Medical monitoring system based on sound analysis in a medical environment

• US 9,659,149 B2
• Filed: 09/25/2012
• Issued: 05/23/2017
• Est. Priority Date: 10/17/2011
• Status: Active Grant

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Kohlrausch, Armin Gerhard, Falck, Thomas, Den Brinker, Albertus Cornelis
• Primary Examiner(s): Chang, Li-Wu
• Application Number:
  US14/351,603
• Publication Number:
  US 20140275856A1
• Time in Patent Office: 1,701 Days
• Field of Search: None
• CPC Class Codes: A61B 2505/03 Intensive care
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 5/0006 ECG or EEG signals
• CPC Class Codes: A61B 5/0077 Devices for viewing the surface of the body, e.g. camera, magnifying lens
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/333 Recording apparatus specially adapted therefor
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/38 Acoustic or auditory stimuli
• CPC Class Codes: A61B 5/389 Electromyography [EMG]
• CPC Class Codes: A61B 5/398 Electrooculography [EOG], e.g. detecting nystagmus; Electroretinography [ERG]
• CPC Class Codes: A61B 5/4815 Sleep quality
• CPC Class Codes: A61B 5/4884 inducing physiological or psychological stress, e.g. applications for stress testing
• CPC Class Codes: G16H 40/63 for local operation

Abstract

The invention relates to a medical monitoring system (100) based on sound analysis in a medical environment. A sound level analyzer (SLA, 10) is capable of providing an indicator for perceived levels of sound from a number of sound events, and a data storage modality (DSM, 20) is receiving and storing said indicator for perceived levels of sound and also corresponding information from an associated patient monitoring system (PMS, 60) handling information indicative of a physical and/or mental condition of a patient under influence by sound. A sound event analyzer (SEA, 30) is further being arranged for performing, within a defined time window, an overall sound analysis (ANA, 50) related to physical and/or mental condition of the patient that may be influenced by sound in order to assist or supervise medical personal with respect to the acoustic environment.

Claims

1. A medical monitoring system comprising a digital data processor configured to implement:

a sound level analyzer configured to receive an audio signal from a medical environment surrounding a patient and provide an indicator for perceived levels of sound generated by sound events occurring in the medical environment;

a data storage modality configured to receive and store the indicator for the perceived levels of sound and corresponding information, obtained from an associated patient monitoring system, and indicative of at least one of physical or mental condition of the patient;

a sound event analyzer configured to perform an overall sound analysis related to the at least one ofthe physical or mental condition of the patient based on the indicator and the corresponding information stored in the data storage; and

a sound scene analyzer configured to analyze and classify the audio signal, create a list of one or more sound sources that generate the sound events occurring in the medical environment surrounding the patient, and differentiate avoidable sources of negative influence on rest or sleep of the patient from unavoidable sources of negative influence,

wherein the sound scene analyzer is configured to distinguish unavoidable and essential alarm sounds from avoidable and non-essential alarm sounds based on training information from at least one of a patient monitoring system or a hospital central monitoring database, and

wherein the sound event analyzer is configured to identify the sound events occurring in the medical environment based on analyzing tonality, harmonic structure, rhythmicity, predictability, spectral content, measures of onset steepness, percussiveness, and repetitiveness of the audio signal.

2. The medical monitoring system of claim 1 wherein the sound level analyzer comprises a perceptual model for providing perceived loudness.

3. The medical monitoring system of claim 1 wherein the sound level analyzer is further configured to provide a measure of an accumulated acoustic dose.

4. The medical monitoring system of claim 1 wherein the associated patient monitoring system comprises information related to a physical activity level of the patient.

5. The medical monitoring system of claim 1 wherein the associated patient monitoring system comprises information comprising at least one of:

sleep or rest monitoring devices, electrodiagnosis, including EEG, ECG, EOG, EMG, actigraphy, movement detection, video-based monitoring, or sound-based monitoring.

6. The medical monitoring system of claim 1 wherein the overall sound analysis comprises information related to at least one of quality or quantity of the rest or sleep of the patient.

7. The medical monitoring system of claim 6 wherein the overall sound analysis comprises a measure of one or more of:

average sound level;

sound impact based on perceptual model estimate of one or more restorative period;

estimated annoyance;

or

an overall sleep or rest indicator, possibly a qualitative indicator.

8. The medical monitoring system of claim 1 further including one or more microphones, the one or more microphones being in communication with the monitoring system and configured to receive audio signals from the patient in the medical environment.

9. The medical monitoring system of claim 1 wherein the monitoring system is configured to communicate with one or more communication devices, the communication devices being accessible by at least one of medical personnel, visitors or patients.

12. The medical monitoring system of claim 1 wherein the sound scene analyzer is configured to differentiate avoidable sources of negative influence from unavoidable sources based on known temporal and spectral characteristics of the sound events, the temporal and spectral characteristics including at least one of pitch range of speech, mel-frequency cepstral coefficients of speech, and envelope variation of speech.

13. The medical monitoring system of claim 1 wherein the sound scene analyzer is configured to differentiate avoidable speech from unavoidable speech involving the patient.

14. The medical monitoring system of claim 13 wherein the sound scene analyzer is configured to differentiate avoidable speech from unavoidable speech involving the patient based on a dedicated beamforming technique using one or more microphones that capture audio signals produced in close vicinity of the patient.

15. The medical monitoring system of claim 1 wherein the sound event analyzer is configured to identify alarm sounds generated in the medical environment based on at least one of the tonality, harmonic structure, and repetitiveness of the audio signal, and in an event an alarm sound is identified, the sound scene analyzer is configured to distinguish avoidable alarm sounds from unavoidable alarm sounds by observing the duration of the identified alarm sound and determining whether the observed duration exceeds a predetermined duration.

16. The medical monitoring system of claim 15 wherein the sound event analyzer is configured to determine the predetermined duration based on at least one of a history of alarm sounds previously generated in the medical environment or urgency of response previously given to a specific alarm sound.

10. A method for monitoring sound in a medical environment, the method comprising using a computer processor for:

receiving an audio signal from a medical environment surrounding a patient, and providing an indicator for perceived levels of sound generated by sound events occurring in the medical environment;

receiving and storing, in a data storage modality, the indicator for the perceived levels of sound and corresponding information, obtained from an associated patient monitoring system, and indicative of at least one of physical or mental condition of the patient;

performing an overall sound analysis related to the at least one of the physical and/or mental condition of the patient based on the indicator and the corresponding information stored in the data storage;

analyzing and classifying the audio signal;

creating a list of one or more sound sources that generate the sound events occurring in the medical environment surrounding the patient; and

differentiating avoidable sources of negative influence on rest or sleep of the patient from unavoidable sources of negative influence;

wherein the analyzing and classifying step includes identifying alarm sounds generated in the medical environment based on at least one of the tonality, harmonic structure, and repetitiveness of the audio signal, and in an event an alarm sound is identified, distinguishing, in the differentiating step, avoidable alarm sounds from unavoidable alarm sounds by observing the duration of the identified alarm sound and determining whether the observed duration exceeds a predetermined duration, and

wherein the predetermined duration is determined based on at least one of a history of alarm sounds previously generated in the medical environment or urgency of response previously given to a specific alarm sound.

11. A computer program product, tangibly embodied in a non-transitory computer readable storage medium, comprising instructions being operable to cause a data processing system to monitor sound in a medical environment according to claim 10.