Computer-implemented method for detecting a food intake of a user

Abstract

A computer-implemented method for detecting a food intake of a user (112) is proposed. The method comprising: a. (122) retrieving motion data generated by a wearable chest motion sensor (110) worn by the user (112); b. (124) determining a swallowing motion pattern by evaluating the motion data; and c. (126) generating a food intake event signal comprising at least information regarding a time of the swallowing motion pattern, wherein the method comprises determining an indicator for meal size (138) and / or an indicator for meal quality (140) by using a pre-defined relationship between the number of detected swallowing events within a time range from the first swallowing event to the last swallowing event and the meal size and / or meal quality.

Description

[0001] July 31, 2025

[0002] Computer-implemented method for detecting a food intake of a user

[0003] Technical Field

[0004] The invention relates to a computer-implemented method for detecting a food intake of a user, an analytical system, computer programs and computer-readable storage mediums. The invention may both be applied in the field of home care as well as in the field of professional care, such as in hospitals. Other applications are feasible.

[0005] Background art

[0006] For diabetes management, especially for personalized predictive guidance, meal intake is an important feature. Currently, several diary options, e.g. digital or non-digital, exist where users can manually enter their meals. Moreover, it is known to use a sensor at a body location to track a meal activity, e.g. tracking stomach sounds or peristaltic movement.

[0007] US 2012 / 0143021 Al discloses a device, system and method for detecting meal event in a subject and in particular a device, system and method for communicating and controlling auxiliary devices and / or systems associated therewith.

[0008] US 9,622,690 B2 discloses a measurement device which includes a housing that has an attached biosensor that includes a reagent selectively responding to a specific analyte in a biological fluid, and is configured so as to be carried by a user, an analyte measurer that measures a concentration of the specific analyte with a biosensor, and a motion measurer that measures a motion level of the housing. A living activity level calculator calculates a living activity level of the user based on the motion level measured by the motion measurer, a recorder records the living activity level calculated by the living activity level calculator, and a controller associates the concentration of the specific analyte measured by the analyte measurer with an event of living activity of the user, estimated based on the living activity level recorded in the recorder, and records them in the recorder.

[0009] Further techniques are described in EP 3 563 224 Al, WO 2023 / 215668 Al, WO 2023 / 080407 Al and US 9,955,914 B2.

[0010] US 2017 / 086779 Al describes an eating and drinking action detection apparatus that acquires vibration produced from inside of a body of a subject. Based on the power of the vibration over time it is determined whether the subject performed swallowing or mastication.

[0011] US 2015 / 080672 Al describes a wearable breathing sensor, such as a piezoelectric chest belt system, generates a breathing signal that is analyzed by a classifier to identify apnea patterns indicating that the subject has swallowed during breathing. These breathing signals are computer-analyzed to extract inferences regarding the subject's eating and drinking patterns and thereby provide useful data for monitoring food or beverage intake for remote health monitoring.

[0012] US 2021 / 113099 Al describes medical sensors and related methods for measuring a realtime personal metric. For example, the metric may be a clinical metric such as a swallowing parameter, a respiration parameter, an aspiration parameter, a coughing parameter, a sneezing parameter, a temperature, a heart rate, a sleep parameter, pulse oximetry, a snoring parameter, body movement, scratching parameter, bowel movement parameter, a neonate subject diagnostic parameter, a cerebral palsy diagnostic parameter, or any combination thereof. The sensor may for example comprise an accelerometer, preferably a high frequency, three-axis accelerometers, capable of detecting a wide range of mechanoacoustic signals.

[0013] CN 108175411 Al describes a detection device with a respiratory mode detection module for detecting the user's breathing pattern and a swallowing status detection module to detect the swallowing status of the user according to the user's breathing pattern.

[0014] Despite the advantages achieved by known methods and devices, several technical challenges remain. As the existing techniques require manual entries, the chances are high that some food intakes are not entered at all or maybe entered with a wrong timestamp, e.g. later. Thus, the food intake information may be incorrect or incomplete.

[0015] Problem to be solved It is therefore desirable to provide methods and devices which at least partially address above-identified technical challenges. Specifically, devices and computer-implemented methods for detecting a food intake of a user shall be provided which enable automatic detection of food intake events without manual interaction by a user.

[0016] Summary

[0017] This problem is addressed by a computer-implemented method for detecting a food intake of a user, an analytical system, computer programs and computer-readable storage mediums with the features of the independent claims. Advantageous embodiments which might be realized in an isolated fashion or in any arbitrary combinations are listed in the dependent claims as well as throughout the specification.

[0018] As used in the following, the terms “have”, “comprise” or “include” or any arbitrary grammatical variations thereof are used in a non-exclusive way. Thus, these terms may both refer to a situation in which, besides the feature introduced by these terms, no further features are present in the entity described in this context and to a situation in which one or more further features are present. As an example, the expressions “A has B”, “A comprises B” and “A includes B” may both refer to a situation in which, besides B, no other element is present in A (i.e. a situation in which A solely and exclusively consists of B) and to a situation in which, besides B, one or more further elements are present in entity A, such as element C, elements C and D or even further elements.

[0019] Further, it shall be noted that the terms “at least one”, “one or more” or similar expressions indicating that a feature or element may be present once or more than once typically will be used only once when introducing the respective feature or element. In the following, in most cases, when referring to the respective feature or element, the expressions “at least one” or “one or more” will not be repeated, non-withstanding the fact that the respective feature or element may be present once or more than once.

[0020] Further, as used in the following, the terms "preferably", "more preferably", "particularly", "more particularly", "specifically", "more specifically" or similar terms are used in conjunction with optional features, without restricting alternative possibilities. Thus, features introduced by these terms are optional features and are not intended to restrict the scope of the claims in any way. The invention may, as the skilled person will recognize, be performed by using alternative features. Similarly, features introduced by "in an embodiment of the invention" or similar expressions are intended to be optional features, without any restriction regarding alternative embodiments of the invention, without any restrictions regarding the scope of the invention and without any restriction regarding the possibility of combining the features introduced in such way with other optional or non-optional features of the invention.

[0021] In a first aspect of the present invention, a computer-implemented method for detecting a food intake of a user is disclosed.

[0022] The term “computer-implemented method” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a method involving at least one computer and / or at least one computing unit. The computer and / or computer unit may comprise at least one processor which is configured for performing at least one of the method steps of the methods according to the present invention. Specifically, each of the method steps may be performed by the computer and / or computer unit. The method may be performed completely automatically, specifically without user interaction.

[0023] The term “user” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a human being in a healthy condition or suffering from one or more diseases. The user may be a patient. As an example, the user or the patient may be a human being suffering from or suspected of suffering from a diabetes. However, additionally or alternatively, the invention may be applied to other types of users. The user may specifically be the patient himself or herself, specifically in homecare applications. The user may specifically be a person handling a wearable chest motion sensor, as described in more detail below.

[0024] The term “food intake” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to solid and / or liquid food intake, in particular a process of eating and / or drinking.

[0025] The term “detecting a food intake” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a quantitative and / or qualitative determination of food intake of a user. A result of the detection may be one or more of: a presence of the food intake, an absence of the food intake, an information on an amount of food intake, a time of a food intake such as start of food intake and / or end of food intake and / or duration of food intake. The detecting of a food intake may be performed automatically. The term "automatically" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process which is performed completely by means of at least one computer and / or computer network and / or machine, in particular without manual action and / or interaction with a user.

[0026] The method comprises the following steps, which may be performed in the given order. A different order, however, may also be feasible. Further, two or more of the method steps may be performed simultaneously. Thereby, the method steps may at least partly overlap in time. Further, the method steps may be performed once or repeatedly. Thus, one or more or even all of the method steps may be performed once or repeatedly. The method may comprise additional method steps, which are not listed herein.

[0027] The method comprises the following steps: a. retrieving motion data generated by a wearable chest motion sensor worn by the user; b. determining a swallowing motion pattern by evaluating the motion data; and c. generating a food intake event signal comprising at least information regarding a time of the swallowing motion pattern.

[0028] The present invention proposes an improved method for meal tracking using wearable chest motion sensor worn by the user, e.g. using a wearable chest patch. It was found that meal tracking can be performed by using motion data of a chest worn motion sensor, e.g. an accelerometer and / or a gyroscope, e.g. by detecting swallowing events. This can allow automatically generating a tracking record with a time stamp for the detected meal intake.

[0029] The term “motion sensor” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a device configured for detecting motion, in particular of at least one part of the body of the user. For example, the motion sensor may be configured for detecting the motion sensor's intrinsic motion or the motion of another device or object. The motion sensor may be or may comprise at least one of: an angular rate sensor; a gyroscope; an accelerometer; a microelectromechanical systems (MEMS) accelerometer; or an inertial measurement unit.

[0030] The term “accelerometer” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a sensor configured for determining acceleration, specifically along at least one motion direction. The accelerometer may specifically be configured for determining at least one acceleration of the motion sensor's intrinsic motion along at least one motion direction. The accelerometer may be configured for generating sensor data comprising the at least one acceleration, specifically the at least one acceleration along at least one motion direction. The acceleration determined by the accelerometer may be a static acceleration, such as gravity, or a dynamic acceleration, such as an acceleration caused by a movement or motion of the motion sensor. The accelerometer may be a capacitive accelerometer, a piezoelectric accelerometer and / or a microelectromechanical systems (MEMS) accelerometer.

[0031] The term “angular rate sensor” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a sensor configured for measuring angular rates.

[0032] The term “gyroscope” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a sensor configured for determining at least one angular velocity, specifically along at least one axis of rotation. The gyroscope may specifically be configured for determining at least one angular velocity of the motion sensor's intrinsic motion. The gyroscope may be configured for generating sensor data comprising the at least one angular velocity, specifically the at least one angular velocity along at least one axis of rotation. The gyroscope may be a microelectromechanical systems (MEMS) gyroscope.

[0033] The term “inertial measurement unit” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a sensor or a combination of sensors configured for determining spatial acceleration data and angular velocity. The inertial measurement unit may comprise a combination of at least one acceleration sensor, at least one gyroscope, and, optionally, at least one magnetometer. The inertial measurement unit may be configured for determining spatial acceleration data and angular velocity of the motion sensor's intrinsic motion, specifically in or along one or more independent spatial directions, preferably in or along all three independent spatial directions.

[0034] The term “wearable” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to suitability of the motions sensor to be body-worn by the user. The motion sensor may be itself attached to the body of the user or may be part of a wearable device. The term “wearable device” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a device that is configured to be body-worn by the user. The motion sensor may be fixedly connected to or mounted in the wearable device. A motion of the wearable device may be equal to a motion of the motion sensor. In other words, the motion sensor's intrinsic motion may be equal to the motion of the wearable device. The motion sensor and / or the wearable device may be configured for being in contact with the body of the user, in particular during an active wear time of the motion sensor and / or the wearable device.

[0035] The wearable chest motion sensor may comprise a patch. The patch may comprise an adhesive surface for attachment to the user’s skin. The motion sensor and / or the wearable device may be configured for being mounted on a skin site of a body of the user. The motion sensor and / or the wearable device may be configured for being mounted on a chest of the user. The motion sensor and / or the wearable device may comprise a surface, such as a flat or plane surface, configured for being placed on the user, e.g. on the skin of the user. The surface may be an adhesive surface. For example, the motion sensor and / or the wearable device may comprise an adhesive surface for attachment to the skin of the user. The motion sensor may be or may be a part of a wearable chest patch. For example, the adhesive surface may comprise a plaster or an adhesive strip. The plaster or the adhesive strip may comprise an adhesive material. Alternatively or in addition, the motion sensor and / or the wearable device may be attached to the body of the user by using a body strap, such as a chest strap. The method may comprise applying the wearable chest motion sensor onto the skin of the user and measuring the motion data by using the wearable chest motion sensor.

[0036] For example, the method may comprise positioning the wearable chest motion sensor on the skin of the user. The term “positioning” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process of attaching of a first object or element to another second object or element. Specifically, the positioning of the wearable chest motion sensor on the user may comprise attaching the wearable chest motion sensor to the user, in particular to the body of the user, e.g. onto a skin site of the user. The positioning may comprise moving the wearable chest motion sensor to the user and mounting the wearable chest motion sensor to the body of the user, e.g. onto a skin site of the user. The wearable chest motion sensor may be mounted to the body of the user e.g. by at least one adhesive surface and / or a body strap, such as a chest strap, holding the wearable device fixedly attached to the body of the user. The positioning may specifically comprise attaching the wearable chest motion sensor to a desired position on the user, preferably in a desired orientation of the wearable chest motion sensor.

[0037] The term “data” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to at least one discrete or continuous value that comprises information. Typically, data may comprise a plurality of said discrete or continuous values. The term “motion data” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to data generated by the motion sensor. The term “generate motion data” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process by which the motion sensor captures information about at least one environmental parameter and converts this information into at least one signal. Generating may refer to actively measuring the at least one physical parameter, preferable in a data acquisition process. For example, the motion data may comprise at least one sensor signal generated by the motion sensor, e.g. a raw sensor signal, a processed sensor signal and / or information derived from the sensor signal. The motion data may be or may comprise at least one of rate of change of velocity; angular velocity with respect to one or more of pitch axis, roll axis, or yaw axis; or orientation information; angular rates; at least one classification. The method may comprise pre-processing of the motion data. The pre-processing may comprise one or more of filtering, smoothing, determining a region of interest, performing at least one transformation, e.g. at least one Fourier transformation.

[0038] The motion data may comprise time stamps. The term “time stamp” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to information about the time point of generating the motion data. The time stamp may comprise information about a date and a time of day e.g. with a resolution of seconds. For example, each sensor signal of the motion sensor may have a corresponding time information indicating the time at which the motion sensor has generated the sensor signal. The time information of the sensor signals may be used as time stamps for the motion data. The time stamp of each if the sensor signals is a unique timestamp such that no two generated sensor signals have the identical timestamp. The term “retrieving” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the process of obtaining data from a data source. The data source may, however, very, in accordance with the specific application. Thus, in the context of the present invention, the retrieving of the motion data may take place by at least one of the following: performing at least one measurement with the motion sensor; downloading the motion data from at least one data source e.g. of the motion sensor, such as from at least one data storage device, from a web- or cloud-based data storage device; obtaining the motion data via at least one computer network, such as the Internet; obtaining the motion data via at least one wire-based and / or wireless interface. The retrieving may fully or partially take place automatically, such as by automatic download and / or may fully or partially take manually. Semiautomatic retrieving processes are also possible. For example, the retrieving may be initiated by a user action, e.g. turning on the motion sensor.

[0039] The motion data may be retrieved in real time. The term “real time” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to without a time offset at least within tolerances. For example, the motion data may be retrieved during the measurement with the motion sensor. For example, the motion data may be retrieved continuously or discontinuously, e.g. repeatably at defined time points or time ranges. For example, the retrieving of the motion data may be triggered by a start event, e.g. in case a sensor signal of the motion sensor exceeds at least one threshold value. The motion data may be retrieved discontinuously. This can allow saving energy. In a low frequency mode at least one trigger pattern may be monitored which may switch the system to a „meal intake mode“.

[0040] As outlined above, step b. comprises determining a swallowing motion pattern by evaluating the motion data.

[0041] The food intake may comprise swallowing. The term "swallowing" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process of transferring food from the mouth to the pharynx and into the esophagus, in particular while shutting the epiglottis. The food intake may comprise pure swallowing, e.g. in case of drinking or eating liquid food. In addition to swallowing, the food intake may comprise chewing, e.g. in case of eating solid food. The term "swallowing motion" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a spe- cial or customized meaning. The term specifically may refer, without limitation, to movement of the user’s body during the swallowing. The process of swallowing may comprise at least one movement of the user’s body which can be detected by the motion sensor. For example, the movement may comprise one or more of motion of the chest, e.g. relating to swallowing and / or chewing; motion of head muscles and / or neck muscles, e.g. in the region of the esophagus such as on or directly below the sternum.

[0042] The term "swallowing motion pattern" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to at least one feature indicative of swallowing. The motion data may comprise at least one sensor signal, preferably a plurality of sensor signals, and corresponding time stamp. The feature indicative of swallowing may be one or more of at least one sensor signal indicative of swallowing; at least one sequence of sensor signals indicative of swallowing; at least one change in sensor signal amplitude, e.g. exceeding at least one predefined limit. With respect to swallowing accelerometry reference is made to www.sciencedirect.com / science / article / pii / S1350453315001022.

[0043] The term "determining" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a process of generating at least one output, e.g. a representative result, in particular, by evaluating an input, such as the received motion data. The result of the determination may be the swallowing motion pattern. The term determining may refer to the computer assisted processing of data, particularly in order to determine the swallowing motion pattern. The swallowing motion pattern may be determined in such a manner that it is available or provided as data or at least one item of information on the swallowing motion pattern. The term “information” may indicate that the representative result is described by the data. The determining of the swallowing pattern may be performed by using a computer program running on a computer or a computer network.

[0044] The term "evaluating" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to performing at least one analysis of the received motion data, e.g. comprising applying at least one pattern identification algorithm to the motion data. The motion data may be used as input for at least one pattern identification algorithm. The pattern identification algorithm may be configured for determining the at least one feature indicative of swallowing from the motion data. The determining of the swallowing motion pattern may comprise at least one evaluation step, e.g. by using the pattern identification algorithm, selected from the group consisting of comparing the motion data to at least one threshold value; comparing of the motion data to at least one reference swallowing pattern. With respect to swallowing accelerometry reference is made to www.sciencedirect.com / science / article / pii / S1350453315001022. The reference swallowing pattern may be one or more of a theoretical swallowing pattern for humans or a group of humans, e.g. considering age, and gender; an experimentally determined swallowing pattern, e.g. determined by at least one study; a reference pattern of the user, e.g. predetermined and / or retrieved from at least one database.

[0045] The method may comprise distinguishing between solid food intake, e.g. eating, and liquid food intake, e.g. drinking. In particular, the swallowing motion patterns of swallowing with chewing and without chewing may be different such that such a distinction can be possible.

[0046] The method may comprise determining a duration and / or amount of the food intake, as will be described in more detail below.

[0047] As outlined above, step c. comprises a.generating a food intake event signal comprising at least information regarding a time of the swallowing motion pattern.

[0048] The term "generating a food intake event signal" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to issuing and / or triggering issuing a food intake event signal.

[0049] The food intake event may comprise at least one swallowing event. The term "swallowing event" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to occurrence of a swallowing feature within the motion data.

[0050] The term "food intake event" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the number of swallowing events associated with the food intake.

[0051] The term "food intake event signal" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limi- tation, to data comprising at least information about presence and time of the food intake event.

[0052] The term "time of the swallowing motion pattern " as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a start point and / or an end point of the swallowing motion of the food intake event.

[0053] The information about the start and / or end points may be used for one or more of: determining a duration of the food intake; determining a glucose concentration correlation; estimating a glucose concentration development of the user; determining a next insulin bolus; determining further actions for diabetes management. For example, the information about the duration of the food intake may be used for estimating a size of food which was taken.

[0054] The method may comprise determining a food intake start. For example, the method may comprise: d. retrieving motion data generated by the wearable chest motion sensor worn by the user; e. determining a first swallowing event by evaluating the motion data; f. generating a food intake start event signal comprising at least information regarding a time of the first swallowing event.

[0055] The first swallowing event may be the swallowing event first in time associated with a food intake event.

[0056] The method may comprise determining a food intake end. The method may comprise g. subsequently to the food intake start event signal, retrieving motion data generated by the wearable chest motion sensor worn by the user; h. determining a last swallowing event and generating a food intake last event signal comprising at least information regarding a time of the last swallowing event, wherein the last swallowing event defines the food intake end.

[0057] The last swallowing event may be the final swallowing event in time associated with a food intake event. After the last swallowing event no further swallowing events may be detected at least for a predefined time range, e.g. 30 s, 60 s or 120 s no swallowing event. In addition a standing up pattern and / or a walking pattern and / or another activity pattern may be used for detecting the time of food intake end. The method may comprise determining a food intake event. The food intake event may comprise counting the detected swallowing events within a time range from a first swallowing event to the last swallowing event. The method may comprise determining a food intake by counting the number of swallowing events of a food intake event and / or within a predefined time range and comparing the number to a predefined limit. In case the number of swallowing events and / or the number of swallowing events per time range exceeds or is equal to the limit, the swallowing events are classified to relate to a food intake. For example, at least two subsequent events may be used as minimum for food intake. This can distinguish from swallowing without food intake. Additionally or alternatively, the distance between two events may be used, e.g. not more than 10 s or more than 6 events per minute. Otherwise, in case the number of swallowing events is lower than the limit, the swallowing events may not be classified as food intake and may be disregarded. Thus, the number of swallowing events can be used as indicator for food intake events.

[0058] The method may comprise determining an indicator for a meal size and / or an indicator for meal quality by using a pre-defined relationship between the number of detected swallowing events within a time range from the first swallowing event to the last swallowing event and the meal size and / or meal quality. The method may comprise determining a meal size by counting the number of swallowing events of a food intake event. The number of swallowing events may be used as indicator for a meal size.

[0059] The determining of a swallowing motion pattern by evaluating the motion data may be performed by using at least one processing device. The processing device may be an element of the motion sensor and / or of the wearable device and / or a further device, e.g. a handheld device of the user, a remote processing device of a health-care provider, a partially cloud based processing device. The term “processing device”, also denoted as processor, as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary logic circuitry configured for performing basic operations of a computer or system, and / or, generally, to a device which is configured for performing calculations or logic operations. In particular, the processing device may be configured for processing basic instructions that drive the computer or system. As an example, the processing device may comprise at least one arithmetic logic unit (ALU), at least one floating-point unit (FPU), such as a math coprocessor or a numeric co-processor, a plurality of registers, specifically registers configured for supplying operands to the ALU and storing results of operations, and a memory, such as an LI and L2 cache memory. In particular, the processing device may be a multicore processor. Specifically, the processing device may be or may comprise a central processing unit (CPU). Additionally or alternatively, the processing device may be or may comprise a microprocessor, thus specifically the processor’s elements may be contained in one single integrated circuitry (IC) chip. Additionally or alternatively, the processing device may be or may comprise one or more application-specific integrated circuits (ASICs) and / or one or more field-programmable gate arrays (FPGAs) and / or one or more tensor processing unit (TPU) and / or one or more chip, such as a dedicated machine learning optimized chip, or the like. The processing device specifically may be configured, such as by software programming, for performing one or more evaluation and / or control operations.

[0060] The method may comprise generating a tracking record with a time stamp for the detected meal intake. The term "tracking record" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an entry of a dataset comprising information about the food intake, e.g. the food intake event signal, and an associated time stamp, e.g. the start and / or end point of the food intake.

[0061] The method may comprise storing the tracking record in at least one database and / or transmitting the tracking record to at least one database. The database may be one or more of a database of a handheld device of the user, a remote database of a health-care provider, a partially cloud based database; a database of an analyte sensor device; a database of a controller, e.g. of an analyte sensor device. For example, the tracking record may be stored as entry in a diabetes logbook.

[0062] The term "database" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an organized collection of data, generally stored and accessed electronically from a computer or computer system. The database may comprise or may be comprised by a data storage device. The database may comprise at least one data base management system, comprising a software running on a computer or computer system, the software allowing for interaction with one or more of a user, an application or the database itself, such as in order to capture and analyze the data contained in the database. The database management system may further encompass facilities to administer the database. The database, containing the data, may, thus, be comprised by a data base system which, besides the data, comprises one or more associated applications.

[0063] For example, the handheld device of the user may be a mobile device. The term “mobile device” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a mobile electronics device, more specifically to a mobile communication device, such as a cell phone or smartphone. Additionally or alternatively, the mobile device may be or may comprise a tablet computer or another type of portable computer.

[0064] The analyte sensor device may be an element of the wearable device. Additionally or alternatively, the analyte sensor device may be a further device. The analyte sensor device may be configured for generating analyte sensor data.

[0065] The term “analyte” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term preferably relates to an arbitrary element, component or compound which may be present in a body fluid and a presence and / or a quantity and / or a concentration of which may be of interest for a user, a patient or medical staff such as for a medical doctor. As will be understood by the skilled person, a "presence" of an analyte, for example, may be a presence of said analyte in an amount above a detection limit. For example, the analyte may be or may comprise an arbitrary chemical substance or chemical compound which may take part in a metabolism of the user or the patient, such as a metabolite. As an example, the analyte may be selected from the group consisting of glucose, ketones, glycerol, a hormone such as testosterone, cortisol, cholesterol, triglycerides, lactic acid, lactate or any analyte which can be measured electrochemically. Additionally or alternatively, however, other types of analytes may be used and / or any combination of analytes may be determined. However, more preferably, the analyte may be glucose.

[0066] The term “analyte sensor data” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term preferably may refer, without limitation, to data on an arbitrary analyte that may be evaluated for a more diagnostic and / or a therapeutic purpose. Analyte sensor data may comprise information on glucose, ketones, glycerol, a hormone such as testosterone, cortisol, cholesterol, triglycerides, lactic acid, lactate or any analyte which can be measured electrochemically.

[0067] The term “analyte sensor device” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term preferably may refer, without limitation, to an arbitrary element or article being configured for use in the field of medical technology, exemplarily in the field of medical analytics or medical diagnostics. The analyte sensor device may be configured for performing a medical function and / or for being used in a medical process, such as in one or more of a therapeutic process, a diagnostic process or another medical process. The analyte sensor device preferably may comprise an assembly of two or more components capable of interacting with each other, such as in order to perform one or more diagnostic and / or therapeutic purposes, such as in order to perform a medical analysis. For example, the two or more components may be capable of performing a detection of the analyte in the body fluid and / or of contributing to the detection of the analyte in the body fluid. The analyte sensor device generally may also be or may comprise at least one of a sensor assembly, a sensor system, a sensor kit or a sensor device. The analyte sensor device may be configured for being at least partially inserted into a body tissue of the user. The term “body tissue” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term preferably may refer, without limitation, to a cellular organizational level intermediate between cells and a complete origin. The body tissue may specifically be an ensemble of similar cells from the same origin that together carry out a specific function. Thereby, organs may then be formed by functional grouping together of multiple tissues. As an example for body tissue, interstitial tissue, i.e. connective tissue between cellular elements if a structure, may be named. The analyte sensor device may be configured for continuous analyte monitoring. The term “continuous analyte monitoring” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to the fact that the analyte sensor device or at least a part of the analyte sensor device may remain in the body tissue of the user for a predetermined period of time, such as for several hours, specifically for one or more days, more specifically for up to one week, even more specifically for up to two weeks or even more.

[0068] The analyte sensor device may comprise at least one analyte sensor configured for detecting quantitatively or qualitative at least one analyte. The term “analyte sensor” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a sensor which is capable of qualitatively or quantitatively detecting the presence and / or the concentration of the at least one analyte. The analyte sensor may be or may comprise at least one electrochemical sensor. The term “electrochemical sensor” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term preferably may refer, without limitation, to a sensor which is configured to conduct an electrochemical measurement in order to detect the at least one analyte contained in the bodily fluid. The term “electrochemical measurement” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term preferably may refer, without limitation, to a detection of an electrochemically detectable property of the analyte, such as an electrochemical detection reaction. Thus, for example, the electrochemical detection reaction may be detected by comparing one or more electrode potentials. The electrochemical sensor specifically may be adapted to and / or may be usable to generate at least one electrical sensor signal which directly or indirectly indicates the presence and / or the extent of the electrochemical detection reaction, such as at least one current and / or at least one voltage. The detection may be analytespecific. The measurement may be a qualitative and / or a quantitative measurement. Still, other embodiments are feasible. The analyte sensor may comprise at least two electrodes, e.g. at least one working electrode, at least one counter electrode and / or at least one reference electrode. The reference electrode may have a stable and well-known electrode potential. For potential embodiments of an analyte sensor, reference may be made to WO 2007 / 071562 Al and / or the prior art documents disclosed therein. Other embodiments, however, are feasible. Other embodiments may be possible, too. For example, the analyte sensor may be an optical analyte sensor.

[0069] As will be outlined in detail below, the warable chest motion sensor and the analyte sensor device may be part of an analytical system . The analytical system may further comprise one or more vital sign sensors such as at least one cardiac motion sensor and / or at least one heart rate variability sensor. The vital sign sensors may be an element of the wearable device. Additionally or alternatively, the vital sign sensors may be a further device.

[0070] The food intake event signal, e.g. the tracking record, may be transmitted to one or more of the analyte sensor device, the analyte sensor device via a controller, e.g. of the analyte sensor device, or the controller, e.g. of the analyte sensor device.

[0071] The term “controller” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary device or system configured for performing the named operations, preferably by using at least one data processing device and, more preferably, by using at least one processor and / or at least one application-specific integrated circuit. Thus, as an example, the at least one controller may comprise at least one data processing device having a software code stored thereon comprising a number of computer commands. The controller may provide one or more hardware elements for performing one or more of the named operations and / or may provide one or more processors with software running thereon for performing one or more of the named operations. The controller may comprise one or more programmable devices such as one or more computers, application-specific integrated circuits (ASICs), Digital Signal Processors (DSPs), or Field Programmable Gate Arrays (FPGAs) which are configured to perform a control function. The controller may comprise at least one computer. The computer can be an embedded computer e.g. micro controller or programmable logic devices such as FPGAs. Additionally or alternatively, however, the controller may also fully or partially be embodied by hardware.

[0072] The term “transmitting” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to sending data from a first device to at least one further device, preferably by using an established wireless connection. The term “wireless connection” as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a communication link between at least two devices in a manner that the at least two devices can exchange data without the use of physical wires or cables. A wireless connection may rely on electromagnetic radiation in order to establish the communication link. Exchanging data may comprise transmitting data from a device to a further device and / or a device receiving data from a further device. The wireless connection may be or may comprise at least one of a Wireless Fidelity (Wi-Fi) connection, a Bluetooth connection, a near field connection (NFC), a Zigbee connection, a Long Range Wide Area Network (LoRaWAN) connection or the like.

[0073] The processing device and / or the analyte sensor device and / or the controller may comprise a communication interface. The term "communication interface" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to a device forming a boundary configured for exchanging data, such as by transmitting data or receiving data. The communication interface may be configured for exchanging data. Therefore, the communication interface may provide means for exchanging data. In particular, the communication interface may be configured for providing a communication link, e.g. a Wireless Fidelity (Wi-Fi) connection, a Bluetooth connection, a near field connection (NFC), a Zigbee connection, a Long Range Wide Area Network (LoRaWAN) connection and / or the like.

[0074] The method may comprise comparing information of a user log entry relating to food intake and / or a food intake signal provided by the analyte sensor device with the food intake event. The method may comprise optimizing meal information depending on the comparison. The method may further comprise storing the optimized meal information in a database, e.g. one or more of a database of a handheld device of the user, a remote database of a health-care provider, a partially cloud based database; a database of an analyte sensor device, and / or the method may comprise replacing the meal information provided by the analyte sensor device or the user by the optimized meal information. The term "optimized meal information" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to meal information which is generated by considering the detected food intake of the user.

[0075] The method may comprise at least one diabetes management action considering the detected food intake. The diabetes management action may be selected from the group consisting of: estimating a bolus; predicting of future analyte concentration values; generating and / or issuing at least one user advice.

[0076] In a further aspect, an analytical system is disclosed. The analytical system comprises

[0077] - at least one wearable chest motion sensor,

[0078] - at least one analyte sensor device and

[0079] - at least one controller.

[0080] The analytical system is configured for performing a method according to the present invention, e.g. as described in one or more embodiments above or in more details below. With respect to definitions and embodiments, reference is made to the description of the method above.

[0081] The term "system" as used herein is a broad term and is to be given its ordinary and customary meaning to a person of ordinary skill in the art and is not to be limited to a special or customized meaning. The term specifically may refer, without limitation, to an arbitrary set of interacting or interdependent components parts forming a whole. Specifically, the components may interact with each other in order to fulfill at least one common function. The at least two components may be handled independently or may be coupled or connectable.

[0082] The controller may be a controller of the analyte sensor device and / or a further controller of the analytical system.

[0083] Further disclosed and proposed herein is a computer program including computerexecutable instructions for performing the method according to the present invention in one or more of the embodiments enclosed herein when the instructions are executed on a computer or computer network. Specifically, the computer program may be stored on a computer-readable data carrier and / or on a computer-readable storage medium. As used herein, the terms “computer-readable data carrier” and “computer-readable storage medium” specifically may refer to non-transitory data storage means, such as a hardware storage medium having stored thereon computer-executable instructions. The computer- readable data carrier or storage medium specifically may be or may comprise a storage medium such as a random-access memory (RAM) and / or a read-only memory (ROM).

[0084] Thus, specifically, one, more than one or even all of method steps a) to c), and optionally steps d) to h), as indicated above may be performed by using a computer or a computer network, preferably by using a computer program.

[0085] Further disclosed and proposed herein is a computer program product having program code means, in order to perform the method according to the present invention in one or more of the embodiments enclosed herein when the program is executed on a computer or computer network. Specifically, the program code means may be stored on a computer-readable data carrier and / or on a computer-readable storage medium.

[0086] Further disclosed and proposed herein is a data carrier having a data structure stored thereon, which, after loading into a computer or computer network, such as into a working memory or main memory of the computer or computer network, may execute the method according to one or more of the embodiments disclosed herein.

[0087] Further disclosed and proposed herein is a non-transient computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform the method according to the present invention.

[0088] Further disclosed and proposed herein is a computer program product with program code means stored on a machine-readable carrier, in order to perform the method according to one or more of the embodiments disclosed herein, when the program is executed on a computer or computer network. As used herein, a computer program product refers to the program as a tradable product. The product may generally exist in an arbitrary format, such as in a paper format, or on a computer-readable data carrier and / or on a computer-readable storage medium. Specifically, the computer program product may be distributed over a data network.

[0089] Finally, disclosed and proposed herein is a modulated data signal which contains instructions readable by a computer system or computer network, for performing the method according to one or more of the embodiments disclosed herein. Referring to the computer-implemented aspects of the invention, one or more of the method steps or even all of the method steps of the method according to one or more of the embodiments disclosed herein may be performed by using a computer or computer network. Thus, generally, any of the method steps including provision and / or manipulation of data may be performed by using a computer or computer network. Generally, these method steps may include any of the method steps, typically except for method steps requiring manual work, such as providing the samples and / or certain aspects of performing the actual measurements.

[0090] Specifically, further disclosed herein are: a computer or computer network comprising at least one processor, wherein the processor is adapted to perform the method according to one of the embodiments described in this description, a computer loadable data structure that is adapted to perform the method according to one of the embodiments described in this description while the data structure is being executed on a computer, a computer program, wherein the computer program is adapted to perform the method according to one of the embodiments described in this description while the program is being executed on a computer, a computer program comprising program means for performing the method according to one of the embodiments described in this description while the computer program is being executed on a computer or on a computer network, a computer program comprising program means according to the preceding embodiment, wherein the program means are stored on a storage medium readable to a computer, a storage medium, wherein a data structure is stored on the storage medium and wherein the data structure is adapted to perform the method according to one of the embodiments described in this description after having been loaded into a main and / or working storage of a computer or of a computer network, and a computer program product having program code means, wherein the program code means can be stored or are stored on a storage medium, for performing the method according to one of the embodiments described in this description, if the program code means are executed on a computer or on a computer network.

[0091] The present invention may provide a large number of advantages over known methods and devices of similar kind. Specifically, a chest patch with at least one appropriate motion sensors may be used for detecting swallowing and food intake. This can allow providing accurate timestamps for meal intake events. Summarizing and without excluding further possible embodiments, the following embodiments may be envisaged:

[0092] Embodiment 1. A computer-implemented method for detecting a food intake of a user, the method comprising: a. retrieving motion data generated by a wearable chest motion sensor worn by the user; b. determining a swallowing motion pattern by evaluating the motion data; and c. generating a food intake event signal comprising at least information regarding a time of the swallowing motion pattern.

[0093] Embodiment 2. The method according to the preceding embodiment, wherein the method comprises generating a tracking record with a time stamp for the detected food intake.

[0094] Embodiment s. The method according to the preceding embodiment, wherein the method comprises storing the tracking record in at least one database and / or transmitting the tracking record to at least one database.

[0095] Embodiment 4. The method according to the preceding embodiment, wherein the database is one or more of: a database of a handheld device of the user, a remote database of a health-care provider, a partially cloud based database; a database of an analyte sensor device.

[0096] Embodiment 5. The method according to any one of the preceding embodiments, wherein the food intake event signal is transmitted to one or more of an analyte sensor device, the analyte sensor device via a controller of the analyte sensor device, or the controller of the analyte sensor device.

[0097] Embodiment 6. The method according to any one of the preceding embodiments, wherein the motion sensor is or comprises at least one of: an angular rate sensor; a gyroscope; an accelerometer; or an inertial measurement unit.

[0098] Embodiment 7. The method according to the any one of the preceding embodiments, wherein the motion data is or comprises at least one of: rate of change of velocity; angular velocity with respect to one or more of pitch axis, roll axis, or yaw axis; or orientation information; angular rates; at least one classification. Embodiment 8. The method according to the any one of the preceding embodiments, wherein the method comprises pre-processing of the motion data, wherein the preprocessing comprises one or more of: filtering, smoothing, determining a region of interest, performing at least one transformation.

[0099] Embodiment 9. The method according to the any one of the preceding embodiments, wherein the motion data is retrieved in real time.

[0100] Embodiment 10. The method according to the any one of the preceding embodiments, wherein the motion data comprises time stamps.

[0101] Embodiment 11. The method according to the any one of the preceding embodiments, wherein the wearable chest motion sensor comprises a patch, wherein the patch comprises an adhesive surface for attachment to the user’s skin.

[0102] Embodiment 12. The method according to the any one of the preceding embodiments, wherein the method comprises applying the wearable chest motion sensor onto the skin of the user and measuring the motion data by using the wearable chest motion sensor.

[0103] Embodiment 13. The method according to the any one of the preceding embodiments, wherein the determining of the swallowing motion pattern comprises at least one evaluation step selected from the group consisting of: comparing the motion data to at least one threshold value; comparing of the motion data to at least one reference swallowing pattern.

[0104] Embodiment 14. The method according to any one of the preceding embodiments, wherein the determining of a swallowing motion pattern by evaluating the motion data is performed by using at least one processing device.

[0105] Embodiment 15. The method according to the any one of the preceding embodiments, wherein the method comprises determining a food intake start, the method comprising: d. retrieving motion data generated by the wearable chest motion sensor worn by the user; e. determining a first swallowing event by evaluating the motion data; f. generating a food intake start event signal comprising at least information regarding a time of the first swallowing event. Embodiment 16. The method according to the preceding embodiment, wherein the method comprises determining a food intake end, the method comprising g. subsequently to the food intake start event signal, retrieving motion data generated by the wearable chest motion sensor worn by the user; h. determining a last swallowing event and generating a food intake last event signal comprising at least information regarding a time of the last swallowing event, wherein the last swallowing event defines the food intake end.

[0106] Embodiment 17. The method according to the preceding embodiment, wherein the method comprises determining a food intake event, wherein the food intake event comprises the detected swallowing events within a time range from the first swallowing event to the last swallowing event.

[0107] Embodiment 18. The method according to any one of the two preceding embodiments, wherein the method comprises determining an indicator for meal size and / or an indicator for meal quality by using a pre-defined relationship between the number of detected swallowing events within a time range from the first swallowing event to the last swallowing event and the meal size and / or meal quality.

[0108] Embodiment 19. The method according to any one of the two preceding embodiments, wherein the method comprises comparing information of a user log entry relating to food intake and / or a food intake signal provided by an analyte sensor device with the food intake event, wherein the method comprises optimizing meal information depending on the comparison.

[0109] Embodiment 20. The method according to any one of the preceding embodiments, wherein the method comprises at least one diabetes management action considering the detected food intake, wherein the diabetes management action is selected from the group consisting of: estimating a bolus; predicting of future analyte concentration values; generating and / or issuing at least one user advice.

[0110] Embodiment 21. An analytical system comprising

[0111] - at least one wearable chest motion sensor,

[0112] - at least one analyte sensor device and

[0113] - at least one controller, wherein the analytical system is configured for performing a method according to any one of the preceding embodiments. Embodiment 22. A computer program comprising instructions which, when the program is executed by the analytical system according to the preceding embodiment, cause the analytical system to perform the method according to any one of the preceding embodiments referring to a method.

[0114] Embodiment 23. A computer-readable storage medium comprising instructions which, when the instructions are executed by the analytical system according to embodiment 21, cause the analytical system to perform the method according to any one of the preceding embodiments referring to a method.

[0115] Embodiment 24. A non-transient computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform the method according to any one of the preceding embodiments referring to a method.

[0116] Short description of the Figures

[0117] Further optional features and embodiments will be disclosed in more detail in the subsequent description of embodiments, preferably in conjunction with the dependent claims. Therein, the respective optional features may be realized in an isolated fashion as well as in any arbitrary feasible combination, as the skilled person will realize. The scope of the invention is not restricted by the preferred embodiments. The embodiments are schematically depicted in the Figures. Therein, identical reference numbers in these Figures refer to identical or functionally comparable elements.

[0118] In the Figures:

[0119] Figures 1 A and IB show an embodiment of wearable chest motion sensor worn by a user and an overview of an embodiment of an analytical system; and

[0120] Figure 2 shows a schematic stateflow of an embodiment of a computer-implemented method for detecting a food intake of a user using the analytical system.

[0121] Detailed description of the embodiments

[0122] Figure 1 A shows an embodiment of wearable chest motion sensor 110 worn by a user 112. The user 112 may be a human being suffering from or suspected of suffering from a diabe- tes. The user 112 may be the patient himself or herself, specifically in homecare applications.

[0123] The wearable chest motion sensor 110 may be configured for detecting motion, in particular of at least one part of the body of the user 112. The wearable chest motion sensor 110 may be configured for detecting the motion sensor's intrinsic motion or the motion of another device or object. The wearable chest motion sensor 110 may be or may comprise at least one of: an angular rate sensor; a gyroscope; an accelerometer; a microelectromechanical systems (MEMS) accelerometer; or an inertial measurement unit.

[0124] The wearable chest motion sensor 110 may be itself attached to the body of the user 112 or may be part of a wearable device. The wearable chest motion sensor 110 may comprise a patch 114. The patch 114 may comprise an adhesive surface for attachment to the user’s skin. The wearable chest motion sensor 110 may be configured for being mounted on a skin site of a body of the user 112. The wearable chest motion sensor 110 may be configured for being mounted on a chest of the user 112. The wearable chest motion sensor 110 may comprise a surface, such as a flat or plane surface, configured for being placed on the user 112, e.g. on the skin of the user 112. The surface may be an adhesive surface. For example, the wearable chest motion sensor 110 may comprise an adhesive surface for attachment to the skin of the user 112. The wearable chest motion sensor 110 may be or may be a part of a wearable chest patch. For example, the adhesive surface may comprise a plaster or an adhesive strip. The plaster or the adhesive strip may comprise an adhesive material. Alternatively or in addition, the wearable chest motion sensor 110 may be attached to the body of the user 112 by using a body strap, such as a chest strap.

[0125] Figure IB shows a very schematic view of an exemplary embodiment of an analytical system 116 according to the present invention. The analytical system 116 comprises the wearable chest motion sensor 110, at least one analyte sensor device 118 and at least one controller 120. For example, the analyte sensor device 118 may be configured for continuous glucose monitoring. However, other embodiments are possible. The arrows shown in Figure IB show embodiments of communication paths within the analytical system 116. For example, information from the wearable chest motion sensor 110, e.g. a processing device of the wearable chest motion sensor 110, may be transmitted directly to the analyte sensor device 118, may be transmitted via the controller 120 to the analyte sensor device 118 or may be transmitted only to the controller 120.

[0126] Figure 2 shows a schematic stateflow of an embodiment of a computer-implemented method for detecting a food intake of a user 112 according to the present invention using the analytical system 116. The food intake may comprise solid and / or liquid food intake, in particular a process of eating and / or drinking. The detection of the food intake may comprise a quantitative and / or qualitative determination of food intake of a user. A result of the detection may be one or more of: a presence of the food intake, an absence of the food intake, an information on an amount of food intake, a time of a food intake such as start of food intake and / or end of food intake and / or duration of food in-take. The detecting of a food intake may be performed automatically, in particular without manual action and / or interaction with a user.

[0127] As shown in Figure 2, the method comprises the following steps a. (122) retrieving motion data generated by a wearable chest motion sensor worn by the user; b. (124) determining a swallowing motion pattern by evaluating the motion data; and c. (126) generating a food intake event signal comprising at least information regarding a time of the swallowing motion pattern.

[0128] After start of the method, indicated by the solid point, step a. may be performed. In this embodiment, the retrieving 122 comprises sensor data acquisition by performing at least one measurement using the wearable chest motion sensor 110, thereby generating motion data.

[0129] For example, the motion data may comprise at least one sensor signal generated by the motion sensor 110, e.g. a raw sensor signal, a processed sensor signal and / or information derived from the sensor signal. The motion data may be or may comprise at least one of: rate of change of velocity; angular velocity with respect to one or more of pitch axis, roll axis, or yaw axis; or orientation information; angular rates; at least one classification.

[0130] The motion data may comprise time stamps. The time stamp may comprise information about a date and a time of day e.g. with a resolution of seconds. For example, each sensor signal of the motion sensor 110 may have a corresponding time information indicating the time at which the motion sensor has generated the sensor signal. The time information of the sensor signals may be used as time stamps for the motion data. The time stamp of each if the sensor signals is a unique timestamp such that no two generated sensor signals have the identical timestamp.

[0131] The motion data may be retrieved in real time. For example, the motion data may be retrieved during the measurement with the motion sensor 110. For example, the motion data may be retrieved continuously or discontinuously, e.g. repeatably at defined time points or time ranges. For example, the retrieving of the motion data may be triggered by a start event, e.g. in case a sensor signal of the motion sensor 110 exceeds at least one threshold value. The motion data may be retrieved discontinuously. This can allow saving energy. In a low frequency mode at least one trigger pattern may be monitored which may switch the system to a „meal intake mode“.

[0132] The method may comprise pre-processing 128 of the motion data. The pre-processing may comprise one or more of: filtering, smoothing, determining a region of interest, performing at least one transformation, e.g. at least one Fourier transformation.

[0133] The swallowing motion pattern may comprise at least one feature indicative of swallowing. The motion data may comprise at least one sensor signal, preferably a plurality of sensor signals, and corresponding time stamp. The feature indicative of swallowing may be one or more of: at least one sensor signal indicative of swallowing; at least one sequence of sensor signals indicative of swallowing; at least one change in sensor signal amplitude, e.g. exceeding at least one predefined limit. With respect to swallowing accelerometry reference is made to www.sciencedirect.com / science / article / pii / S1350453315001022.

[0134] The method in step b. 124 comprises evaluating the motion data. For example, the evaluation may comprise performing at least one analysis of the received motion data, e.g. comprising applying at least one pattern identification algorithm to the motion data. The motion data may be used as input for at least one pattern identification algorithm. The pattern identification algorithm may be configured for determining the at least one feature indicative of swallowing from the motion data. The determining of the swallowing motion pattern may comprises at least one evaluation step, e.g. by using the pattern identification algorithm, selected from the group consisting of: comparing the motion data to at least one threshold value; comparing of the motion data to at least one reference swallowing pattern. With respect to swallowing accelerometry reference is made to www.sciencedirect.com / science / article / pii / S1350453315001022. The reference swallowing pattern may be one or more of: a theoretical swallowing pattern for humans or a group of humans, e.g. considering age, and gender; an experimentally determined swallowing pattern, e.g. determined by at least one study; a reference pattern of the user, e.g. predetermined and / or retrieved from at least one database.

[0135] In case a swallowing pattern is detected, indicated with “Yes”, a food intake event signal may be generated 126. The food intake event may comprise at least one swallowing event. The swallowing event may relate to occurrence of a swallowing feature within the motion data. The food intake event may refer to the number of swallowing events associated with the food intake. The food intake event signal may comprise data comprising at least information about presence and time of the food intake event. The time of the swallowing motion pattern may comprise a start point and / or an end point of the swallowing motion of the food intake event. The method may comprise determining a food intake start 130. After retrieving 122 motion data generated by the wearable chest motion sensor worn 110 by the user 112, a first swallowing event may be determined by evaluating the motion data. The first swallowing event may be the swallowing event first in time associated with a food intake event. The method may comprise generating a food intake start event signal comprising at least information regarding a time of the first swallowing event.

[0136] The method may comprise determining a food intake end 132. The method may comprise, subsequently to the food intake start event signal, retrieving 122 motion data generated by the wearable chest motion sensor 110 worn by the user 112, determining a last swallowing event and generating a food intake last event signal comprising at least information regarding a time of the last swallowing event. The last swallowing event defines the food intake end.

[0137] The last swallowing event may be the final swallowing event in time associated with a food intake event. After the last swallowing event no further swallowing events may be detected at least for a predefined time range, e.g. 30 s, 60 s or 120 s no swallowing event. In addition a standing up pattern and / or a walking pattern and / or another activity pattern may be used for detecting the time of food intake end.

[0138] The method may comprise counting 134 swallowing events within a time range from a first swallowing event to the last swallowing event. The method may comprise determining a food intake event 136. The method may comprise determining a food intake by counting the number of swallowing events of a food intake event and / or within a predefined time range and comparing the number to a predefined limit. In case the number of swallowing events and / or the number of swallowing events per time range exceeds or is equal to the limit, the swallowing events are classified to relate to a food intake. For example, at least two subsequent events may be used as minimum for food intake. This can distinguish from swallowing without food intake. Additionally or alternatively, the distance between two events may be used, e.g. not more than 10 s or more than 6 events per minute. Otherwise, in case the number of swallowing events is lower than the limit, the swallowing events may not be classified as food intake and may be disregarded. Thus, the number of swallowing events can be used as indicator for food intake events.

[0139] The method may comprise determining an indicator for a meal size 138 and / or an indicator for meal quality 140 by using a pre-defined relationship between the number of detected swallowing events within a time range from the first swallowing event to the last swallowing event and the meal size and / or meal quality. The method may comprise determining a meal size 138 by counting the number of swallowing events of a food intake event. The number of swallowing events may be used as indicator for a meal size.

[0140] The method steps a. to c., and optionally preprocessing of data, data analysis and evaluation, may be performed by using at least one processing device 142. The processing device 142 may be an element of the motion sensor 110 and / or a further device, e.g. a handheld device of the user, a remote processing device of a health-care provider, a partially cloud based processing device.

[0141] The method may comprise generating a tracking record with a time stamp for the detected meal intake. The tracking record may be or may comprise an entry of a dataset comprising information about the food intake, e.g. the food intake event signal, and an associated time stamp, e.g. the start and / or end point of the food intake. The method may comprise storing 144 the tracking record in at least one database and / or transmitting the tracking record to at least one database. The database may be one or more of: a database of a handheld device of the user, a remote database of a health-care provider, a partially cloud based database; a database of an analyte sensor device; a database of a controller of an analyte sensor device. For example, the tracking record may be stored as entry in a diabetes logbook.

[0142] The food intake event signal, e.g. the tracking record, may be transmitted 146 to one or more of the analyte sensor device 118, the analyte sensor device 118 via the controller 120, e.g. of the analyte sensor device 118, or a controller, e.g. the controller of the analyte sensor device 118.

[0143] The controller 120 and / or the analyte sensor device 118 may additionally provide a user log entry 148 and / or a meal signal 150 generated by the analyte sensor device 118. The user log entry 148 may be provided by the user 110 e.g. via a user interface, e.g. of a mobile device of the user 112. A processing device of the controller 120 and / or the analyte sensor device 118 or of a further device, e.g. the mobile device of the user 112, may determine meal information 152 by one or more of the user log entry 148 and / or the meal signal 150.

[0144] The method may further comprise comparing the meal information 154. If the food intake event signal, e.g. the tracking record, indicates a meal that is not indicated manually by the user, the method may comprise checking for the meal signal 150 generated by the analyte sensor device 118 and entering the meal event into a list, e.g. of a database. If the food intake event signal, e.g. the tracking record, indicates a meal that is not indicated manually by the user, the method may comprise, e.g. as default, entering the tracking record and the meal signal 150 into the list. The method may further comprise optimizing 156 meal entries by addition at least one measure of meal size and / or duration of meal. The method may comprise at least one diabetes management action 158 considering the detected food intake. The diabetes management action may be selected from the group consisting of: estimating a bolus; predicting of future analyte concentration values; generating and / or issuing at least one user advice.

[0145] List of reference numbers wearable chest motion sensor user patch analytical system analyte sensor device controller retrieving determining a swallowing motion pattern generating a food intake event signal preprocessing determining a food intake start determining a food intake end counting determining a food intake event indicator for a meal size indicator for a meal quality processing device storing transmitting user log entry meal signal determine meal information comparing the meal information optimizing diabetes management action

Claims

P39421-EP- 33 -July 31, 2025Claims1. A computer-implemented method for detecting a food intake of a user (112), the method comprising: a. (122) retrieving motion data generated by a wearable chest motion sensor (110) worn by the user (112); b. (124) determining a swallowing motion pattern by evaluating the motion data; and c. (126) generating a food intake event signal comprising at least information regarding a time of the swallowing motion pattern, d. wherein the method comprises determining an indicator for meal size (138) and / or an indicator for meal quality (140) by using a pre-defined relationship between the number of detected swallowing events within a time range from the first swallowing event to the last swallowing event and the meal size and / or meal quality.

2. The method according to the preceding claim, wherein the method comprises generating a tracking record with a time stamp for the detected food intake.

3. The method according to any one of the preceding claims, wherein the food intake event signal is transmitted (146) to one or more of an analyte sensor device (118), the analyte sensor device (118) via a controller (120) of the analyte sensor device (118), or the controller (120) of the analyte sensor device.

4. The method according to any one of the preceding claims, wherein the wearable chest motion sensor (110) is or comprises at least one of: an angular rate sensor; a gyroscope; an accelerometer; or an inertial measurement unit.

5. The method according to the any one of the preceding claims, wherein the motion data is or comprises at least one of: rate of change of velocity; angular velocity with respect to one or more of pitch axis, roll axis, or yaw axis; or orientation information; angular rates; at least one classification.P39421-EP- 34 -6. The method according to the any one of the preceding claims, wherein the motion data comprises time stamps.

7. The method according to the any one of the preceding claims, wherein the wearable chest motion sensor (110) comprises a patch, wherein the patch comprises an adhesive surface for attachment to the user’s skin.

8. The method according to the any one of the preceding claims, wherein the determining of the swallowing motion pattern (124) comprises at least one evaluation step selected from the group consisting of: comparing the motion data to at least one threshold value; comparing of the motion data to at least one reference swallowing pattern.

9. The method according to the any one of the preceding claims, wherein the method comprises determining a food intake start, the method comprising: e. retrieving motion data generated by the wearable chest motion sensor (110) worn by the user (112); f. determining a first swallowing event by evaluating the motion data; g. generating a food intake start event signal comprising at least information regarding a time of the first swallowing event.

10. The method according to the preceding claim, wherein the method comprises determining a food intake end, the method comprising h. subsequently to the food intake start event signal, retrieving motion data generated by the wearable chest motion sensor (110)worn by the user (112); i. determining a last swallowing event and generating a food intake last event signal comprising at least information regarding a time of the last swallowing event, wherein the last swallowing event defines the food intake end.

11. The method according to the preceding claim, wherein the method comprises determining a food intake event (136), wherein the food intake event comprises the detected swallowing events within a time range from the first swallowing event to the last swallowing event.

12. An analytical system (116) comprisingP39421-EP- 35 -- at least one wearable chest motion sensor (110),- at least one analyte sensor device (118) and- at least one controller (120), wherein the analytical system (116) is configured for performing a method according to any one of the preceding claims.

13. A computer program comprising instructions which, when the program is executed by the analytical system (116) according to the preceding claim, cause the analytical system (116) to perform the method according to any one of the preceding claims referring to a method.

14. A computer-readable storage medium comprising instructions which, when the instructions are executed by the analytical system (116) according to claim 13, cause the analytical system (116) to perform the method according to any one of the preceding claims referring to a method.

15. A non-transient computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform the method according to any one of the preceding claims referring to a method.

Images