automated and objective symptom severity score

Abstract

The present invention relates to a system and method for determining the severity of a respiratory disease of a patient. The system directs the patient to recite a phrase. The system receives the recited phrase of the patient as an acoustic signal and analyzes the acoustic signal with respect to the severity of the respiratory disease. An analysis result is provided, the analysis result being indicative of the severity of the respiratory disease of the patient.

Description

Technical Field

[0001] This invention relates to a system for determining the severity of a patient's respiratory disease and a method for determining the severity of a patient's respiratory disease. Background Technology

[0002] Patients with respiratory conditions such as chronic obstructive pulmonary disease (COPD) often manage their condition at home. Daily phone calls can serve as part of remote health monitoring for these patients. During these calls, patients are typically asked to complete a questionnaire about their symptoms. The answers to these questions can then be used to generate a symptom severity score, which allows for an assessment of the patient's health and identification of the risk of worsening. However, compliance with these questions is often low, leading to missing or incomplete data and a high probability of error in calculating symptom severity scores. Furthermore, patients may provide inaccurate or unreliable information when answering questionnaires, further increasing the probability of errors in symptom severity scoring.

[0003] US2018296092A1 discloses a system and method for monitoring and determining a user's medical condition via a user's communication device. The system includes a memory and a processor configured to receive audio signals related to the user's voice and determine the user's disease progression based on a comparison of the audio signals with reference audio signals.

[0004] It would be advantageous to have a system and method for determining the severity of a patient’s respiratory disease that does not suffer from the above-mentioned drawbacks. Summary of the Invention

[0005] One object of the present invention is to provide a system and method for determining the severity of a patient’s respiratory disease, which can determine the severity automatically and objectively.

[0006] The object of the invention is achieved through the subject matter of the independent claims, wherein further embodiments are incorporated in the dependent claims. The described embodiments similarly relate to systems and methods for determining the severity of a patient's respiratory illness. Synergistic effects may arise from different combinations of embodiments, although they may not be described in detail.

[0007] Furthermore, it should be noted that all embodiments of the method of the present invention can be performed in the order of the described steps; however, this is not necessarily the only and necessary order of the steps of the method. Unless expressly stated otherwise below, the method proposed herein can be performed in a different order of the disclosed steps without departing from the corresponding method embodiments.

[0008] According to a first aspect of the invention, a system for determining the severity of a patient's respiratory illness is provided. The system includes a user interface configured to provide the patient with instructions for stating a phrase, and the user interface is also configured to provide the patient with instructions for performing a physical action. The system further includes a receiving device configured to receive acoustic signals from the patient, and a measuring unit configured to detect movement of the patient. The system also includes an analysis device configured to analyze the received acoustic signals with respect to the severity of the respiratory illness, configured to analyze the detected patient movement with respect to the physical action guided by the user interface, and configured to provide an analysis result of the received acoustic signals indicating the severity of the patient's respiratory illness. The analysis device is configured to determine whether the patient's movement corresponds to a physical action guided by the user interface, and the user interface is configured to instruct the patient to state a phrase when the detected patient movement corresponds to a physical action guided by the user interface, and / or the user interface is configured to repeat the instruction to the patient when the detected patient movement does not correspond to a physical action guided by the user interface.

[0009] This system can determine the severity or extent of a patient's illness, which is related to the patient's respiratory system. Respiratory diseases often affect, for example, a patient's speech or breathing, and therefore acoustic detection can be performed by analyzing the sounds produced by the patient. A system according to this aspect of the invention includes an interface for providing instructions to the patient. This interface can be, for example, an optical or acoustic interface, such as a screen where the patient can read the instructions, or a speaker or headphones that provide voice instructions to the user. These instructions can prompt the patient to utter phrases, which may be polysyllabic sentences. The sentence may include several different pronunciations because they are affected by the respiratory disease, so they are suitable for detecting the respiratory disease. Furthermore, the sentence may also have a positive meaning so as to unconsciously influence the patient. When the phrase is uttered by the patient, a receiving device detects the patient's acoustic signal. The receiving device may be a microphone that records the patient's speech and related sounds. An analysis device analyzes the received acoustic signal in relation to the severity of the respiratory disease. The analysis results are provided, which are a measurement of the severity or extent of the patient's respiratory disease. Severity can be indicated by providing a score or by providing a trend of the disease. The results can be provided to the patient via the interface. The results can also be stored or transmitted to caregivers or physicians. According to the present invention, the severity of a patient's symptoms can be objectively assessed without requiring explicit patient input associated with a questionnaire.

[0010] The interface can be configured to provide instructions to the patient to perform a physical action. This action can be a specific movement or a series of movements that can be repeated. The number of repetitions may depend on the patient's physical condition, such as age, sex, disease severity, or past measurements / examinations of disease severity. The physical action may be adapted to accelerate the patient's breathing, which can facilitate the analysis of acoustic signals regarding the patient's respiratory disease. In this embodiment of the invention, the system includes a measuring unit that detects the patient's movement. An analysis device is configured to analyze the detected patient movement in relation to the physical action. The analysis device can compare the detected movement with the physical action and detect whether the movement corresponds to the physical action instructing the user. To compare the detected patient movement with the physical action, a template matching algorithm can be performed. Furthermore, it may be advantageous to examine the differences in acoustic signals before and after performing the physical action. Patients with higher disease severity may exhibit greater differences. This can often also provide additional information about the severity of the patient's disease.

[0011] The analysis device can compare detected patient movements with body movements guided by a user interface. In this embodiment of the invention, the analysis device can determine whether the patient complied with and correctly performed the body movements.

[0012] If the detected movement corresponds to a physical action and the patient follows the instruction, the user interface can guide the patient to utter the phrase. Otherwise, if the analysis device cannot detect a movement corresponding to a physical action, the user interface can repeat the instruction to the patient to perform the physical action. This can be repeated several times. Alternatively, the user interface can inform the patient of the importance of performing the physical action, as this is necessary for accurate and reliable results in analyzing the severity of the patient's respiratory illness. Chatbots can be provided to communicate with patients. Furthermore, the system can notify the patient's caregiver or physician about the patient's inability or unwillingness to perform a physical action. Chatbots can also be used for data validation, such as confirming the patient's emotional / well-being status, or interacting with the patient through the chatbot to obtain more emotional / well-being data. Additionally, interactive chatbots can tailor their interactions with patients based on detected emotional / well-being status to support the acquisition of additional reliable data. For example, if the patient is in a bad mood, the chatbot can say encouraging phrases to encourage the patient.

[0013] In one embodiment of the present invention, the respiratory disease is chronic obstructive pulmonary disease.

[0014] Respiratory diseases can be chronic obstructive pulmonary disease (COPD). Alternatively, the system according to this embodiment of the invention can be configured to detect other respiratory diseases, such as asthma.

[0015] In one embodiment of the invention, the received acoustic signal from the patient is the patient's speech, and the analysis device is configured to analyze the received acoustic signal in relation to phrases described in a user interface.

[0016] In this embodiment of the invention, the received acoustic signal from the patient is the speech of the patient uttering a phrase. The analysis device can analyze the acoustic signal and determine whether the patient uttered the phrase as instructed by the user interface. Therefore, reliable and accurate analysis of the acoustic signal regarding respiratory diseases can be ensured, as this analysis is best performed if the patient utters the phrase as instructed. Alternatively, sounds not directly related to the patient's speech, such as breathing or coughing, can be detected and analyzed. Furthermore, words or phrases spoken by the patient that are unrelated to the instructed phrase can be analyzed by the analysis device.

[0017] In one embodiment of the invention, the analysis device is configured to analyze received acoustic signals from a patient with respect to at least one of the following: breathing, shortness of breath, wheezing, breathing tone, cough frequency, mood, well-being, voice tone, flu or infection status, voice timbre, voice amplitude, and combinations thereof, thereby deriving the severity of the patient's respiratory illness.

[0018] To determine the severity of a patient's respiratory illness, analytical devices may consider several parameters. Which parameter or combination of parameters the analytical device uses to determine the severity of the respiratory illness can depend on the disease being detected or classified.

[0019] In one embodiment of the invention, the analysis device is configured to analyze the received acoustic signals relative to the severity of the respiratory disease based on a comparison of the received acoustic signals with data derived from multiple patients.

[0020] To determine the severity of a respiratory illness, in this embodiment of the invention, the received acoustic signals from a patient are compared with data received from multiple patients. Multiple patients may suffer from respiratory illnesses, and they may have varying degrees of illness severity. The illnesses of multiple patients can be categorized by a physician, thereby providing a severity score. The severity of a patient can be categorized based on the similarity between the received acoustic signals and data from patients with similar severity levels. Alternatively, an artificial intelligence module can be used to determine the severity of the illness. The artificial intelligence module can be trained using a dataset of multiple patients, including their acoustic signals and corresponding severity scores.

[0021] In one embodiment of the invention, the system is a communication device, such as a telephone, smartphone, tablet computer, smartwatch, or smart glasses.

[0022] The system can be a communication device in which appropriate applications are installed. A screen or speaker can be used as a user interface, while a microphone can be used as a receiving device for receiving acoustic signals from the patient. The inertial measurement unit of the communication device can be used as a measuring unit for detecting the patient's movement, and the analysis device can be the processor of the communication device. The communication device can establish a connection via a data connection or a voice connection to guide the patient via the Internet or via telephone calls. The received acoustic signals and / or measured movement can be transmitted via the connection and can be analyzed by a server acting as the analysis device.

[0023] In one embodiment of the invention, the measurement unit includes an inertial measurement unit, which includes an accelerometer, a gyroscope, and / or a barometric pressure sensor.

[0024] The measurement unit is configured to detect patient movement. This can be achieved using an inertial measurement unit (IMU). An IMU may include one or more accelerometers and / or gyroscopes. A barometric pressure sensor can also be used to detect patient movement, as the relative change in the height of the barometric pressure sensor, and therefore the relative change in the patient's height, can be determined.

[0025] In one embodiment of the present invention, the measuring unit includes a camera.

[0026] A camera can record video or a series of images of a patient. By analyzing this video or images from the camera, the patient's movement can be determined. In addition to an inertial measurement unit (IMU), a camera can be used to improve the reliability of detecting incorrect or erroneous movements of the patient when the IMU signal is interfered with (e.g., due to coughing or talking during movement or ambient noise). Furthermore, data from the camera can be processed to provide additional objective parameters about the patient's current health status. In particular, video data can be processed to assess the patient's emotional / well-being state, thereby improving assessments based solely on voice tone. Emotional / well-being state can be assessed from imaging data using facial expression classifiers, such as nearest neighbor classifiers, neural networks, SVMs, Bayesian networks, AdaBoost classifiers, and multilevel hidden Markov models.

[0027] In one embodiment of the invention, the body movements guided by the user interface may be a sit-stand test, a forced exhalation movement, a timed standing and walking movement, and / or a Valsalva movement.

[0028] Physical movements performed by the patient can be actions that put stress on the patient and increase heart rate and respiratory rate, such as sit-to-stand tests or getting up and walking. Alternatively or additionally, physical movements can be movements or actions of the patient's airway, such as forced exhalation or the valsalva maneuver.

[0029] According to another aspect of the invention, a method for determining a patient's physical condition is provided. The method includes the steps of: providing the patient with instructions to utter a phrase, receiving acoustic signals from the patient, analyzing the received acoustic signals relative to the severity of a respiratory illness, and providing an analysis result of the received acoustic signals, the analysis result indicating the patient's physical condition.

[0030] The method according to the invention determines a patient's physical condition. In a first step, the patient is given instructions to utter a phrase. In a second step, acoustic signals from the patient are received, which may be the patient's voice and / or other sounds produced by the patient. In a third step, the received acoustic signals are analyzed in relation to the severity of the patient's respiratory illness. In a fourth step, the analysis results of the received acoustic signals are provided, indicating the patient's physical condition.

[0031] The method also includes the following steps: providing the patient with instructions to perform physical movements, detecting the patient's movements, and analyzing the detected patient movements in relation to the physical movements.

[0032] The method also includes steps of providing the patient with instructions to perform a physical action and detecting the patient's movement, followed by steps of analyzing the detected patient movement in relation to the physical action to determine whether the patient's movement corresponds to a physical action. If the detected movement does not correspond to a physical action, the instruction is repeated to the patient; if the detected movement corresponds to a physical action, the instruction to utter a phrase is provided to the patient. These steps are preferably performed before the first step of providing the instruction to utter a phrase. Therefore, it can be ensured that the patient is instructed to utter a phrase only after the physical action has been performed. Furthermore, it may be advantageous to examine the difference in acoustic signals before and after performing the physical action. Patients in poorer physical condition may exhibit a greater difference. This can often also provide additional information about the patient's physical condition.

[0033] In this embodiment of the invention, the method is executed automatically by a system for determining the severity of a patient's respiratory illness. The method can be performed by a communication device, such as a smartphone, with or without a network connection. No human operator, such as a doctor, is required to perform any steps of the method.

[0034] According to another aspect of the present invention, a computer program element is provided that, when executed on a processing unit, instructs the processing unit to perform a method according to any of the foregoing embodiments.

[0035] Computer program elements can be executed on one or more processing units, which are instructed to perform methods for determining a patient's physical condition.

[0036] According to another aspect of the present invention, a processing unit is provided, which is configured to execute computer program elements according to the foregoing embodiments.

[0037] The processing unit can be, for example, a processor in a communication device such as a telephone, smartphone, tablet, smartwatch, or smart glasses. The processing unit can also be distributed across one or more different devices, allowing one part of the computer program elements to execute on the communication device while another part executes, for example, on a server.

[0038] Therefore, the benefits provided by any of the above aspects also apply to all other aspects, and vice versa.

[0039] In summary, the present invention relates to a system and method for determining the severity of a patient's respiratory illness. The system guides the patient to narrate a phrase. The system receives the patient's narrated phrase as an acoustic signal and analyzes the acoustic signal in relation to the severity of the respiratory illness. The analysis results are provided, indicating the severity of the patient's respiratory illness.

[0040] The above aspects and embodiments will become apparent and elucidated with reference to the exemplary embodiments described below. Exemplary embodiments of the invention will now be described with reference to the following drawings: Attached Figure Description

[0041] Figure 1 A schematic setup of a system for determining the severity of a patient’s respiratory disease according to a first embodiment of the present invention is shown.

[0042] Figure 2 A schematic setup of a system for determining the severity of a patient’s respiratory disease according to a second embodiment of the present invention is shown.

[0043] Figure 3 A block diagram is shown for a method to determine the severity of a patient's respiratory illness.

[0044] Figure 4 A block diagram of a method for determining the severity of a patient's respiratory disease according to an embodiment of the present invention is shown. Detailed Implementation

[0045] Figure 1A schematic setup of a system 100 for determining the severity of a respiratory illness in patient 140 according to a first embodiment of the present invention is shown. A user interface 110 guides patient 140 to utter a phrase 151. A receiving device 120 receives an acoustic signal 161 from patient 140, which may be the voice of patient 140 uttering the phrase 151. An analysis device 130 analyzes the acoustic signal in relation to the patient's respiratory illness. The analysis result 170 is provided. The result 170 may be provided to patient 140 and / or patient 140's caregiver or physician. A processing unit 200 may be communicatively connected to the user interface 110, the receiving device 120, and the analysis device 130.

[0046] Figure 2 A schematic setup of a system 100 for determining the severity of a respiratory illness in a patient 140 according to a second embodiment of the present invention is shown. A user interface 110 is configured to provide instructions to the patient 140 to perform a body movement 152 and to provide instructions to the patient to utter a phrase 151. The patient 140 may perform a movement 162, which may correspond to the body movement 152. A measurement unit 180 is configured to detect the movement 162 of the patient 140. The measurement unit 180 may include an inertial measurement unit 181 and / or a camera 182. An acoustic signal 161 from the patient 140 is received by a receiving device 120, which may be the patient 140's speech uttering the phrase 151. An analysis device 130 analyzes the detected movement 162 in relation to the instructed body movement 152. The analysis device 130 analyzes the acoustic signal 161 in relation to the patient 140's respiratory illness. The analysis of the acoustic signal 161 may be performed only if the detected movement 162 corresponds to the instructed body movement 152. The result 170 of the analysis is provided. The results can be provided to patient 140 and / or patient 140's caregivers or physicians. Processing unit 200 can be communicatively connected to user interface 110, receiving device 120, measurement unit 180, and analysis device 130.

[0047] Figure 3 A block diagram of a method for determining the severity of a respiratory illness in patient 140 is shown. The method includes a first step of providing patient 140 with instructions for uttering a phrase 151. This is followed by a second step of receiving an acoustic signal 161 from patient 140. A third step includes analyzing the received acoustic signal 161 in relation to the severity of the respiratory illness. A fourth step includes providing the analysis results of the received acoustic signal 161, indicating the severity of the respiratory illness in patient 140.

[0048] Figure 4 A block diagram of a method for determining the severity of a respiratory disease in patient 140 according to an embodiment of the present invention is shown. Figure 3Compared to the method shown, this embodiment of the invention includes three additional steps, which can preferably be performed before the first step. However, different order of steps is also possible. The three additional steps are: providing instructions to the patient 140 for performing body movements 152, detecting movement 162 of the patient 140, and analyzing the detected movement 162 of the patient 140 relative to body movements 152.

[0049] While the invention has been illustrated and described in detail in the accompanying drawings and foregoing description, such illustrations and descriptions should be considered illustrative or exemplary rather than restrictive. The invention is not limited to the disclosed embodiments. Other variations to the disclosed embodiments will be understood and implemented by those skilled in the art in practicing the claimed invention through study of the drawings, disclosure, and dependent claims.

[0050] In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite articles "a" or "an" do not exclude multiple. The fact that certain measures are referenced in mutually different dependent claims does not indicate that a combination of these measures cannot be used advantageously. Any reference signs in the claims should not be construed as limiting the scope.

Claims

1. A system (100) for determining the severity of a respiratory illness in a patient (140), the system (100) comprising: User interface (110) The user interface (110) is configured to provide the patient (140) with instructions for narrating phrases (151), and the user interface (110) is configured to provide the patient (140) with instructions for performing physical actions (152); The receiving device (120) is configured to receive the acoustic signal (161) of the patient (140). The measuring unit (180) is configured to detect the movement (162) of the patient (140). Analytical equipment (130) The analysis device (130) is configured to analyze the received acoustic signal (161) relative to the severity of the respiratory disease, and the analysis device (130) is configured to analyze the detected movement (162) of the patient relative to the body movements (152) guided by the user interface (110), and The analysis device (130) is configured to provide the results (170) of the analysis of the received acoustic signal (161), the results (170) indicating the severity of the respiratory disease of the patient (140). Its features are: The analysis device (130) is also configured to determine whether the patient's (140) movement (162) corresponds to a body movement (152) guided by the user interface (110), and The user interface (110) is configured to instruct the patient (140) to utter the phrase (151) when the detected movement (162) of the patient corresponds to the body movement (152) guided by the user interface (110), and / or The user interface (110) is configured to repeat the instruction to the patient (140) if the detected movement (162) of the patient (140) does not correspond to the body movement (152) guided by the user interface (110).

2. The system (100) according to claim 1. The respiratory disease mentioned is chronic obstructive pulmonary disease.

3. The system (100) according to any one of claims 1-2. The acoustic signal (161) received from the patient (140) is the patient's voice, and The analysis device (130) is configured to analyze the received acoustic signal (161) relative to a phrase (151) narrated as directed by the user interface (110).

4. The system (100) according to any one of claims 1-2. The analytical device (130) is configured to analyze the received acoustic signals (161) of the patient (140) relative to at least one of the following: breathing, shortness of breath, wheezing, breathing tone, cough frequency, mood, well-being, voice tone, flu or infection status, voice timbre, voice amplitude and combinations thereof, thereby deriving the severity of the respiratory disease of the patient (140).

5. The system (100) according to any one of claims 1-2. The analysis device (130) is configured to analyze the received acoustic signal (161) relative to the severity of the respiratory disease based on a comparison of the received acoustic signal (161) with data derived from multiple patients.

6. The system (100) according to any one of claims 1-2. The system (100) mentioned therein is a communication device.

7. The system (100) according to any one of claims 1-2. The system (100) includes a telephone, smartphone, tablet computer, smartwatch or smart glasses.

8. The system (100) according to any one of claims 1-2. The measurement unit (180) includes an inertial measurement unit (181), which includes an accelerometer, a gyroscope, and / or a barometric pressure sensor, and / or The measuring unit (180) includes a camera (182).

9. The system (100) according to any one of claims 1-2. The body movements (152) guided by the user interface (110) are sit-up tests, forced exhalation movements, timed standing and walking, and / or Valsalva movements.

10. A computer program element that, when executed on a processing unit (200), instructs the processing unit to perform a method comprising the steps of: Provide the patient (140) with instructions to perform physical actions (152). The movement (162) of the patient (140) was detected. The movement (162) of the patient (140) detected relative to the body movement (152) is analyzed. Determine whether the patient’s movement corresponds to the body movement (152). If the detected movement (162) of the patient (140) does not correspond to the body movement (152), the instruction is repeated to the patient (140). If the detected movement (162) of the patient corresponds to the body movement (152), the patient (140) is given an instruction to utter a phrase (151). Acoustic signals (161) from the patient (140) are received. The received acoustic signals (161) were analyzed relative to the severity of the respiratory disease, and The results of the analysis of the received acoustic signal (161) are provided, the results indicating the severity of the respiratory disease of the patient (140).

11. A processing unit (200) configured to execute a computer program element according to claim 10.

Images