WO2019122315A1 - Inhaler training system and method - Google Patents

Inhaler training system and method Download PDF

Info

Publication number
WO2019122315A1
WO2019122315A1 PCT/EP2018/086541 EP2018086541W WO2019122315A1 WO 2019122315 A1 WO2019122315 A1 WO 2019122315A1 EP 2018086541 W EP2018086541 W EP 2018086541W WO 2019122315 A1 WO2019122315 A1 WO 2019122315A1
Authority
WO
WIPO (PCT)
Prior art keywords
patient
inhaler
computer
deviation
video signals
Prior art date
Application number
PCT/EP2018/086541
Other languages
French (fr)
Inventor
Sabine Häussermann
Alexandros SIVRIS
Jonas Benedikt NATZER
Original Assignee
Visionhealth Gmbh
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Visionhealth Gmbh filed Critical Visionhealth Gmbh
Priority to KR1020207021283A priority Critical patent/KR20200103061A/en
Priority to CA3086773A priority patent/CA3086773A1/en
Priority to SG11202005467WA priority patent/SG11202005467WA/en
Priority to EP18833233.2A priority patent/EP3729452B1/en
Priority to PL18833233.2T priority patent/PL3729452T3/en
Priority to AU2018386559A priority patent/AU2018386559A1/en
Priority to CN201880083273.3A priority patent/CN111886654A/en
Priority to US16/955,802 priority patent/US11664104B2/en
Priority to JP2020554930A priority patent/JP2021508577A/en
Publication of WO2019122315A1 publication Critical patent/WO2019122315A1/en
Priority to US18/302,015 priority patent/US20230253086A1/en

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G16H20/13—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered from dispensers
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/63—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for local operation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M15/00—Inhalators
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/251—Fusion techniques of input or preprocessed data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/215—Motion-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/40—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2209/00—Ancillary equipment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30061—Lung

Definitions

  • the release of the pharmaceuticals needs to be aligned with the start of inhalation or the inhalation with dry powder inhalers needs to be swift and forceful.
  • Some of the devices have to be held upright or in another defined angle in order to release the full amount of drug.
  • inhaled therapy is common according to the literature, but can be avoided through proper and repeated education and training of the patient.
  • training approaches comprise the provision of films and other illustrating manuals to the patient as well as additional assistive equipment and devices which measure the outcome during the use of an inhaler.
  • the devices constitute specific constructions for example with sensors coupled to a patient and related computer processed feedback mechanism.
  • a self-learning system giving guidance to inhaler systems using a portable computer device and a camera device.
  • the system comprises guidance of multiple stages of real-time learning, for example simultaneous viewing of the instructional video and the patient’s real-time video.
  • a training method is described which can train a patient to use a predetermined inhalation system.
  • the system is specifically adapted per patient and inhaler. A universally applicable system would be more efficient.
  • the invention relates to a computer-implemented method for providing feedback to a patient using an inhaler of a specific type for inhaling a therapeutic aerosol according to instructions for use provided to the patient for, or along with, the inhaler.
  • the method comprises the steps of (a) obtaining a sequence of digital audio signals and a sequence of digital video signals emitted from the patient while using the inhaler; (b) recognising the type of the inhaler by processing the video signals; (c) recognising whether the patient has deviated from the instructions by processing the audio and video signals; (d) if a deviation was recognised in step (c), recognising the type of the deviation; and (e) presenting to the patient one or more feedback messages indicating (i) whether a deviation was recognised; (ii) if a deviation was recognised, the type of deviation; and optionally (iii) an inhalation manoeuvre without the deviation.
  • the invention provides a data processing system which comprises a processor adapted to carry out the method as described herein.
  • the invention provides a computer programme comprising instructions which, when the programme is executed by a computer, cause the computer to carry out the steps of the method described herein.
  • the invention provides a computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the method of the invention.
  • Fig. 1 represents a diagram illustrating the steps of the method of the invention according to a first embodiment.
  • Fig. 2 represents a diagram illustrating the steps of the method of the invention according to a further optional embodiment.
  • the invention provides a computer-implemented method for providing feedback to a patient using an inhaler of a specific type for inhaling a therapeutic aerosol according to instructions for use provided to the patient along with the inhaler as defined in claim 1.
  • the method comprises the steps of:
  • step (d) if a deviation was recognised in step (c), recognising the type of the deviation
  • steps b) and c) are performed by analysing the video and audio signals using an artificial neural network trained to identify an inhaler type and to identify deviations, or by a method to detect a regular motion;
  • steps (a) to (e) are performed by a portable feedback device for handheld use comprising
  • steps b) and c) comprise performing an analysis of the video and audio signals using an artificial neural network trained to identify an inhaler type and to identify deviations, and step c) also comprises the use of a method to detect a regular motion.
  • an inhaler is an inhalation device capable of emitting a therapeutic aerosol such as to enable a user or patient to inhale the aerosol.
  • An aerosol is a dispersion of a solid, semisolid or liquid phase in a continuous gaseous phase, thus including e. g. powder aerosols - pharmaceutically known as powders for inhalation - and nebulised aerosols.
  • Inhalation devices for delivering powder aerosols are commonly described as powder inhalers. Aerosolised liquids are administered by means of various inhalation devices including nebulisers, pressurised metered-dose inhalers, and soft mist inhalers.
  • the method of the invention provides feedback to a patient using a powder inhaler, a nebuliser, a metered-dose inhaler or a soft mist inhaler.
  • a major advantage of the method according to the invention is the possibility to perform the method on a handheld device.
  • a suitable handheld device may be a smartphone.
  • the method in general can be performed on any processor, even on a relatively slow processor such as smartphones or a raspberry pie.
  • the present method can be performed in real time and does not require access to a server with much computational power, i.e. the method can be performed offline.
  • the inhaler type refers to the specific inhaler model or model family.
  • a model family means those variants of a model which are used by a patient in essentially the same manner, in particular with respect to the breathing manoeuvre.
  • a specific type of nebuliser is the PARI eFlow rapid nebuliser system, which is an electronic nebuliser incorporating a vibrating mesh technology
  • an example of a specific type of powder inhaler is the ADVAIR DISKUS® sold by GSK
  • an example of a specific type of soft mist inhaler is the SPIRIVA® RESPIMAT® sold by Boehringer Ingelheim
  • an example of a specific type of metered-dose inhaler is VENTOLIN® HFA sold by GSK.
  • Each inhaler is provided to a patient together with instructions for use, which are typically printed on a patient leaflet, but which may also be provided to the patient through the internet or by oral and/or visual information received from a health care provider such as a physician, pharmacist or nurse.
  • a health care provider such as a physician, pharmacist or nurse.
  • the patient using the inhaler is a human subject who is in need of, or would benefit from, the therapeutic aerosol administered through the inhaler.
  • the use may be for any medical purpose, including the prevention or treatment of any disease, condition or symptom for which the aerosol is potentially beneficial.
  • An advantage of the method of the invention is that the method identifies the inhaler type. Methods of the prior art, e.g as described in US 2013/0063579 A1 may be suitable to train a patient but require to be adapted to a specific inhaler beforehand.
  • the inhaler may be identified using a pre-trained artificial neural network. As such, the method may be performed on a handheld device with limited computing power, e.g. a smartphone.
  • the method of the invention is computer-implemented. Any suitable computer or other device comprising a data processing system, a data memory, means for obtaining audio and video signals and means for presenting audio and video feedback messages may be used for the purpose of carrying out the method, e.g. by installing software that, when executed by the data processing system of the device, causes the device to perform the method steps as described herein.
  • the device is a portable feedback device.
  • An example of a suitable device is portable and may be configured by means of a computer programme to carry out the steps of the invention is a smartphone.
  • the method comprises a step of obtaining a sequence of digital audio signals and a sequence of digital video signals emitted from the patient while using the inhaler.
  • the audio signals may be obtained from a microphone, and the video signals may be obtained from a camera; the microphone and the camera may be incorporated within the portable feedback device.
  • the relevant signals are emitted from the patient while using the inhaler, which includes the signals emitted from the inhaler itself during the use by the patient.
  • the sequence of audio signals covers, or is collected over, the time during which the patient performs one breathing manoeuvre using the inhaler.
  • audio signals from two or more consecutive breathing manoeuvres are obtained or collected.
  • a breathing manoeuvre includes an inspiratory phase in which the patient breathes in, or inhales, aerosol emitted from the inhaler, and an expiratory phase in which the patient breathes out, or exhales.
  • the breathing manoeuvre further includes a phase during which the patient holds the breath, and neither inhales or exhales.
  • the video signals may cover, or be collected over, the time during which the patient performs one breathing manoeuvre using the inhaler, and optionally the time during which the patient performs two or more consecutive breathing manoeuvres.
  • the video signals include signals from the patient's face as well as the inhaler.
  • the sequences of the audio signals and of the video signals are obtained simultaneously.
  • the method further comprises a step of recognising the type of the inhaler, which is performed by processing the video signals in the previous step.
  • This step may be performed by using a frame from the video signal, which is suspected to capture an inhaler A, as an input to a pretrained neural network-based classifier.
  • the classifier outputs x different values, where each value corresponds to the likelihood of detecting inhaler Ai, and i is a number from one to x corresponding to the inhaler type.
  • the method further comprises a step of recognising whether the patient has deviated from the instructions, which is carried out by processing the audio and video signals which were obtained in a previous step.
  • a deviation relates to the way the patient uses, or has used, the inhaler for inhaling the therapeutic aerosol, and while the audio and video signals were obtained or collected.
  • This step may be carried out after the step of recognising the type of the inhaler. In part, it may also be carried out simultaneously with recognising the inhaler type.
  • a deviation from the instructions may relate, for example, to the posture of the patient, the position or orientation of the inhaler, or the breathing manoeuvre of the patient.
  • a deviation from the instructions may, for example, be represented by too fast or too slow inhalation, a too short or too long inspiration phase, the presence or absence of a phase of holding the breath, an incorrect timing of actuation of the inhaler, incorrect expiration (e.g. through the mouthpiece of the inhaler if the instructions provide otherwise, or vice versa) and the like.
  • a further deviation may be a wrong preparation of the inhaler.
  • Some inhalers, in particular suspension aerosols in the form of metered-dose inhalers require shaking in order to provide an optimized suspension to be inhaled.
  • a slow stirring of the (optionally reconstituted) active composition may be required.
  • the step of recognising whether the patient has deviated from the instructions may be carried out by processing the audio and video signals emitted from the patient such as to calculate the likelihood of whether (or not) the breathing manoeuvre performed by the patient conforms with a properly performed breathing manoeuvre according to the instructions applicable to the respective inhaler.
  • the inventors were able to develop a new method to identify if the inhaler was correctly prepared.
  • Prior art methods are based on optical flow analysis, which requires substantial computational power and cannot be performed on a smartphone or low power processor in real time.
  • the inventors developed a new method, which allows the
  • the method is in general based on movement recognition. Any method suitable for the selected device may be utilized. In particular, the method is a method for detecting regular movement as defined below.
  • the method further comprises a step of recognising the type of the deviation that occurred. Also this step involves the processing of the audio and video signals which were obtained in a previous step.
  • one or more feedback messages are presented to the patient, indicating whether a deviation was recognised, and if so, the type of deviation which occurred.
  • the feedback includes information on an inhalation manoeuvre without the respective deviation and how it should be performed by the patient.
  • a feedback message may be presented to the patient in an audio and/or video format, e.g. through a speaker and/or display which may be part of a portable feedback device, such as the speaker and display of a smartphone that is configured to carry out the method of the invention.
  • the feedback message or at least one of several feedback messages, is presented to the patient in an audio-visual format.
  • Other formats may also be used in addition to audio and/or video formats, such as haptic feedback.
  • said feedback message is presented using augmented reality.
  • a feedback message in an audio format with an indication that a deviation has occurred may be presented as a specific sound having a "negative" connotation, such as an alarm sound; or it may be presented as a spoken word message.
  • the feedback may include displaying a symbol, colour , or text message indicating the presence of a deviation.
  • a video clip may be displayed to convey this information.
  • the indication of the type of the deviation may be presented as a feedback message in an audio format, a visual format, or a combined audio-visual format.
  • the format of this feedback is audio-visual.
  • the optional feedback indicating the correct use of the inhaler and in particular the correct breathing manoeuvre according to the respective instructions may also be presented in any of the formats mentioned above.
  • the format is audio visual.
  • the format is audio-visual using augmented reality.
  • steps (a) to (e) of the method may be performed by a portable feedback device for handheld use.
  • a portable feedback device for handheld use.
  • Such device comprises at least a data processing system, a data memory, a camera, a microphone, a display and a speaker.
  • "portable” in combination with “for handheld use” means that the feedback device can be held in the hand of the patient while the method is being performed.
  • the device may be custom-made or generic, such as a smartphone.
  • it In order for it to be a feedback device according to the invention, it must be adapted to perform the method steps, which adaptation is achieved by a computer programme which is executed on the device, i.e. by the data processing system of the device, so that, when the programme is executed, the method steps (a) to (e) are carried out.
  • the computer programme may be stored in the data memory of the portable feedback device.
  • the sequence of digital audio signals emitted from the patient may be obtained in step (a) by means of the microphone, and the digital video signals by means of the camera of the device.
  • the one or more feedback messages presented to the patient according to step (e) may be displayed on the display of the device, sounded through the speaker, or by using a combination of these output means.
  • the recognition of the inhaler type according to step (b) is based on the processing of the video signals, which may be performed by the data processing system of the device.
  • the predefined inhaler shape parameters Ai to A x may be stored in a database in the data memory of the feedback device.
  • parameters Ai to A x may be stored in a database which is stored in a remote memory or data storage device (e.g. cloud based), which is accessible by the data processing system preferably by wireless communication.
  • the feedback device comprises a means for wireless communication with such external data memory or data storage device, optionally via the internet.
  • the recognition of the presence and type of a deviation from the instructions by the patient in using the inhaler according to steps (c) and (d) may be carried out by the data processing system of the device, on which the computer programme is executed.
  • the pre-existing data based on which the data processing system recognises the deviation in the patient's breathing manoeuvre may be stored in the data memory of the feedback device, or may be obtained from an external data memory or data storage device which is preferably accessed by the feedback device by means of wireless communication.
  • one or more feedback messages are presented to the patient, indicating whether a deviation was recognised, and if so, the type of deviation which occurred.
  • the feedback includes information on an inhalation manoeuvre without the respective deviation and how it should be performed by the patient.
  • the feedback message may be presented to the patient in an audio and/or video format, e.g. through a speaker and/or display which may be part of a portable feedback device, such as the speaker and display of a smartphone that is configured to carry out the method of the invention.
  • said feedback messages are presented using augmented reality.
  • the method comprises a further step of recognising the identity of the patient on the basis of video signals.
  • This step may also be performed by the data processing system of the portable feedback device which is configured such as to obtain video signals from the camera, to process these signals and to compare them with stored data
  • the database in which such data are stored may be located in the data memory of the portable feedback device, or it may be located on an external data memory or data storage device which is preferably accessed by the feedback device by means of wireless communication.
  • step (a) The timing of this step is somewhat flexible. Its performance requires the availability of the sequence of digital video signals emitted from the patient, but not necessarily while using the inhaler. Thus, the recognition of the identity of the patient could even be carried out before step (a) or after step (e). Optionally, however, the identity of the patient is recognised by processing the sequence of digital video signals emitted from the patient while using the inhaler, as provided according to step (a), and the recognition itself may be performed at least partially in parallel to step (a), or simultaneously with steps (b), (c), and/or (d).
  • the method may comprise a further optional step of presenting a feedback message to the patient indicating the fact that the patient has been recognised or identified, or indicating the identity of the patient that has been recognised.
  • a feedback message to the patient indicating the fact that the patient has been recognised or identified, or indicating the identity of the patient that has been recognised.
  • message regarding the identity of the patient may be presented in an audio and/or video format, e.g. through a speaker and/or display which may be part of a portable feedback device, such as the speaker and display of a smartphone that is configured to carry out the method of the invention.
  • the name of the patient may be displayed in writing, or a vocal message indicating the name may be sounded via the speaker, or an image of the face of the patient may be displayed, or any combinations thereof.
  • the feedback message indicating the fact that the patient has been recognised or identified, or indicating the identity of the patient that has been recognised is presented before the presentation of the one or more feedback messages indicating whether a deviation was recognised and the type of deviation, if any.
  • the feedback message regarding the patient identity is presented at least partially in parallel (or simultaneously) with one or more other feedback messages of step (e).
  • the method may optionally comprise a step of identifying whether a detrimental condition capable of adversely affecting the quality of the audio signals or of the video signals is present, and optionally, identifying the nature and magnitude of such detrimental condition.
  • a detrimental condition should be interpreted broadly such as to include environmental conditions as well as the handling of the portable feedback device by the patient, or combinations of both.
  • the detrimental condition is an environmental condition.
  • such environmental condition may relate to a particularly low or high luminous intensity prevailing when the patient is about to use the inhaler.
  • a detrimental environmental condition co-affected by the patient e.g. by the way in which the patient holds the inhaler and/or the portable feedback device
  • the luminance contrast in the video signals emitted from the patient is very high. If this is very high, the performance of steps (b), (c) and/or (d) as well as the optional step of recognising the identity of the patient based on the video signals may be difficult or - in extreme cases - impossible.
  • a detrimental environmental condition is the presence of acoustic noise, i.e. unwanted sound that is not related to the use of the inhaler by the patient.
  • the average acoustic background noise should preferably be lower than about 50 dB, and more preferably lower than about 40 dB, or lower than about 35 dB.
  • the threshold value is about 30 dB, above which the presence of a detrimental environmental condition is recognised.
  • An example of a detrimental condition caused by the patient is the shaking of the portable feedback device.
  • a shaking frequency of about 1 Hz or more, or of about 2 Hz or more, or in particular a shaking frequency of about 3 Hz or more, may make it difficult to obtain a sufficiently high quality of video signals allowing the performance of steps (b) to (d), or the recognition of the identity of the patient.
  • Each of these shaking frequencies may serve as a threshold value above which the presence of a detrimental condition is recognised.
  • the method preferably comprises a further step of presenting to the patient a feedback message indicating the presence and optionally the nature of the detrimental condition.
  • a feedback message such as "too dark”, “too much noise”, or "please avoid shaking” may be displayed on the display or sounded via the speaker of the portable feedback device.
  • the method of the invention may further comprise a step of instructing the patient to inhale the therapeutic aerosol using the inhaler according to the instructions for use while the feedback device is operating and is held such that the camera and the microphone are directed towards the patient's face.
  • This step may be performed prior to step (a), and the respective instructions may be presented to the patient in various optional forms.
  • the instructions may be printed in a leaflet or manual distributed along with the portable feedback device if the device is a custom-made device, or along with the computer programme, if the device is generic (such as a smartphone) and configured to perform the method of the invention by means of such software.
  • the instructions may be displayed on the display or sounded through the speaker of the portable feedback device in the same manner as one of the feedback messages as described above.
  • a data processing system which comprises a processor adapted to carry out the method as described herein.
  • the data processing system may be of a generic nature, such as the data processing system of a smartphone, which is adapted or configured to carry out the method steps by means of a computer programme which is loaded and executed on the data processing system.
  • the device is portable and suitable for handheld use, and further comprises a data memory, a camera, a microphone, a display, and a speaker.
  • the invention provides a computer programme comprising instructions which, when the programme is executed by a computer, cause the computer to carry out the steps of the method described herein.
  • the computer preferably comprises the data processing system as defined above.
  • the invention provides a computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the method of the invention.
  • the computer-readable storage medium may be any type of data storage medium, i.e. an optical, magnetic, semiconductor-based or any other class of medium. It is preferably a non-volatile storage medium, such as a flash memory, a digital optical disc, a hard disc drive or a solid-state drive.
  • the invention relates to a computer-implemented method to detect and/or analyse a regular motion comprising the steps of:
  • the new method developed by the inventors is advantageous over the methods of prior art, as it allows a real time analysis even on slower, less powerful processors, e.g. smartphone processors or a raspberry pie.
  • said method steps (a) to (f) are performed by a computing system comprising at least
  • said device additionally comprises a camera.
  • the method steps (a) to (f) are performed by computing system comprising
  • said computing system is portable, more preferably portable and for handheld use. In some embodiments, In a particular embodiment said computing system is a smartphone.
  • Steps (i) to (iii) should be performed over a plurality of frames, covering at least 1 second of motion. Preferably, said steps are repeated for at least about 24 frames, or preferably for at least about 48 frames.
  • the method requires the selection of a portion of a frame.
  • Said frame should cover part of the motion, i.e. the motion passes through the device, but is not completely performed inside said portion of the frame.
  • Said portion of the frame should be the same for the analysis of the motion.
  • said portion of the frame is identical in each frame analyzed, preferably identical relative to the position of the regular movement.
  • the portion of the frame is corrected for camera movements, if the camera or video capture device is e.g. a handheld device.
  • said selection of a portion of a frame is adapted to adjust and correct for movement of the video capture device.
  • the method is particularly suitable for computing systems with limited computational power, such as a smartphone.
  • some further adjustment may be made to the method.
  • the method utilizes and stores the mean brightness values of said portion of a frame.
  • said brightness values are
  • the buffer to store the mean brightness values is a circular buffer.
  • the brightness values may be easier calculated if the video signal is converted into greyscale instead of full color.
  • the methods comprises in step (b) a further step prior to step (i):
  • the method provides a zero-crossing rate, which is proportional to the strength or speed of the regular motion. As such, the speed or strength of the regular motion may be determined by comparison with a reference value.
  • the invention relates to a method as defined above additionally comprising step (g):

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Medicinal Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Biophysics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Pathology (AREA)
  • Urology & Nephrology (AREA)
  • Surgery (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Mathematical Physics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Psychiatry (AREA)
  • Human Computer Interaction (AREA)
  • Social Psychology (AREA)

Abstract

The invention relates to a method and system for providing feedback to a patient using an inhaler of a specific type for inhaling a therapeutic aerosol according to instructions for use provided to the patient with the inhaler. The method comprises the steps of obtaining a sequence of digital audio signals and a sequence of digital video signals emitted from the patient while using the inhaler, recognising the type of the inhaler by processing the video signals, recognising whether the patient has deviated from the instructions by processing the audio and video signals, and recognising the type of the deviation; and presenting to the patient one or more feedback messages indicating whether a deviation was recognised, and if so, what type of deviation occurred, and optionally an inhalation manoeuvre without the deviation.

Description

INHALER TRAINING SYSTEM AND METHOD
DESCRIPTION
BACKGROUND OF THE INVENTION
Respiratory patients receive most of their drug via inhalation devices. That way, the drug reaches the lungs directly, which is the target region to be treated. The known problem is that the market of inhalation devices is growing and therefore the variety. There are at least 4 different categories of devices which support inhalation of pharmaceuticals into the lung: dry powder inhalers, nebulizers, metered dose inhalers (MDI) and soft mist inhalers. They all meant to be used for the self-administration of the drugs for the patient at home.
When drugs are administered as tablets, only adherence is crucial for the success of the therapy. With inhaled drugs, not only the regular use of the drug, but the proper handling of the inhalation device and the inhalation manoeuvre are crucial. If the inhalation is not performed properly, the amount of administered drug to the lung is too low for the therapeutic success. The chronic disease, like Asthma or COPD, is more likely to be unstable, patients are prescribed higher doses unnecessarily or end up in hospital more frequently. Therefore, patients need guidance to the proper use of the inhalation system.
In MDIS for example, the release of the pharmaceuticals needs to be aligned with the start of inhalation or the inhalation with dry powder inhalers needs to be swift and forceful. Some of the devices have to be held upright or in another defined angle in order to release the full amount of drug.
The wrong use of inhaled therapy is common according to the literature, but can be avoided through proper and repeated education and training of the patient. Such training approaches comprise the provision of films and other illustrating manuals to the patient as well as additional assistive equipment and devices which measure the outcome during the use of an inhaler. The devices constitute specific constructions for example with sensors coupled to a patient and related computer processed feedback mechanism.
For example, in US 2015/0339953 A1 a self-learning system is provided giving guidance to inhaler systems using a portable computer device and a camera device. The system comprises guidance of multiple stages of real-time learning, for example simultaneous viewing of the instructional video and the patient’s real-time video. In US 2013/0063579 Al, a training method is described which can train a patient to use a predetermined inhalation system. The system is specifically adapted per patient and inhaler. A universally applicable system would be more efficient.
Existing methods for inhalation training either lack personal interaction with the patient or come together with the requirement of additional equipment and are therefore, not portable. Therefore, there is a need for personalised and convenient training methods for patients using inhalation devices.
SUMMARY OF THE INVENTION
In a first aspect, the invention relates to a computer-implemented method for providing feedback to a patient using an inhaler of a specific type for inhaling a therapeutic aerosol according to instructions for use provided to the patient for, or along with, the inhaler. The method comprises the steps of (a) obtaining a sequence of digital audio signals and a sequence of digital video signals emitted from the patient while using the inhaler; (b) recognising the type of the inhaler by processing the video signals; (c) recognising whether the patient has deviated from the instructions by processing the audio and video signals; (d) if a deviation was recognised in step (c), recognising the type of the deviation; and (e) presenting to the patient one or more feedback messages indicating (i) whether a deviation was recognised; (ii) if a deviation was recognised, the type of deviation; and optionally (iii) an inhalation manoeuvre without the deviation.
In a further aspect, the invention provides a data processing system which comprises a processor adapted to carry out the method as described herein.
In yet a further aspect, the invention provides a computer programme comprising instructions which, when the programme is executed by a computer, cause the computer to carry out the steps of the method described herein.
According to a yet a further aspect, the invention provides a computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the method of the invention.
BRIEF DESCRIPTION OF THE DRAWINGS
Fig. 1 represents a diagram illustrating the steps of the method of the invention according to a first embodiment. Fig. 2 represents a diagram illustrating the steps of the method of the invention according to a further optional embodiment.
DETAILED DESCRIPTION OF THE INVENTION
In a first aspect, the invention provides a computer-implemented method for providing feedback to a patient using an inhaler of a specific type for inhaling a therapeutic aerosol according to instructions for use provided to the patient along with the inhaler as defined in claim 1.
In one embodiment, the method comprises the steps of:
(a) obtaining a sequence of digital audio signals and a sequence of digital video signals emitted from the patient while using the inhaler;
(b) recognising the type of the inhaler by processing the video signals;
(c) recognising whether the patient has deviated from the instructions by processing the audio and video signals;
(d) if a deviation was recognised in step (c), recognising the type of the deviation; and
(e) presenting to the patient one or more feedback messages indicating
(i) whether a deviation was recognised;
(ii) if a deviation was recognised, the type of deviation; and optionally
(iii) an inhalation manoeuvre without the deviation;
wherein preferably steps b) and c) are performed by analysing the video and audio signals using an artificial neural network trained to identify an inhaler type and to identify deviations, or by a method to detect a regular motion;
wherein steps (a) to (e) are performed by a portable feedback device for handheld use comprising
- a data processing system;
- a data memory;
- a camera;
- a microphone;
- a display; and
- a speaker.
Preferably, steps b) and c) comprise performing an analysis of the video and audio signals using an artificial neural network trained to identify an inhaler type and to identify deviations, and step c) also comprises the use of a method to detect a regular motion. As used herein, an inhaler is an inhalation device capable of emitting a therapeutic aerosol such as to enable a user or patient to inhale the aerosol. An aerosol is a dispersion of a solid, semisolid or liquid phase in a continuous gaseous phase, thus including e. g. powder aerosols - pharmaceutically known as powders for inhalation - and nebulised aerosols.
Inhalation devices for delivering powder aerosols are commonly described as powder inhalers. Aerosolised liquids are administered by means of various inhalation devices including nebulisers, pressurised metered-dose inhalers, and soft mist inhalers. In one embodiment, the method of the invention provides feedback to a patient using a powder inhaler, a nebuliser, a metered-dose inhaler or a soft mist inhaler.
A major advantage of the method according to the invention is the possibility to perform the method on a handheld device. A suitable handheld device may be a smartphone. The method in general can be performed on any processor, even on a relatively slow processor such as smartphones or a raspberry pie. The present method can be performed in real time and does not require access to a server with much computational power, i.e. the method can be performed offline.
The inhaler type refers to the specific inhaler model or model family. In this context, a model family means those variants of a model which are used by a patient in essentially the same manner, in particular with respect to the breathing manoeuvre. For illustration, an example of a specific type of nebuliser is the PARI eFlow rapid nebuliser system, which is an electronic nebuliser incorporating a vibrating mesh technology; an example of a specific type of powder inhaler is the ADVAIR DISKUS® sold by GSK; an example of a specific type of soft mist inhaler is the SPIRIVA® RESPIMAT® sold by Boehringer Ingelheim; and an example of a specific type of metered-dose inhaler is VENTOLIN® HFA sold by GSK.
Each inhaler is provided to a patient together with instructions for use, which are typically printed on a patient leaflet, but which may also be provided to the patient through the internet or by oral and/or visual information received from a health care provider such as a physician, pharmacist or nurse.
The patient using the inhaler is a human subject who is in need of, or would benefit from, the therapeutic aerosol administered through the inhaler. The use may be for any medical purpose, including the prevention or treatment of any disease, condition or symptom for which the aerosol is potentially beneficial. An advantage of the method of the invention is that the method identifies the inhaler type. Methods of the prior art, e.g as described in US 2013/0063579 A1 may be suitable to train a patient but require to be adapted to a specific inhaler beforehand.
The inhaler may be identified using a pre-trained artificial neural network. As such, the method may be performed on a handheld device with limited computing power, e.g. a smartphone.
The method of the invention is computer-implemented. Any suitable computer or other device comprising a data processing system, a data memory, means for obtaining audio and video signals and means for presenting audio and video feedback messages may be used for the purpose of carrying out the method, e.g. by installing software that, when executed by the data processing system of the device, causes the device to perform the method steps as described herein. In one of the preferred embodiments, the device is a portable feedback device. An example of a suitable device is portable and may be configured by means of a computer programme to carry out the steps of the invention is a smartphone.
The method comprises a step of obtaining a sequence of digital audio signals and a sequence of digital video signals emitted from the patient while using the inhaler. The audio signals may be obtained from a microphone, and the video signals may be obtained from a camera; the microphone and the camera may be incorporated within the portable feedback device. The relevant signals are emitted from the patient while using the inhaler, which includes the signals emitted from the inhaler itself during the use by the patient.
In one embodiment, the sequence of audio signals covers, or is collected over, the time during which the patient performs one breathing manoeuvre using the inhaler. In another embodiment, audio signals from two or more consecutive breathing manoeuvres are obtained or collected. As used herein, a breathing manoeuvre includes an inspiratory phase in which the patient breathes in, or inhales, aerosol emitted from the inhaler, and an expiratory phase in which the patient breathes out, or exhales. In some cases, the breathing manoeuvre further includes a phase during which the patient holds the breath, and neither inhales or exhales.
Similarly, the video signals may cover, or be collected over, the time during which the patient performs one breathing manoeuvre using the inhaler, and optionally the time during which the patient performs two or more consecutive breathing manoeuvres. In one of the preferred embodiments, the video signals include signals from the patient's face as well as the inhaler.
In one embodiment, the sequences of the audio signals and of the video signals are obtained simultaneously.
The method further comprises a step of recognising the type of the inhaler, which is performed by processing the video signals in the previous step. This step may be performed by using a frame from the video signal, which is suspected to capture an inhaler A, as an input to a pretrained neural network-based classifier. The classifier outputs x different values, where each value corresponds to the likelihood of detecting inhaler Ai, and i is a number from one to x corresponding to the inhaler type.
The method further comprises a step of recognising whether the patient has deviated from the instructions, which is carried out by processing the audio and video signals which were obtained in a previous step. In this context, a deviation relates to the way the patient uses, or has used, the inhaler for inhaling the therapeutic aerosol, and while the audio and video signals were obtained or collected. This step may be carried out after the step of recognising the type of the inhaler. In part, it may also be carried out simultaneously with recognising the inhaler type.
A deviation from the instructions may relate, for example, to the posture of the patient, the position or orientation of the inhaler, or the breathing manoeuvre of the patient. With respect to the breathing manoeuvre, a deviation from the instructions may, for example, be represented by too fast or too slow inhalation, a too short or too long inspiration phase, the presence or absence of a phase of holding the breath, an incorrect timing of actuation of the inhaler, incorrect expiration (e.g. through the mouthpiece of the inhaler if the instructions provide otherwise, or vice versa) and the like.
A further deviation may be a wrong preparation of the inhaler. Some inhalers, in particular suspension aerosols in the form of metered-dose inhalers require shaking in order to provide an optimized suspension to be inhaled. For other inhalers or combinations of inhalers and drug products, a slow stirring of the (optionally reconstituted) active composition may be required.
The step of recognising whether the patient has deviated from the instructions may be carried out by processing the audio and video signals emitted from the patient such as to calculate the likelihood of whether (or not) the breathing manoeuvre performed by the patient conforms with a properly performed breathing manoeuvre according to the instructions applicable to the respective inhaler.
The inventors were able to develop a new method to identify if the inhaler was correctly prepared. Prior art methods are based on optical flow analysis, which requires substantial computational power and cannot be performed on a smartphone or low power processor in real time. The inventors developed a new method, which allows the
identification of regular movement, i.e. shaking or stirring in real time on processors with limited power, e.g. smartphone processors.
The method is in general based on movement recognition. Any method suitable for the selected device may be utilized. In particular, the method is a method for detecting regular movement as defined below.
If a deviation has been recognised, the method further comprises a step of recognising the type of the deviation that occurred. Also this step involves the processing of the audio and video signals which were obtained in a previous step.
In a further step, one or more feedback messages are presented to the patient, indicating whether a deviation was recognised, and if so, the type of deviation which occurred. Optionally, the feedback includes information on an inhalation manoeuvre without the respective deviation and how it should be performed by the patient.
According to the invention, a feedback message may be presented to the patient in an audio and/or video format, e.g. through a speaker and/or display which may be part of a portable feedback device, such as the speaker and display of a smartphone that is configured to carry out the method of the invention. In one embodiment, the feedback message, or at least one of several feedback messages, is presented to the patient in an audio-visual format. Other formats may also be used in addition to audio and/or video formats, such as haptic feedback. In one embodiment said feedback message is presented using augmented reality.
For example, a feedback message in an audio format with an indication that a deviation has occurred may be presented as a specific sound having a "negative" connotation, such as an alarm sound; or it may be presented as a spoken word message. In a visual format, the feedback may include displaying a symbol, colour , or text message indicating the presence of a deviation. Optionally, a video clip may be displayed to convey this information. Similarly, the indication of the type of the deviation may be presented as a feedback message in an audio format, a visual format, or a combined audio-visual format. In one of the preferred embodiments, and due to the higher complexity of this indication, the format of this feedback is audio-visual.
The optional feedback indicating the correct use of the inhaler and in particular the correct breathing manoeuvre according to the respective instructions may also be presented in any of the formats mentioned above. In a preferred embodiment, the format is audio visual. In a particular preferred embodiment, the format is audio-visual using augmented reality.
As mentioned, steps (a) to (e) of the method may be performed by a portable feedback device for handheld use. Such device comprises at least a data processing system, a data memory, a camera, a microphone, a display and a speaker. In the context of the invention, "portable" in combination with "for handheld use" means that the feedback device can be held in the hand of the patient while the method is being performed. The device may be custom-made or generic, such as a smartphone. In order for it to be a feedback device according to the invention, it must be adapted to perform the method steps, which adaptation is achieved by a computer programme which is executed on the device, i.e. by the data processing system of the device, so that, when the programme is executed, the method steps (a) to (e) are carried out.
The computer programme may be stored in the data memory of the portable feedback device. The sequence of digital audio signals emitted from the patient may be obtained in step (a) by means of the microphone, and the digital video signals by means of the camera of the device. The one or more feedback messages presented to the patient according to step (e) may be displayed on the display of the device, sounded through the speaker, or by using a combination of these output means.
The recognition of the inhaler type according to step (b) is based on the processing of the video signals, which may be performed by the data processing system of the device. The predefined inhaler shape parameters Ai to Axmay be stored in a database in the data memory of the feedback device. Alternatively, parameters Ai to Axmay be stored in a database which is stored in a remote memory or data storage device (e.g. cloud based), which is accessible by the data processing system preferably by wireless communication. Accordingly, it is preferred that the feedback device comprises a means for wireless communication with such external data memory or data storage device, optionally via the internet. Similarly, the recognition of the presence and type of a deviation from the instructions by the patient in using the inhaler according to steps (c) and (d) may be carried out by the data processing system of the device, on which the computer programme is executed. Again, the pre-existing data based on which the data processing system recognises the deviation in the patient's breathing manoeuvre may be stored in the data memory of the feedback device, or may be obtained from an external data memory or data storage device which is preferably accessed by the feedback device by means of wireless communication.
As described above, one or more feedback messages are presented to the patient, indicating whether a deviation was recognised, and if so, the type of deviation which occurred. Optionally, the feedback includes information on an inhalation manoeuvre without the respective deviation and how it should be performed by the patient. The feedback message may be presented to the patient in an audio and/or video format, e.g. through a speaker and/or display which may be part of a portable feedback device, such as the speaker and display of a smartphone that is configured to carry out the method of the invention.
In one embodiment, said feedback messages are presented using augmented reality.
Optionally, the method comprises a further step of recognising the identity of the patient on the basis of video signals. This step may also be performed by the data processing system of the portable feedback device which is configured such as to obtain video signals from the camera, to process these signals and to compare them with stored data
corresponding to specific faces. Again, the database in which such data are stored may be located in the data memory of the portable feedback device, or it may be located on an external data memory or data storage device which is preferably accessed by the feedback device by means of wireless communication.
The timing of this step is somewhat flexible. Its performance requires the availability of the sequence of digital video signals emitted from the patient, but not necessarily while using the inhaler. Thus, the recognition of the identity of the patient could even be carried out before step (a) or after step (e). Optionally, however, the identity of the patient is recognised by processing the sequence of digital video signals emitted from the patient while using the inhaler, as provided according to step (a), and the recognition itself may be performed at least partially in parallel to step (a), or simultaneously with steps (b), (c), and/or (d).
If the identity of the patient is recognised, the method may comprise a further optional step of presenting a feedback message to the patient indicating the fact that the patient has been recognised or identified, or indicating the identity of the patient that has been recognised. Like the other feedback messages, such message regarding the identity of the patient may be presented in an audio and/or video format, e.g. through a speaker and/or display which may be part of a portable feedback device, such as the speaker and display of a smartphone that is configured to carry out the method of the invention. For example, the name of the patient may be displayed in writing, or a vocal message indicating the name may be sounded via the speaker, or an image of the face of the patient may be displayed, or any combinations thereof.
In one embodiment, the feedback message indicating the fact that the patient has been recognised or identified, or indicating the identity of the patient that has been recognised, is presented before the presentation of the one or more feedback messages indicating whether a deviation was recognised and the type of deviation, if any. In another embodiment, the feedback message regarding the patient identity is presented at least partially in parallel (or simultaneously) with one or more other feedback messages of step (e).
Furthermore, the method may optionally comprise a step of identifying whether a detrimental condition capable of adversely affecting the quality of the audio signals or of the video signals is present, and optionally, identifying the nature and magnitude of such detrimental condition. As used herein, a detrimental condition should be interpreted broadly such as to include environmental conditions as well as the handling of the portable feedback device by the patient, or combinations of both.
In one embodiment, the detrimental condition is an environmental condition. For example, such environmental condition may relate to a particularly low or high luminous intensity prevailing when the patient is about to use the inhaler. A detrimental environmental condition co-affected by the patient (e.g. by the way in which the patient holds the inhaler and/or the portable feedback device) is the luminance contrast in the video signals emitted from the patient. If this is very high, the performance of steps (b), (c) and/or (d) as well as the optional step of recognising the identity of the patient based on the video signals may be difficult or - in extreme cases - impossible.
Another example of a detrimental environmental condition is the presence of acoustic noise, i.e. unwanted sound that is not related to the use of the inhaler by the patient. For example, the average acoustic background noise should preferably be lower than about 50 dB, and more preferably lower than about 40 dB, or lower than about 35 dB. In one of the particularly preferred embodiments, the threshold value is about 30 dB, above which the presence of a detrimental environmental condition is recognised.
An example of a detrimental condition caused by the patient is the shaking of the portable feedback device. A shaking frequency of about 1 Hz or more, or of about 2 Hz or more, or in particular a shaking frequency of about 3 Hz or more, may make it difficult to obtain a sufficiently high quality of video signals allowing the performance of steps (b) to (d), or the recognition of the identity of the patient. Each of these shaking frequencies may serve as a threshold value above which the presence of a detrimental condition is recognised.
If a detrimental condition capable of adversely affecting the quality of the audio signals or of the video signals is identified, the method preferably comprises a further step of presenting to the patient a feedback message indicating the presence and optionally the nature of the detrimental condition. With respect to the options and preferences relating to the feedback message, its formats, and the means by which it is presented, reference is made to the above parts of the description which describe the presentation of other feedback messages, which should be applied in analogy. For example, a feedback message such as "too dark", "too much noise", or "please avoid shaking" may be displayed on the display or sounded via the speaker of the portable feedback device.
The method of the invention may further comprise a step of instructing the patient to inhale the therapeutic aerosol using the inhaler according to the instructions for use while the feedback device is operating and is held such that the camera and the microphone are directed towards the patient's face. This step may be performed prior to step (a), and the respective instructions may be presented to the patient in various optional forms. For example, the instructions may be printed in a leaflet or manual distributed along with the portable feedback device if the device is a custom-made device, or along with the computer programme, if the device is generic (such as a smartphone) and configured to perform the method of the invention by means of such software. Alternatively, or in addition, the instructions may be displayed on the display or sounded through the speaker of the portable feedback device in the same manner as one of the feedback messages as described above.
In a further aspect of the invention, a data processing system is provided which comprises a processor adapted to carry out the method as described herein. As mentioned, the data processing system may be of a generic nature, such as the data processing system of a smartphone, which is adapted or configured to carry out the method steps by means of a computer programme which is loaded and executed on the data processing system. However, regardless of whether the device within which the data processing system is incorporated is generic or custom-made, it is preferred that the device is portable and suitable for handheld use, and further comprises a data memory, a camera, a microphone, a display, and a speaker.
In yet a further aspect, the invention provides a computer programme comprising instructions which, when the programme is executed by a computer, cause the computer to carry out the steps of the method described herein. Again, the computer preferably comprises the data processing system as defined above.
In yet a further aspect, the invention provides a computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the method of the invention. The computer-readable storage medium may be any type of data storage medium, i.e. an optical, magnetic, semiconductor-based or any other class of medium. It is preferably a non-volatile storage medium, such as a flash memory, a digital optical disc, a hard disc drive or a solid-state drive.
In a further aspect, the invention relates to a computer-implemented method to detect and/or analyse a regular motion comprising the steps of:
(a) obtaining a sequence of digital video signals emitted from said regular motion;
(b) in said video signals performing the following steps on a series of frames of said video signal:
(i) selecting a portion of a frame through which said regular motion passes through;
(ii) computing the mean brightness value within said portion of the frame;
(iii) storing said mean brightness value of said portion of said frame in a buffer;
(c) repeating steps (i) - (iii) for a sequence of frames comprising a plurality of frames, wherein said portion of a frame is identical in each frame, creating a buffer of said mean brightness values;
(d) calculating the average of the mean brightness of all values determined and stored in said buffer of brightness values;
(e) subtracting said determined average of the mean brightness from each value in said buffer to generate a zero centered buffer;
(f) computing the zero crossing rate of said zero centered buffer.
The new method developed by the inventors is advantageous over the methods of prior art, as it allows a real time analysis even on slower, less powerful processors, e.g. smartphone processors or a raspberry pie. Preferably said method steps (a) to (f) are performed by a computing system comprising at least
- a data processing system;
- a data memory.
In some embodiments said device additionally comprises a camera.
In some embodiments, the method steps (a) to (f) are performed by computing system comprising
- a data processing system;
- a data memory;
- a camera;
- a microphone;
- a display; and
- a speaker.
In a more preferred embodiment, said computing system is portable, more preferably portable and for handheld use. In some embodiments, In a particular embodiment said computing system is a smartphone.
Steps (i) to (iii) should be performed over a plurality of frames, covering at least 1 second of motion. Preferably, said steps are repeated for at least about 24 frames, or preferably for at least about 48 frames.
The method requires the selection of a portion of a frame. Said frame should cover part of the motion, i.e. the motion passes through the device, but is not completely performed inside said portion of the frame. Said portion of the frame should be the same for the analysis of the motion. Preferably, said portion of the frame is identical in each frame analyzed, preferably identical relative to the position of the regular movement. Preferably, the portion of the frame is corrected for camera movements, if the camera or video capture device is e.g. a handheld device.
In some embodiments said selection of a portion of a frame is adapted to adjust and correct for movement of the video capture device.
As already noted, the method is particularly suitable for computing systems with limited computational power, such as a smartphone. In order to improve the performance of the method, some further adjustment may be made to the method. The method utilizes and stores the mean brightness values of said portion of a frame. Preferably, said brightness values are
In some embodiments of the invention, the buffer to store the mean brightness values is a circular buffer. The brightness values may be easier calculated if the video signal is converted into greyscale instead of full color. As such in some embodiments, the methods comprises in step (b) a further step prior to step (i):
(o) converting the color information of said frame to greyscale.
The method provides a zero-crossing rate, which is proportional to the strength or speed of the regular motion. As such, the speed or strength of the regular motion may be determined by comparison with a reference value.
Accordingly, in one embodiment, the invention relates to a method as defined above additionally comprising step (g):
(g) comparing the determined zero crossing rate with predetermined reference values to obtain an estimate on the speed or strength of said regular motion.
Further embodiments and optional feature will be apparent to a person skilled in the art.

Claims

Claims
1. A computer-implemented method for providing feedback to a patient using an inhaler of a specific type for inhaling a therapeutic aerosol according to instructions for use provided to the patient for, or along with, the inhaler, the method comprising the steps of:
(a) obtaining a sequence of digital audio signals and a sequence of digital video signals emitted from the patient while using the inhaler;
(b) recognising the type of the inhaler by processing the video signals;
(c) recognising whether the patient has deviated from the instructions by processing the audio and video signals;
(d) if a deviation was recognised in step (c), recognising the type of the deviation; and
(e) presenting to the patient one or more feedback messages indicating
(i) whether a deviation was recognised;
(ii) if a deviation was recognised, the type of deviation; and optionally
(iii) an inhalation manoeuvre without the deviation;
wherein steps b) and c) are performed by analysing the video and audio signals using an artifical neural network trained to identify an inhaler type and to identify deviations, or by a method to detect a regular motion;
wherein steps (a) to (e) are performed by a portable feedback device for handheld use comprising
- a data processing system;
- a data memory;
- a camera;
- a microphone;
- a display; and
- a speaker.
2. The method of claim Ϊ, wherein step c) is performed in real time on said portable feedback device and said feedback messages in step e) are presented immediately.
3. The method of claims 1 or 2, wherein in step e) said feedback messages are presented using augmented reality.
4. The method of any one of the preceding claims, wherein the inhaler is a powder inhaler, a nebuliser, a metered-dose inhaler or a soft mist inhaler.
5. The method of any one of the preceding claims, further comprising a step of recognising the identity of the patient on the basis of the video signals.
6. The method of any one of the preceding claims, further comprising a step of identifying whether a detrimental condition capable of adversely affecting the quality of the audio signals or of the video signals is present, wherein the detrimental condition is optionally an environmental condition such as a luminous contrast or acoustic noise, or a patient activity such as shaking of the portable feedback device.
7. The method of claim 6, further comprising a step of presenting to the patient a feedback message indicating the presence and the nature of the detrimental condition.
8. The method of any one of the preceding claims, further comprising a step of instructing the patient to inhale the therapeutic aerosol using the inhaler according to the instructions for use while the feedback device is operating and is held such that the camera and the microphone are directed towards the patient's face.
9. A data processing system comprising a processor adapted to carry out the method of any one of claims 1 to 8.
10. The data processing system of claim 9, being incorporated within a portable feedback device for handheld use, said feedback device further comprising
- a data memory;
- a camera;
- a microphone;
- a display; and
- a speaker.
11. A computer programme comprising instructions which, when the programme is executed by a computer, cause the computer to carry out the steps of the method of any one of claims 1 to 8.
12. The computer programme of claim 11, wherein the computer comprises the data processing system of claim 8 or 9.
13. A computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to carry out the steps of the method of any one of claims 1 to 8.
14. The computer-readable storage medium of claim 13, wherein the computer comprises the data processing system of claim 9 or 10.
15. A computer-implemented method to detect and/or analyse a regular motion comprising:
(a) obtaining sequence of digital video signals emitted from said regular motion;
(b) in said video signals perform the following steps on a series of frames of said video signals:
(i) selecting a portion of a frame through which said regular motion passes through;
(ii) computing the mean brightness value within said portion of the frame;
(iii) storing said mean brightness value of said portion of said frame in a buffer;
(c) repeating steps (i) - (iii) for a sequence of frames comprising a plurality of frames, wherein said portion of a frame is identical in each frame creating a buffer of brightness values;
(d) calculating the average of the mean brightness of all values determined and stored in said buffer of brightness values;
(e) subtracting said determined average of the mean brightness from each value in said buffer to generate a zero centered buffer;
(f) computing the zero crossing rate of said zero centered buffer;
wherein steps (a) to (f) are performed by a computing device comprising at least
- a data processing system;
- a data memory.
16. The computer implemented method according to claim 15, wherein steps (i) to (iii) are repeated for at least 48 frames.
17. The computer-implemented method according to claims 15 or 16, wherein said selection of a portion of a frame is adapted to adjust and correct for movement of the video capture device.
18. The computer-implemented method according to any one of claims 15 to 17, wherein the buffer is a circular buffer.
19. The computer-implemented method according to any one of claims 15 to 18, wherein comprising in step (b) a further step prior to step (i):
(o) converting the color information of said frame to greyscale.
20. The computer-implemented method according to any one of claims 15 top 19, additionally comprising step (g):
(g) comparing the determined zero crossing rate with predetermined reference values to obtain an estimate on the speed or strength of said regular motion.
PCT/EP2018/086541 2017-12-21 2018-12-21 Inhaler training system and method WO2019122315A1 (en)

Priority Applications (10)

Application Number Priority Date Filing Date Title
KR1020207021283A KR20200103061A (en) 2017-12-21 2018-12-21 Inhaler training system and method
CA3086773A CA3086773A1 (en) 2017-12-21 2018-12-21 Inhaler training system and method
SG11202005467WA SG11202005467WA (en) 2017-12-21 2018-12-21 Inhaler training system and method
EP18833233.2A EP3729452B1 (en) 2017-12-21 2018-12-21 Inhaler training system and method
PL18833233.2T PL3729452T3 (en) 2017-12-21 2018-12-21 Inhaler training system and method
AU2018386559A AU2018386559A1 (en) 2017-12-21 2018-12-21 Inhaler training system and method
CN201880083273.3A CN111886654A (en) 2017-12-21 2018-12-21 Inhaler training system and method
US16/955,802 US11664104B2 (en) 2017-12-21 2018-12-21 Inhaler training system and method
JP2020554930A JP2021508577A (en) 2017-12-21 2018-12-21 Inhaler training system and method
US18/302,015 US20230253086A1 (en) 2017-12-21 2023-04-18 Inhaler training system and method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP17209861 2017-12-21
EP17209861.8 2017-12-21

Related Child Applications (2)

Application Number Title Priority Date Filing Date
US16/955,802 A-371-Of-International US11664104B2 (en) 2017-12-21 2018-12-21 Inhaler training system and method
US18/302,015 Continuation US20230253086A1 (en) 2017-12-21 2023-04-18 Inhaler training system and method

Publications (1)

Publication Number Publication Date
WO2019122315A1 true WO2019122315A1 (en) 2019-06-27

Family

ID=60813635

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2018/086541 WO2019122315A1 (en) 2017-12-21 2018-12-21 Inhaler training system and method

Country Status (10)

Country Link
US (2) US11664104B2 (en)
EP (1) EP3729452B1 (en)
JP (1) JP2021508577A (en)
KR (1) KR20200103061A (en)
CN (1) CN111886654A (en)
AU (1) AU2018386559A1 (en)
CA (1) CA3086773A1 (en)
PL (1) PL3729452T3 (en)
SG (1) SG11202005467WA (en)
WO (1) WO2019122315A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021060867A (en) * 2019-10-08 2021-04-15 大日本印刷株式会社 Inhalation action estimation device, computer program and inhalation action estimation method
EP4068296A1 (en) 2021-04-01 2022-10-05 Hephaï Detection of the synchronisation between actuation of a pressurised inhaler-doser and a patient breathing in

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113730756A (en) * 2021-09-29 2021-12-03 河北小企鹅医疗科技有限公司 Neural network-based design method for self-adaptive respirator controller
KR102462532B1 (en) * 2022-04-12 2022-11-03 주식회사 티알 Portable nebulizer system
KR20240057712A (en) * 2022-10-25 2024-05-07 가톨릭대학교 산학협력단 Server for providing metered-dose inhaler training service based on virtual reality, method and program

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020140694A1 (en) * 2001-03-27 2002-10-03 Frank Sauer Augmented reality guided instrument positioning with guiding graphics
US20050251030A1 (en) * 2004-04-21 2005-11-10 Azar Fred S Method for augmented reality instrument placement using an image based navigation system
US20130063579A1 (en) 2010-05-06 2013-03-14 AI Cure Technologies, Inc. Method and Apparatus for Recognition of Inhaler Actuation
US20150339953A1 (en) 2013-05-22 2015-11-26 Fenil Shah Guidance/self-learning process for using inhalers
US20170160549A1 (en) * 2014-03-28 2017-06-08 Alma Mater Studiorum-Universita' Di Bologna Augmented reality glasses for medical applications and corresponding augmented reality system
US20170323062A1 (en) * 2014-11-18 2017-11-09 Koninklijke Philips N.V. User guidance system and method, use of an augmented reality device

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6909359B1 (en) * 2003-04-04 2005-06-21 Mcgovern Robert T. Real-time medical alerting system
US10116903B2 (en) * 2010-05-06 2018-10-30 Aic Innovations Group, Inc. Apparatus and method for recognition of suspicious activities
WO2014152828A1 (en) 2013-03-14 2014-09-25 AI Cure Technologies, Inc. Apparatus and method for recognition of suspicious activties
CA2937985C (en) * 2014-04-07 2022-07-05 Boehringer Ingelheim International Gmbh Inhalation training device and system for practicing of an inhalation process of a patient
GB201420039D0 (en) * 2014-11-11 2014-12-24 Teva Uk Ltd System for training a user in administering a medicament
CN104834946B (en) 2015-04-09 2018-02-09 清华大学 A kind of contactless sleep monitor method and system
KR101607054B1 (en) * 2015-04-23 2016-03-29 현대제철 주식회사 Apparatus for detecting error of a rotary atomizer and method thereof
FR3036036B1 (en) * 2015-05-13 2017-04-21 Kappa Sante DEVICE FOR ANALYZING A SUCCESSION OF MOVEMENTS OF A PATIENT IN RELATION TO THE PROTOCOL USING AN INHALER
CA2958010C (en) 2016-02-19 2021-09-07 Covidien Lp System and methods for video-based monitoring of vital signs
US20180092595A1 (en) * 2016-10-04 2018-04-05 Mundipharma Laboratories Gmbh System and method for training and monitoring administration of inhaler medication

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020140694A1 (en) * 2001-03-27 2002-10-03 Frank Sauer Augmented reality guided instrument positioning with guiding graphics
US20050251030A1 (en) * 2004-04-21 2005-11-10 Azar Fred S Method for augmented reality instrument placement using an image based navigation system
US20130063579A1 (en) 2010-05-06 2013-03-14 AI Cure Technologies, Inc. Method and Apparatus for Recognition of Inhaler Actuation
US20150339953A1 (en) 2013-05-22 2015-11-26 Fenil Shah Guidance/self-learning process for using inhalers
US20170160549A1 (en) * 2014-03-28 2017-06-08 Alma Mater Studiorum-Universita' Di Bologna Augmented reality glasses for medical applications and corresponding augmented reality system
US20170323062A1 (en) * 2014-11-18 2017-11-09 Koninklijke Philips N.V. User guidance system and method, use of an augmented reality device

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021060867A (en) * 2019-10-08 2021-04-15 大日本印刷株式会社 Inhalation action estimation device, computer program and inhalation action estimation method
JP7353605B2 (en) 2019-10-08 2023-10-02 大日本印刷株式会社 Inhalation motion estimation device, computer program, and inhalation motion estimation method
EP4068296A1 (en) 2021-04-01 2022-10-05 Hephaï Detection of the synchronisation between actuation of a pressurised inhaler-doser and a patient breathing in
FR3121361A1 (en) 2021-04-01 2022-10-07 Hephaï Detection of the synchronization between the actuation of a pressurized metered-dose inhaler and the inspiration of a patient

Also Published As

Publication number Publication date
US20210110905A1 (en) 2021-04-15
AU2018386559A1 (en) 2020-06-25
SG11202005467WA (en) 2020-07-29
KR20200103061A (en) 2020-09-01
EP3729452B1 (en) 2024-05-15
CA3086773A1 (en) 2019-06-27
US11664104B2 (en) 2023-05-30
EP3729452A1 (en) 2020-10-28
PL3729452T3 (en) 2024-09-23
JP2021508577A (en) 2021-03-11
EP3729452C0 (en) 2024-05-15
CN111886654A (en) 2020-11-03
US20230253086A1 (en) 2023-08-10

Similar Documents

Publication Publication Date Title
US20230253086A1 (en) Inhaler training system and method
US20150283341A1 (en) Method, electronic device, inhalation training system and information storage medium for practicing and/or controlling an inhalation process of a patient
US9320863B2 (en) System and method for inexsufflating a subject
US10398352B2 (en) Inhaler spacer with a medicament compliance system
US10335564B2 (en) System and method for controlling exsufflation pressure during in-exsufflation
US20190192046A1 (en) Method and system for selecting an inhaler
US20180240353A1 (en) Virtual and augmented reality based training of inhaler technique
EP3773833A1 (en) Adjunct diagnostic device and method
Ari et al. Differential medical aerosol device and interface selection in patients during spontaneous, conventional mechanical and noninvasive ventilation
Wan et al. In vitro evaluation of aerosol delivery by different nebulization modes in pediatric and adult mechanical ventilators
RU2653624C2 (en) Critical care ventilator with mouth piece ventilation
EP3294392B1 (en) Nebulizers having yawn detection
US20190217031A1 (en) Multi-Sensual Immersive Device And Systems And Methods Of Using Same
JP2018520714A (en) System and method for improving cough segmentation
CN116549785A (en) Atomized respiration control method and device, electronic equipment and storage medium
WO2018097098A1 (en) General-anesthesia introduction assistance system, general-anesthesia introduction assistance game device and program for general-anesthesia introduction assistance game device
JP7353605B2 (en) Inhalation motion estimation device, computer program, and inhalation motion estimation method
US20230133142A1 (en) Patient stratification and clinical decision support on mechanical ventilation settings from sonar responses through an endotracheal tube (ett)
BR112019012035A2 (en) training device for use in an inhaler, inhaler and a user's training method for operating an inhaler
JP2024534338A (en) Detection of pendulum flow through an endotracheal tube using acoustic interferometry
CN108498915A (en) A kind of the sucking diagnosing and treating apparatus and control application method of game guiding
Fonseca et al. 33 Noninvasive Ventilation and Droplet Dispersion: Health Professional Protocols from
Sanjar The Importance of Device Selection, Education, and Training for Appropriate and Effective Inhalation Therapy in COPD
Fonseca et al. Noninvasive Ventilation and Droplet Dispersion: Health Professional Protocols from a Nursing Perspective

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18833233

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020554930

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 3086773

Country of ref document: CA

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018386559

Country of ref document: AU

Date of ref document: 20181221

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20207021283

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2018833233

Country of ref document: EP

Effective date: 20200721