Drug delivery device usage detection

Abstract

The present disclosure relates to a method and a drug delivery monitoring system for detecting a usage of a drug delivery device. The method comprises the steps of: Analyzing the received sensor unit data to determine the occurrence of a drug delivery device activation event, wherein the analysis involves comparing the operational data with predefined criteria for a drug delivery device usage, and providing a usage data set based on the analysis, wherein the usage data set includes information on the drug delivery device activation event.

Description

[0001] Title

[0002] Drug delivery device usage detection

[0003] Background

[0004] The present disclosure relates to a drug delivery monitoring system, a method for detecting a usage of a drug delivery device, and a method for verifying a drug administration.

[0005] Known intelligent assistants (such as "Siri" or "Alexa") may capture voices through a smartphone, smartwatch, and / or further electronic devices. Smartphones and / or smartwatches and their fitness and / or health software application may constantly capture body movements, emotional states and / or vital parameters. Additional cameras and smart home devices detect user movements and / or noises.

[0006] Drug delivery monitoring systems that use a variety of different data sources are becoming increasingly important, e.g., with respect to plausibility checks for the usage of a drug delivery device.

[0007] Summary

[0008] It is an object of the present disclosure to facilitate improvements associated with a drug delivery monitoring system for conducting plausibility checks on the usage of a drug delivery device.

[0009] This object is achieved by the subject matter of the independent claims. Advantageous embodiments and refinements are subject to dependent claims. The present disclosure is not restricted to the currently claimed subject-matter. Rather, this disclosure may also cover currently unclaimed subject-matter which, however, could provide improvements and / or be made subject to the claims as will be readily appreciated by the skilled reader.

[0010] One aspect of the disclosure relates to method for detecting a usage of a drug delivery device. The method may be a computer-implemented method and / or may be processed by a computing unit. The method may comprise the method step of: analyzing sensor unit data, e.g. received sensor unit data, to determine the occurrence of a drug delivery device activation event. The analysis may involve comparing operational data with predefined criteria for a drug delivery device usage.

[0011] The (received) sensor unit data may refer to the data collected by a sensor unit or a plurality of sensor units associated with a drug delivery device. The data may include various types of information such as time stamps, device status (e.g. on / off / idle), environmental conditions (e.g. temperature and / or humidity), patient's physiological data (e.g. heart rate and / or skin resistance), and / or the specific actions performed by the device (e.g. movement and / or activation signals). By collecting detailed data, e.g. directly, from the sensor unit, the user, patient and / or healthcare provider may achieve a more accurate and comprehensive understanding of the drug delivery device's usage and / or the user's or patient's condition. A real-time monitoring of critical parameters or quantities can support in identifying potential issues early, thus ensuring timely interventions and reducing the risk of adverse events. The data may allow for the customization and / or monitoring of drug delivery schedules and / or dosages based on the patient's unique needs and / or responses, leading e.g. to more effective treatments.

[0012] An activation event of a drug delivery device may refer to any action or sequence of actions in which the device's primary function, e.g. to administer or deliver, e.g. inject, a dose of drug to a patient, is initiated. The administration can be triggered manually by the patient or caregiver. The administration may occur based on a predefined administration schedule. The activation event may ensure that the medicament in the drug delivery device is delivered at the correct time, e.g. optimizing therapeutic effectiveness and patient compliance. This may minimize the risk of overdose or underdose by controlling the exact amount of medication dispensed during each activation event and / or it may allow for the documentation of each activation event, facilitating better patient monitoring and adherence tracking.

[0013] Within the context of the disclosure, operational data may encompass real-time data of the drug delivery device during its operation, which may be monitored by the disclosed drug delivery monitoring system. This operational data may for example include data on device status, activation times, dose amounts, and / or any errors or malfunctions. A device monitoring may enable the detection of device malfunctions or deviations from expected performance, ensuring the reliability and safety of a drug delivery. It may support in assessing whether the user is using the device at all and / or as prescribed, which may be critical for evaluating treatment efficacy. Further, the monitoring facilitates the early identification of maintenance needs and / or troubleshooting requirements, potentially extending the device's lifespan. Predefined criteria for drug delivery device usage may refer to a set of conditions, protocols, and / or parameters established to guide and / or to verify the plausibility of the correct and / or safe use of the drug delivery device. These criteria may include dosage schedules, indications for use, contraindications, and / or operational thresholds (like battery levels and / or sensor readings). A standardization of treatment may ensure that a drug delivery, e.g. a drug administration, is carried out consistently and / or at the correct time in accordance with best medical practices, enhancing treatment outcomes. It may reduce the risk of incorrect usage by providing clear guidelines and / or thresholds for operation, thereby safeguarding patient health.

[0014] The method may comprise providing a usage data set based on the analysis. The usage data set may include information on the drug delivery device activation event.

[0015] The usage data set may allow for the tracking of when and / or how the drug delivery device is used, e.g. providing insights into patient compliance with prescribed medication regimens. The usage data set may enable early intervention in cases of non-compliance, potentially reducing the risk of adverse health outcomes. The usage data set may facilitate the collection and / or analysis of detailed usage information, e.g. enabling healthcare providers to make informed decisions based on empirical data. The usage data set may improve patient care through personalized treatment plans that may be optimized based on actual device usage patterns.

[0016] The usage data set may serve as a foundation for managing the inventory, maintenance, and / or update cycles of drug delivery devices more efficiently. It may enhance operational efficiency by ensuring that devices are in optimal working condition, e.g. ready for patient use. A detailed record of drug delivery device activation events may be recorded, contributing to the body of evidence supporting the effectiveness and reliability of the drug delivery device.

[0017] By analyzing usage data sets, healthcare providers may identify users and / or patients who may benefit from additional education and / or support regarding the proper use of their drug delivery device. The usage data set may enhances patient engagement and empowerment, e.g. leading to better health outcomes and increased satisfaction with treatment.

[0018] Within the context of the disclosure, a usage data set in the context of a drug delivery monitoring system (e.g. the one discussed in more detail below) may refer to the aggregation of data that captures how and / or when the drug delivery device is used. In the context of a drug delivery monitoring system, such a usage data set may include timestamps of drug administrations, dosages delivered (e.g. the size and / or the amount of the dose delivered), frequency of use, operational status of the device, and / or any user interactions and / or interventions. This data may be beneficial for monitoring adherence, for evaluating the effectiveness of treatment protocols, and / or for ensuring the proper functioning of the drug delivery device.

[0019] A centralized data management system may be used to collect data from a sensor unit or various sensor units. The management system may be capable of handling high volumes of data and / or data from multiple devices simultaneously. An algorithm may be used to clean the data by removing duplicates, correcting errors, filling missing values, and / or preprocess the data to convert it into a uniform format, making it easier to analyze. The sensor unit data may be encrypted during transmission to protect confidentiality and integrity. A security protocol for data transfer may be used. The sensor unit data may be stored in a secure and / or scalable environment. The sensor unit data may be stored in a local storage solution or a cloud-based storage ensuring they comply with healthcare data protection standards, such as HI PAA and / or GDPR.

[0020] The sensor unit data from a drug delivery device may be incorporated into a report or made accessible via platforms, websites, and / or software applications. This may not only ensure that the data is collected efficiently and accurately but also that it is presented in a user-friendly manner, e.g. enabling stakeholders to derive meaningful insights and take appropriate actions. Reports may summarize the findings from the data analysis. These reports may include graphs, charts, and / or tables to illustrate usage patterns, compliance rates, and / or any issues detected. Reports may be customized for different stakeholders, such as patients, healthcare providers, and / or device manufacturers. Websites, platforms, and / or software applications may allow users to interact with the data in real-time. A user-friendly interface may be provided through which users can view key metrics, receive alerts for anomalies, and / or track the effectiveness of drug delivery. Functionalities may be provided to export data or reports for further analysis and / or for sharing with healthcare providers. Tools may be provided that allow users to filter, search, and / or analyze the data based on specific parameters, enhancing the ability to find relevant information quickly.

[0021] According to at least one embodiment, the method comprises receiving sensor unit data, e.g. as operational data, from at least one sensor unit associated with a drug delivery device.

[0022] The functionality and reliability of the drug delivery monitoring system may be enhanced. By, e.g. continuously, receiving sensor data, the drug delivery monitoring system may precisely control the timing, dosage, and / or rate of drug delivery, e.g. ensuring that patients receive their medication exactly as prescribed. Further, operational data from the sensor unit may enable the drug delivery monitoring system to detect and / or respond to variables such as changes in environmental conditions or the patient's physical state, e.g. allowing for immediate adjustments to the delivery process to maintain efficacy and / or safety. The sensor data may be further analyzed, e.g. to predict drug delivery device failures and / or maintenance needs, e.g. expediently before they lead to a malfunction. This may ensure continuous operation and / or reducing the risk of missed medication doses. Further the user or patient safety may be increased through early detection of issues.

[0023] According to at least one embodiment, the method comprises transmitting the usage data set to a, e.g. designated, recipient. Transmitting the usage data set to a (designated) recipient offers several technical advantages, beneficial for enhancing the effectiveness, efficiency, and / or user experience of a drug delivery device.

[0024] By enabling the transmission of usage data sets to designated recipients, such as healthcare professionals and / or caregivers, the drug delivery monitoring system may ensure that one or more other entities, e.g. those responsible for the patient's care, have access to up-to-date information on medication adherence, drug delivery device functionality, and / or any issues and / or anomalies detected by the drug delivery monitoring system. This may include real-time data sharing that may support more informed decision-making, timely interventions, and / or personalized care strategies, e.g. ultimately contributing to improved user or patient outcomes. Transmitting the usage data set may enable the collection of large-scale data for analysis, e.g. contributing to research and / or the continuous improvement of treatment protocols and drug delivery device designs. When usage data sets are aggregated across many users / patients and / or transmitted to researchers and / or manufacturers, they may provide a rich source of data that may be analyzed to uncover patterns, trends, and / or insights. This may prompt the development of more effective drug delivery devices, the optimization of treatment protocols, and / or the identification of common issues and / or user needs, e.g. driving innovation and enhancing the quality of care. Further, by transmitting usage data to platforms and / or software that the users or patients can interact with, they may receive personalized feedback, reminders, and / or educational content based on their own data. This may empower users or patients to take a more active role in their treatment, understand their progress, and / or make informed decisions about their health, leading to higher engagement and satisfaction.

[0025] The (designated) recipient may comprise one of, more of, or all of: a healthcare provider system, a monitoring system, a device manufacturer, a user’s handheld device and / or a user's computing device.

[0026] The usage data set may be sent to a healthcare provider system, e.g., an electronic health record (EHR) system. The healthcare provider system may be utilized by a patient's primary care physician and / or facilitate the immediate integration of real-world usage data into the patient's medical records. This may significantly enhance the physician's capacity to make informed and / or data-driven treatment decisions.

[0027] The usage data set may be provided to a monitoring system, e.g., a remote patient monitoring platform. The monitoring platform may track medication adherence in real-time. The monitoring system may enable proactive health management, alerting healthcare teams to potential issues of non-adherence or adverse reactions, thereby allowing for timely and effective intervention.

[0028] The usage data set may be provided to the manufacturer, e.g. for post-market surveillance and / or quality control. This may provide the manufacturer with valuable insights into the drug delivery device performance and / or user experience, which may be beneficial for driving continuous product improvements and / or fostering innovation in device development.

[0029] The usage data set may be provided to a user’s handheld device. A handheld device may include a smartphone, PDA, tablet capable of processing applications (APP). For instance, a smartphone app may receive and / or display dosage times and / or reminders, based on the transmitted usage data set, empower the user or patient by giving them direct access to their medication schedules and adherence records, which may encourage better self-management and / or compliance with their treatment regimes.

[0030] The usage data set may be provided to a user's computing device, e.g. allowing the usage data set to be synchronized with personal health management software, which may be installed on the user's laptop and / or tablet and / or other electronic device. This may enable users to manage their health data comprehensively, e.g. integrating drug delivery information with other health metrics such as for a holistic and detailed view of their overall health status.

[0031] According to at least one embodiment, the information of the usage data set may include one of, more of, or all of: a timestamp indicative of the time of the activation of the drug delivery device for a drug delivery operation;

[0032] - a timestamp indicative of the time of the completion of the drug delivery operation;

[0033] - a duration of the drug delivery operation; and / or

[0034] - a confirmation that the drug delivery operation has been completed

[0035] According to at least one embodiment, the information of the usage data set may include a timestamp, e.g. indicative of the time of the activation of the drug delivery device for a drug delivery operation. Within the context of the disclosure, a timestamp may be a sequence of characters and / or encoded information identifying when a certain event occurred, usually giving date and time of day, sometimes accurate to a small fraction of a second. In the context of the drug delivery monitoring system, timestamps may be advantageous for logging events, recording data entries, synchronizing processes, and / or tracking the sequence and / or duration of activities. Incorporating a timestamp indicative of the time of activation of the drug delivery device for a drug delivery operation facilitates a precise record of medication administration times. It may enhance the accuracy of adherence tracking and / or may enable the assessment of the timing's impact on the effectiveness of the treatment. This may offer insights into optimal drug delivery schedules for improved user or patient outcomes.

[0036] According to at least one embodiment, the information of the usage data set may include a timestamp indicative of the time of the completion of the drug delivery operation. Including a timestamp indicative of the time of completion of the drug delivery operation in the usage data set may enable tracking, e.g. precise tracking, of the duration and / or conclusion of medication administration. It may facilitate the evaluation of the drug delivery device efficiency and / or reliability, e.g. ensuring timely medication delivery and supporting the optimization of treatment protocols for enhanced patient care.

[0037] According to at least one embodiment, the information of the usage data set may include a duration of the drug delivery operation. Incorporating the duration of the drug delivery operation into the usage data set facilitates analysis of the time taken for each medication administration. It may provide insights into the efficiency of drug delivery and / or potential variability in drug absorption rates, e.g. important for optimizing dosing schedules and enhancing the overall effectiveness of treatment regimens.

[0038] According to at least one embodiment, the information of the usage data set may include a confirmation that the drug delivery operation has been completed. Including a confirmation that the drug delivery operation has been completed in the usage data set may provide a reliable method to verify successful drug administration. It may ensure accuracy in adherence tracking and / or support user safety or patient safety, e.g. by enabling healthcare providers to promptly address any discrepancies or failures in drug delivery, thereby expediently enhancing the overall management of treatment plans.

[0039] According to at least one embodiment, the sensor unit data comprises one of, more of, or all of:

[0040] - information on the position of the drug delivery device and / or changes in the position of the drug delivery device,

[0041] - usage information on the usage of the drug delivery device,

[0042] - a timestamp indicative of when the drug delivery device is activated, and / or

[0043] - duration of usage of the drug delivery device. According to at least one embodiment, the sensor unit data may comprise information on the position of the drug delivery device. Including information on the position of the drug delivery device in the sensor unit data may enable precise monitoring of the device's orientation and / or location relative to the patient's body, e.g. during the administration process. Incorporating sensor data that tracks the position of the drug delivery device, including e.g. its status within packaging, during storage, when taken out for use, and / or throughout the delivery process, may provide a comprehensive understanding, identification, and / or monitoring of the device's handling and / or operational context. For instance, tracking the drug delivery device's transition from being in its packaging (indicating it's not in use) to being held in hand and / or positioned for a delivery may enhance safety protocols, e.g. by confirming that the drug delivery device is being used and / or used correctly, e.g. with the correct orientation, and / or at the right moments. Monitoring changes in the device's position may ensure accurate and consistent drug delivery, contributing to the efficacy of the treatment and enhancing user or patient compliance by verifying that the injection is administered, in particular administered in the intended anatomical site.

[0044] According to at least one embodiment, the sensor unit data may comprise information on changes in the position of the drug delivery device. Incorporating sensor unit data that captures information on changes in the position of the drug delivery device, e.g. including any movements, may facilitate a dynamic monitoring of the handling and / or operational use of the drug delivery device. It may significantly enhance the safety and / or efficacy of the drug administration process, e.g. by ensuring that the movements of the drug delivery device are consistent with correct usage patterns, such as moving from a storage position to an administration position. Moreover, the movement of the drug delivery device may indicate the use of the device and / or administration of the drug. Additionally, these movements may help in identifying incorrect handling and / or potential misuse of the drug delivery device, facilitate realtime corrective feedback to the user or patient, and / or ensure the drug delivery device is accurately positioned for optimal drug delivery, thereby reducing the risk of administration errors and improving patient outcomes.

[0045] According to at least one embodiment, the sensor unit data may comprise usage information on the usage of the drug delivery device. Incorporating sensor unit data that includes, e.g. comprehensive, usage information on the drug delivery device may facilitate a , e.g. detailed, tracking of how and / or when the drug delivery device is utilized. It may significantly improve the ability to monitor medication adherence, e.g. allowing healthcare providers to assess whether the prescribed treatment regimen is being followed. It may support personalized user or patient care by enabling adjustments to treatment plans based on actual usage patterns, thereby expediently enhancing the effectiveness of therapy and / or contributing to better outcomes.

[0046] According to at least one embodiment, the sensor unit data may comprise timestamps indicative of when the drug delivery device is activated. Incorporating timestamps in the sensor unit data that indicate the activation of the drug delivery device may play an important role in identifying the moments, e.g. the exact moments, of medication administration. It may be vital for distinguishing actual drug delivery device usage from mere handling and / or preparation activities, allowing for example for accurate adherence tracking and / or assessment. It may further enhance the ability to correlate specific doses with patient responses and / or side effects, providing a foundation for data-driven adjustments to therapy protocols.

[0047] According to at least one embodiment, the sensor unit data may comprise duration of usage of the drug delivery device. Incorporating the duration of usage of the drug delivery device into the sensor unit data may provide a quantifiable measure of how long the device is (actively) engaged in the medication administration process. It may serve as an important marker to distinguish between the device being in use versus merely being on and / or in a standby state. By capturing the active usage duration, healthcare providers may assess the efficiency and / or correctness of the drug delivery process, ensuring that the drug delivery device operates within the expected time frame for each administration. This insight may help in identifying any deviations from prescribed treatment protocols, facilitating timely interventions to correct usage patterns and / or enhance the overall effectiveness of therapy.

[0048] Another aspect of the disclosure relates to a computer-implemented method for verifying a drug administration using a self-learning model in a drug delivery monitoring system. The computer- implemented method may comprise the step of receiving sensor unit data. The sensor unit data may be related to a drug delivery device. Receiving sensor unit data related to a drug delivery device may allow for real-time monitoring and / or analysis of the operational status of the drug delivery device and / or a patient interaction with the drug delivery device. It may enhance the ability to promptly detect and / or respond to issues, ensuring optimal drug delivery device performance and / or supporting effective medication management.

[0049] The computer implemented method may comprise the step of processing the received sensor unit data with a machine learning model. The machine learning model may be processed on the monitoring system. Processing the received sensor unit data with the machine learning model may be done to determine whether a drug delivery device activation event has occurred, for example based on the processed sensor unit data. The machine learning model may initially be trained on a dataset, e.g. a training dataset, comprising examples of confirmed drug delivery device activation events and / or non-drug delivery device activation events.

[0050] Processing the received sensor unit data with a machine learning model to determine whether a drug injection event has occurred may enable the drug delivery monitoring system to differentiate between actual medication administrations and / or other drug delivery device interactions. It may leverage the model's ability to learn from a dataset, e.g. comprising examples of confirmed drug delivery device activation events and / or non-drug delivery device activation events, and enhance the precision of drug delivery monitoring.

[0051] The machine learning model may be trained through a supervised learning process. The supervised learning process may be fed with a dataset, e.g. a training dataset, that may include labeled examples of drug injection events and / or non-injection events. This dataset may be generated from historical sensor data that may comprise various parameters such as device activation times, duration of use, device orientation, and / or user interactions. The parameter may be labeled according to whether they correspond to actual drug delivery device activation events. The dataset may be stored securely, e.g. in cloud-based systems and / or dedicated servers, to facilitate easy access for model training and / or updates. By analyzing new data, e.g. continuously analyzing new data, the model may refine its predictions over time, improving its accuracy in identifying drug delivery device activation events, thereby supporting more effective and personalized patient care.

[0052] The computer implemented method may comprise the step of capturing user feedback and / or sensor unit confirmation regarding the accuracy of the determined drug delivery device activation event to identify actual drug administrations and incorrectly identified drug administrations. Capturing user feedback and / or sensor unit confirmation regarding the accuracy of the determined drug injection event may enable the validation and / or refinement of drug administration records. It may ensure the high fidelity of injection tracking by distinguishing between actual injections and false positives, thereby improving the reliability of adherence data and / or enhancing patient care through accurate medication management.

[0053] When collecting user feedback to enhance the accuracy of drug delivery device activation event detection, the feedback may be integrated in various engaging and straightforward formats, important for refining machine learning models. Users might receive digital surveys and / or questionnaires on their devices, mobile devices and / or other communication devices to confirm drug administration and / or detail their experiences. This may facilitate the collection of diverse data points for model training. Interactive notifications on mobile devices may prompt users for quick confirmation of drug administration, providing quick and easily categorizable data. Voice feedback via smart home devices and / or smartphone and / or smartwatch may offer a hands-free option for confirming drug administration, adding another layer of user interaction data. Visual confirmations, such as photographs of the used drug delivery device, may supply rich and / or verifiable evidence of drug administration. Manual entries into apps or web platforms may allow for detailed user-generated data, capturing nuances in user behavior and / or drug administration experiences. This multifaceted feedback may ensure that the drug delivery monitoring system adapts to real-world user or patient interactions and / or improves over time in identifying true drug delivery device activation events.

[0054] The computer-implemented method may comprise the step of updating the machine learning model based on the collected feedback. Updating may comprise employing reinforcement learning techniques and / or supervised learning adjustments to refine the ability of the model to identify drug delivery device activation events. Updating the machine learning model based on collected feedback, through the use of reinforcement learning techniques and / or supervised learning adjustments, may enhance the model's precision in identifying drug delivery device activation events. This adaptive approach may allow the model to continuously learn from real- world user or patient interactions and feedback, improving its accuracy over time by incorporating new data and / or correcting any identified inaccuracies. It may ensure the drug delivery monitoring system becomes increasingly reliable in detecting actual drug delivery device activation events, thereby optimizing medication adherence monitoring and / or supporting more effective patient care.

[0055] In the realm of enhancing machine learning models for drug delivery systems, reinforcement learning techniques and / or supervised learning adjustments offer robust methods for improving the accuracy of drug delivery device activation event identification. Reinforcement learning techniques, e.g., Q-learning, are effectively applied where the model learns the optimal action to take (confirming and / or denying drug delivery device activation events) based on the current state, which may include sensor unit data and / or user feedback. The technical implementation may involve updating a Q-table with rewards that may reflect the accuracy of the model's predictions, guiding for example the model to refine its decision-making process over time. For more complex scenarios with high-dimensional input data, Deep Q-Networks (DQN) may utilize deep neural networks to approximate the Q-value function, employing for example a replay memory for experience storage and a target network to stabilize the learning process. This may enable the model to draw nuanced inferences from patterns in sensor data and / or feedback, enhancing prediction accuracy.

[0056] On the supervised learning side, Convolutional Neural Networks (CNNs) may provide capabilities for analyzing visual confirmations of drug injections, such as images of used patches and / or syringes. By automatically detecting and / or learning the most relevant features from images, CNNs may accurately classify these images to verify drug delivery device activation events. This approach leverages layers of convolutions and / or pooling operations to improve the model's visual recognition capabilities. Furthermore, for sequential sensor data that captures the steps of a drug delivery process, Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) Networks may adept at predicting the next likely step and / or identifying discrepancies. LSTMs, in particular, are advantageous for remembering information for extended periods, making them useful for analyzing time-series data from drug delivery devices and thus refining the accuracy of activation event detection.

[0057] Reinforcement and / or supervised learning methods may utilize collected data to iteratively refine the model's performance, adapting to new information and / or refining predictive capabilities. It may ensure high levels of accuracy in detecting and / or confirming drug delivery device activation events, accommodating evolving patterns and / or incorporating valuable user feedback.

[0058] According to at least one embodiment, the computer-implemented method may further comprise iteratively repeating the method steps of the method for verifying a drug administration. This may be achieved by using a self-learning model in a drug delivery monitoring system with subsequent sensor unit data inputs to (continuously) enhance the injection monitoring systems accuracy in verifying drug delivery device activation events. Iteratively repeating the method steps may enable the model and / or the drug delivery monitoring system to refine its accuracy and / or performance over time. It may leverage the accumulation of new data and / or feedback to continuously train and improve the model, ensuring that the drug delivery monitoring system becomes progressively more adept at accurately identifying and verifying drug delivery device activation events. This iterative process may enhance the reliability of the drug delivery monitoring system and may adapt to changes in usage patterns, device performance, and / or patient behavior, ensuring sustained efficacy in monitoring drug administrations.

[0059] Another aspect of the disclosure relates to a drug delivery monitoring system for detecting the usage of a drug delivery device. The drug delivery monitoring system may be designed as a component of a computer, a smart home device, and / or on outsourced e.g. on an external, server. The drug delivery monitoring system may comprise at least one sensor unit configured to capture sensor unit data associated with the drug delivery device. The at least one sensor unit may be integrated in the drug delivery monitoring system and / or connected by using a communication interface and / or communication protocol with the drug delivery monitoring system. Integrating at least one sensor unit configured to capture sensor unit data associated with a drug delivery device into a drug delivery monitoring system may enable real-time tracking and analysis of the usage of the drug delivery device. It may facilitate the detection, e.g. the immediate detection, of drug administration events, enhancing the monitoring system's capability and ensure medication adherence and / or to accurately record the timing and frequency of drug deliveries.

[0060] The drug delivery monitoring system may comprise a processing unit coupled to the at least one sensor unit. The processing unit may be configured to analyze the captured sensor unit data to determine the occurrence of a drug delivery device activation event. The determination may be based on predefined criteria for drug delivery device usage. Incorporating a processing unit that may be coupled to the sensor unit or to several sensor units and which may be configured to analyze the captured sensor unit data may enable the drug delivery monitoring system to (intelligently) determine the occurrence of drug delivery device activation events. It may significantly enhance the ability of the drug delivery monitoring system to autonomously verify when and / or how the drug delivery device is used, according to predefined usage criteria, ensuring accurate tracking of medication administration. This level of analysis may support more reliable adherence monitoring and may provide a foundation for data-driven adjustments to treatment plans, improving patient outcomes through precise medication management.

[0061] The drug delivery monitoring system may comprise an output interface connected to the processing unit. The output interface may be configured to generate and / or provide a usage data set based on the analysis of the sensor unit data. The usage data set may include information of the drug delivery device activation event. Equipping the drug delivery monitoring system with an output interface connected to the processing unit, e.g. designed to generate and / or provide a usage data set based for example on the analysis of the sensor unit data, may enable efficient communication of medication administration information. It may facilitate the seamless dissemination of detailed insights regarding drug delivery device activation events to healthcare providers, patients, and / or caregivers. By making such information readily accessible, the system may significantly improve the management of medication adherence and / or may enable informed decision-making, thereby enhancing the overall effectiveness of treatment regimens and promoting better health outcomes.

[0062] The output interface of a drug delivery monitoring system may be provided to communicate essential usage data sets to various stakeholders. The communication may for example, utilize multiple platforms and / or technologies for maximal accessibility and efficiency. One example may include the development of a dedicated mobile application that receives data from the processing unit, e.g. via Bluetooth or Wi-Fi. The mobile application may be designed to display information for a drug delivery device activation event, medication administration times, dosage details, and / or alerts for upcoming doses. The mobile application may further synchronize with wearable devices like smartwatches and / or smartphones and may provide vibration, sound, and / or visual alerts. Further, a secure web-based dashboard which may be accessible through internet browsers on computers or tablets may be implemented. This may allow healthcare providers to access detailed reports on their patients' medication adherence, including e.g. specific drug delivery device activation events.

[0063] An integration with smart home assistants via, e.g. Bluetooth and / or Wi-Fi, may provide verbal medication reminders and / or enable users or patients to confirm medication administrations through voice recognition technology. This system may interact with other smart home devices, such as lights or speakers, to provide additional visual and / or auditory cues, enhancing the reminder system's effectiveness.

[0064] For more formal healthcare settings, the monitoring system may include an API for secure transmission of usage data sets e.g. directly to Electronic Health Record systems used by healthcare facilities. This may ensure that data on medication administration is integrated into the comprehensive health records of the user or patient, with the potential to automate alerts to medical staff via hospital information systems and / or directly to handheld devices used in clinical environments.

[0065] The drug delivery monitoring system may provide the functionality to generate printable and / or digital reports e.g. summarizing drug delivery device usage. This feature may cater to patients and / or healthcare providers who prefer and / or require hardcopy documentation and / or digital reports that may be easily shared during medical consultations and / or stored for record-keeping.

[0066] According to at least one embodiment, the drug delivery monitoring system may comprise a memory unit. The memory unit may be coupled to the processing unit, e.g. for storing the predefined criteria for drug delivery device usage, captured sensor unit data, and / or analysis results. The memory unit may be an internal and / or external memory unit and may include a flash memory, RAM, HDD, SSD, and / or a portable memory device.

[0067] According to at least one embodiment, the at least one sensor unit may include a hierarchical configuration of several sensor units categorized into levels based on their proximity to the user and / or the sensor unit capabilities.

[0068] According to at least one embodiment, the at least one sensor unit may comprise at least one Level-1 sensor unit. The Level-1 sensor unit may be configured to detect user body motions, noises, e.g. noises made by an user, and / or environment noises, which may be indicative of the drug delivery device usage. Incorporating a Level-1 sensor unit which may be configured to detect user body motions, (user) noises, and / or environmental noises, which may be indicative of the usage of the drug delivery device, positions this sensor, e.g. the Level-1 sensor, at the top of a hierarchy. Such Level-1 sensor units may provide high sensitivity and specificity in monitoring drug delivery device activation events. Such a setup may enable the system to capture a comprehensive range of data directly related to the act of medication administration, enhancing the accuracy of detecting and / or verifying Drug delivery device activation events e.g. by distinguishing them from unrelated activities. This capability ensures precise adherence tracking and / or can significantly contribute to personalized patient care by recognizing and / or analyzing the nuanced physical and / or auditory cues associated with successful drug delivery.

[0069] Detecting body motions associated with the usage of a drug delivery device, such as taking it in hand, removing it from storage (e.g. a fridge) and / or packaging, and / or using it, may provide a comprehensive approach to monitoring medication adherence. The sequence of actions leading to medication administration, enabling a more nuanced understanding of patient behavior and adherence patterns may be captured. By identifying specific movements related to drug delivery device preparation and / or administration, the drug delivery monitoring system may more accurately verify that the medication has indeed been taken, e.g. as prescribed. This level of detail may enhance the accuracy of adherence tracking and may allow for the identification of potential barriers and / or challenges patients may face in their medication routines.

[0070] Detecting user noises indicative of the usage of a drug delivery device, such as the sounds made when taking the drug delivery device in hand, removing it from storage and / or opening its packaging, and / or using it, may significantly enhance the ability of the drug delivery monitoring system to monitor and / or confirm medication administration. These auditory cues, identified as specific noises associated with the use and / or preparation of the drug delivery device, may provide a reliable method for verifying one, more than one or all steps of the medication administration process. This capability may ensure a more accurate assessment of patient adherence by capturing the entire sequence of device handling and / or usage and may enable the drug delivery monitoring system to differentiate between handling of the drug delivery device and its actual operational use. By accurately identifying these distinct sounds, the system may provide real-time feedback and / or record detailed logs of medication administration events.

[0071] Environmental noises that may occur when using a drug delivery device may include background sounds typical of the setting in which the drug delivery device may be used, such as household sounds (e.g., open wardrobe or open fridge where the drug delivery device is stored). Detecting these environmental noises, alongside specific user noises and / or body motions associated with the use of the drug delivery device, may contribute to a comprehensive auditory scene analysis. The drug delivery monitoring system may gain the ability to discern the context of medication administration events, which may inform the interpretation of data related to the drug delivery device usage. The noise discrimination capability may be important for minimizing false positives and / or negatives in adherence tracking, ensuring that the system's assessments are both accurate and reliable.

[0072] According to at least one embodiment, the Level-1 sensor unit may include a smartwatch. The smartwatch may be a wearable device that may be worn on the wrist and may feature advanced functions that go beyond merely displaying the time. In some cases, the smartwatch may work in conjunction with a smartphone, e.g. displaying notifications, forwarding calls, recording health and / or fitness data, and / or supporting navigation and / or position detection. Smartwatches offer a range of functions that can be expanded through the installation of applications. The smartwatch may include a display, particularly a touchscreen display, for showing data and / or for operation. The smartwatch may have interfaces for communication with other devices. Specifically, it may be equipped with Bluetooth for connection to smartphones and / or Wi-Fi, and / or additionally LTE / 4G / 5G for independent communication. Furthermore, the smartwatch may comprise various sensors, including e.g. heart rate monitors, accelerometers, gyroscopes, GPS, temperature and / or blood oxygen saturation sensors (SpO2) for comprehensive health and / or fitness tracking. Using the accelerometer and / or gyroscope, movements of the arm, wrist, and / or fingers, e.g. made gestures, may be detected. The detected movements may be provided as data for further use. The smartwatch may comprise internal storage for apps and / or data, as well as for example a processor for e.g. running apps. The smartwatch may be used to detect the motion of the arm and / or fingers when grabbing and / or using the drug delivery device. Specific positions and / or holding positions of the drug delivery may be detected. These detections may be used to determine the use of the drug delivery device. Further, the smartwatch may comprise a microphone, e.g. an internal microphone. The microphone may be used to detect specific noises e.g. noises made when using the drug delivery device.

[0073] According to at least one embodiment, the Level-1 sensor unit may include a smart ring. The smart ring may be a wearable device in the form of a ring that may be worn on the finger and which may offer similar functions and / or connectivity features as smartwatches, e.g. in a more compact and / or inconspicuous format. The smart ring may be equipped with one or more sensors and may enable interaction with smartphones and / or other smart devices e.g. to receive notifications, track fitness data, make payments, and / or serve as a digital key replacement. The smart ring may comprise an interface, for example a Bluetooth Low Energy (BLE) interface, for connecting to a smartphone. Through the connection, the smart ring may receive notifications from the phone and / or may access certain functions of the phone without having to take the phone out of the pocket. The smart ring may inform the user about incoming calls, messages, emails, and / or app notifications, for example using vibration and / or light signals. The smart ring may include one or more sensors for monitoring health and / or fitness data, such as steps, heart rate, sleep quality, and / or calorie consumption. Furthermore, one or more sensors for detecting movements and / or accelerations may be provided. The smart ring may be used as a physical key for digital locks and / or as an authentication means for secure logins on various platforms and / or services, e.g. by providing two-factor authentication through the physical presence of the ring. The smart ring may be used to detect the motion of the arm and / or fingers when grabbing and / or using the drug delivery device. Specific positions and / or holding positions of the drug delivery may be detected. The smart ring may provide more detailed and / or precise information of the motion of the hand and / or fingers. The detections made through the smart ring may be used to determine the use of the drug delivery device. The smart ring may comprise a microphone, e.g. an internal microphone. The microphone may be used to detect specific noises made when using the drug delivery device.

[0074] According to at least one embodiment the Level-1 sensor unit may include smart glasses. Smart glasses may be wearable devices that may be equipped with advanced technology e.g. to perform a wide array of functions e.g. functions beyond mere vision correction and / or protection from the sun. These glasses may integrate miniature displays, cameras, sensors, and / or wireless connectivity, enabling them to project information into the user's field of view, capture photos and / or videos, track health and / or fitness metrics, and / or provide navigation assistance. Smart glasses may comprise Bluetooth, Wi-Fi, and / or sometimes cellular connectivity for connecting to a smartphone and / or other (smart) devices, allowing users to access notifications, control music playback, and / or make hands-free calls. Smart glasses may feature voice recognition capabilities, enabling users to interact with virtual assistants and / or control device functions through voice commands. The integration of augmented reality (AR) technology in some smart glasses models may offer interactive experiences by overlaying digital information onto the real world, enhancing educational, professional, and / or gaming applications. By using smart glasses, the usage of the drug delivery device may be visually detected and confirmed.

[0075] According to at least one embodiment, the Level-1 sensor unit may include smart fabrics. Smart fabrics may represent intelligent textiles, e.g. fabrics that have the capability to provide technical functions through the integration of digital components, conductive materials, and / or special fibers. They may contain one or more sensors, one or more microelectronics, and / or other technologies to collect, store, transmit data, and / or respond to changes in the environment. The textiles may combine the comfort and convenience of fabrics with the advanced capabilities of modern technology to enable a variety of applications in areas such as health monitoring, fitness tracking, fashion, security, and / or environmental interaction. Smart fabrics may communicate with an external device, such as a smartphone and / or computer, to transmit collected data and / or receive instructions. This data may include simple input parameters like temperature and / or humidity and / or more complex information like heart rate and / or movement patterns. By using integrated microcontrollers and / or wireless communication modules, smart fabrics may also be programmed to respond to specific data and / or changes in the environment. Smart fabrics may have one or more integrated sensors to capture physiological and / or environmental data as well as movement and / or position data. Smart fabrics may include Bluetooth, NFC, and / or other forms of wireless technology, which allow the transmission of data to and / or from smart fabrics to one or more other devices. Smart fabrics may be used to detect the motion of the arm and / or hand indicating the usage of the drug delivery device.

[0076] The at least one Level-1 sensor unit may include at least one of, more of, or all of:

[0077] - a smartwatch,

[0078] - a smart ring,

[0079] - smart glasses, and / or

[0080] - a smart fabric.

[0081] In the context of a drug delivery monitoring system, utilizing a hierarchical structure for sensor units which may be based on their proximity to the user and / or their specific functionalities may offer a comprehensive approach to monitoring and / or verifying medication administration.

[0082] According to at least one embodiment, the Level-1 sensor unit may further be configured to analyze the detected body motions, user noises and / or environment noises using one or more quantities which are monitored by the sensor unit. The quantities may be suitable to be sensed in proximity to the user. Level-1 , being the closest to the user, may include wearable technologies like smartwatches, smart rings, smart fabrics, and / or smart glasses. These devices are directly on the body of the user or patient, making them advantageously positioned to detect physical and / or auditory cues related to drug delivery, such as body motions, motions of body parts, and / or user noises. Due to their proximity, Level-1 devices play an important role in capturing high-fidelity, real-time data, and may serve as the primary source of information for detecting and / or confirming medication administration events.

[0083] According to at least one embodiment, the at least one sensor unit may comprise a Level-2 sensor unit. The Level-2 sensor unit may be configured to complement the Level-1 sensor unit by providing additional sensor data. The Level-2 sensor unit may be or may comprise a smartphone. The Level-2 sensor unit, e.g. the smartphone, may be configured to complement the Level-1 sensor unit by providing additional sensor data. The additional sensor data may be based on applications and / or features inherent to the smartphone, e.g., optimized for detecting drug delivery device usage. Level-2 sensor unit may comprise smartphones, which, while not worn directly on the body, may typically be kept close to the user throughout the day. Smartphones may support Level-1 sensor units by providing a platform for data aggregation, further analysis, and / or user feedback collection. Smartphones may offer a broad range of functionalities, including for example the ability to run complex applications, process and / or store larger data sets, and / or facilitate communication with healthcare providers and / or caregivers.

[0084] According to at least one embodiment, the Level-2 sensor unit may be further configured to process sensor data from Level-1 and / or Level-2 sensor units to enhance the accuracy of detecting drug delivery device activation events, e.g. through the integration of body motion, user noises, environment noises, and / or smartphone-derived data into the data processing. It may leverage the integration of diverse data types, e.g. body motion, user noises, environmental noises, and / or smartphone-derived data, to create a multifaceted profile of one, more or each drug delivery event. Additionally, special noise which may be provided by the drug delivery device (e.g. click, triggering, label and / or cap removal) and / or delivery supporting aids like alcohol atomizer and / or needle packaging noises may be detected and / or may support a detection of the usage of the drug delivery device.

[0085] Such a configuration may improve the ability of the drug delivery monitoring system to distinguish genuine medication administration actions from other unrelated activities, thereby reducing false positives and / or increasing the reliability of adherence tracking. This methodology may ensure a more nuanced and precise monitoring capability, contributing to optimized patient care and treatment outcomes by ensuring medication is administered, in particular administered correctly, and / or at intended times.

[0086] According to at least one embodiment, the Level-1 and / or Level-2 sensor units may be considered the primary levels for monitoring, due to their proximity to the user and / or their combined capabilities in detecting detailed physical and / or auditory signs of drug delivery device usage. Different level may mean different devices and / or different sensor parameters, which may be used for detecting the usage of a drug delivery device. Level-1 and / or Level-2 may be considered as the main level being the close located device to the user or patient. They may detect body motion and / or user or patient noises (caused e.g. by user or patient activities and / or motion sequences). A connecting device, e.g., a home hub may be used to connect the user or patient devices (Level-1 sensor unit(s) and / or Level-2 sensor unit(s)), such that capturing of each device parameter may be suitable.

[0087] According to at least one embodiment, the drug delivery monitoring system, e.g. the at least one sensor unit may comprise a Level-3 sensor unit. The Level-3 sensor unit may comprise or may consist of a smart speaker. The smart speaker may be configured to detect ambient sounds associated with drug delivery device usage and / or to provide a supplementary layer of monitoring through voice recognition and / or environment noise analysis. The smart speakers may expand the ecosystem by offering voice-controlled interaction and / or the ability to process auditory signals within the environment. Although less directly connected to the user's physical activities, smart speakers may enhance the understanding of the drug delivery monitoring system of the environment of the user or patient.

[0088] According to at least one embodiment, the drug delivery monitoring system, e.g. the at least one sensor unit may comprise a Level-4 sensor unit. The Level-4 sensor unit may comprise or may consist of a camera, e.g. a smart camera. The camera may be configured to visually monitor the user and / or the drug delivery device. The Level-4 sensor unit may provide visual confirmation of drug delivery device usage and / or may augment the data collected by the Level-1 , Level-2, and / or Level-3 sensor units. Level 4, which may be represented by cameras, may provide an additional layer of monitoring by visually capturing the user's interactions with the drug delivery device. While offering a less direct method of observation compared to Level-1 sensor units and / or Level-2 sensor units, cameras may still contribute valuable context and / or verification for drug administration events, particularly in controlled environments. The interaction of the user with the drug delivery device may be captured and / or observed. In particular, the application of the drug delivery device may be recorded and / or evaluated. Furthermore, the movement of the drug delivery device may be captured and / or analyzed. In this way, the execution, especially the correct usage of the drug delivery device, may be monitored.

[0089] This hierarchical structure may ensure that data collection and / or analysis are optimized for immediacy and / or depth, with each level playing a role based on its proximity to the user and / or its capabilities. Level-1 and / or Level-2 sensor units may be important for their data capture and interaction with the user. Level-3 and / or Level-4 sensor units may provide increasingly broad support, enhancing the system's overall ability to monitor, verify, and / or support the user's medication administration process through a at least one or more of or all of detailed data collection, processing capabilities, and / or environmental context. This structured approach may allow for a nuanced understanding of user behavior, the usage of the drug delivery device, and / or the device interaction, supporting effective medication management and adherence.

[0090] According to at least one embodiment, the drug delivery device is an injection device, e.g. a needle-based injection device. The drug delivery device may be a pen-type device. The drug delivery device may be an autoinjector. Throughout the disclosure, when reference is made to one type of a drug delivery device, e.g. a pen-injector, also autoinjectors are encompassed. Embodiments referring to a pen-injector may also be provided with ab autoinjector According to at least one embodiment, the drug delivery device may be a single dose device (e.g. a device which is configured to deliver only one dose from one drug container. In some embodiments the drug delivery device is a multi-dose device (e.g. a device which is configured to deliver multiple doses from one drug container).

[0091] According to at least one embodiment, the drug delivery device is a reusable drug delivery device (e.g. a device which can be used with different drug containers, such as be replacing a used or emptied drug container with a new one).

[0092] The above description can be summarized in other words and in a possible more concrete embodiment of the disclosure as described below, with the understanding that the following description is not to be interpreted as limiting for the disclosure.

[0093] The disclosure may use preliminary capturing smartwatch motion and noises sensor parameters to detect drug administering supported by additional available devices sensor parameters in a modern smart home.

[0094] Special noises which may be provided by the drug delivery device (click, triggering, label and / or rather cap removal) and drug delivery supporting aids like alcohol atomizer and / or needle packaging noises may support a drug delivery monitoring.

[0095] An opened fridge by a user or patient may be detected, e.g. to remove the drug or the drug delivery device from the fridge. The noise resulting from the fridge itself and / or the noise resulting from a door opening action may be detected. Further, using the drug delivery device, any user or patient activity and / or user or patient physiological parameters including pulse, blood pressure, and / or oxygen saturation in the blood may be detected and interpreted as a drug delivery device activation event that may be captured by one or more sensors of the smartwatch or any other device applicable for detecting relevant parameters. A plausibility test may be performed, verifying date and / or time of the use of the drug delivery device.

[0096] A camera may be used to visually detect that the user or patient opens the fridge.

[0097] A home speaker system (which usually have integrated microphones) may be used to detect noises including e.g. steps, walking to the fridge, opening the fridge, removing a packaging from fridge, and / or closing the fridge for detecting a drug delivery device activation event. With the present disclosure, an opening of a packaging to remove a drug delivery device or a drug by the user or patient from the packaging may be detected. A smartwatch and / or a camera may be used to detect this, for example.

[0098] With the present disclosure, the preparation of a drug delivery site, e.g. an injection site, by the user may be detected. A smartwatch may detect the motion. The smart watch may detect typical noises including removing a swipe from a packaging and / or operating an atomizer with a disinfectant, e.g. alcohol.

[0099] With the present disclosure, for example, removing an autoinjector from its packaging by the user or patient can be detected. For example, the smartwatch may detect a motion- caused noise. Alternatively or additionally, the smartwatch may detect noise caused by opening a packaging, e.g., tearing or ripping apart a label.

[0100] With the present disclosure, arranging an injection device on an injection site can be detected. The smartwatch can be used to detect the relevant motion.

[0101] With the present disclosure, a drug delivery, e.g. a drug administration may be detected. The smartwatch may be used to detect noises characteristic for a drug delivery, e.g. the beginning or completion thereof. Beginning and / or end of a drug injection are often detectable by characteristic noises of the drug delivery device, e.g. by clicks. A first noise may indicate the beginning of the event. A second noise may indicate the completion. Alternatively, or additionally, the smartwatch may be used to detect its motion as movement to the body and a subsequent stop of the motion. A smart speaker may detect noise including detecting clicks, and / or when music is played, or no user activity may be detected.

[0102] With the disclosure, further situations may be detected. The situations may include that the user or patient removes the drug delivery device from the body (e.g. after the drug delivery has been completed, the user or patient puts the drug delivery device into the waste, e.g. into a waste bin, and / or the user or patient puts the drug delivery device back to the fridge. The linked motions and / or noises associated with said situations may be detected.

[0103] Furthermore, a computer program may be provided. The computer program may comprise commands that, when executed by a computer or a processing unit (e.g. of the drug delivery monitoring system), may cause it to carry out or execute the method described above, e.g. at least in part or the entire method and / or to control the operation of the drug delivery monitoring system. The program code of the computer program may be in any code, in particular in a code suitable for controlling a drug delivery monitoring system. The features described above relating to the drug delivery monitoring system and the associated method(s) may also apply analogously to the computer program and / or vice versa.

[0104] As a further solution, the disclosure may encompass a computer-readable storage medium, e.g. a non-transitory storage medium. The computer-readable storage medium may comprise program code that, when executed by a computer, a processing unit or a computer network, causes it to execute an embodiment of the method according to the disclosure or to control operation of the drug delivery monitoring system. The storage medium may be provided at least in part as non-volatile data storage (e.g., as a flash memory and / or as an SSD - solid-state drive) and / or at least in part as volatile data storage (e.g., as a RAM - random access memory). The storage medium may be arranged in the computer or computer network. However, the storage medium may also, for example, be operated as a so-called app store server and / or cloud server on the internet. The computer and / or computer network may provide a processor circuit with, for example, at least one microprocessor. The program code may be provided as binary code and / or assembler code and / or as a source code of a programming language (e.g., C) and / or as a program script (e.g., Python).

[0105] Features described above and below in connection with different aspects or embodiments may be combined with one another.

[0106] The making and using of the presently preferred embodiments are discussed in detail below. It should be appreciated, however, that the present disclosure provides many applicable concepts that can be embodied in a wide variety of specific contexts. The specific embodiments discussed are merely illustrative of specific ways to make and use the disclosed concepts, and do not limit the scope of the claims.

[0107] Moreover, same reference numerals refer to same technical features if not stated otherwise. As far as "may" is used in this application it means the possibility of doing so as well as the actual technical implementation. The present concepts of the present disclosure will be described with respect to preferred embodiments below in a more specific context namely drug delivery devices, especially drug delivery devices for humans or animals. The disclosed concepts may also be applied, however, to other situations and / or arrangements as well, e.g. for other injectors, spraying devices or inhalation devices.

[0108] The foregoing has outlined rather broadly the features and technical advantages of embodiments of the present disclosure. Additional features and advantages of embodiments of the present disclosure will be described hereinafter, e.g. of the subject-matter of dependent claims. It should be appreciated by those skilled in the art that the conception and specific embodiments disclosed may be readily utilized as a basis for modifying or designing other structures or processes for realizing concepts which have the same or similar purposes as the concepts specifically discussed herein. It should also be recognized by those skilled in the art that equivalent constructions do not depart from the spirit and scope of the disclosure, such as defined in the appended claims.

[0109] Brief description of the drawings

[0110] For a more complete understanding of the presently disclosed concepts and the advantages thereof, reference is now made to the following description in conjunction with the accompanying drawings. The drawings are not drawn to scale, wherein

[0111] Figure 1 shows an exemplary embodiment of a drug delivery device and an electronic dose capturing system,

[0112] Figure 2 schematically illustrates an exemplary embodiment of a drug delivery monitoring system in accordance with the present disclosure,

[0113] Figure 3 schematically illustrates a further exemplary embodiment of a drug delivery monitoring system in accordance with the present disclosure,

[0114] Figure 4 schematically illustrates a flow diagram of an exemplary embodiment of the method according to the disclosure,

[0115] Figure 5 schematically illustrates a further flow diagram of an exemplary embodiment of the method according to the disclosure,

[0116] Figure 6 shows schematically a hierarchical structure with example of sensor units according to one exemplary embodiment, and

[0117] Figure 7 shows a flow diagram of a patient perfuming drug delivery device activation events accosting to one exemplary embodiment.

[0118] Description of exemplary embodiments

[0119] In the following description, for purposes of explanation and not limitation, specific details are set forth, in order to provide a thorough understanding of the current disclosure. It will be apparent to one skilled in the art that the current disclosure may be practiced in other embodiments that depart from these specific details. For example, the skilled person will appreciate that the current disclosure may be practiced with any application for different functionalities or for different computing entities. As another example, the disclosure may also be implemented in any mobile device, having the respective interfaces, like a smartphone, a mobile phone, a mobile computer system, or a personal digital assistant.

[0120] In the following, some concepts will be described with reference to a drug delivery device, in particular, insulin injection device. The present disclosure is however not limited to such an application and may equally well be used for or in injection devices that are configured to eject other medicaments or drug delivery devices in general, preferably pen-type devices and / or injection devices such as autoinjectors.

[0121] In the following, embodiments are provided in relation to injection devices, in particular to variable dose injection devices, which record and / or track data on doses delivered thereby. These data may include the size of the selected dose and / or the size of the actually delivered dose, the time and date of administration, the duration of the administration and the like. Features described herein may include power management techniques (e.g. to facilitate small batteries and / or to enable efficient power usage) or related concepts.

[0122] As a general note, “distal” is used herein to specify directions, ends or surfaces which are arranged or are to be arranged to face or point towards a dispensing end of the drug delivery device and / or point away from, are to be arranged to face away from or face away from the proximal end. On the other hand, “proximal” is used to specify directions, ends or surfaces which are arranged or are to be arranged to face away from or point away from the dispensing end and / or from the distal end of the drug delivery device or components thereof. The distal end may be the end closest to the dispensing end and / or furthest away from the proximal end and the proximal end may be the end furthest away from the dispensing end. A proximal surface may face away from the distal end and / or towards the proximal end. A distal surface may face towards the distal end and / or away from the proximal end. The dispensing end may be the needle end where a needle is arranged or a needle or needle unit is or is to be mounted to the device, for example.

[0123] Certain embodiments in this document are illustrated with respect to an injection device where an injection button and grip (dose setting member or dose setter) are combined e.g. similar to the device described in WO 2014 / 033195 A1. The injection button may provide the user interface member for initiating and / or performing a dose delivery operation of the drug delivery device. The grip or knob may provide the user interface member for initiating and / or performing a dose setting operation. The devices may be of the dial extension type, i.e. their length increases during dose setting. Other injection devices with the same kinematical behaviour of the dial extension and button during dose setting and dose expelling operational mode are known as, for example, the Kwikpen® or Savvio® device marketed by Eli Lilly and the FlexPen®, FlexTouch® or Novopen® device marketed by Novo Nordisk. An application of the general principles to these devices therefore appears straightforward and further explanations will be omitted. However, the general principles of the present disclosure are not limited to that kinematical behaviour. Certain other embodiments may be conceived for application to injection devices where there are separate injection button and grip components I dose setting members e.g. the device described in WO 2004 / 078239 A1. Thus, the present disclosure also relates to systems with two separate user interface members, one for the dose setting operation and one for the dose delivery operation. In order to switch between a dose setting configuration of the device and a dose delivery configuration, the user interface member for dose delivery may be moved relative to the user interface member for dose setting. If one user interface member is provided, the user interface member may be moved distally relative to a housing. In the course of the respective movement, a clutch between two members of the dose setting and drive mechanism of the device changes its state, e.g. from engaged to released or vice versa. When the clutch, e.g. formed by sets of meshing teeth on the two members, is engaged, the two members may be rotationally locked to one another and when the clutch is disengaged or released, one of the members may be permitted to rotate relative to the other one of the two members. One of the members may be a drive member or drive sleeve which engages a piston rod of the dose setting and drive mechanism. The drive sleeve may be designed to rotate relative to the housing during dose setting and may be rotationally locked relative to the housing during dose delivery. The engagement between drive sleeve and piston rod may be a threaded engagement. Thus, as the drive sleeve cannot rotate during dose delivery, axial movement of the drive sleeve relative to the housing will cause the piston rod to rotate. This rotation may be converted into axial displacement of the piston rod during the delivery operation by a threaded coupling between piston rod and housing.

[0124] Figure 1 shows an exemplary embodiment of a drug delivery device, e.g. a pen-type injector, and an electronic dose capturing system.

[0125] The present Figure 1 shows an electronic dose capturing system which is attachable to a proximal end of a drug delivery device, e.g. an injection device, such as a pen injector, such as to fit the injector device like a cap. The electronic dose capturing system is configured such that it can be push-fitted over a dosage knob or dose dialing knob of the injection device. In particular, a first portion of the electronic dose capturing system includes a cavity that receives the dosage knob and includes a deformable inner surface such as to provide a tight fit over the dosage knob and / or has features that mate closely with external features of the dosage knob. Through the push-fit features, the electronic dose capturing system can easily be installed on the injection device and can easily be removed through application of a removal force between the electronic dose capturing system and the injection device in an axial direction. When installed, the electronic dose capturing system is manipulated by the user in order to effect operation of the injection device. The electronic dose capturing system when installed monitors quantities and times of medicament delivery from the injection pen.

[0126] Medicament quantities can be transmitted to an external device, e.g. to a smartphone, and / or displayed on a display of the electronic dose capturing system. By providing the electronic dose capturing system with push-fit features, it can be located onto and used with a series of different drug delivery devices and thus monitor a user's medicament treatment over multiple devices. Moreover, this can be achieved without impeding normal use of the injection device and without obscuring a dosage window, e.g. a device dose indicator of the injection device.

[0127] In the following, embodiments of the present invention will be described with reference to an insulin injection device. The present invention is however not limited to such application and may equally well be deployed with injection devices that eject other medicaments or drug delivery devices that deliver other medicaments. Figure 1 is an exploded view of a medicament delivery device. In this example, the medicament delivery device is an injection device 1, such as the one disclosed in the patent application WO 2004 / 078239 A1. The injection device, however is not limited to this type and also auto-injectors are encompassed.

[0128] The injection device 1 of Figure 1 is a pre-filled, disposable injection pen that may comprise a housing 10 comprising an insulin container 14, to which a needle 15 can be affixed. The needle is protected by an inner needle cap 16 and either an outer needle cap 17 or an alternative cap 18. An insulin dose to be ejected from injection device 1 can be programmed, or 'dialed in' by turning a dosage knob 12, and a currently programmed dose is then displayed via device dose indicator 13, for instance in multiples of units. For example, where the injection device 1 is configured to administer human insulin, the dosage may be displayed in so-called International Units (IU), wherein one IU is the biological equivalent of about 45.5 micrograms of pure crystalline insulin (1 / 22 mg). Other units may be employed in injection devices for delivering analogue insulin or other medicaments. It should be noted that the selected dose may equally well be displayed differently than as shown in device dose indicator 13 in Figure 1.

[0129] The device dose indicator 13 may be in the form of an aperture in the housing 10, which permits a user to view a limited portion of a number sleeve 70 that may be configured to move when the dosage knob 12 is turned, to provide a visual indication of a currently set dose, e.g. a set specific dosage size of a drug dose. The dosage knob 12 may be rotated on a helical path with respect to the housing 10 when turned during setting. The device dose indicator 13 may be and / or comprise the number sleeve 70.

[0130] In this example, the dosage knob 12 includes one or more formations 71a, 71b, 71c to facilitate attachment of the electronic dose capturing system.

[0131] The injection device 1 may be configured so that turning the dosage knob 12 causes a mechanical click sound to provide acoustical feedback to a user. The number sleeve 70 mechanically interacts with a piston in insulin container 14. When needle 15 is stuck into a skin portion of a patient or in an injection pad, and then injection button 11 is pushed, the insulin dose displayed in device dose indicator 13 will be ejected from injection device 1. When the needle 15 of injection device 1 remains for a certain time in the skin portion or the injection pad after the injection button 11 is pushed, a high percentage of the dose is actually injected into the patient's body or the injection pad. Ejection of the insulin dose may also cause a mechanical click sound, which is however different from the sounds produced when using dosage knob 12.

[0132] In this embodiment, during delivery of the insulin dose, the dosage knob 12 is turned to its initial position, in an axial movement, that is to say without rotation, while the number sleeve 70 is rotated to return to its initial position, e.g. to a zero-dose position, e.g. to display a dose of zero units.

[0133] Injection device 1 may be used for several injection processes until either the insulin container 14 is empty or the expiration date of the medicament in the injection device 1 (e.g. 28 days after the first use) is reached.

[0134] Furthermore, before using injection device 1 for the first time, it may be necessary to perform a so-called "prime shot" to remove air from insulin container 14 and needle 15, for instance by selecting two units of insulin and pressing injection button 11 while holding injection device 1 with the needle 15 upwards. For simplicity of presentation, in the following, it will be assumed that the ejected amounts substantially correspond to the injected doses, so that, for instance the amount of medicament ejected from the injection device 1 is equal to the dose received by the user. Nevertheless, differences (e.g. losses) between the ejected amounts and the injected doses, e.g. the dosing accuracy, may need to be taken into account.

[0135] Figure 2 schematically illustrates an exemplary embodiment of a drug delivery monitoring system 20 in accordance with the present disclosure. The drug delivery monitoring system may for example be designated as a component of a smart home device. The schematically illustrated monitoring system 20 may comprise at least one sensor unit 30. The sensor unit 30 may be part, e.g. may be an integrated part, of the drug delivery monitoring system 20 or coupled with the drug delivery monitoring system 20, e.g. by communication means, e.g. via WiFi. The at least one sensor unit 30 may be configured to capture sensor unit data associated with the drug delivery device 1. The at least one sensor unit 30 may comprise a Level-1 sensor unit. The Level-1 sensor unit may be configured to detect user body motions, user noises and / or environment noises, which are indicative of the drug delivery device usage. The Level-1 sensor unit may include at least one of, more of, or all of a smartwatch, a smart ring, smart classes, and / or a smart fabric. The drug delivery monitoring system 20 may comprise specific interfaces for communicating with the sensor unit 30.

[0136] The drug delivery monitoring system 20 may further comprise a processing unit 21 that may be coupled to the at least one sensor unit 30. The processing unit 21 may be configured to analyze the captured sensor unit data to determine the occurrence of a drug delivery device activation event e.g. based on predefined criteria for drug delivery device usage. Incorporating the processing unit 21 that may be coupled to the sensor unit or to several sensor units may enable the drug delivery monitoring system to (intelligently) determine the occurrence of drug delivery device activation events.

[0137] The drug delivery monitoring system 20 may further comprises an output interface 22. The output interface may be connected to the processing unit 21. The output interface may be configured to generate and / or provide a usage data set based on the analysis of the sensor unit data. The usage data set may include information of the drug delivery device activation event. The usage data set may be provided to different stakeholders for further processing and / or use, e.g. to healthcare providers, patients, and / or caregivers. The usage data set may also be converted in a report for presenting the data user-readable view, e.g. the drug delivery monitoring system may provide the functionality to generate printable and / or digital reports e.g. summarizing drug delivery device usage.

[0138] The output interface may be provided to communicate essential usage data sets to the stakeholders, for example via communications means, such as Bluetooth and / or Wi-Fi. A mobile application may for example receive data from the processing unit via the communication means. The mobile application may be designed to display information for a drug delivery device activation event, medication administration times, dosage details, and / or alerts for upcoming doses. The mobile application may further synchronize with wearable devices like smartwatches and / or smartphones and may provide vibration sound, and / or visual alerts The monitoring system may include an API for secure transmission of usage data sets e.g. directly to Electronic Health Record systems used by healthcare facilities.

[0139] The drug delivery monitoring system may comprise a memory unit (not shown). The memory unit may be coupled to the processing unit, e.g. for storing the predefined criteria for drug delivery device usage, captured sensor unit data, and / or analysis results. The memory unit may be an internal and / or external memory unit and may include a flash memory, RAM, HDD, SSD, and / or a portable memory device.

[0140] The sensor unit 30 may provide sensor unit data including motion information of the body of the user or patient and / or body parts of the user or patient and / or noise detected in the environment of the user. The sensor unit data may comprise information on the position of the drug delivery device 1 and / or changes in the position of the drug delivery device 1 , usage information on the usage of the drug delivery device 1 , timestamps indicative of when the drug delivery device 1 is activated, and / or duration of usage of the drug delivery device 1. Further, the detected environment noise may include sounds that occur when opening the fridge, e.g. when a user opens the fridge in which the drug delivery device and / or the medicament container of the drug delivery device is stored, e.g. prior to use. These could include the sound of the seal breaking as the door opens, the slight whoosh of cooler air meeting the warmer room air, and / or possibly the hum or click of the appliance's motor and / or cooling system becoming more noticeable as the door is no longer blocking the sound. Further environment noise that occurs and may be detected is clicks sounds when de-packing the drug delivery device 1 and / or activate and / or deactive the drug delivery device 1.

[0141] The usage data set may include a timestamp indicative of the time of the event activation of the drug delivery device 1 for a drug delivery operation, a timestamp indicative of the time of the completion of the drug delivery operation, a duration of the drug delivery operation; and / or a confirmation that the drug delivery operation has been completed.

[0142] The drug delivery device 1 may be an insulin injection device as described in relation to Figure 1 , e.g. a pen-type injector. The embodiments are however not limited to pen-type injectors and encompass also other injection devices, e.g. autoinjectors 1.

[0143] Furthermore, a computer program may be provided. The computer program may comprise commands that, when executed by a computer or a processing unit (e.g. of the drug delivery monitoring system), may cause it to carry out or execute the method described above, e.g. at least in part or the entire method and / or to control the operation of the drug delivery monitoring system. The program code of the computer program may be in any code, in particular in a code suitable for controlling a drug delivery monitoring system.

[0144] The drug delivery monitoring system 20 may be designed to execute the method 200 for verifying a drug administration using a self-learning model in a drug delivery monitoring system 20, which is described more in detail with reference to Figure 5.

[0145] Figure 3 schematically illustrates a further exemplary embodiment of a drug delivery monitoring system 20 in accordance with the present disclosure. The drug delivery monitoring system of Figure 3 may be similar to the drug delivery monitoring system of Figure 2, e.g. comprise one of, more of or all of the features described with respect to the drug delivery monitoring system of Figure 2, or vice versa.

[0146] The drug delivery monitoring system 20 may be connected to several stakeholders, e.g. patients, healthcare providers, and / or device manufacturers, for providing the usage data set. The usage data set is transmitted to a designated recipient, wherein the designated recipient may comprise a healthcare provider system 50, a device manufacturer 80, a user’s handheld device 60 and / or a user's computing device 40. The designated recipients may further analyze the usage data set for verifying the use of the drug delivery device 1 , e.g. of the pen-type injector and / or of the autoinjector, the correct usage of the drug delivery device 1 and, if necessary, the correct medication. The designated recipients may be connected to the drug delivery monitoring system 20 by using standardized communication means, e.g., Wi-Fi, Ethernet communication, Bluetooth, and / or communication protocols for a secure communication of the World Wide Web.

[0147] The drug delivery monitoring system 20 may be designed to execute the method 100 for detecting a usage of a drug delivery device 1 , which is also described in detail with reference to a method shown in Figure 4. Features described in relation to the method which relate to the drug delivery monitoring system may be implemented in the drug delivery monitoring systems of Figure 2 and / or Figure 3 and vice-versa.

[0148] As schematically shown in Figure 4, in a first step 110, sensor unit data e.g. received by a sensor unit or a plurality of sensor units associated with a drug delivery device, may be analyzed to determine the occurrence of a drug delivery device activation event.

[0149] The analysis may involve comparing operational data with predefined criteria for a drug delivery device usage. The data may include various types of information such as time stamps, device status (e.g. on / off / idle), environmental conditions (e.g. temperature and / or humidity), patient's physiological data (e.g. heart rate and / or skin resistance), and / or the specific actions performed by the device (e.g. movement and / or activation signals). The data may allow for the customization and / or monitoring of drug delivery schedules and / or dosages based on the patient's unique needs and / or responses, leading to more effective treatments. Predefined criteria for drug delivery device usage may refer to a set of conditions, protocols, and / or parameters established to guide and / or to verify the plausibility of the correct and safe use of the device.

[0150] The activation event of the drug delivery device (herein also called "drug delivery device activation event”) may refer to an action or sequence of actions in which the device's primary function, e.g. to administer or deliver, e.g. inject, a dose of drug to a patient, is initiated. Some possible sequence of actions are described in more detail in Figure 7 and may comprise for example one of, more of, or all of: the retrieval of the drug delivery device or of the medicament container from a fridge, the removal of the drug delivery device or the medicament container from the packaging, the removal of the cap from the drug delivery device, the sterilization of the area in which the injection should occur, the medicament delivery as such and the throwing away of the drug delivery device and / or packaging of the drug delivery device.

[0151] The sequences of actions may also comprise more actions or less actions than the one mentioned and the disclosure is not limited to these. Any specific or generic step which may be required for completing a drug administration may be part of the sequence of actions.

[0152] The operational data may encompass real-time data of the drug delivery device, e.g. of the autoinjector or pen-type injector, during its operation, which may be monitored by the disclosed drug delivery monitoring system, e.g. the drug delivery monitoring system of Figures 2 and / or Figure 3.

[0153] The predefined criteria to which the operational data is compared may comprise a set of conditions, protocols, and / or parameters established to guide and / or to verify the plausibility of the correct and / or safe use of the drug delivery device.

[0154] In a further step 120, a usage data set based on the analysis of step 110 may be provided. The usage data set may include information on the drug delivery device activation event.

[0155] The sensor unit data may be provided by at least one sensor unit 30 comprising at least one Level-1 sensor unit. In this example reference will be made to one Level-1 sensor unit, however more than one Level-1 sensor units may also be envisaged, e.g. 2, 3, 4 or more Level-1 sensor units. The Level-1 sensor unit may be configured to detect user body motions, user noises and / or environment noises, which may be indicative of the injector's usage. The Level-1 sensor unit may include one of, more of, or all of: a smartwatch, a smart ring, smart glasses, and / or smart fabrics. The Level-1 sensor unit may be configured to analyze the detected body motions, user noises and / or environment noises using one or more quantities which are monitored by the sensor unit, the quantities being suitable to be sensed in proximity to the user.

[0156] The body motion may be associated with the usage of a drug delivery device, e.g. the drug delivery device of Figure 1 , e.g. a pen-type injector or an autoinjector. The body motions may include the opening motion of the user while opening a fridge, e.g. to take out the drug delivery device or the medicament container. It may include the opening of the package of the drug delivery device. It may include motion of the drug delivery device for performing the drug administration, including e.g. the activation and / or deactivation of the drug delivery device as well as the administering.

[0157] The noise, e.g. the user noise in conjunction with the usage of the drug delivery device, may include sounds (e.g. a click sound) made while opening the fridge, the package of the drug delivery device and / or activating or deactivating the drug delivery device. Additionally, or alternatively environmental noises may be detected by the Level-1 sensor unit, such as background sounds typical of the setting in which the device may be used, e.g. the steps made by the user walking towards the fridge and / or noises of the fridge itself not related to any user interaction, e.g. the hum or click of the appliance's motor.

[0158] The Level-1 sensor unit may for example include a smartwatch. It may however also comprise a smart ring, a smart fabric and / or smart glasses. The smartwatch may comprise functions suitable for detecting body motions, user noises and / or environment noises, such as gyroscopes, accelerometer, GPS, temperature and / or blood oxygen saturation sensors and / or microphones. The Level-1 sensor unit may be configured to communicate with other devices, e.g. smart devices, such as Level-2, Level-3 and / or Level-4 sensor units, other home devices and / or cloud systems.

[0159] The sensor unit 30 may comprise additionally or alternatively a Level-2 sensor unit (or more), wherein the Level-2 sensor unit may be configured to complement the Level-1 sensor unit by providing additional sensor data. The Level-2 sensor unit may be or may comprise a smartphone. The smartphone may be configured to complement the Level-1 sensor unit by providing additional sensor data based on applications and features inherent to the smartphone, e.g. optimized for detecting drug delivery device usage. Application(s) may be installed on the smartphone and may support visualization of the usage data set. Further, one or more internal sensor of the smartphone, e.g. microphone, GPS ad / or accelerators may be used to detect motion and / or noises.

[0160] The Level-2 sensor unit may be configured to process sensor data from Level-1 and / or Level-2 sensor units to enhance the accuracy of detecting drug delivery device usage detection through e.g. the integration of body motion, user noises, environment noises, and / or smartphone- derived data into the data processing. The smartphone may be capable to process sensor unit data provided from, the Level-1 and / or Level-2 sensor units.

[0161] Level-1 and / or Level-2 sensor units may be considered the primary levels for monitoring, due to their proximity to the user and / or their combined capabilities in detecting detailed physical and / or auditory signs of drug delivery device usage.

[0162] The sensor unit 30 may comprise additionally or alternatively at least one Level-3 sensor unit. The Level-3 sensor unit may comprise or may consist of a smart speaker. The smart speaker may be configured to detect ambient sounds associated with drug delivery device usage and / or to provide a supplementary layer of monitoring through voice recognition and / or environment noise analysis. Additional special noises in the environment provided by the drug delivery device may be captured. The Level-3 sensor unit may augment the data collected by the Level- 1 , and / or Level-2 sensor units.

[0163] The sensor unit 30 may comprise additionally or alternatively at least one Level-4 sensor unit. The Level-4 sensor unit may comprise or may consist of a camera. The camera may be configured to visually monitor the user and the drug delivery device. The Level-4 sensor unit may provide visual confirmation of drug delivery device usage and may augment the data collected by the Level-1 , Level-2, and / or Level-3 sensor units.

[0164] A centralized data management system may be used to collect data from one or more sensor unit 30. An algorithm may be used to clean the data by removing duplicates, correcting errors, and / or filling missing values, preprocess the data to convert it into a uniform format, making it easier to analyze. The sensor unit data may be encrypted during transmission to protect confidentiality and integrity. A security protocol for data transfer may be used. The sensor unit data may be stored in a secure and / or scalable environment. The sensor unit data may be stored in a local storage solution or a cloud-based storage ensuring they comply with healthcare data protection standards, such as HIPAA and / or GDPR. According to a further step 130, the method further comprises transmitting the usage data set to a, e.g. designated, recipient. The designated recipient may comprise one of, more of, or all of a healthcare provider system, a monitoring system, a device manufacturer, a user’s handheld device and / or a user's computing device. This may include real-time data sharing that may support more informed decision-making, timely interventions, and / or personalized care strategies, e.g. ultimately contributing to improved user or patient outcomes. Transmitting the usage data set may enable the collection of large-scale data for analysis, e.g. contributing to research and / or the continuous improvement of treatment protocols and drug delivery device designs.

[0165] Figure 5 shows an exemplary embodiment of a computer implemented method for verifying a drug administration using a self-learning model in a drug delivery monitoring system.

[0166] As shown in Figure 5, in a first step 210, sensor unit data related to a drug delivery device 1, e.g. a pen-type injector or an autoinjector as described in relation to Figure 1 may be received.

[0167] In a further step 220, the received sensor unit data may be processed with a machine learning model. The machine learning model may be processed on the drug delivery monitoring system 20 to determine whether a drug delivery device activation event has occurred, based on the processed sensor unit data, The machine learning model may initially be trained on a (training) dataset comprising examples of confirmed drug delivery device activation events and non-drug delivery device activation events.

[0168] Processing the received sensor unit data with a machine learning model to determine whether a drug delivery device activation event has occurred may enable the drug delivery monitoring system (e.g. the one described in Figure 2 and / or in Figure 3) to differentiate between actual medication administrations and / or other drug delivery device interactions.

[0169] The machine learning model may be trained through a supervised learning process. The supervised learning process may be fed with a dataset, e.g. a training data set, that may include labeled examples of drug delivery device activation events and / or non-drug delivery device activation events. The training dataset may be generated from historical sensor data that may comprise various parameters such as device activation times, duration of use, device orientation, and / or user interactions. The training dataset may be stored securely, e.g. in cloudbased systems and / or dedicated servers, to facilitate easy access for model training and / or updates In a further step 230 user feedback and / or sensor unit confirmation regarding the accuracy of the determined drug delivery device activation events to identify actual drug administrations and incorrectly identified drug administrations may be captured. The feedback may be integrated in various formats, important for refining machine learning models. Users might receive digital surveys and / or questionnaires on their devices, mobile devices and / or other communication devices to confirm drug administration and / or detail their experiences.

[0170] Interactive notifications on mobile devices may prompt users for quick confirmation of drug administration. Additionally, or alternatively, voice feedback, e.g. via smart home devices and / or smartphone and / or smartwatch may be used to confirm drug administration. Additionally, or alternatively, visual confirmations, such as photographs of the used drug delivery device, may supply evidence and / or confirmation of drug administration. Additionally, or alternatively, manual entries into apps or web platforms may allow for user-generated data and feedback.

[0171] In a further step 240, the machine learning model based on the collected feedback may be updated by employing reinforcement learning techniques and / or supervised learning adjustments to refine the ability of the model to identify drug injection events .

[0172] Reinforcement learning techniques, e.g., Q-learning, are effectively applied where the model learns the optimal action to take (confirming and / or denying injection events) based on the current state, which may include sensor unit data and / or user feedback. The technical implementation may involve updating a Q-table with rewards that may reflect the accuracy of the model's predictions, guiding for example the model to refine its decision-making process over time. For more complex scenarios with high-dimensional input data, Deep Q-Networks (DQN) my utilize deep neural networks to approximate the Q-value function, employing for example a replay memory for experience storage and a target network to stabilize the learning process.

[0173] On the supervised learning side, Convolutional Neural Networks (CNNs) may provide capabilities for analyzing visual confirmations of drug delivery device activation events, such as images of used patches and / or syringes. By automatically detecting and / or learning the most relevant features from images, CNNs may accurately classify these images to verify drug delivery device activation events. This approach leverages layers of convolutions and / or pooling operations to improve the model's visual recognition capabilities. Furthermore, for sequential sensor data that captures the steps of a drug delivery process, Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) Networks may adept at predicting the next likely step and / or identifying discrepancies. LSTMs, in particular, are advantageous for remembering information for extended periods, making them useful for analyzing time-series data from drug delivery devices and thus refining the accuracy of event detection.

[0174] Reinforcement and / or supervised learning methods may utilize collected data to iteratively refine the model's performance, adapting to new information and / or refining predictive capabilities.

[0175] The computer-implemented method may further comprise the steps of iteratively repeating the method steps of the method for verifying a drug administration.

[0176] In a further step, the sensor unit data may be incorporated into a report or made accessible via platforms, websites, and / or software applications.

[0177] Figure 6 shows an exemplary embodiment of hierarchical structure of sensor units.

[0178] Level-1 , Lvl-1, sensor units may for example comprise or be configured as a wearable device, such as a smartwatch as in this example. Level-1 sensor units are not limited to smartwatches and also other wearable devices may be encompassed, such as for example smart rings, smart glasses and / or smart fabrics. The Level-1 sensor unit may be configured to detect user body motions, user noises and / or environment noises, which may be indicative of the drug delivery device’s usage. The Level-1 sensor unit may further be configured to analyze the detected body motions, user noises and / or environment noises using one or more quantities which are monitored by the sensor unit

[0179] Level 2, Lvl-2, sensor units may for example comprise or be configured as a smartphone. The Level-2 sensor unit may be configured to complement the Level-1 sensor unit by providing additional sensor data. The Level-2 sensor unit may be further configured to process sensor data from Level-1 and / or Level-2 sensor units to enhance the accuracy of detecting drug delivery device usage detection, e.g. through the integration of body motion, user noises, environment noises, and / or smartphone-derived data into the data processing.

[0180] According to at least one embodiment, the Level-1 and / or Level-2 sensor units may be considered the primary levels for monitoring, due to their proximity to the user and / or their combined capabilities in detecting detailed physical and / or auditory signs of drug delivery device usage.

[0181] Level 3, Lvl-3, sensor units may for example comprise or be configured as a smart speaker. The Level 3, Lvl-3, sensor units may be configured to detect ambient sounds associated with drug delivery device usage and / or to provide a supplementary layer of monitoring through voice recognition and / or environment noise analysis. The smart speakers may expand the ecosystem by offering voice-controlled interaction and / or the ability to process auditory signals within the environment.

[0182] Level 4, Lvl-4, sensor units may for example comprise or be configured as a camera. The Level 4, Lvl-4, sensor units may provide visual confirmation of drug delivery device usage and / or may augment the data collected by the Level-1 , Level-2, and / or Level-3 sensor units.

[0183] This hierarchical structure may ensure that data collection and / or analysis are optimized for immediacy and / or depth, with each level playing a role based on its proximity to the user and / or its capabilities. Level-1 and / or Level-2 devices may be important for their data capture and interaction with the user. Level-3 and / or Level-4 may provide increasingly broad support, enhancing the system's overall ability to monitor, verify, and / or support the user's medication administration process through a at least one of, or more of, or all of detailed data collection, processing capabilities, and / or environmental context.

[0184] A connecting device, e.g., a home hub 600 may be used to connect the user or patient sensor units (Level-1 , Level-2, Level-3 and / or Level 4). Information from one, more or all of the sensor units, may therefore be received, e.g. collected, by the home hub 600, thereby centralizing and connecting the data collection.

[0185] Figure 7 shows a flow diagram of an exemplary drug delivery device activation event. More specifically it shows a flow diagram of a sequence of actions in which the device's primary function, e.g. to administer or deliver, e.g. inject, a dose of drug to a patient, is initiated. The example is illustrated with specific sensor units. The disclosure is however not limited to those specific sensor units.

[0186] A user, e.g. a patient, may for example be located in his home environment and may require a dose of a medicament administered through a drug delivery device. The drug delivery device may for example be, but is not limited to, the drug delivery device of Figure 1.

[0187] The drug delivery device or the medicament container comprising the medicament may be located inside the fridge in the kitchen of the user. The user may therefore walk towards the kitchen and open the fridge to remove the medicament from the fridge 310.

[0188] At this stage a Level-1 sensor unit, such as a smartwatch (but not limited to a smartwatch) worn by the user on the wrist, may collect data associated with an occurrence of a drug delivery device activation event 310a. The smartwatch may for example detect the fridge noises made by the user, e.g. the noise of the door of the fridge opening. Additionally, or alternatively, the smartwatch may detect the body motion of the user when opening the door of the fridge, e.g. the motion of the arm opening the fridge door. Additionally, or alternatively, the user activity, such as standing up and walking to the fridge, may be determined by the smartwatch, for example through determination of the pulse and / or the blood pressure.

[0189] Additionally, or alternatively a plausibility test may be done, either by the smartwatch or by other devices in which the date and the time of the detected movements and / or sounds are analyzed and compared with known usual date and / or times in which the user is known to administer the medicament with the drug delivery device. The plausibility test may assess whether it is plausible that the user is opening the fridge to remove the drug delivery device or the medicament container for a delivery operation.

[0190] Additionally, or alternatively, a Level-3 sensor unit, such as a home speaker, but not limited to a home speaker, may detect noises of the user 310b, e.g. the steps of the user towards the fridge, the opening of the fridge, the removal of packaging, e.g. of the drug delivery device or of the medicament container from the fridge, and / or the door of the fridge closing. The home speaker may also detect environmental noises, such as the inherent noises of the fridge being louder, e.g. because of the open fridge door.

[0191] A Level-4 sensor unit, such as a camera, e.g. an integrated camera of a smart home device, but not limited to a camera, may detect the user being at the fridge 310c. Depending on the position of the camera, the camera may even detect if the user is extracting the drug delivery device or the medicament container or not.

[0192] After having removed the medicament container or the drug delivery device from the fridge the user may open the drug packaging (of the drug delivery device or of the medicament container) in order to remove the drug delivery device or the medicament container 320.

[0193] At this stage, the smartwatch (or any alternative or additional Level-1 sensor unit) may detect noises which are typical for the opening of a packaging 320a. Also, the smart speaker (or any alternative or additional Level-3 sensor unit) and / or a smartphone (or any alternative or additional Level-2 sensor unit) may detect the typical noises 320b.

[0194] The camera may additionally or alternatively detect the user moving towards or being at its typical medicament administration place, e.g. in front of the fridge or back in the living room and / or may detect the drug delivery device or the medicament container 320c. After unpacking the drug delivery device or the medicament container, the user may prepare the injection site, such as for example using alcohol swipes, or (partially) removing the cloth on the injection site 330, e.g. the arm.

[0195] At this stage, the smartwatch (or any alternative or additional Level-1 sensor unit) may detect the motion of the arm and / or of other parts of the body 330a. The smartwatch may further detect the typical noises related to the preparation of the injection sire, such as the removal of the swipe form the packaging and / or the push of the alcohol atomizer and / or similar 330b.

[0196] Those noises may of course also be captured by a Level-3 device, such as by the smart speaker.

[0197] The camera may detect the user being at its typical medicament administration place and / or may detect the drug delivery device or the medicament container 330c.

[0198] After unpacking the drug delivery device or the medicament container, the user may remove the cap of the injection device, e.g. of the autoinjector.

[0199] At this stage, the smartwatch (or any alternative or additional Level-1 sensor unit) may detect the motion of the arm and / or of other parts of the body 340a and / or may detect the noise of the cap being removed, e.g. of the label tear-open ripping 340a, 340b. The noises may of course also be captured by a Level-3 device, such as by smart speaker.

[0200] The camera may possibly detect the user removing the cap 340c. However, it could also be that the user is positioned such that the removal of the cap 300 is not detected by the camera.

[0201] Additionally, If the drug delivery device is for example an injector with multiple doses in which the dose of medicament to be injected may be set, the smartwatch may detect the motion of setting the dose (not denoted in the figure) on the drug delivery device.

[0202] After the above steps, e.g. after the preparation steps, the medicament may be administered 350.

[0203] At this stage, the smartwatch (or any alternative or additional Level-1 sensor unit) may detect the motion of the arm and / or of other parts of the body 350a and / or the subsequent "stand still" which may be required during administration, e.g. the stand still of the arm while the dose is being administered. The smartwatch may additionally or alternatively detect the noise, e.g. the clicks (one or more clicks) of the drug delivery device during and after administration.

[0204] The smart speaker may also detect the clicks of the drug delivery device. The received sensor unit data from the sensor units during any, some or all of the steps described before may be used to determine an occurrence of a drug delivery device activation event. This may for example be done by comparing operational data with predefined criteria for a drug delivery device usage. A usage data set based on the analysis may be provided, wherein the usage data set includes information on the drug delivery device activation event.

[0205] The method of course is not limited to the above steps, the above sensor units and the above detections. Other, additional or alternative sounds, motions and / or visual indication, indicative of a step during or prior to the drug administration may be determined and / or analyzed (schematically illustrated by the dashed elements in the Figure as a further step after step 350, but not intending as limiting for only after step 350).

[0206] Furthermore, other actions may also be determined, such as the user removing the device from the body, the user throwing the device in the waste and / or the user putting the device packaging back in the fridge.

[0207] In some case, some sensor units may not be capable of detecting a drug delivery device activation event. For example, music might be playing in the home of the user, such that the home speaker is not capable of determining any sound related to a drug delivery device activation event. It may therefore be advantageous to have several sensor units of different levels, e.g. Level-1 , Level-2, Level-3 and / or Level-4.

[0208] The terms “drug” or “medicament” are used synonymously herein and describe a pharmaceutical formulation containing one or more active pharmaceutical ingredients or pharmaceutically acceptable salts or solvates thereof, and optionally a pharmaceutically acceptable carrier. An active pharmaceutical ingredient (“API”), in the broadest terms, is a chemical structure that has a biological effect on humans or animals. In pharmacology, a drug or medicament is used in the treatment, cure, prevention, or diagnosis of disease or used to otherwise enhance physical or mental well-being. A drug or medicament may be used for a limited duration, or on a regular basis for chronic disorders.

[0209] As described below, a drug or medicament can include at least one API, or combinations thereof, in various types of formulations, for the treatment of one or more diseases. Examples of API may include small molecules having a molecular weight of 500 Da or less; polypeptides, peptides and proteins (e.g., hormones, growth factors, antibodies, antibody fragments, and enzymes); carbohydrates and polysaccharides; and nucleic acids, double or single stranded DNA (including naked and cDNA), RNA, antisense nucleic acids such as antisense DNA and RNA, small interfering RNA (siRNA), ribozymes, genes, and oligonucleotides. Nucleic acids may be incorporated into molecular delivery systems such as vectors, plasmids, or liposomes. Mixtures of one or more drugs are also contemplated.

[0210] The drug or medicament may be contained in a primary package or “drug container” adapted for use with a drug delivery device. The drug container may be, e.g., a cartridge, syringe, reservoir, or other solid or flexible vessel configured to provide a suitable chamber for storage (e.g., shorter long-term storage) of one or more drugs. For example, in some instances, the chamber may be designed to store a drug for at least one day (e.g., 1 to at least 30 days). In some instances, the chamber may be designed to store a drug for about 1 month to about 2 years. Storage may occur at room temperature (e.g., about 20°C), or refrigerated temperatures (e.g., from about - 4°C to about 4°C). In some instances, the drug container may be or may include a dualchamber cartridge configured to store two or more components of the pharmaceutical formulation to-be-administered (e.g., an API and a diluent, or two different drugs) separately, one in each chamber. In such instances, the two chambers of the dual-chamber cartridge may be configured to allow mixing between the two or more components prior to and / or during dispensing into the human or animal body. For example, the two chambers may be configured such that they are in fluid communication with each other (e.g., by way of a conduit between the two chambers) and allow mixing of the two components when desired by a user prior to dispensing. Alternatively or in addition, the two chambers may be configured to allow mixing as the components are being dispensed into the human or animal body.

[0211] The drugs or medicaments contained in the drug delivery devices as described herein can be used for the treatment and / or prophylaxis of many different types of medical disorders. Examples of disorders include, e.g., diabetes mellitus or complications associated with diabetes mellitus such as diabetic retinopathy, thromboembolism disorders such as deep vein or pulmonary thromboembolism. Further examples of disorders are acute coronary syndrome (ACS), angina, myocardial infarction, cancer, macular degeneration, inflammation, hay fever, atherosclerosis and / or rheumatoid arthritis. Examples of APIs and drugs are those as described in handbooks such as Rote Liste 2014, for example, without limitation, main groups 12 (antidiabetic drugs) or 86 (oncology drugs), and Merck Index, 15th edition.

[0212] Examples of APIs for the treatment and / or prophylaxis of type 1 or type 2 diabetes mellitus or complications associated with type 1 or type 2 diabetes mellitus include an insulin, e.g., human insulin, or a human insulin analogue or derivative, a glucagon-like peptide (GLP-1), GLP-1 analogues or GLP-1 receptor agonists, or an analogue or derivative thereof, a dipeptidyl peptidase-4 (DPP4) inhibitor, or a pharmaceutically acceptable salt or solvate thereof, or any mixture thereof. As used herein, the terms “analogue” and “derivative” refers to a polypeptide which has a molecular structure which formally can be derived from the structure of a naturally occurring peptide, for example that of human insulin, by deleting and / or exchanging at least one amino acid residue occurring in the naturally occurring peptide and / or by adding at least one amino acid residue. The added and / or exchanged amino acid residue can either be codable amino acid residues or other naturally occurring residues or purely synthetic amino acid residues. Insulin analogues are also referred to as "insulin receptor ligands". In particular, the term ..derivative” refers to a polypeptide which has a molecular structure which formally can be derived from the structure of a naturally occurring peptide, for example that of human insulin, in which one or more organic substituent (e.g. a fatty acid) is bound to one or more of the amino acids. Optionally, one or more amino acids occurring in the naturally occurring peptide may have been deleted and / or replaced by other amino acids, including non-codeable amino acids, or amino acids, including non-codeable, have been added to the naturally occurring peptide.

[0213] Examples of insulin analogues are Gly(A21), Arg(B31), Arg(B32) human insulin (insulin glargine); Lys(B3), Glu(B29) human insulin (insulin glulisine); Lys(B28), Pro(B29) human insulin (insulin lispro); Asp(B28) human insulin (insulin aspart); human insulin, wherein proline in position B28 is replaced by Asp, Lys, Leu, Vai or Ala and wherein in position B29 Lys may be replaced by Pro; Ala(B26) human insulin; Des(B28-B30) human insulin; Des(B27) human insulin and Des(B30) human insulin.

[0214] Examples of insulin derivatives are, for example, B29-N-myristoyl-des(B30) human insulin, Lys(B29) (N- tetradecanoyl)-des(B30) human insulin (insulin detemir, Levemir®); B29-N- palmitoyl-des(B30) human insulin; B29-N-myristoyl human insulin; B29-N-palmitoyl human insulin; B28-N-myristoyl LysB28ProB29 human insulin; B28-N-palmitoyl-LysB28ProB29 human insulin; B30-N-myristoyl-ThrB29LysB30 human insulin; B30-N-palmitoyl- ThrB29LysB30 human insulin; B29-N-(N-palmitoyl-gamma-glutamyl)-des(B30) human insulin, B29-N-omega- carboxypentadecanoyl-gamma-L-glutamyl-des(B30) human insulin (insulin degludec, Tresiba®); B29-N-(N-lithocholyl-gamma-glutamyl)-des(B30) human insulin; B29-N-(w- carboxyheptadecanoyl)-des(B30) human insulin and B29-N-(w-carboxyheptadecanoyl) human insulin.

[0215] Examples of GLP-1 , GLP-1 analogues and GLP-1 receptor agonists are, for example, Lixisenatide (Lyxumia®), Exenatide (Exendin-4, Byetta®, Bydureon®, a 39 amino acid peptide which is produced by the salivary glands of the Gila monster), Liraglutide (Victoza®), Semaglutide, Taspoglutide, Albiglutide (Syncria®), Dulaglutide (Trulicity®), rExendin-4, CJC- 1134-PC, PB-1023, TTP-054, Langlenatide / HM-11260C (Efpeglenatide), HM-15211 , CM-3, GLP-1 Eligen, GRMD-0901 , NN-9423, NN-9709, NN-9924, NN-9926, NN-9927, Nodexen, Viador-GLP-1, CVX-096, ZYOG-1, ZYD-1 , GSK-2374697, DA-3091 , MAR-701 , MAR709, ZP- 2929, ZP-3022, ZP-DI-70, TT-401 (Pegapamodtide), BHM-034. MOD-6030, CAM-2036, DA- 15864, ARI-2651 , ARI-2255, Tirzepatide (LY3298176), Bamadutide (SAR425899), Exenatide- XTEN and Glucagon-Xten.

[0216] An example of an oligonucleotide is, for example: mipomersen sodium (Kynamro®), a cholesterol-reducing antisense therapeutic for the treatment of familial hypercholesterolemia or RG012 for the treatment of Alport syndrom.

[0217] Examples of DPP4 inhibitors are Linagliptin, Vildagliptin, Sitagliptin, Denagliptin, Saxagliptin, Berberine.

[0218] Examples of hormones include hypophysis hormones or hypothalamus hormones or regulatory active peptides and their antagonists, such as Gonadotropine (Follitropin, Lutropin, Choriongonadotropin, Menotropin), Somatropine (Somatropin), Desmopressin, Terlipressin, Gonadorelin, Triptorelin, Leuprorelin, Buserelin, Nafarelin, and Goserelin.

[0219] Examples of polysaccharides include a glucosaminoglycane, a hyaluronic acid, a heparin, a low molecular weight heparin or an ultra-low molecular weight heparin or a derivative thereof, or a sulphated polysaccharide, e.g. a poly-sulphated form of the above-mentioned polysaccharides, and / or a pharmaceutically acceptable salt thereof. An example of a pharmaceutically acceptable salt of a poly-sulphated low molecular weight heparin is enoxaparin sodium. An example of a hyaluronic acid derivative is Hylan G-F 20 (Synvisc®), a sodium hyaluronate.

[0220] The term “antibody”, as used herein, refers to an immunoglobulin molecule or an antigenbinding portion thereof. Examples of antigen-binding portions of immunoglobulin molecules include F(ab) and F(ab')2 fragments, which retain the ability to bind antigen. The antibody can be polyclonal, monoclonal, recombinant, chimeric, de-immunized or humanized, fully human, non-human, (e.g., murine), or single chain antibody. In some embodiments, the antibody has effector function and can fix complement. In some embodiments, the antibody has reduced or no ability to bind an Fc receptor. For example, the antibody can be an isotype or subtype, an antibody fragment or mutant, which does not support binding to an Fc receptor, e.g., it has a mutagenized or deleted Fc receptor binding region. The term antibody also includes an antigen-binding molecule based on tetravalent bispecific tandem immunoglobulins (TBTI) and / or a dual variable region antibody-like binding protein having cross-over binding region orientation (CODV). The terms “fragment” or “antibody fragment” refer to a polypeptide derived from an antibody polypeptide molecule (e.g., an antibody heavy and / or light chain polypeptide) that does not comprise a full-length antibody polypeptide, but that still comprises at least a portion of a full- length antibody polypeptide that is capable of binding to an antigen. Antibody fragments can comprise a cleaved portion of a full length antibody polypeptide, although the term is not limited to such cleaved fragments. Antibody fragments that are useful in the present invention include, for example, Fab fragments, F(ab')2 fragments, scFv (single-chain Fv) fragments, linear antibodies, monospecific or multispecific antibody fragments such as bispecific, trispecific, tetraspecific and multispecific antibodies (e.g., diabodies, triabodies, tetrabodies), monovalent or multivalent antibody fragments such as bivalent, trivalent, tetravalent and multivalent antibodies, minibodies, chelating recombinant antibodies, tribodies or bibodies, intrabodies, small modular immunopharmaceuticals (SMIP), binding-domain immunoglobulin fusion proteins, camelized antibodies, and immunoglobulin single variable domains. Additional examples of antigen-binding antibody fragments are known in the art.

[0221] The term “immunoglobulin single variable domain” (ISV), interchangeably used with “single variable domain”, defines immunoglobulin molecules wherein the antigen binding site is present on, and formed by, a single immunoglobulin domain. As such, immunoglobulin single variable domains are capable of specifically binding to an epitope of the antigen without pairing with an additional immunoglobulin variable domain. The binding site of an immunoglobulin single variable domain is formed by a single heavy chain variable domain (VH domain or VHH domain) or a single light chain variable domain (VL domain). Hence, the antigen binding site of an immunoglobulin single variable domain is formed by no more than three CDRs.

[0222] An immunoglobulin single variable domain (ISV) can be a heavy chain ISV, such as a VH (derived from a conventional four-chain antibody), or VHH (derived from a heavy-chain antibody), including a camelized VH or humanized VHH. For example, the immunoglobulin single variable domain may be a (single) domain antibody, a "dAb" or dAb or a Nanobody® ISV (such as a VHH, including a humanized VHH or camelized VH) or a suitable fragment thereof. [Note: Nanobody® is a registered trademark of Ablynx N.V.]; other single variable domains, or any suitable fragment of any one thereof.

[0223] “VHH domains”, also known as VHHs, VHH antibody fragments, and VHH antibodies, have originally been described as the antigen binding immunoglobulin variable domain of “heavy chain antibodies” (i.e. , of “antibodies devoid of light chains”; Hamers-Casterman et al. 1993 (Nature 363: 446-448). The term “VHH domain” has been chosen in order to distinguish these variable domains from the heavy chain variable domains that are present in conventional 4- chain antibodies (which are referred to herein as “VH domains”) and from the light chain variable domains that are present in conventional 4-chain antibodies (which are referred to herein as “VL domains”). For a further description of VHH’s, reference is made to the review article by Muyldermans 2001 (Reviews in Molecular Biotechnology 74: 277-302).

[0224] For the term “dAb’s” and “domain antibody”, reference is for example made to Ward et al. 1989 (Nature 341: 544), to Holt et al. 2003 (Trends Biotechnol. 21: 484); as well as to WO 2004 / 068820, WO 2006 / 030220, WO 2006 / 003388. It should also be noted that, although less preferred in the context of the present invention because they are not of mammalian origin, single variable domains can be derived from certain species of shark (for example, the so-called “IgNAR domains”, see for example WO 2005 / 18629).

[0225] The terms “Complementarity-determining region” or “CDR” refer to short polypeptide sequences within the variable region of both heavy and light chain polypeptides that are primarily responsible for mediating specific antigen recognition. The term “framework region” refers to amino acid sequences within the variable region of both heavy and light chain polypeptides that are not CDR sequences, and are primarily responsible for maintaining correct positioning of the CDR sequences to permit antigen binding. Although the framework regions themselves typically do not directly participate in antigen binding, as is known in the art, certain residues within the framework regions of certain antibodies can directly participate in antigen binding or can affect the ability of one or more amino acids in CDRs to interact with antigen.

[0226] Examples of antibodies are anti PCSK-9 mAb (e.g., Alirocumab), anti IL-6 mAb (e.g., Sarilumab), and anti IL-4 mAb (e.g., Dupilumab).

[0227] Pharmaceutically acceptable salts of any API described herein are also contemplated for use in a drug or medicament in a drug delivery device. Pharmaceutically acceptable salts are for example acid addition salts and basic salts.

[0228] Those of skill in the art will understand that modifications (additions and / or removals) of various components of the APIs, formulations, apparatuses, methods, systems and embodiments described herein may be made without departing from the full scope and spirit of the present invention, which encompass such modifications and any and all equivalents thereof.

[0229] An example drug delivery device may involve a needle-based injection system as described in Table 1 of section 5.2 of ISO 11608-1 :2014(E). As described in ISO 11608-1 :2014(E), needlebased injection systems may be broadly distinguished into multi-dose container systems and single-dose (with partial or full evacuation) container systems. The container may be a replaceable container or an integrated non-replaceable container. As further described in ISO 11608-1 :2014(E), a multi-dose container system may involve a needle-based injection device with a replaceable container. In such a system, each container holds multiple doses, the size of which may be fixed or variable (pre-set by the user). Another multi-dose container system may involve a needle-based injection device with an integrated non-replaceable container. In such a system, each container holds multiple doses, the size of which may be fixed or variable (pre-set by the user).

[0230] As further described in ISO 11608-1 :2014(E), a single-dose container system may involve a needle-based injection device with a replaceable container. In one example for such a system, each container holds a single dose, whereby the entire deliverable volume is expelled (full evacuation). In a further example, each container holds a single dose, whereby a portion of the deliverable volume is expelled (partial evacuation). As also described in ISO 11608-1:2014(E), a single-dose container system may involve a needle-based injection device with an integrated non-replaceable container. In one example for such a system, each container holds a single dose, whereby the entire deliverable volume is expelled (full evacuation). In a further example, each container holds a single dose, whereby a portion of the deliverable volume is expelled (partial evacuation).

[0231] Reference numerals

[0232] 1 drug delivery device

[0233] 10 housing

[0234] 12 dosage knob

[0235] 13 dosage window

[0236] 14 medicament container

[0237] 15 needle

[0238] 16 inner needle cap

[0239] 17 outer needle cap

[0240] 18 other cap

[0241] 20 monitoring system

[0242] 21 processing unit

[0243] 22 output interface

[0244] 30 sensor unit

[0245] 40 computing device

[0246] 50 health care provider system

[0247] 60 handheld device

[0248] 70 dial sleeve

[0249] 71a-c formations

[0250] 80 device manufacturer

[0251] 100 method

[0252] 110-130 method steps

[0253] 200 method

[0254] 210-240 method steps

[0255] 310-350 method steps

[0256] 600 home hub

Claims

Claims1. A method (100) for detecting a usage of a drug delivery device, comprising the steps of:- analyzing (110) received sensor unit data to determine an occurrence of a drug delivery device activation event, wherein the analysis involves comparing operational data with predefined criteria for a drug delivery device usage, and- providing (120) a usage data set based on the analysis, wherein the usage data set includes information on the drug delivery device activation event.

2. The method for detecting a usage of a drug delivery device according claim 1, wherein the method further comprises: transmitting (130) the usage data set to a designated recipient, the designated recipient comprising one of, more of, or all of:- a healthcare provider system (50),- a device manufacturer (80),- a user’s handheld device (60), and / or- a user's computing device (40).

3. The method for detecting a usage of a drug delivery device according to any one of the preceding claims, wherein the information of the usage data set includes one of, more of, or all of:- a timestamp indicative of the time of the activation of the drug delivery device for a drug delivery operation,- a timestamp indicative of the time of the completion of the drug delivery operation,- a duration of the drug delivery operation, and / or- a confirmation that the drug delivery operation has been completed.

4. The method for detecting a usage of a drug delivery device according to any one of the preceding claims, wherein the sensor unit data comprises one of, more of, or all of:- information on the position of the drug delivery device and / or changes in the position of the drug delivery device,- usage information on the usage of the drug delivery device,- a timestamp indicative of when the drug delivery device is activated, and / or- duration of usage of the drug delivery device.

5. A computer-implemented method (200) for verifying a drug administration using a selflearning model in a drug delivery monitoring system (20), comprising the steps of:- receiving (210) sensor unit data related to a drug delivery device (1);- processing (220) the received sensor unit data with a machine learning model processed on the monitoring system (20) to determine whether a drug delivery device activation event has occurred, based on the processed sensor unit data, wherein the machine learning model is initially trained on a dataset comprising examples of confirmed drug delivery device activation events and non-drug delivery device activation events;- capturing (230) user feedback and / or sensor unit confirmation regarding the accuracy of the determined drug delivery device activation event to identify actual drug administrations and incorrectly identified drug administrations;- updating (240) the machine learning model based on the collected feedback by employing reinforcement learning techniques and / or supervised learning adjustments to refine the ability of the model to identify drug delivery device activation events.

6. A drug delivery monitoring system (20) for detecting the usage of a drug delivery device (1), comprising:- at least one sensor unit (30) configured to capture sensor unit data associated with the drug delivery device (1);- a processing unit (21) coupled to the at least one sensor unit (30), configured to analyze the captured sensor unit data to determine the occurrence of a drug delivery activation event based on predefined criteria for drug delivery device usage;- an output interface (22) connected to the processing unit (21), configured to generate and / or provide a usage data set based on the analysis of the sensor unit data, wherein the usage data set includes information of the drug delivery activation event.

7. The drug delivery monitoring system (20) according to claim 6, wherein the at least one sensor unit (30) includes a hierarchical configuration of several sensor units (30) categorized into levels based on their proximity to the user and / or the sensor unit capabilities.

8. The drug delivery monitoring system (20) according to any one of claims 6 or 7, wherein the at least one sensor unit (30) comprises at least one Level-1 sensor unit, wherein the at least one Level-1 sensor unit is configured to detect user body motions, user noises and / or environment noises, which are indicative of the usage of the drug delivery device,9. The drug delivery monitoring system (20) according claim 8, wherein the at least one Level-1 sensor unit includes at least one of, more of, or all of:- a smartwatch,- a smart ring,- smart glasses, and / or- a smart fabric.

10. The drug delivery monitoring system (20) according to any one of claims 8 or 9, wherein the Level-1 sensor unit is further configured to analyze the detected body motions, user noises and / or environment noises using one or more quantities which are monitored by the sensor unit, the quantities being suitable to be sensed in proximity to the user.11 . The drug delivery monitoring system (20) according to any one of claims 8 to 10, wherein the at least one sensor unit (30) comprises at least one Level-2 sensor unit, wherein the at least one Level-2 sensor unit is configured to complement the Level-1 sensor unit by providing additional sensor data.

12. The drug delivery monitoring system (20) according to claim 11 , wherein the Level-2 sensor unit is further configured to process sensor data from both Level-1 and Level-2 sensor units to enhance the accuracy of detecting drug delivery activation events through the integration of body motion, user noises, environment noises, and / or smartphone-derived data into the data processing.

13. The drug delivery monitoring system (20) according to any one of claims 8 to 12, wherein the at least one sensor unit (30) comprises a Level-3 sensor unit comprising or consisting of a smart speaker, wherein the smart speaker is configured to detect ambient sounds associated with drug delivery device usage and / or to provide a supplementary layer of monitoring through voice recognition and / or environment noise analysis.

14. The drug delivery monitoring system (20) according to any one of claims 8 to 13, wherein the at least one sensor unit (30) comprises a Level-4 sensor unit comprising or consisting of a camera, wherein the camera is configured to visually monitor the user and the drug deliverydevice (1), the Level-4 sensor unit providing visual confirmation of drug delivery device usage and augmenting the data collected by the Level-1 , Level-2, and / or Level-3 sensor units.

15. A computer program having program code or program means, wherein, when the computer program is executed on a computer or a processing unit, the program code or the program means causes the computer or the processing unit to execute a method according to any one of the preceding method claims 1 to 5.

16. The method for detecting a usage of a drug delivery device according claim 1, wherein the method further comprises: transmitting (130) the usage data set to a designated recipient, the designated recipient comprising a device manufacturer (80).

17. The drug delivery monitoring system (20) according to any one of claims 6 or 7, wherein the at least one sensor unit (30) comprises at least one Level-1 sensor unit, wherein the at least one Level-1 sensor unit is configured to detect environment noises, which are indicative of the usage of the drug delivery device, wherein the at least one sensor unit (30) comprises a Level-3 sensor unit comprising or consisting of a smart speaker, wherein the smart speaker is configured to detect ambient sounds associated with drug delivery device usage and to provide environment noise analysis.

18. A method (100) for detecting a usage of a drug delivery device, wherein the drug delivery device is an injection device, comprising the steps of:- analyzing (110) received sensor unit data to determine an occurrence of a drug delivery device activation event, wherein the analysis involves comparing operational data with predefined criteria for a drug delivery device usage, and- providing (120) a usage data set based on the analysis, wherein the usage data set includes information on the drug delivery device activation event.

19. A method (100) for detecting a usage of a drug delivery device, comprising the steps of:- analyzing (110) received sensor unit data to determine an occurrence of a drug delivery device activation event, wherein the analysis involves comparing operational data with predefined criteria for a drug delivery device usage, wherein the sensor unit data comprises information on the position of the drug delivery device and / or changes in the position of the drug delivery device, and- providing (120) a usage data set based on the analysis, wherein the usage data set includes information on the drug delivery device activation event.

20. A drug delivery monitoring system (20) for detecting the usage of a drug delivery device (1), wherein the drug delivery device (1) is an injection device, the drug delivery monitoring system (20) comprising:- at least one sensor unit (30) configured to capture sensor unit data associated with the drug delivery device (1);- a processing unit (21) coupled to the at least one sensor unit (30), configured to analyze the captured sensor unit data to determine the occurrence of a drug delivery activation event based on predefined criteria for drug delivery device usage;- an output interface (22) connected to the processing unit (21), configured to generate and / or provide a usage data set based on the analysis of the sensor unit data, wherein the usage data set includes information of the drug delivery activation event.21 . A drug delivery monitoring system (20) for detecting the usage of a drug delivery device (1), comprising:- at least one sensor unit (30) configured to capture sensor unit data associated with the drug delivery device (1);- a processing unit (21) coupled to the at least one sensor unit (30), configured to analyze the captured sensor unit data to determine the occurrence of a drug delivery activation event based on predefined criteria for drug delivery device usage;- an output interface (22) connected to the processing unit (21), configured to generate and / or provide a usage data set based on the analysis of the sensor unit data, wherein the usage data set includes information of the drug delivery activation event, wherein the at least one sensor unit (30) comprises at least one Level-1 sensor unit, wherein the at least one Level-1 sensor unit is configured to detect user body motions, user noises and / or environment noises, which are indicative of the usage of the drug delivery device, and wherein the Level-1 sensor unit is further configured to analyze the environment noises using one or more quantities which are monitored by the sensor unit, the quantities being suitable to be sensed in proximity to the user.

22. A drug delivery monitoring system (20) according to claim 21 , wherein environmental noises are noises that occur when using a drug delivery device and which include background sounds typical of the setting in which the drug delivery device is used.

Images