period may range from 1 day to 6 months.

[0063] As instruction 205 is generated, data collector 140 may send, provide, or otherwise transmit instruction 205 to user equipment 110 or instrumentation equipment 135. Transmission of instruction 205 may be scheduled (e.g., at intervals of 5 minutes to 2 weeks). In some embodiments, data collector 140 may transmit instruction 205 to user equipment 110 for at least a subset of measurements. Data collector 140 may transmit instruction 205 for another subset of measurements to instrumentation equipment 135. Instruction 205 may take various formats associated with application 125. In some embodiments, instruction 205 may be displayed, presented, or otherwise presented to user 210 through user interface 130 of application 125. Instruction 205 may take the form of lists, tables, databases, charts, or graphs, displaying one or more measurement fields for user 210 to input. In some embodiments, instruction 205 may include Short Message Service (SMS) (e.g., text messages) or Multimedia Messaging Service (MMS) (e.g., audio messages, video messages). For example, instruction 205 may include a link to open application 125, which guides the user to input one or more measurement fields through the user interface 130 of application 125.

[0064] Application 125 on user equipment 110 may retrieve, identify, or otherwise receive instructions 205 from session management service 105. Upon receiving instruction 205, application 125 may parse instruction 205 to identify measurement fields to be provided to session management service 105. In some embodiments, application 125 may use instruction 205 to display, present, or otherwise render user interface 130. Application 125 may then prompt or guide user 210 to provide measurement values ​​215A-N (e.g., one or more measurement values ​​are referred to herein as measurement values ​​215). Measurement values ​​215 may be text strings, strings, or numerical values ​​entered by user 210 on user interface 130. In some embodiments, upon receipt, application 125 may retrieve, obtain, or otherwise identify the measurement value 215 specified by instruction 205. Application 125 on user equipment 110 may already be generating and storing data related to measurement values ​​215 from user 210 (or instrumentation 135 communicating with user equipment 110). In response to instruction 205, application 125 can retrieve measurement value 215 stored in the data. Upon identification, application 125 can return, provide, or otherwise send measurement value 215 to session management service 105.

[0065] In some embodiments, instrument device 135 may retrieve, identify, or otherwise receive instructions 205 from session management service 105. Upon receipt, instrument device 135 may parse instructions 205 to identify measurement fields to be provided to session management service 105. Instrument device 135 may retrieve, acquire, or otherwise identify the measurement value 215 specified by instructions 205. Instrument device 135 on user device 110 may already be generating and storing data related to measurement value 215 from user 210. Upon identification, instrument device 135 may return, provide, or otherwise send measurement value 215 to session management service 105. In some embodiments, instrument device 135 may acquire measurement value 215 for one or more measurement fields (e.g., heart rate). Instrument device 135 may include a wearable continuous glucose monitor, a smartwatch capable of monitoring a user's heart rate and biometrics, a scale, or other technologies capable of acquiring data related to a user's physiological health. Instrument device 135 may provide measurement value 215 to data collector 140 in real time (e.g., continuously) via application 125.

[0066] Conversely, data collector 140 can retrieve, identify, or otherwise receive measurement values ​​215 from user 210 (or application 125 or instrument device 135). Upon receipt, data collector 140 can associate or correspond each measurement value 215 with a corresponding measurement field. For example, instruction 205 may include a weight measurement field, and data collector 140 receives a numerical value of the user 210's weight. Data collector 140 can store measurement values ​​215 in database 170 and associate measurement values ​​215 with user profile 175. Through storage, data collector 140 can update user profile 175 to add or include measurement values ​​215. Measurement values ​​215 of user 210 can be obtained through at least one of user device 110 or instrument device 135 on user 210. Data collector 140 can receive measurement values ​​215 from at least one of user device 110 or instrument device 135 over a period of time. In various embodiments, data collector 140 receives one or more subsequent physiological measurements of user 210. For example, data collector 140 may receive measurement values ​​215 after they have been provided to model applicator 145. In various embodiments, measurement values ​​215 are continuously updated based on the instrumentation 135 provided to user 210.

[0067] Now for reference Figure 3This diagram depicts a block diagram of a process 300 in system 100 that applies measurements from user 210 to ML model 165 to select a drug. Process 300 may include or correspond to operations performed by system 100 for receiving and processing data provided by user 210. For process 300, ML model 165 may be initialized, trained, and built (e.g., via model applicator 145) using training dataset 180 on database 170. Training dataset 180 may identify or include a set of examples. In training dataset 170, each example may include one or more sample physiological measurements of a sample user and a corresponding sample weight-loss drug administered to the sample user. Each example may include sample measurement 215'AN (referred to herein as sample measurement 215') and sample metric 305'AN (referred to herein as sample metric 305'), etc.

[0068] In some embodiments, at least one example of the training dataset 180 may include a drug identifier (ID) 310'AN (referred to herein as drug identifier 310') for each sample user. The sample user may be a real-world patient. The sample user may be 18 years of age or older at the time of first starting the weight-loss medication. The sample user may have a BMI greater than 25 within 60 days of first starting the weight-loss medication. The sample measurements 215' may also include information for each sample user, such as patient identity, year of birth, or diagnosis (e.g., obesity, type 1 diabetes, type 2 diabetes, or NASH). The sample users included in the training dataset 180 may have at least one BMI or height and weight measurement before starting the weight-loss medication, and may have at least one BMI or height and weight measurement after starting the weight-loss medication.

[0069] Sample measurements 215' may include corresponding physiological measurements 215, which include at least one of the following: body mass index, weight, blood pressure, heart rate, smoking status, glucose excretion (measured by blood or urine glucose levels), comprehensive metabolomics (e.g., kidney and liver function, blood protein levels, blood electrolyte concentrations, etc.), complete blood cell count (e.g., red blood cell and white blood cell counts), lipase levels, thyroid group (measurements of thyroid-stimulating hormone, thyroxine, triiodothyronine, thyroid antibodies), magnesium levels, HgA1c (average blood glucose levels over a specified time period), fasting blood glucose, energy expenditure (measured by calorie expenditure), physical activity, hormone levels (e.g., testosterone, estrogen, progesterone, etc.), weight, body fat percentage, genetic markers (e.g., genetic markers for obesity, diabetes, genetic markers associated with metabolic disorders, etc.), gut microbiome assessment (assessed via fecal microbiota), or energy intake (calorie, fat, protein, and carbohydrate intake). Each sample measurement 215' may be associated with a sample user within a given time period.

[0070] Sample metric 305' may include at least one of treatment discontinuation, side effects, or treatment effects associated with the sample user. For example, sample metric 305' may include the International Classification of Diseases, 10th Revision (ICD-10) diagnostic codes for at least 20 side effects (e.g., vomiting, diarrhea, headache), laboratory results (e.g., complete blood count, comprehensive metabolomics), total cholesterol, lipase, thyroid group, magnesium, HgA1c, withdrawal time (e.g., discontinuation of weight-loss medication), and available vital sign measurements (e.g., height, weight, smoking status). Sample metric 305' may be associated with the sample user. Sample metric 305' may include a set of dosing parameters for the weight-loss medication, such as the dosage of the weight-loss medication, the time of administration (e.g., morning or evening), the frequency of administration (e.g., daily, weekly, monthly), the route of administration (intravenous, subcutaneous, intramuscular), the dose escalation regimen (increasing or decreasing the dose over time), or the administration status (e.g., combination with other drugs or therapies).

[0071] Sample metric 305' may include information about drug side effects, such as the onset time of side effects, the duration of side effects, the probability of side effects, or the relief of side effects. Sample metric 305' may include information related to potential treatment discontinuation, such as the duration of discontinuation (the length of time from taking the medication to discontinuing treatment), the reason for discontinuation, the probability of discontinuation (the likelihood that a user will discontinue treatment within a given time period), or the relief of discontinuation (e.g., psychotherapy, drug side effect relief measures). Sample metric 305' may include information about treatment effectiveness, such as weight loss, fat reduction, fasting blood glucose, cholesterol levels, hormone levels, duration of fat reduction, changes in body mass index, or the risk of weight rebound.

[0072] Each of the sample user's sample measurements 215' and sample metrics 305' can be associated with a drug identifier 310'. The drug identifier 310' can identify which weight-loss medication the sample user is currently taking and / or has taken. The drug identifier 310' may include an identifier for at least one of duraglutide, exenatide, semaglutide, liraglutide, liximab, or tezepamide. In some embodiments, the drug identifier 310' may also indicate at least one or any combination of the following: dosage of the weight-loss medication, time of administration, frequency of administration, route of administration, dose escalation regimen, and administration status.

[0073] For initialization, model applicator 145 can set the values ​​of the weight regroups in ML model 165 to initial values ​​(e.g., random or bounded values). For training, model applicator 145 can input, feed, or otherwise apply sample measurements 215' and drug identifiers 310', and compare the output metric of ML model 165 with the sample metric 305' for each sample user. Based on this comparison, model applicator 145 can determine a loss metric according to a loss function (e.g., mean squared error, cross-entropy loss, hinge loss, or Huber loss). Using the loss metric, model applicator 145 can update one or more weights of ML model 165. The weight update can be performed based on backpropagation and an optimization function (sometimes referred to herein as an objective function) having one or more parameters (e.g., learning rate, momentum, weight decay, and number of iterations). The optimization function can bound one or more parameters on which the weights of ML model 165 are updated. The optimization function can be based on stochastic gradient descent and can include, for example, adaptive moment estimation (Adam), implicit update (ISGD), and adaptive gradient algorithm (AdaGrad). ML Model 165 can be updated iteratively until it converges.

[0074] As the ML model 165 is established, the model applicator 145 can feed, provide, or otherwise apply the measurement value 215 to the ML model 165. In application, the model applicator 145 can process the measurement value 215 according to the weighting of the ML model 165. In some embodiments, the weighting of the ML model 165 corresponds to the measurement value 215. For example, for each measurement value 215, the ML model 165 includes a set of corresponding weights. In some embodiments, this set of corresponding weights can include at least one of binary weights (e.g., 0 or 1) or continuous weights (e.g., values ​​between -100 and 100). For example, the percentage of body fat of user 210 can have a higher weight than the weight of user 210. Based on this set of corresponding weights, the ML model 165 generates one or more values. These one or more values ​​can be a function of the measurement value 215 and its corresponding weights.

[0075] In some embodiments, ML model 165 may be specific to a particular user (e.g., user 210) of application 125. ML model 165 may have a bias on a set of weights based on a machine learning architecture to provide higher or lower values ​​based on user 210's measurements. This biasing can be performed using techniques such as reweighting (e.g., manually setting weight values), data augmentation, regularization, or sampling. The weights of ML model 165 may be assigned or set based on a user profile 175 for a particular user 210. For example, user profile 175 may indicate that user 210 experienced a specific type of side effect (e.g., dizziness or nausea) with a particular drug, while user 210 had no problems with another drug. The weights of ML model 165 may be updated or assigned with bias to generate an output indicating that user 175's expected outcome value for one drug is higher than the expected outcome value for other drugs. The weights of ML model 165 may be assigned or set by a clinician (e.g., the doctor examining user 210) using a user interface provided by session management service 105. For example, the doctor may have two individuals. One individual might convey past experiences with side effects as susceptibility to a particular medication. Another individual might indicate no concern about the same medication but have issues with adherence to other medications administered at higher frequencies due to a busy work schedule. An instance of the ML model 165 for the first individual could be configured with a bias to output a higher probability of factors related to the medication identified by that individual. Another instance of the ML model 165 for the second individual could have higher weights assigned to side effects known to cause low adherence (e.g., higher dosing frequency). Therefore, even if the two individuals have the same or similar measurement data, the ML models 165 for these two individuals may produce different expected results.

[0076] In some embodiments, model applicator 145 may apply measurement 215 in response to the elapsed time period defined by instruction 205. Model applicator 145 may wait to apply measurement 215 received by user device 110 or instrument device 135 within the time period defined by instruction 205. After the time period has elapsed, model applicator 145 may apply measurement 215 to ML model 165. In some embodiments, model applicator 145 may apply one or more subsequent physiological measurements to ML model 165 after data collector 140 receives such measurements.

[0077] Based on the application of measurement 215 to ML model 165, ML model 165 can calculate, determine, or otherwise generate at least one metric 305A-N (collectively referred to as metric 305). Metric 305 can identify or indicate expected outcomes related to the weight-loss medication for user 210. Metric 305 can be for a subsequent time period relative to the acquisition of measurement 215. The time period of metric 305 can be future relative to the time period of measurement 215 and can have any range between 1 day and 6 months. The expected outcome of metric 305 can identify or include at least one dosing parameter of the weight-loss medication. Dosing parameters can include at least one or any combination of the following: dosage of the weight-loss medication, time of administration of the weight-loss medication, frequency of administration, route of administration, dose escalation regimen, and dosing condition.

[0078] In some embodiments, ML model 165 may determine metric 305 based on at least one of the following: the mean of a sample group, a weighted combination of sample groups, or a comparison with a training dataset 180 including sample groups. For example, ML model 165 may determine metric 305 based on the mean of sample measurements 215' for each drug identifier 310'. As another example, ML model 165 may determine metric 305 based on comparing user 210's information along with measurements 215' with sample measurements 215' for each sample user. For example, ML model 165 may identify the sample user with the highest similarity to user 210 (e.g., weight, height, side effect preferences, weight loss goals, drug dosage) and generate metric 305 based on the sample metric 305' of the sample user with the highest similarity. ML model 165 may also determine metric 305 based on user 210's responses to a side effect questionnaire. Based on the questionnaire, ML model 165 may adjust metric 305 in response to side effects (e.g., nausea) that user 210 wishes to avoid.

[0079] In some embodiments, ML model 165 may calculate, determine, or otherwise generate a set of metrics 305 corresponding to a group of weight-loss drugs. The weight-loss drug group may be selected from GLP-1 receptor agonists or GIP receptor agonists. GLP-1 receptor agonists may be selected from one or more of semaglutide, liraglutide, exenatide, and dulaglutide, while GIP receptor agonists include tezepatide. In some embodiments, the drug may include any analogue of GLP-1 RA or GIP. The drug may include functionally equivalent peptides or therapeutic agents. Furthermore, the drug may include any drug demonstrated to be effective in treating obesity and obesity-related conditions. For example, the drug may include agents capable of agonizing GLP-1 or GIP, or drugs capable of inducing fat reduction and / or suppressing the user's appetite. Each metric 305 may identify or indicate an expected outcome related to the weight-loss drug for the user 210. Expected outcomes may identify or include at least one dosing parameter of the weight-loss drug.

[0080] In some embodiments, the expected outcome of measurement 305 may include identifying at least one of treatment discontinuation, side effects, or treatment effectiveness. Side effects may be selected from nausea, vomiting, diarrhea, early satiety, loss of appetite, anorexia, dizziness, tachycardia, indigestion, headache, hypoglycemia, kidney or ureteral stones, pancreatitis, diabetic retinopathy, depression, suicidal ideation or attempt, abdominal pain, acute kidney injury, muscle wasting and atrophy, constipation, or any combination thereof. Expected outcomes may identify side effects associated with at least one of the drug and dosing parameters of user 210.

[0081] In some embodiments, the model applicator 145 may generate a set of metrics 305 for the expected outcome parameter set based on applying the measurement 215 to the ML model 165. The expected outcome may include at least one expected outcome parameter. Expected outcome parameters may include at least one or any combination of termination time, termination reason, termination probability, and termination relief. For example, expected outcomes may include expected outcome parameters related to treatment termination. Expected outcome parameters may also include at least one or any combination of side effect onset time, side effect duration, side effect probability, and side effect relief.

[0082] In some embodiments, the expected outcome of metric 305 may include parameters related to side effects. Expected outcome parameters may also include at least one or any combination of weight loss, fat reduction, fasting blood glucose, cholesterol levels, hormone levels, duration of fat reduction, risk of weight regain, and change in body mass index. Expected outcomes may include parameters related to the therapeutic effect of the weight-loss drug. For example, model applicator 145 may generate metric 305 for the onset and duration of side effects for each weight-loss drug. In another example, model applicator 145 may generate metric 305 that identifies predicted changes (e.g., increases or decreases) in body mass index below a certain threshold (e.g., 25-30).

[0083] Using metric 305, metric evaluator 150 can identify or select at least one drug identifier 310 from a set of drug identifiers 310. This set of drug identifiers 310 may include weight-loss drugs. In some embodiments, metric evaluator 150 may select a weight-loss drug for user 210 from this set of weight-loss drugs. Drug identifier 310 may indicate the drug selected for user 210 based on metric 305. In some embodiments, drug identifier 310 may include dosing parameters, such as route of administration and frequency. In some embodiments, metric evaluator 150 may select at least one weight-loss drug based on a comparison between metric 305 for each weight-loss drug and at least one threshold. The threshold may indicate, define, or otherwise identify the value of metric 305 at which the corresponding weight-loss drug is selected. If metric 305 meets (e.g., is greater than or equal to) the threshold, metric evaluator 150 may select the corresponding weight-loss drug for user 210. Otherwise, if metric 305 does not meet (e.g., is less than) the threshold, metric evaluator 150 may exclude the corresponding weight-loss drug for user 210.

[0084] In some embodiments, the measurement evaluator 150 may select a weight-loss drug for user 210 from a group of weight-loss drugs based on a set of measurements 305. For example, the measurement evaluator 150 may select and generate a drug identifier 310 based on the weight-loss drug with the lowest probability of discontinuation, the lowest probability of side effects, and the highest rate of fat reduction. In some embodiments, the set of measurements 305 includes measurements 305 of a set of dosing parameters for the weight-loss drug. In some embodiments, the measurement evaluator 150 may select a weight-loss drug based on predicted side effects that may occur in user 210. In response to predicted side effects (corresponding to selections on a side effect questionnaire that user 210 wishes to avoid), the measurement evaluator 150 selects different weight-loss drugs. In some embodiments, the measurement evaluator 150 selects one or more weight-loss drugs for user 210 and / or user 210's clinician to choose from. Thus, the measurement evaluator 150 may generate multiple drug identifiers 310 and multiple expected outcomes associated with each drug identifier 310.

[0085] In some embodiments, the measurement evaluator 150 may also use measurement 305 and / or drug identifier 310 to generate interventions to mitigate and / or resolve side effects indicated by the expected outcome. For example, in response to measurement 305 indicating nausea during the administration of a selected drug, the measurement evaluator 150 may provide interventions such as drinking more water and avoiding fatty foods. The measurement evaluator 150 may also map interventions based on the onset time, duration, and probability of side effects associated with drug identifier 310.

[0086] Now for reference Figure 4 This diagram depicts a block diagram of a process 400 for generating a message 405 using a metric 305 and a drug identifier 310 within system 100. Process 400 may include or correspond to operations performed by system 100 for receiving and processing data provided by user 210. Under process 400, a simulation processor 155 executing on session management service 105 can generate at least one simulation 410. Simulation 410 can identify expected outcome groups at corresponding time point groups. Simulation 410 can identify expected outcome parameters over a time period including that time point group. For example, simulation 410 may show the probability of side effects occurring during the duration of a treatment regimen (e.g., ranging from 1 week to 6 months). To generate simulation 410, simulation processor 155 can identify expected outcome groups and expected outcome parameters over a time period by applying the measurement 215 to ML model 165 over multiple time periods. The time periods can be progressively further back in time, such as from 1 day to 6 months. Simulation processor 155 can generate simulation 410 for each expected outcome in the expected outcome group.

[0087] Using the expected results, simulation processor 155 can generate a representation of the expected results group. Simulation 410 can include a representation of the expected results group. This representation can include at least one of the following: a timeline (e.g., a measure showing how the expected results change over time), a graph (e.g., expected results categorized by type), a video (e.g., a video showing how the values ​​of the expected results change over time), audio (e.g., a narration of the expected results), or an icon (e.g., an animation). For example, simulation 410 can include an icon showing the user 210's weight loss at a time point group. The size of the icon can vary based on the expected results identified in simulation 410.

[0088] Simultaneously, output generator 160 can generate, create, or otherwise produce at least one message 405. The generation of message 405 is based on metric 305 and drug identifier 310. The generation and delivery of message 405 can be scheduled (e.g., at intervals between 5 minutes and 2 weeks). Message 405 can identify or indicate expected results related to a weight loss metric. In some embodiments, output generator 160 can generate message 405 to include metric 305 and drug identifier 310, etc. Drug identifier 310 can be selected from a set of drug identifiers 310 (corresponding to weight loss drugs) using metric 305.

[0089] In some embodiments, output generator 160 may generate message 405 to include information derived from or generated from metric 305, drug identifier 310, or simulation 410, etc. Output generator 160 may generate message 405 to include information based on a template. The template may include a set of predefined content (e.g., text, images, video, or audio) with one or more placeholders to include metric 305, drug identifier 310, or simulation 410, etc. Message 405 may indicate an expected outcome related to a weight-loss drug. For example, output generator 160 may extract information about the expected outcome to include in message 405. In this case, output generator 160 may include expected outcome parameters in message 405, such as the duration of fat reduction associated with drug identifier 310. Output generator 160 may insert expected outcome parameters (e.g., duration of fat reduction and drug) into the template to generate message 405. Message 405 may include the expected outcome associated with drug identifier 310. In some embodiments, message 405 may include interventions to mitigate and / or resolve side effects.

[0090] In some embodiments, output generator 160 may generate message 405 to include simulation 410 (e.g., a representation of a set of expected results). In some embodiments, message 405 may include simulation 410. After generating simulation 410, simulation processor 155 may provide simulation 410 to output generator 160 for inclusion in message 405. In this case, message 405 includes both drug identifier 310 (e.g., a selected weight-loss drug) and simulation 410. Both drug identifier 310 and simulation 410 may be provided to user device 110 and / or the clinician of user 210. Drug identifier 310 and simulation 410 may be displayed together or sequentially on user device 110. As message 405 is generated, output generator 160 may transmit, send, or otherwise provide message 405 to user device 110. In some embodiments, output generator 160 may also provide message 405 to a computing device associated with the clinician of user 210.

[0091] Upon receipt, application 125 on user device 110 may present, display, or otherwise present information based on message 405 via user interface 130. In some embodiments, a computing device associated with a clinician may receive message 405 and present information based on message 405. This information may include or identify metrics 305 and drug identifiers 310. For example, application 125 may display a set of metrics 305 related to the type of weight-loss drug, the likelihood of side effects, and the likelihood of adherence. In some embodiments, application 125 may display information identifying interventions for user 210. In some embodiments, application 125 may present, display, or otherwise present simulation 410 via user interface 130. Figure 5A-11 An example of message 405 presented on user device 110 is depicted.

[0092] Using the information presented through user interface 130, user 210 (or a clinician examining user 210) can determine whether to take or be administered at least one drug 415 corresponding to drug identifier 310. Drug 415 may be provided by, for example, user 210's clinician. Drug 415 may include, for example, a GLP-1 receptor agonist or a GIP receptor agonist (e.g., as detailed herein). User 210 and / or user 210's clinician may administer drug 415 according to the dosing parameters indicated in message 405. User 210 may use or take drug 415 corresponding to drug identifier 310.

[0093] The above process can be repeated any number of times. In some embodiments, the data collector 140 can retrieve or receive subsequent measurements in subsequent time periods. The model applicator 145 can generate another metric 305 for subsequent time periods by applying the subsequent measurements to the ML model 165. The metric generated after this time period may differ from the metric 305 generated before this time period. In some embodiments, the model applicator 145 generates a subsequent metric (e.g., after generating metric 305) indicating the expected subsequent outcome related to the user 210's subsequent weight-loss medication. The model applicator 145 can generate the subsequent metric after the time period in which the user 210 takes the weight-loss medication. In this case, using the ML model 165, the model applicator 145 can update the metric 305 based on changes represented by the user 210's subsequent physiological measurements. Based on the subsequent physiological measurements, the expected subsequent outcome may differ from the expected outcome, such as a decrease in the frequency of subsequent weight-loss medication administration. The subsequent weight-loss medication may differ from the expected weight-loss medication.

[0094] In some embodiments, the output generator 160 provides a follow-up message within a defined time period relative to the receipt of one or more subsequent physiological measurements. The output generator 160 may provide the follow-up message in response to the receipt of a subsequent metric. Thus, the follow-up message may indicate at least one of the following: a) selection of a weight-loss drug or a subsequent weight-loss medication based on a follow-up metric indicating a subsequent expected outcome, or b) a subsequent expected outcome related to a subsequent weight-loss medication. The defined time period may range from 1 second to 1 hour. In this case, the metric evaluator 150 may also generate a follow-up drug identifier. Thus, given a subsequent physiological measurement, the ML model 165 may generate at least one follow-up metric, the metric evaluator 150 may generate a follow-up drug v, and the output generator 160 may generate a follow-up message based on the follow-up drug ID and the follow-up metric within the defined time period. In some embodiments, the simulation processor 155 may generate a follow-up simulation to be included in the follow-up message.

[0095] In this way, the session management service 105 can aggregate physiological measurements from user 210 and use ML model 165 to determine the optimal weight-loss medication that matches the user's unique physiological profile, thereby enhancing weight-loss outcomes. By utilizing multimodal data in the form of different ranges of physiological parameters, the session management service 105 can algorithmically select targeted weight-loss medications and dynamically generate personalized predictions for the user. As more physiological measurements are received over time, the session management service 105 can dynamically adjust the expected outcomes, and consequently, dynamically adjust the recommended weight-loss medications. For example, as users progress in their weight loss, the session management service 105 can automatically adjust the dosage and frequency of medications based on updated physiological data, thereby improving the expected outcomes accordingly. The session management service 105 can integrate drug therapy and digital therapy to create a comprehensive, data-driven weight-loss solution, thereby reducing reliance on trial-and-error drug prescriptions and providing a personalized, adaptive approach to addressing user 210's obesity symptoms.

[0096] Figure 5A and 5B Screenshots depict an example group 500 of user interfaces for selecting a drug according to an illustrative embodiment. The user interface in group 500 may be part of application 125 and presented to user 210 who is to be given a weight-loss drug via user interface 130. User interface 505 may prompt the user to enter values ​​(e.g., one or more measurements) corresponding to displayed measurement fields. The user can then enter numerical values, text strings, or strings, etc., into the measurement fields. User interfaces 510 and 515 may provide the user with suggestions regarding the selected weight-loss drug. Suggestions may include expected results, such as the amount of weight loss or side effects associated with the weight-loss drug.

[0097] Figure 6A and 6B Screenshots depicting example group 600 of user interfaces for selecting medication according to illustrative embodiments are shown. The user interface in group 600 may be part of an application and presented via a user interface of a computing device associated with a clinician examining the user. User interface 605 may prompt the user to enter values ​​(e.g., one or more measurements) corresponding to displayed measurement fields. The user can then enter numerical values, text strings, or strings, etc., into the measurement fields. User interfaces 610 and 615 may display recommended weight-loss medications to the user or the user's doctor and prompt the user or the user's doctor to select a weight-loss medication. User interfaces 610 and 615 also display the possibility of side effects and the possibility of discontinuation (e.g., withdrawal risk).

[0098] Figure 7 Screenshots depict an example group 700 of user interfaces for selecting a drug according to an illustrative embodiment. The user interface in group 700 may be part of application 125 and presented via user interface 130. User interface 705 may be shown to the user's clinician (e.g., a physician). User interface 705 allows the clinician to select recommendations to be provided to the user (e.g., specific drugs and dosing parameters). For example, the selected recommendation might be to administer semaglutide twice daily for a week. In some aspects, user interface 705 may show and allow the user to select recommendations.

[0099] Figure 8 A screenshot depicts an example group 800 of a user interface for selecting a drug according to an illustrative embodiment. The user interface in group 800 may be part of application 125 and is presented via user interface 130. User interface 805 displays a notification to the user indicating the onset of side effects related to the weight-loss drug. This notification may be generated based on the user's wearable technology. The notification may identify actions to be taken to prevent or mitigate the side effects.

[0100] Figure 9 Screenshots depict an example group 900 of user interfaces for selecting medication according to an illustrative embodiment. The user interface in group 900 may be part of application 125 and is presented via user interface 130. User interface 905 may be presented to the user's clinician and provides suggestions for easing withdrawal and a predicted discontinuation time for the user to stop taking the weight-loss medication.

[0101] Figure 10Screenshots depict an example group 1000 of user interfaces for selecting medication according to an illustrative embodiment. The user interface in group 1000 may be part of application 125 and is presented via user interface 130. User interface 1005 displays a simulation of weight-loss drug recommendations. For example, the simulation includes a graph showing weight loss and side effects over time. The graph can compare multiple weight-loss drug recommendations.

[0102] Figure 11 Screenshots depict an example group 1100 of user interfaces for selecting medication according to an illustrative embodiment. The user interface in group 1100 may be part of application 125 and is presented via user interface 130. User interface 1105 may prompt the user to enter values ​​(e.g., one or more measurements) corresponding to displayed measurement fields. The user can then enter numerical values, text strings, or strings, etc., into the measurement fields. Both user interfaces 1110 and 1115 display weight-loss medication recommendations, along with predicted side effects and weight loss over time. User interfaces 1110 and 1115 also allow the user to select medication based on the information provided by user interfaces 1110 and 1115.

[0103] Figure 12 A flowchart depicts a method 1200 for selecting a medication for a user to address obesity according to an illustrative embodiment. Method 1200 can be performed by any component of system 100, such as session management service 105, user device 110, or user 210. In method 1200, one or more processors may provide instructions (1202). These instructions may include one or more measurement fields for user input. The one or more processors may receive measurement values ​​from the user (1204). Measurement values ​​may be input by the user and / or an instrument worn by the user. The one or more processors may then apply the measurement values ​​to a machine learning model (1206). The machine learning model may be trained on a dataset including sample measurement values, metrics, and medication IDs. The machine learning model may generate metrics (1208). These metrics may indicate the expected outcome of the weight-loss medication. The metrics may be a set of metrics for each weight-loss medication in a weight-loss medication group. The one or more processors may select a medication (1210). The one or more processors may select a medication based on the set of metrics of the weight-loss medication group. The one or more processors may provide a message (1212). This message may be based on the medication and the metrics.

[0104] In some embodiments, this disclosure provides a method for selecting a weight-loss drug for a user suffering from obesity, comprising: receiving one or more physiological measurements of the user via one or more processors; applying the one or more physiological measurements to a machine learning model via one or more processors, wherein the machine learning model is trained using multiple examples, each example including one or more sample physiological measurements of a sample user and a corresponding sample weight-loss drug administered to the sample user; generating a metric for the user indicating an expected outcome related to the weight-loss drug based on applying the one or more physiological measurements to the machine learning model via one or more processors; and providing a message indicating at least one of the selection of a weight-loss drug to a user device associated with the user via the one or more processors based on the metric indicating the expected outcome or the expected outcome related to the weight-loss drug.

[0105] In some embodiments, the method may further include selecting a weight-loss drug from a plurality of weight-loss drugs by one or more processors based on a plurality of expected outcomes associated with the weight-loss drugs.

[0106] In some embodiments, one or more physiological measurements may include at least one of the following: body mass index, weight, blood pressure, heart rate, smoking status, glucose excretion, comprehensive metabolomics, complete blood cell count, lipase level, thyroid group, magnesium level, HgA1c, fasting blood glucose, energy expenditure, physical activity, hormone level, weight, body fat percentage, genetic markers, gut microbiome assessment, or energy intake.

[0107] In some embodiments, the machine learning model may include one or more corresponding weights to generate one or more values, the one or more corresponding weights including at least one of binary weights or continuous weights; and wherein generating a metric further includes generating a metric based on one or more values ​​by one or more processors. The weight-loss drug may be selected from GLP-1 receptor agonists or GIP receptor agonists. GLP-1 receptor agonists may be selected from one or more of semaglutide, liraglutide, exenatide, and dulaglutide, and wherein GIP receptor agonists include tezepamide.

[0108] In some embodiments, the expected outcome may also include at least one administration parameter of the weight-loss drug, including at least one of the following: dosage of the weight-loss drug, time of administration of the weight-loss drug, frequency of administration, route of administration, dose escalation scheme, administration conditions, or any combination thereof.

[0109] In some embodiments, the expected outcome may also include identifying at least one of treatment discontinuation, side effects, or treatment effectiveness. Side effects are selected from nausea, vomiting, diarrhea, early satiety, loss of appetite, anorexia, dizziness, rapid heart rate, indigestion, headache, hypoglycemia, kidney or ureteral stones, pancreatitis, diabetic retinopathy, depression, suicidal ideation or attempt, abdominal pain, acute kidney injury, muscle wasting and atrophy, constipation, or any combination thereof.

[0110] In some embodiments, the generation metric also includes multiple metrics based on applying one or more physiological measurements to a machine learning model to generate multiple expected outcome parameters.

[0111] In some embodiments, the expected outcome may further include at least one expected outcome parameter, which includes at least one or any combination of termination time, termination reason, termination probability, and termination relief. In another embodiment, the expected outcome may further include at least one expected outcome parameter, which includes at least one or any combination of side effect onset time, side effect duration, side effect probability, and side effect relief. In yet another embodiment, the expected outcome may further include at least one or any combination of weight loss, fat reduction, fasting blood glucose, cholesterol level, hormone level, duration of fat reduction, risk of weight rebound, and change in body mass index.

[0112] In some embodiments, the method may further include generating a simulation using one or more processors, the simulation identifying multiple expected outcomes at corresponding multiple time points. The simulation may include representations of the multiple expected outcomes at corresponding multiple time points, wherein the representation includes at least one of timelines, graphs, videos, audio, or icons. The multiple expected outcomes identified by the simulation may include at least one expected outcome parameter, which includes at least one of termination time, termination reason, termination probability, termination relief, or any combination thereof. In another embodiment, the multiple expected outcomes identified by the simulation may include at least one expected outcome parameter, which includes at least one of side effect onset time, side effect duration, side effect probability, side effect relief, or any combination thereof. In another embodiment, the multiple expected outcomes identified by the simulation may include expected outcome parameters, which include at least one of weight loss, fat reduction, fasting blood glucose, cholesterol levels, hormone levels, duration of fat reduction, risk of weight rebound, and changes in body mass index, or any combination thereof.

[0113] In some embodiments, the user has a BMI greater than 25, a body fat percentage greater than 20%, and suffers from type 1 diabetes, type 2 diabetes, or non-alcoholic steatohepatitis (NASH). The message is provided to the user's device or the user's clinician. One or more physiological measurements of the user are obtained through at least one of the user's device or instruments worn on the user.

[0114] In some embodiments, generating a metric indicating an expected outcome may include determining a metric by one or more processors based on at least one of: (i) an average of multiple examples, (ii) a weighted combination of multiple examples, or (iii) a comparison with a dataset consisting of multiple examples. Receiving one or more physiological measurements may also include receiving one or more physiological measurements from at least one of a user device or instrument device by one or more processors over a time period. Applying to a machine learning model may also include applying one or more physiological measurements to a machine learning model by one or more processors in response to the passage of time. Generating a metric may also include generating a metric indicating an expected outcome related to the weight-loss drug in subsequent time periods by one or more processors.

[0115] In some embodiments, the method further includes: receiving one or more subsequent physiological measurements of a user via one or more processors; applying the one or more subsequent physiological measurements to a machine learning model via one or more processors in response to the receipt of the one or more subsequent physiological measurements; generating a subsequent metric via one or more processors based on the application of the one or more subsequent physiological measurements to the machine learning model, the subsequent metric indicating a subsequent expected outcome related to the user's subsequent weight-loss medication; and providing a subsequent message via one or more processors to a user device within a defined time period relative to the receipt of the one or more subsequent physiological measurements, the subsequent message indicating at least one of the following: a) selection of a weight-loss medication or a subsequent weight-loss medication based on the subsequent metric indicating the subsequent expected outcome, or b) a subsequent expected outcome related to the subsequent weight-loss medication. In another embodiment, the defined time period may range from 1 second to 1 hour.

[0116] B. Network and Computing Environment

[0117] The various operations described in this article can be implemented on a computer system. Figure 13A simplified block diagram of a representative server system 1300, client computing system 1314, and network 1326 that can be used to implement certain embodiments of this disclosure is shown. In various embodiments, server system 1300 or similar systems can implement the services or servers or portions thereof described herein. Client computing system 1314 or similar systems can implement the clients described herein. System 100 described herein can be similar to server system 1300. Server system 1300 can have a modular design that incorporates multiple modules 1302 (e.g., blades in a blade server embodiment); although two modules 1302 are shown, any number of modules can be provided. Each module 1302 may include a processing unit 1304 and local storage 1306.

[0118] Processing unit 1304 may include a single processor, which may have one or more cores, or multiple processors. In some embodiments, processing unit 1304 may include a general-purpose main processor and one or more dedicated coprocessors, such as a graphics processor, a digital signal processor, etc. In some embodiments, some or all of processing unit 1304 may be implemented using custom circuitry, such as an application-specific integrated circuit (ASIC) or a field-programmable gate array (FPGA). In some embodiments, such an integrated circuit executes instructions stored on the circuit itself. In other embodiments, processing unit 1304 may execute instructions stored in local memory 1306. Processors of any type and in any combination may be included in processing unit 1304.

[0119] Local storage 1306 may include volatile storage media (e.g., DRAM, SRAM, SDRAM, etc.) or non-volatile storage media (e.g., disk or optical disk, flash memory, etc.). The storage media incorporated in local storage 1306 may be fixed, removable, or upgradeable as needed. Local storage 1306 may be physically or logically divided into various sub-units, such as system memory, read-only memory (ROM), and permanent storage devices. System memory may be a read-write memory device or a volatile read-write memory, such as dynamic random access memory. System memory may store some or all of the instructions and data required by processing unit 1304 during operation. ROM may store static data and instructions required by processing unit 1304. Permanent storage devices may be non-volatile read-write memory devices that can store instructions and data even when module 1302 is powered off. The term "storage media" as used herein includes any medium that can store data indefinitely (subject to overlay, electrical interference, power outages, etc.), but excludes carrier waves and transient electronic signals propagated via wireless or wired connections.

[0120] In some embodiments, local storage 1306 may store one or more software programs executed by processing unit 1304, such as operating systems or programs that implement various server functions, such as the functions of system 130 or any other system described herein, or any other server associated with system 130 or any other system described herein.

[0121] "Software" generally refers to a sequence of instructions that, when executed by processing unit 1304, cause server system 1300 (or a portion thereof) to perform various operations, thereby defining one or more specific machine embodiments for executing and implementing software program operations. Instructions may be stored as firmware residing in read-only memory or program code stored in non-volatile storage media, which can be read into volatile working memory for execution by processing unit 1304. Software may be implemented as a single program or a collection of separate programs or program modules that interact as needed. From local storage 1306 (or non-local storage described below), processing unit 1304 may retrieve program instructions to be executed and data to be processed in order to perform the various operations described above.

[0122] In some server systems 1300, multiple modules 1302 can be interconnected via a bus or other interconnect 1308 to form a local area network that supports communication between the modules 1302 and other components of the server system 1300. The interconnect 1308 can be implemented using various technologies, including server racks, hubs, routers, etc.

[0123] The wide area network (WAN) interface 1310 can provide data communication capabilities between a local area network (e.g., via interconnection 1308) and a network 1326 (such as the Internet). Other technologies can be used to couple the server system to communication with the network 1326, including wired (e.g., Ethernet, IEEE 802.3 standard) or wireless technologies (e.g., Wi-Fi, IEEE 802.11 standard).

[0124] In some embodiments, local storage 1306 is designed to provide working memory for processing unit 1304, providing fast access to programs or data to be processed while reducing traffic on interconnect 1308. Storage of large amounts of data can be provided on a local area network via one or more mass storage subsystems 1312 that can be connected to interconnect 1308. Mass storage subsystem 1312 can be based on magnetic, optical, semiconductor, or other data storage media. Direct-attached storage, storage area networks, network-attached storage, etc., can be used. Any data storage or other collection of data generated, used, or maintained by a service or server as described herein can be stored in mass storage subsystem 1312. In some embodiments, additional data storage resources (potentially with increased latency) can be accessed via WAN interface 1310.

[0125] Server system 1300 can operate in response to requests received via WAN interface 1310. For example, one of modules 1302 can implement monitoring functions and, in response to received requests, distribute discrete tasks to other modules 1302. Work assignment techniques can be used. While processing a request, results can be returned to the requester via WAN interface 1310. This operation can typically be automated. Furthermore, in some embodiments, WAN interface 1310 can interconnect multiple server systems 1300, thereby providing a scalable system capable of managing a large volume of activity. Other techniques for managing server systems and server farms (collections of cooperating server systems) can be used, including dynamic resource allocation and reallocation.

[0126] The server system 1300 can interact with various user-owned or user-operated devices via a wide area network (such as the Internet). Figure 13 An example of a user-operated device, namely client computing system 1314, is shown. Client computing system 1314 can be implemented as, for example, a consumer device, such as a smartphone, other mobile phone, tablet computer, wearable computing device (e.g., smartwatch, glasses), desktop computer, laptop computer, etc.

[0127] For example, the client computing system 1314 can communicate via WAN interface 1310. The client computing system 1314 may include computer components such as processing unit 1316, storage device 1318, network interface 1320, user input device 1322, and user output device 1324. The client computing system 1314 can be a computing device implemented in various forms, such as a desktop computer, laptop computer, tablet computer, smartphone, other mobile computing device, wearable computing device, etc.

[0128] Processing unit 1316 and storage device 1318 may be similar to processing unit 1304 and local storage 1306 described above. Appropriate devices can be selected based on the requirements to be arranged on client computing system 1314. For example, client computing system 1314 may be implemented as a "thin" client with limited processing power or a high-performance computing device. Client computing system 1314 may be equipped with program code executable by processing unit 1316 to enable various interactions with server system 1300.

[0129] Network interface 1320 can provide connectivity to network 1326, such as a wide area network (e.g., the Internet), to which the WAN interface 1310 of server system 1300 is also connected. In various embodiments, network interface 1320 may include a wired interface (e.g., Ethernet) or a wireless interface that implements various RF data communication standards (e.g., Wi-Fi, Bluetooth, or cellular data network standards (e.g., 3G, 4G, LTE, etc.)).

[0130] User input device 1322 may include any device (or multiple devices) through which a user provides signals to client computing system 1314; client computing system 1314 may interpret the signals as indications of specific user requests or information. In various embodiments, user input device 1322 may include any one or all of the following: keyboard, touchpad, touchscreen, mouse or other pointing device, scroll wheel, click wheel, dial pad, button, switch, keypad, microphone, etc.

[0131] User output device 1324 may include any device through which client computing system 1314 can provide information to a user. For example, user output device 1324 may include display-to-display images generated by or transmitted to client computing system 1314. The display may incorporate various image generation technologies, such as liquid crystal displays (LCDs), light-emitting diode (LED) displays (including organic light-emitting diodes (OLEDs)), projection systems, cathode ray tubes (CRTs), etc., and supporting electronic devices (e.g., digital-to-analog converters or analog-to-digital converters, signal processors, etc.). Some embodiments may include devices that function as both input and output devices (such as touchscreens). In some embodiments, other user output devices 1324 may be provided in addition to or in lieu of a display. Examples include indicator lights, speakers, haptic "display" devices, printers, etc.

[0132] Some embodiments include electronic components, such as microprocessors, storage, and memories, that store computer program instructions in a computer-readable storage medium. Many of the features described herein can be implemented as processes specified as a set of program instructions encoded on a computer-readable storage medium. When these program instructions are executed by one or more processing units, they cause the processing units to perform various operations indicated in the program instructions. Examples of program instructions or computer code include machine code, such as machine code generated by a compiler, and files containing higher-level code executed by a computer, electronic component, or microprocessor using an interpreter. With appropriate programming, processing units 1304 and 1316 can provide various functionalities for server system 1300 and client computing system 1314, including any of the functions or other functions described herein that are performed by the server or client.

[0133] It should be understood that server system 1300 and client computing system 1314 are illustrative and can be varied and modified. Computer systems used in conjunction with embodiments of this disclosure may have additional functionalities not specifically described herein. Furthermore, while server system 1300 and client computing system 1314 are described with reference to specific blocks, it should be understood that these blocks are defined for ease of description and are not intended to imply a specific physical arrangement of component portions. For example, different blocks may, but do not necessarily, reside in the same facility, the same server rack, or the same motherboard. Moreover, blocks do not necessarily correspond to physically different components. Blocks may be configured to perform various operations, such as by programming a processor or providing appropriate control circuitry, and various blocks may or may not be reconfigured, depending on how the initial configuration is obtained. Embodiments of this disclosure can be implemented in a variety of devices, including electronic devices implemented using any combination of circuitry and software.

[0134] While this disclosure has described specific embodiments, those skilled in the art will recognize that various modifications can be made. Embodiments of this disclosure can be implemented using various computer systems and communication technologies, including but not limited to the specific examples described herein. Embodiments of this disclosure can be implemented using any combination of dedicated components or programmable processors or other programmable devices. The various processes described herein can be implemented in any combination on the same or different processors. When a component is described as being configured to perform certain operations, such configuration can be implemented, for example, by designing electronic circuits to perform the operations, by programming programmable electronic circuits (e.g., microprocessors), or any combination thereof. Furthermore, while the above embodiments may refer to specific hardware and software components, those skilled in the art will recognize that different combinations of hardware or software components can also be used, and specific operations described as implemented in hardware can also be implemented in software, and vice versa.

[0135] Computer programs incorporating the various features of this disclosure can be encoded and stored on a variety of computer-readable storage media; suitable media include magnetic disks or magnetic tapes, optical storage media (e.g., optical discs (CDs) or digital versatile optical discs (DVDs), flash memory, and other non-transitory media). Computer-readable media encoding program code can be packaged together with a compatible electronic device, or the program code can be provided separately from the electronic device (e.g., downloaded via the Internet or as a separately packaged computer-readable storage medium).

[0136] Therefore, although this disclosure has been described with reference to specific embodiments, it should be understood that this disclosure is intended to cover all modifications and equivalents within the scope of the following claims.

Claims

1. A method for selecting weight-loss drugs for users suffering from obesity, comprising: One or more physiological measurements of the user are received through one or more processors; The one or more physiological measurements are applied to a machine learning model by the one or more processors, wherein the machine learning model is trained using multiple examples, each example including one or more sample physiological measurements of a sample user and a corresponding sample weight loss drug administered to the sample user; The one or more processors generate metrics for the user that indicate expected outcomes related to weight-loss drugs by applying the one or more physiological measurements to the machine learning model; as well as The one or more processors provide a message indicating the selection of at least one weight loss drug to a user device associated with the user, based on the metric indicating the expected result or the expected result related to the weight loss drug.

2. The method of claim 1, further comprising selecting a weight-loss drug from the plurality of weight-loss drugs by the one or more processors based on a plurality of expected outcomes associated with the plurality of weight-loss drugs.

3. The method according to claim 1, wherein, The one or more physiological measurements include at least one of the following: body mass index, weight, blood pressure, heart rate, smoking status, glucose excretion, comprehensive metabolomics, complete blood cell count, lipase level, thyroid group, magnesium level, HgA1c, fasting blood glucose, energy expenditure, physical activity, hormone level, weight, body fat percentage, genetic markers, gut microbiome assessment, or energy intake.

4. The method according to claim 1, wherein, The machine learning model includes one or more corresponding weights to generate one or more values, and the one or more corresponding weights include at least one of binary weights or continuous weights; as well as Generating the metric further includes generating the metric based on the one or more values ​​through the one or more processors.

5. The method according to claim 1, wherein, The weight-loss drug is selected from GLP-1 receptor agonists or GIP receptor agonists.

6. The method according to claim 5, wherein, The GLP-1 receptor agonist is selected from one or more of semaglutide, liraglutide, exenatide, and dulaglutide, wherein the GLP-1 receptor agonist includes tezepatide.

7. The method according to claim 1, wherein, The expected results also include at least one administration parameter of the weight-loss drug, which includes at least one or any combination of the following: dosage of the weight-loss drug, administration time of the weight-loss drug, administration frequency, route of administration, dose escalation scheme, and administration conditions.

8. The method according to claim 1, wherein, The expected results also include identifying at least one of treatment discontinuation, side effects, or treatment effectiveness.

9. The method according to claim 8, wherein, The side effects are selected from nausea, vomiting, diarrhea, early satiety, loss of appetite, anorexia, dizziness, rapid heart rate, indigestion, headache, hypoglycemia, kidney or ureteral stones, pancreatitis, diabetic retinopathy, depression, suicidal ideation or attempt, abdominal pain, acute kidney injury, muscle wasting and atrophy, constipation, or any combination thereof.

10. The method according to claim 1, wherein, Generating the metrics also includes multiple metrics based on applying the one or more physiological measurements to the machine learning model to generate multiple expected result parameters.

11. The method according to claim 8, wherein, The expected outcome also includes at least one expected outcome parameter, which includes at least one of termination time, termination reason, termination probability, and termination mitigation, or any combination thereof.

12. The method according to claim 8, wherein, The expected outcome also includes at least one expected outcome parameter, which includes at least one of the following: side effect onset time, side effect duration, side effect probability, and side effect relief, or any combination thereof.

13. The method according to claim 8, wherein, The expected results also include expected result parameters, which include at least one or any combination of weight loss, fat reduction, fasting blood glucose, cholesterol level, hormone level, duration of fat reduction, risk of weight rebound, and changes in body mass index.

14. The method according to claim 1, further comprising: Simulations are generated by the one or more processors, and the simulations identify multiple expected results at corresponding multiple time points.

15. The method according to claim 14, wherein, The simulation includes representations of the multiple expected results at the corresponding multiple points in time, wherein the representation includes at least one of timelines, charts, videos, audio, or icons.

16. The method of claim 14, wherein, The plurality of expected results identified by the simulation include at least one expected result parameter, which includes at least one of termination time, termination reason, termination probability, termination mitigation, or any combination thereof.

17. The method of claim 14, wherein, The plurality of expected outcomes identified by the simulation include at least one expected outcome parameter, which includes at least one of side effect onset time, side effect duration, side effect probability, and side effect relief, or any combination thereof.

18. The method according to claim 14, wherein, The plurality of expected outcomes identified by the simulation include expected outcome parameters, which include at least one or any combination of weight loss, fat reduction, fasting blood glucose, cholesterol level, hormone level, duration of fat reduction, risk of weight rebound, and change in body mass index.

19. The method according to claim 1, wherein, The user has a BMI greater than 25, a body fat percentage greater than 20%, and suffers from type I diabetes, type II diabetes, or non-alcoholic steatohepatitis (NASH).

20. The method according to claim 1, wherein, The message is provided to the user device or the user's clinician.

21. The method according to claim 1, wherein, The user's one or more physiological measurements are obtained through at least one of the user's device or instruments on the user's person.

22. The method according to claim 1, wherein, Generating the metric indicating the expected result includes determining the metric by the one or more processors based on at least one of the following: (i) the average of the plurality of examples, (ii) a weighted combination of the plurality of examples, or (iii) a comparison with a dataset consisting of the plurality of examples.

23. The method according to claim 1, wherein, Receiving the one or more physiological measurements also includes receiving the one or more physiological measurements from at least one of the user equipment or instrumentation devices via the one or more processors within a time period. The application to the machine learning model further includes applying the one or more physiological measurements to the machine learning model in response to the passage of the time period via the one or more processors. The generation of the metric also includes generating the metric through the one or more processors that indicates the expected outcome in relation to the weight-loss drug in subsequent time periods.

24. The method according to claim 1, further comprising: The user receives one or more subsequent physiological measurements via the one or more processors; The one or more processors, in response to the receipt of the one or more subsequent physiological measurements, apply the one or more subsequent physiological measurements to the machine learning model; The one or more processors generate subsequent metrics based on applying the one or more subsequent physiological measurements to the machine learning model, the subsequent metrics indicating expected subsequent outcomes related to the user's subsequent weight loss medication; as well as The one or more processors provide subsequent messages to the user equipment within a defined time period relative to the reception of the one or more subsequent physiological measurements, the subsequent messages indicating at least one of the following: a) Selection of the weight-loss drug or subsequent weight-loss drugs based on the subsequent metric indicating the expected subsequent outcome, or b) The expected subsequent results related to the subsequent weight loss medication.

25. The method according to claim 24, wherein, The time period is defined as ranging from 1 second to 1 hour.

26. A system comprising: One or more processors, which are configured as follows: Receive one or more physiological measurements from the user; One or more measurements are applied to a machine learning model, wherein the machine learning model is trained using multiple examples, each example including one or more sample physiological measurements of a sample user and a corresponding sample weight loss drug administered to the sample user; This is based on applying one or more physiological measurements to the machine learning model to generate a metric that indicates the expected outcome related to weight loss drugs for the user; as well as Based on the metric indicating the expected result or the expected result related to the weight loss drug, a message indicating the selection of at least one weight loss drug is provided to the user device associated with the user.

27. The system according to claim 26, wherein, The one or more processors are also configured to select the weight-loss drug from the plurality of weight-loss drugs based on multiple expected outcomes associated with the plurality of weight-loss drugs.

28. The system according to claim 26, wherein, The one or more physiological measurements include at least one of the following: body mass index, weight, blood pressure, heart rate, smoking status, glucose excretion, comprehensive metabolomics, complete blood cell count, lipase level, thyroid group, magnesium level, HgA1c, fasting blood glucose, energy expenditure, physical activity, hormone level, weight, body fat percentage, genetic markers, gut microbiome assessment, or energy intake.

29. The system according to claim 26, wherein, The machine learning model corresponds to weights to generate one or more values, and the one or more corresponding weights include at least one of binary weights or continuous weights; In order to generate the metric, the one or more processors are further configured to generate the metric based on the one or more values.

30. The system according to claim 26, wherein, The weight-loss drug is selected from GLP-1 receptor agonists or GIP receptor agonists.

31. The system according to claim 30, wherein, The GLP-1 receptor agonist is selected from one or more of semaglutide, liraglutide, exenatide, and dulaglutide, and the GLP-1 receptor agonist includes tezepatide.

32. The system according to claim 26, wherein, The expected results also include at least one administration parameter of the weight-loss drug, which includes at least one or any combination of the following: dosage of the weight-loss drug, administration time of the weight-loss drug, administration frequency, route of administration, dose escalation scheme, and administration conditions.

33. The system according to claim 26, wherein, The expected results also include identifying at least one of treatment discontinuation, side effects, or treatment effectiveness.

34. The system according to claim 33, wherein, The side effects are selected from nausea, vomiting, diarrhea, early satiety, loss of appetite, anorexia, dizziness, rapid heart rate, indigestion, headache, hypoglycemia, kidney or ureteral stones, pancreatitis, diabetic retinopathy, depression, suicidal ideation or attempt, abdominal pain, acute kidney injury, muscle wasting and atrophy, constipation, or any combination thereof.

35. The system according to claim 26, wherein, In order to generate the metrics, the one or more processors are also configured to generate multiple metrics based on applying the one or more physiological measurements to the machine learning model to generate multiple expected result parameters.

36. The system according to claim 33, wherein, The expected outcome also includes at least one expected outcome parameter, which includes at least one of termination time, termination reason, termination probability, and termination mitigation, or any combination thereof.

37. The system according to claim 33, wherein, The expected outcome also includes at least one expected outcome parameter, which includes at least one of the following: side effect onset time, side effect duration, side effect probability, and side effect relief, or any combination thereof.

38. The system according to claim 33, wherein, The expected results also include expected result parameters, which include at least one or any combination of weight loss, fat reduction, fasting blood glucose, cholesterol level, hormone level, duration of fat reduction, risk of weight rebound, and changes in body mass index.

39. The system of claim 26, wherein the one or more processors are further configured to generate simulations that identify multiple expected results at corresponding multiple time points.

40. The system according to claim 39, wherein, The simulation includes representations of the multiple expected results at the corresponding multiple points in time, wherein the representation includes at least one of timelines, charts, videos, audio, or icons.

41. The system according to claim 39, wherein, The plurality of expected results identified by the simulation include at least one expected result parameter, which includes at least one of termination time, termination reason, termination probability, termination mitigation, or any combination thereof.

42. The system according to claim 39, wherein, The plurality of expected outcomes identified by the simulation include at least one expected outcome parameter, which includes at least one of side effect onset time, side effect duration, side effect probability, and side effect relief, or any combination thereof.

43. The system according to claim 39, wherein, The plurality of expected outcomes identified by the simulation include expected outcome parameters, which include at least one or any combination of weight loss, fat reduction, fasting blood glucose, cholesterol level, hormone level, duration of fat reduction, risk of weight rebound, and change in body mass index.

44. The system according to claim 26, wherein, The user has a BMI greater than 25, a body fat percentage greater than 20%, and suffers from type I diabetes, type II diabetes, or non-alcoholic steatohepatitis (NASH).

45. The system according to claim 26, wherein, The message is provided to the user device or the user's clinician.

46. ​​The system according to claim 26, wherein, The user's one or more physiological measurements are obtained through at least one of the user's device or instruments on the user's person.

47. The system according to claim 26, wherein, In order to generate the metric indicating the expected result, the one or more processors are further configured to determine the metric, which includes determining the metric based on at least one of the following: (i) the average of the plurality of examples, (ii) a weighted combination of the plurality of examples, or (iii) a comparison with a dataset consisting of the plurality of examples.

48. The system according to claim 26, wherein, In order to receive the one or more physiological measurements, the one or more processors are also configured to receive the one or more physiological measurements from at least one of the user equipment or instrumentation devices within a time period. In order to apply the one or more physiological measurements to the machine learning model, the one or more processors are further configured to apply the one or more physiological measurements to the machine learning model in response to the passage of the time period. In order to generate the metric, the one or more processors are further configured to generate the metric indicating the expected results related to the weight-loss drug in subsequent time periods.

49. The system according to claim 26, wherein, The one or more processors are further configured to: Receive one or more subsequent physiological measurements from the user; In response to the receipt of the one or more subsequent physiological measurements, the one or more subsequent physiological measurements are applied to the machine learning model; The subsequent metric is generated by applying the one or more subsequent physiological measurements to the machine learning model, and the subsequent metric indicates the expected subsequent outcome related to the user's subsequent weight loss medication. as well as A follow-up message is provided to the user equipment within a defined time period relative to the receipt of the one or more subsequent physiological measurements, the follow-up message indicating at least one of the following: a) Selection of the weight-loss drug or subsequent weight-loss drugs based on the subsequent metric indicating the expected subsequent outcome, or b) The expected subsequent results related to the subsequent weight loss medication.

50. The system according to claim 49, wherein, The time period is defined as ranging from 1 second to 1 hour.

Images