Enhanced detection and analysis of bioacoustic signals

Abstract

The invention relates to enhanced detection and analysis of bioacoustic signals. Devices and methods are provided for predicting risk and the likelihood of postoperative gastrointestinal tract injury based on regression analysis of multiple spectral events related to intestinal sound, where the values at which these events resulting from ambient noise were erroneously increased are reduced or eliminated.

Description

[0001] This application is a divisional application, and the original application it is targeting is a Chinese invention patent application with a filing date of April 16, 2020, the applicant is "Intech Medical Corporation", the invention name is "Enhanced Detection and Analysis of Bioacoustic Signals", and the application number is 202080029144.3. Technical Field

[0002] The present invention relates to enhanced detection and analysis of bioacoustic signals, and in particular, to intestinal audio analysis devices and methods for predicting the likelihood of the occurrence of gastrointestinal damage. Background Art

[0003] Postoperative ileus (POI) is an acute gastrointestinal paralysis that occurs 2 to 6 days after surgery, causing adverse side effects such as nausea and vomiting, abdominal pain and bloating. It occurs most frequently during gastrointestinal surgery. The lack of the ability to predict which patients are likely to experience these intestinal problems leads to increased postoperative complications, length of stay, and readmission rates. There is also a lack of intestinal audio analysis devices and methods that more accurately provide risk level analysis by limiting and / or eliminating environmental noise that causes erroneous data points, where the devices and methods are more independent.

[0004] Therefore, there remains a need for devices and methods to reduce these problems, wherein healthcare providers are better able to reduce hospitalizations and readmissions and avoid exacerbations through more accurate feeding guidance, wherein this is achieved by improving the ability to obtain more accurate risk level information related to the patient's likelihood of developing a gastrointestinal injury (e.g., post-surgery). Summary of the invention

[0005] The present invention involves the use of a gut audio analysis device to predict gastrointestinal damage before any clinical manifestations or symptoms occur.

[0006] In certain embodiments, a gut audio analysis device is provided having a patient interface adapted to be attached to a surface of a patient's abdomen for a period of time post-operatively. The device has a diaphragm that vibrates in response to gut sounds to generate acoustic pressure waves that amplify gut sounds emitted within the patient's abdomen. This allows audio data associated with gut sounds to be collected through an acoustic chamber that receives the amplified sounds that are then transmitted to an audio collection device located in or near the acoustic chamber. The gut audio analysis device has an external housing and an internal computer and memory and one or more algorithms for providing instructions to the system to perform various required steps to provide accurate collected data and analysis. The one or more algorithms can analyze the collected audio data for false signals due to ambient noise, analyze two or more spectral event values ​​(e.g., MH4) over time, generate a slope of a linear regression analysis for comparison with a predetermined slope threshold to make a binary prediction associated with the likelihood and risk of GII, wherein the risk is communicated, for example, on a user interface display.

[0007] In other embodiments, a method of using a gut audio analysis device is provided. In certain embodiments, a method of predicting the likelihood and risk level of GII occurrence prior to clinical symptoms is provided. Intestinal sounds are recorded to generate audio data of the patient's intestinal sounds. The audio data is processed to identify certain predicted spectral events (e.g., MH4), and the audio data is analyzed for false signals due to environmental noise. If necessary, certain embodiments provide mitigation for false signals to ensure that a more accurate total number of identified predicted spectral events is obtained for linear regression analysis. The slope obtained using the spectral event values ​​over time is associated with the likelihood of gastrointestinal injury occurring (e.g., postoperatively), and based on the association, a likelihood-based risk level is provided to the user.

[0008] Embodiments of the present invention provide improved control of environmental noise, which increases the accuracy of data used to make correlations based on which postoperative GII is predicted prior to clinical symptoms. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 An example of the device described herein is shown.

[0010] Figure 2 A top view of an example of an apparatus described herein is shown.

[0011] Figure 3 An exploded view of the apparatus described herein is shown.

[0012] Figure 4 An exploded view of the apparatus described herein is shown.

[0013] Figure 5 A bottom view of an example of a device described herein is shown.

[0014] Figure 6 A front view of a split housing showing an example of the apparatus described herein is shown.

[0015] Figure 7 A side view of a split housing showing an example of the apparatus described herein is shown.

[0016] Figure 8 A rear view of a split housing of an example of the apparatus described herein is shown.

[0017] Fig. 9 The interior of the top of the housing is shown without the user interface of an example of the device described herein.

[0018] Fig.10 An interior view of a lower portion of a housing of an example of a device described herein is shown.

[0019] Fig.11 A bottom view of the lower portion of the housing of an example auxiliary audio device and a base without the devices described herein is shown.

[0020] Fig.12 A side view of an example of an apparatus described herein is shown.

[0021] Fig.13 A front view of an example of an apparatus described herein is shown.

[0022] Fig.14 A rear view of the device described herein is shown.

[0023] Fig.15 is an example spectrogram illustrating spectral events contained in recorded abdominal sounds.

[0024] Fig.16 is a graph plotting the temporal changes in a specific spectrum event (MH4) in patients with and without GI tract injury.

[0025] Fig.17 is a flow chart of an embodiment of a method of predicting gastrointestinal injury.

[0026] Fig.18 is a device (such as Figures 1 to 14 A block diagram of an embodiment of the architecture of a device) shown in , which can process the collected data to assist in gastrointestinal injury prediction and risk assessment. DETAILED DESCRIPTION

[0027] Gastrointestinal injury (GII) is a common problem after surgical procedures. Disclosed herein are systems and methods for predicting GII based on a patient's intestinal sounds. As described below, the disclosed systems and methods identify discrete acoustic spectral events in intestinal sounds that can be used to predict subsequent GII and, in some cases, postoperative GII. These spectral events are good indicators of intestinal function and / or dysfunction because the sounds are produced by motor activity in the intestine.

[0028] In the following disclosure, various embodiments are described. It is to be understood that these embodiments are merely example implementations of the present invention, and other embodiments are possible. All such other embodiments are within the scope of the present disclosure.

[0029] Certain embodiments include a device including a housing, a display, a processor, and at least one audio collection device. In certain embodiments, there is a primary audio collection device and a secondary audio collection device. In some embodiments, the primary audio collection device can be attached to or inserted into a subject.

[0030] Figure 1 to Figure 2 Examples of embodiments of apparatus are provided. Figure 1 and Figure 2 An example of a device is partially shown, the device comprising a housing 101, at least one button 102 for a user to interact with the device and control the operation of the device, and a user interface 103. The user interface may be a graphical user interface (GUI).

[0031] In some embodiments, the device includes an auxiliary audio collection device. In some embodiments, the auxiliary audio collection device can be a microphone or other sound receiving mechanism that can collect ambient noise. In other embodiments, the ambient noise from the main microphone data is signal subtracted to achieve true noise cancellation. In some embodiments, the device described herein can be used in a method for predicting or diagnosing GII. In some embodiments, the systems and methods described herein can include predicting GII before symptoms appear. In some cases, the auxiliary audio collection device can remove interference associated with ambient noise that may interfere with the collection of intestinal sounds. This configuration can produce surprising and unexpected results that more accurately predict GII. In some cases, GII prediction is performed postoperatively. In some embodiments, the environmental audio collection device further includes a diaphragm.

[0032] Figure 3 to Figure 4 An exploded view of an example of a device is shown. Figure 3 and Figure 4A device is shown comprising a user interface 103 , a separated top portion of a housing 104 , a computer 105 , a lower portion of a housing 106 , at least one fastening means 107 , a membrane 108 , a gasket 109 and an adhesive wafer 110 . Figure 5 An example of a device with a secondary audio collecting device 111 is shown.

[0033] Figures 8 to 10 Different views of the top of housing 104 and the bottom of housing 106 are shown. Fig. 9 An internal view of the top of the housing 104 is shown, and Figure 10 to Figure 11 Different views of the lower portion of the housing 106 are shown. Figure 12 to Figure 14 Different views of some embodiments of the device of the invention are shown.

[0034] The GUI can be configured to allow a user to interact with the device and collect audio data from a subject. Certain embodiments include a housing. The housing can include an upper portion and an adhesive sheet. The size (width and length) of the adhesive sheet can vary. For example, the sheet can have a width and length that is the same as or less than the bottom surface area of ​​the unit. The sheet can have different thicknesses. The shape of the sheet is designed to best fit the unit to the patient for safe monitoring / recording / collection of GII events. The housing can include a detachable top and lower portion.

[0035] In the embodiment where the housing comprises a detachable top and lower portion, the detachable top and lower portion are fixed using an attachment device. The attachment device may include screws, fasteners, pins, brackets, wedges, rivets, clips, etc.

[0036] Embodiments of the system may be used to predict gastrointestinal damage. Embodiments of the system may include a data collection device, a patient interface, and a computer 105. The computer 105 or data collection device may be a separate device that collects and / or stores data retrieved from the patient interface and the computer 105. The patient interface may include any device capable of collecting audio data generated within the patient's intestine. In some embodiments, the patient interface includes a portable (e.g., handheld) digital audio recorder. In this case, the patient interface may include an integrated microphone (not shown) for capturing intestinal sounds, and wherein the integrated microphone may be placed in or near the acoustic chamber. For example, the acoustic chamber may be formed between the diaphragm 108 and the lower portion of the housing 106. The acoustic chamber greatly increases data collection by amplifying the patient's intestinal sounds relative to ambient noise; increases the ability to reduce ambient noise at the audio collection point; provides simplicity of audio data collection by reducing the inventory of extraneous components; and provides continuous audio data collection capabilities in combination with the patient interface, diaphragm, and audio data collection device (e.g., a microphone within the device of the present invention placed in or near the acoustic chamber).

[0037] The patient interface can be a device applied directly to the abdomen of the patient to detect intestinal sounds. In some embodiments, the patient interface includes a stethoscope head or is similar to a stethoscope head in design or function. The stethoscope head can include a diaphragm placed in contact with the patient and vibrating in response to the sounds produced in the body. These sounds can be transmitted to a microphone that can transmit signals to a computer 105, which can optionally transmit the data to a data collection device. In some embodiments, the patient interface can transmit sound through a pipe extending between the patient interface and a sound collection device (such as a microphone that can be located in an acoustic chamber). In some embodiments, the patient interface can convert sound waves into digital signals that can be processed by the computer 105. For example, the sound pressure waves created by the vibration of the diaphragm can travel to the microphone in the inner cavity of the pipe. In some embodiments, the patient interface can include a microphone or other device that converts the sound pressure waves into digital signals, which can be processed and analyzed by the system to predict GII. As an example, a microphone or other device for converting the sound pressure waves into digital signals can be placed in or communicate with the acoustic chamber, which is located between the diaphragm 108 and the lower part of the housing 106. In some embodiments, all or part of the patient interface may be disposable to avoid cross contamination between patients.The patient interface may be used with a disposable sheath or sleeve (not shown) that may be discarded after use.

[0038] The audio data collected by the computer 105 may be stored in an internal memory included by the computer. In some embodiments, the memory may be separate from the computer 105, but in data communication with the computer 105. In some embodiments, the audio data may be stored in a non-volatile memory (e.g., flash memory) of the device. The data may then be transmitted to the computer 105 for processing. In some embodiments, the data and data analysis are transmitted via wires or cables that are used to physically connect the computer 105 to a separate processor or computer, such as a laptop or desktop computer or a handheld or portable device, that has the necessary components for receiving and communicating the data and data analysis. In some embodiments, for example, data and data analytics may be wirelessly transmitted from the device to a separate processor or computer via a suitable wireless protocol, such as Bluetooth or Wi-Fi (IEEE 802.11), or a suitable cellular protocol, such as Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Enhanced Data Rates for GSM Evolution (EDGE), Universal Mobile Telecommunications Service (UMTS), High Speed ​​Packet Access (HSPA), Code Division Multiple Access (CDMA), Evolution-Data Optimized (EV-DO, EVDO, lxEV-DO), Short Message Service (SMS), and Wi-MAX.

[0039] In some embodiments, the separate computer may include a desktop computer. However, it should be noted that substantially any computing device capable of receiving and processing the audio data collected by the computer 105 may be used. Therefore, the separate computer may alternatively take the form of a mobile computer, such as a notebook computer, a tablet computer, a smart phone, or a handheld computer. In some embodiments, the computer 105 may process any data generated by the acoustic sounds received from the patient, and output information through the user interface 103. In some embodiments, the user interface may include a display function, and may also be a touch screen that allows the user to interact with the device and control the operation of the device. For example, the device may be provided with a digital signal processor and appropriate software / firmware that may be used to analyze the collected audio data.

[0040] In some embodiments, patient sounds can be transmitted wirelessly from the patient interface to the device. In some embodiments, the patient interface can have an adhesive surface that enables the interface to be temporarily attached to the patient's skin in a manner similar to electrocardiogram (EKG) leads. In some embodiments, patient data can be transmitted from the patient interface to the computer 105 via a wired connection (via a wire or cable) or wirelessly.

[0041] In some embodiments, the patient interface may include a device having its own integrated microphone (not shown), and the patient sounds picked up by the microphone may be transmitted electronically to the device along a wire or cable. In some embodiments, the device may include a component designed to dock with a patient monitoring system, which may be placed next to the patient for a continuous period of time, such as hours, days, or weeks. Such patient monitoring systems are currently used to monitor other patient parameters, such as blood pressure and oxygen saturation. For example, a patient monitoring system may include a docking station and an associated display. In some embodiments, this enables alarms or notifications to be received at an auxiliary location (e.g., at a nurse's station). The device may also be designed to dock in a free compartment of a station before use. Other means of connecting the device of the present invention are through various ports known in the industry for these types of electronic systems, including, for example: PS / 2, serial port (e.g., DB-25, DE-9 or COM port), parallel port or parallel interface 36-pin port, audio port, S / PDIF, TOSLINK, video port, digital video interface (DVI) (e.g., mini DVI, micro DVI), display port, RCA connector, component video, super video, HDMI, USB (e.g., type A, type C), RJ-45, e-SATA, etc. It will be understood that certain adapters for hard-connecting the present invention to a patient monitoring system are also contemplated. Types of patient monitoring systems are known and include, for example: standard hospital patient monitoring systems for systems fixed to an appropriate location as well as mobile and / or portable monitoring systems; remote and / or wireless; home systems; and / or combinations thereof.

[0042] In some embodiments, the device may not include an internal power source, so patient data can only be collected when docked. In some embodiments, the device may include a power connection, such as an A / C connection, or may include an internal power source, such as a battery. In some embodiments, the device may include a photovoltaic and / or thermal power source, such as a solar cell. In some embodiments, the patient interface may include a power source, such as a battery, a photovoltaic device, and / or a thermoelectric device, which can be used to collect acoustic sound waves and / or process acoustic sound waves into data that can be used to predict GII. For example, the device may have an electrical pin that electrically couples the device to a patient monitoring system to receive power and transfer the collected data to the patient monitoring system. The patient data can be stored in a memory of the patient monitoring system and / or can be transmitted to a central computer to be stored in association with a patient record in an associated medical record database.

[0043] The device may include an electrical port that may receive a plug for an electrical wire or cable. Additionally, the device may include one or more indicator lights, such as light emitting diode (LED) indicators, that convey information to an operator, such as a positive electrical connection to a patient monitoring system and patient signal quality.

[0044] The device can be coupled to a patient monitoring system. In some embodiments, in addition to the external patient interface, the device can include an internal patient interface designed to collect sound from the abdominal cavity. For example, the patient interface can include a small diameter microphone catheter that is left in place after the operation is completed in a manner similar to a drainage catheter. This patient interface may be particularly useful in cases where the patient is obese and it is difficult to obtain a high-quality signal from the skin surface. To avoid electric current entering the patient, the patient interface can include a laser microphone. In this case, a laser beam is guided through the catheter and reflected by a target in the body. The reflected light signal can be received by a receiver that converts the light signal into an audio signal. The slight difference in the distance traveled by the light when it is reflected from the target is detected using interferometry. In some embodiments, the patient interface can include a microphone located at the tip of the catheter.

[0045] The device may include a central processing unit (CPU), such as computer 105, or other processing device, such as a microprocessor or digital signal processor. The device may include a memory, which may include any one or combination of volatile memory elements (e.g., RAM) and non-volatile memory elements (e.g., flash memory, hard disk, ROM).

[0046] The user interface 103 may include components with which a user interacts with the device. For example, the user interface 103 may include a keyboard, a mouse (mouse pad), an interactive touch display, and / or a display device, such as a liquid crystal display (LCD). The device may include one or more buttons 102 that may allow a user to use the device and manipulate the user interface 103, such as to navigate through menus, view data, etc. Alternatively or in addition, the user interface 103 may include one or more buttons and / or a touch screen. One or more I / O devices may be adapted to facilitate communication with other devices and may include one or more electrical connectors and wireless transmitters and / or receivers. Additionally, in the case where the device is also collecting and / or processing data retrieved from a patient, the I / O device may include a microphone.

[0047] In some embodiments, the memory may be a computer-readable medium and may store various programs (i.e., logic), including an operating system and a bowel sound analyzer. The operating system may control the execution of other programs and may also provide scheduling, input-output control, file and data management, memory management, and communication control and related services. The bowel sound analyzer may include one or more algorithms configured to analyze intestinal audio data to predict the likelihood of a patient experiencing GII. In some embodiments, the analyzer may analyze relevant data stored in a database (and such a database may be stored in the computer 105), and may present predictive indicators of GII risk to a user (e.g., a doctor, hospital staff, and / or clinician). In some embodiments, the analyzer may use target signal parameters, signal-to-noise ratio parameters, and noise power estimation parameters to identify specific spectral events of interest. Then, a decision tree analysis that predicts the number of spectral events during a specified time interval may be used to deliver high, medium, or low risk of GII. In some embodiments, the risks associated with each risk level are 83%, 30%, and 0%, respectively, or approximately thereabouts.

[0048] In certain methods of using the device, patient intestinal sounds can be recorded to generate audio data. As described above, sounds can be obtained non-invasively, such as using a stethoscope head or other patient interfaces applied to the skin on or near the patient's abdomen. Alternatively, a device extending into the patient's abdominal cavity can be used to collect sounds. Sounds can be recorded early in the postoperative period, for example, on the day of surgery or the first day after surgery and any desired length of time thereafter. In some embodiments, acoustic sounds are obtained immediately after surgery, and the acoustic sounds can be continuously monitored and analyzed for hours, days, or weeks, as understood by a skilled technician based on the instant disclosure. In some embodiments, sounds are continuously collected. In some embodiments, sounds are collected at predetermined intervals over a period of time. Regardless of when sounds are recorded, they can be recorded for a duration sufficient to achieve identification of spectrum events that predict intestinal function and / or damage. For example, sounds are recorded over a period of about 4 to 6 minutes. In some embodiments, all sounds within the range of 20 Hz to 20,000 Hz are recorded. In some embodiments, sounds beyond the audible range of the human ear are collected and analyzed. Filters can be applied to reduce the frequency range of the recording, thereby reducing the amount of data analyzed. In some embodiments, the auxiliary audio device 111 can work in conjunction with the patient interface to provide improved analysis results. For example, the auxiliary audio collection device can include a microphone that can measure the ambient noise near the patient. The ambient noise can then be subtracted from the acoustic sound collected from the patient to ensure that any acoustic sound analyzed by the device is actually collected from the patient rather than from any external source. In some embodiments, for example, the auxiliary microphone and the integrated microphone of the unit independently collect audio data in a synchronized manner. Both audio data sets are run through the MH4 detector to determine whether the ambient noise may trigger an erroneous MH4 event count from the integrated microphone, and where, if (multiple) ambient sounds meet certain criteria, the ambient data count can be subtracted from the final count. In some embodiments, filters can be used so that only sounds with frequencies of approximately 700 Hz to 1500 Hz are recorded or analyzed, but filters can be incorporated to allow the device to analyze only sounds within a predetermined frequency range. As part of mitigating the effects of ambient noise, an alarm indicator or warning mechanism can be part of the device, where, for example, the alarm indicator or warning mechanism notifies a doctor, caregiver, nurse, or clinician that (multiple) ambient noises must be reduced. There are scenarios where the ambient noise level is too high for the device's noise mitigation strategies to kick in. In such scenarios, no meaningful MH4 values ​​can be obtained. An alert indicator (which can be any combination of a light, noise, audible sound, or a graphic on the device display) can be used to indicate to the user that the ambient noise needs to be reduced and / or controlled.For example, the threshold for triggering the alarm indicator may be based on: the current ambient noise decibel level from the outward-pointing microphone; an analysis of the signal-to-noise ratio of the primary microphone to the outward-pointing microphone; processing the sound from the outward-pointing microphone for a false trigger MH4 value above a preset threshold. Although the sound is described as "recorded", it will be understood that the sound may alternatively be obtained in a simple manner and processed in real time (as described below) without actually recording the sound.

[0049] Once the audio signal is generated, the data can be processed, for example in real time, to identify one or more predicted spectral signals. For example, real time can mean that when the patient generates the sound, the data is processed while being acquired by the device. As described above, the sound generated by the intestine can be the result of intestinal peristalsis, whereby the device can predict the possibility of GII, which means that the device indicates (pre-GII) the possibility of GII occurring after data collection and analysis. Therefore, the sound collected and / or analyzed by the device can provide an indication of how the intestine is functioning. For example, paralysis of a large portion of the intestine will proportionally reduce the number of high-energy propulsive contractions in the intestine, which will result in some loss of higher energy, resulting in a higher frequency acoustic spectrum, which is typical for a normally functioning intestine. As described below, it has been determined that certain predefined spectral events that highly predict whether GII may occur can be identified in the sound. As also described below, each predefined spectral event is defined by specific features or parameters, such as their frequency, amplitude, duration, and separation in time from other spectral events.

[0050] After the spectral events are identified, their number can be totaled for a particular duration (e.g., the total duration of the recording). The total number of predicted spectral events identified is time-stamped and written to a data buffer (buffer) of the device of the present invention. As will be appreciated, the buffer can be stored, for example, in physical memory for temporary storage of data, but it should be understood that the buffer can be in fixed memory of the hardware or as a virtual data buffer in software that points to a location in the physical memory. At this point, the total number of spectral events can be compared with associated data that associates the number of spectral events with the likelihood of subsequent GII. As an example, spectral events designated as "MH4" are identified in the following study. For MH4, if the number of MH4 events observed during the four-minute recording period is less than about 21 times, there is a high risk of GII, if the number of MH4 events observed during the four-minute recording period is greater than about 21 times but less than about 131 times, there is a medium risk of GII, and if the number of MH4 events observed during the four-minute recording period is greater than about 131 times, there is a low risk of GII. Therefore, the number of predefined spectrum events can be used as an indicator to convey the magnitude of the GII risk, where a lower number indicates a greater risk and a higher number indicates a lower risk.

[0051] Once the likelihood of subsequent GII is determined, the risk can be communicated to the user. For example, a computer 105 or other device (such as a separate computer) can be used to perform the analysis and can display the risk level on an associated display (such as a user interface 103), although the prediction can be displayed on a separate display (such as a separate computer monitor). In some embodiments, the prediction can be automatically communicated to the hospital tabulation and / or recording system so that the prediction is automatically stored with the patient record. In some cases, the data can be anonymized and used as aggregated data. In some embodiments, the risk can be communicated as an indicator (i.e., a number). In other embodiments, the risk can be indicated as "high", "medium" or "low". In any case, appropriate action can then be taken relative to the indication, and can include allowing or prohibiting oral feeding. It is worth noting that further records and analysis can be performed on the patient within a few days after the operation to evaluate intestinal function and confirm the initial patient assessment.

[0052] Any features described herein may be combined or substituted as understood by a skilled artisan based on the disclosure and description herein.

[0053] As can be appreciated from the above methods, the risk of GII can be assessed in much the same way that the risk of heart problems is assessed non-invasively with an EKG. In some embodiments, the risk assessment can be performed in real time.

[0054] A clinical study was performed to evaluate the feasibility of the disclosed system and method. One goal of the study was to confirm that spectral events present in bowel sounds in the early postoperative period were indeed associated with subsequent GII, before clinical manifestations and symptoms appeared. Another goal of the study was to develop a model for predicting GII that could be implemented as a simple, noninvasive, bedside test that would enable hospitals and other institutions to use analysis of bowel sounds to risk stratify patients who present with clinically significant GII.

[0055] Patients scheduled for inpatient surgery were enrolled in the study using an IRB-approved protocol. Patients undergoing abdominal and non-abdominal surgery were included. Patients admitted to the ICU postoperatively were excluded from the remainder of the study.

[0056] For the study, an apparatus for digitally recording abdominal sounds was assembled using a two-channel digital audio recorder (Microtrak II, M-Audio, Irwindale, California), a condenser microphone (ATR35s, Audio-Technica Ltd., Leeds, UK), a stethoscope tube, and a stethoscope head. To record bowel sounds, the stethoscope head was applied to the upper and lower anterior abdominal wall, and the two channels were recorded simultaneously for periods of 5 to 6 minutes. A standardized tone was also applied to each recording to calibrate the audio level.

[0057] Recordings of bowel sounds were performed by the research team immediately preoperatively and then every postoperative day. Clinical outcome data were also collected daily by the research team. Variables associated with the presence of GII are shown in Table 1 . The clinical team providing patient care was blinded to the results of the audio recordings.

[0058]

[0059] Table 1. Clinical variables collected daily and associated with the presence of GII

[0060] The audio recordings were then processed using a digital signal processing algorithm. The algorithm was applied in an iterative manner to focus on identifying spectral events in the preoperative or early postoperative period that predicted the occurrence of GII during the remaining hospital stay. Five types of spectral events across different parts of the audible spectrum were ultimately used for analysis. Each type of spectral event was defined by unique target signal parameters (minimum and maximum frequency, minimum and maximum duration, and minimum separation), signal-to-noise ratio parameters (minimum occupancy, signal-to-noise ratio threshold), and noise power estimation parameters (block size, hop size, percentile). The five spectral events were designated H4, M4, L4, ML4, and MH4, and the parameters of each event are shown in Table 2. Spectral events were counted in four-minute intervals. GII was defined as the occurrence of vomiting, the need for nasogastric intubation, or a change in diet.

[0061]

[0062] Table 2. Detector settings for defining spectral events

[0063] RavenPro 1.4 software was used for visualization, analysis, and measurements of the recorded audio signals. Statistical analysis was performed using PASW 18 and Clementine 10.1.

[0064] Thirty-seven patients were recruited for the study. Five patients were excluded because of postoperative ICU admission. Two patients who were discharged on the day of surgery were excluded, so no postoperative data were obtained. Of the remaining 30 patients, 11 were male and 19 were female. The mean age was 52 (SD = 12). Five patients underwent extra-abdominal surgery and 25 patients underwent intra-abdominal surgery. Nine patients (30% of the total) subsequently developed GII, all within the first 4 days after surgery. Of these patients, four started taking POD1, one took POD2, and four took POD4.

[0065] Three examples of spectral events are shown in Fig.15 are shown in the spectrogram. The mean number of each specified spectral event was calculated for patients who subsequently developed or did not develop GII. A two-tailed t-test was then used to assess the significance of any differences. Spectral events obtained from POD0 were not associated with the subsequent development of GII. However, spectral events obtained from POD1 did prove to be associated with the subsequent development of GII. Specifically, the mean count of MH4 spectral events was 154 in patients who did not subsequently develop GII, while the mean count was 44 in patients who developed GII (p=.004).

[0066] Fig.16 An example of GII prediction based on the data collection described herein is shown, and a graph plotting the temporal changes of MH4 spectral events is shown. The results of the study confirm that spectral events that appear in bowel sounds early during surgery, before clinical manifestations and symptoms appear, are indeed associated with GII. Specifically, it was determined that MH4 was highly and significantly separated from the subsequent occurrence of GI. Therefore, the prediction model based on MH4 measurement can be used to evaluate patients with high risk, medium risk, and low risk of GII. Significantly, no patient in the low-risk group experienced GII. In the study, the predictive value for the low-risk classification without GII was 100%, while the predictive value for the high-risk classification of GII was 83%. Thirty percent (30%) of the medium-risk patients experienced GII.

[0067] As described herein and above with respect to embodiments of the present invention, Fig.17A flow chart of an embodiment of the method of the present invention for predicting GII is provided. As shown, once the device of the present invention is placed on the patient, the patient's intestinal sounds are recorded to generate audio data in box 100. As described herein, the sounds can be obtained non-invasively through a patient interface on the patient's skin. Then, in box 102, the recorded audio data from box 100 is processed to identify predicted spectral events (e.g., MH4). Then, in box 104A, the processed audio data of box 102 is analyzed for error signals due to environmental noise. If the device of the present invention does not indicate the need to mitigate such error signals, the total number of predicted spectral events identified is calculated in box 106. However, if the device of the present invention detects an error signal exceeding a threshold number in box 104A, then in box 104B, the reduction of the error signal generated by the environmental noise is performed, and the device recalculates by adjusting the number of predicted spectral events identified to take into account the error signal, while warning / reminding the user that the environmental noise needs to be reduced or controlled. Once the mitigation in box 104B is completed, the total number of predicted spectral events identified is provided in box 106, as described above for the non-mitigation determination in box 104A. Based on the total number of predicted events identified calculated in box 106, the timestamp and number of spectral events are written to the buffer in box 108A, and the slope of the spectral event value over time is generated from the regression analysis of the buffered data in box 108B. Then, in box 110, the slope value is compared with the data, which associates the slope with the possibility of GII occurring in the future. By analyzing the slope of two or more spectral event values ​​(i.e., MH4 values) over time, this aspect provides a significant improvement over other methods. For example, MH4 values ​​between about 7 hours and about 12 hours after surgery are obtained and the slope of the linear regression analysis of these points is calculated. In addition to the single MH4 value collected at 12 hours after surgery that acts as a predictor, the calculated slope of the present invention is compared with a predetermined slope threshold for binary prediction. This aspect of the invention corrects for potential erroneous interpretations due to a single MH4 value that may be erroneously elevated by ambient noise interference; however, the invention provides results based on analysis of multiple values ​​and results and having analysis results that are more resilient to external interference (such as ambient noise). This ability to mitigate false signals greatly increases risk level analysis and strategies, particularly when used in the device of the invention including the acoustic chamber defined herein. From the association of box 110, in box 112, the device of the invention indicates the risk level to the user to make decisions related to preparation, prevention, treatment and other strategies in response to the likelihood of the predicted GII event occurring. As discussed herein, devices and methods are provided that allow real-time data collection, analysis and correlation to provide results predicting the occurrence of GII at a specific risk level.

[0068] Fig.18 An example architecture of a device 72 is shown that can be used in a system to predict gastrointestinal damage to analyze collected patient data. For example, Fig.18 The architecture shown in may be the architecture of the device of the present invention, including for example Figure 3 to Figure 4 Computer 105 and user interface 103 as well as data collection devices, processing devices, user interfaces, (multiple) I / O devices (including microphones), memory (including operating systems, intestinal sound analyzers, databases, etc.), as described herein. In addition, it should be noted that the illustrated architecture can be distributed across one or more devices.

[0069] like Fig.18 As shown in FIG. 1 , device 72 typically includes a processing device 74 , a memory 76 , a user interface 78 , and input / output devices 80 , each of which is coupled to a local interface 82 , such as a local bus.

[0070] The processing device 74 may include a central processing unit (CPU) or other processing device such as a microprocessor or a digital signal processor. The memory 76 includes any one or combination of volatile memory elements (eg, RAM) and non-volatile memory elements (eg, flash memory, hard disk, ROM).

[0071] The user interface 78 includes components through which a user interacts with the device 72. For example, the user interface 78 may include a keyboard, a mouse, and a display device, such as a liquid crystal display (LCD). Alternatively or additionally, the user interface 78 may include one or more buttons and / or a touch screen. One or more I / O devices 80 are suitable for facilitating communication with other devices and may include one or more electrical connectors and wireless transmitters and / or receivers. In addition, in the case where the device 72 is a data collection device, the I / O device 80 may include one or more microphones 84.

[0072] The memory 76 is a computer readable medium and stores various programs (i.e., logic), including an operating system 86 and a bowel sound analyzer 88. The operating system 86 controls the execution of other programs and provides scheduling, input-output control, file and data management, memory management, and communication control and related services. The device 72, preferably the memory 86, includes a data buffer to which time-stamped spectral events are written for analysis by one or more algorithms and / or other software to compare slope values ​​with the data to determine the correlation between the slope and the likelihood of future GII, the risk level being determined by the correlation. The bowel sound analyzer 88 includes one or more algorithms configured to analyze the bowel audio data to predict the likelihood of a patient experiencing GII. In some embodiments, the analyzer 88 performs analysis relative to relevant data stored in a database 90 and presents a predictive indicator of GII risk to a user (e.g., a physician or hospital staff). In some embodiments, the analyzer 88 uses target signal parameters, signal-to-noise ratio parameters, and noise power estimation parameters to identify specific spectral events of interest. A decision tree analysis that predicts the number of spectral events during a specified time interval can then be used to deliver a GII of high risk, medium risk, or low risk. In some embodiments, the risk associated with each risk level is 83%, 30%, and 0%, respectively, or thereabouts.

[0073] It is believed that powerful models can be generated from larger patient data sets and by monitoring intestinal sounds over longer time periods, such as a 24-hour period. Continuous recording with data averaging and the addition of additional types of spectral analysis can improve the predictive accuracy of the disclosed technology. It is expected that future trials will focus on collecting larger data sets, validating the proposed prediction models, refining the spectral events analyzed, evaluating alternative timings for data collection, and developing broadly applicable prediction models. In addition, further development of reliable techniques for rapid, continuous acquisition and analysis of bedside data will be invaluable for expanding these studies and ultimately applying them to any clinical use. In any case, the above studies have demonstrated the feasibility and promise of using acoustic spectral analysis in the study of GII and other gastrointestinal diseases.

[0074] Colic is the leading cause of premature death in horses. While colic refers to pain in the abdomen, it can reflect a number of underlying conditions affecting the large intestine, including blockage, spasm, or torsion. Early diagnosis is key to preventing mortality; however, early diagnosis is challenging in larger mammals such as horses. Because the underlying causes of colic reflect mechanical changes in the intestine, these changes can be identified as subtle differences in the type of noises made by the regular contractions of the intestine.

[0075] The devices and systems of the present invention can be modified to perform audio spectrum analysis of intestinal sounds of large mammals (such as horses). In another aspect of the present invention, a series of devices can be used to monitor multiple horses at the same time or overlapping times, wherein the devices are networked with a network management device to transmit data to at least one other receiving system and / or analyze the data. The devices and systems are configured to be attached to the body (e.g., trunk or abdomen or lower abdomen) of the horse (i.e., by a belt, adhesion, elastic band, other similar mechanism and / or combination thereof), wherein the device microphone is positioned toward the body. The data collected by the device can be analyzed by the device. The result analysis can be accessed and reviewed on the device, as described herein, or the data analysis can be transmitted to a gateway device, which is located, for example, in a barn, animal shelter, field, pasture, or primarily in one area, in which the gateway device can receive information from the device attached to the horse and transmit the information to the device at another site for the caregiver to review the analysis and determine the necessary actions for the horse. The audio spectrum analysis algorithm is specifically targeted for early identification of spectral events that predict the likelihood of the onset of colic or the early stages of colic, and there will be a power consumption strategy that allows for several weeks to months of use before replacing the device. It should be recognized that while the ambient noise near and around a horse is different than the ambient noise in a hospital or other place where other humans are cared for, the device of the present invention can be easily adjusted to accommodate the ambient noise near and around a horse. The use of an alarm indicator associated with a notification and / or warning that ambient noise needs to be controlled is described in the above section of this document.

[0076] Although the above description relates to a preferred embodiment of the present invention, it is to be noted that other changes and modifications are apparent to those skilled in the art and may be made without departing from the spirit or scope of the present invention. In addition, the features described in conjunction with one embodiment of the present invention may be used in conjunction with other embodiments, even if not explicitly stated above.

Claims

1. A device for analyzing intestinal audio, comprising: a patient interface adapted to be attached to a surface of the patient's abdomen; a diaphragm adapted to vibrate in response to bowel sounds to generate acoustic pressure waves that amplify the bowel sounds emanating from within the patient's abdomen; an acoustic chamber adapted to receive said sound pressure waves caused by vibrations of the diaphragm which amplify said intestinal sounds; a primary audio collection device located in or near the acoustic chamber; Auxiliary audio collection equipment; a user interface comprising a display; A housing comprising a computer, the computer comprising a processor and a non-transitory computer-readable storage medium, the processor being configured to receive collected audio data from at least one of the primary audio collecting device and the secondary audio collecting device, the non-transitory computer-readable storage medium storing instructions, the instructions comprising one or more algorithms that, when executed by the processor, cause the processor to perform operations comprising the following steps: analyzing the collected audio data from the sound pressure waves collected by the primary audio collecting device for erroneous signals due to ambient noise; analyzing two or more spectral event values ​​of the collected audio data over time; after analyzing the collected audio data for the error signal, generating a slope of a linear regression analysis of two or more spectral event values ​​of the collected audio data over time; as well as comparing the slope of the linear regression analysis to a predetermined slope threshold, Wherein, one of the two or more spectral event values ​​comprises a predefined signal parameter, and the predefined signal parameter comprises a frequency in the range of 900 to 20,000 Hz.

2. The device according to claim 1, wherein The predefined signal parameters include: Duration in the range of 5 to 600 milliseconds.

3. The device according to claim 2, wherein: The predefined signal parameters include: The minimum time separation between one spectrum event value and other spectrum event values, wherein the minimum time separation is 20 milliseconds.

4. The device according to claim 3, wherein: The predefined signal parameters include: The signal-to-noise ratio is 70%.

5. The device according to claim 4, wherein: The predefined signal parameters include: The signal-to-noise ratio threshold is 10 dB.

6. The device according to claim 1, wherein: The steps also include: A binary prediction of gastrointestinal injury is made based on comparing the slope of the linear regression analysis to the predetermined slope threshold.

7. The device according to claim 6, wherein: The steps also include: On the display, the binary prediction regarding gastrointestinal tract damage is displayed.

8. The device according to claim 1, wherein: The steps also include: Based on comparing the slope of the linear regression analysis with the predetermined slope threshold, a risk level regarding gastrointestinal injury is provided to the user.

9. The device according to claim 6, wherein: The steps also include: The risk level is displayed on the display.

10. The device according to claim 1, wherein: The display includes a graphical user interface.

11. The device according to claim 1, wherein: The device is configured to collect and analyze audio signals from the patient to predict the likelihood of gastrointestinal tract injury before clinical symptoms of the gastrointestinal tract injury occur.

12. The device according to claim 1, wherein: The computer, the primary audio collecting device, and the secondary audio collecting device are contained within the housing.

13. The apparatus according to claim 1, wherein: The auxiliary audio collection device includes a microphone located on the housing that is directed outward and configured to collect the ambient noise.

14. The apparatus according to claim 1, wherein: The auxiliary audio collecting device is configured to collect the ambient noise.

15. The apparatus according to claim 1, wherein: The patient interface collects acoustic sound waves, and At least one of the primary audio collecting device and the secondary audio collecting device collects sound pressure waves caused by vibration of the diaphragm caused by the acoustic sound waves vibrating the diaphragm.

16. The apparatus according to claim 1, wherein: The secondary audio collecting device also includes a second diaphragm.

17. The apparatus according to claim 1, wherein: The housing also includes a separable top and lower portion, and Wherein, the separable top and lower parts are fixed using attachment means.

18. The apparatus according to claim 1, wherein: The device includes an alarm indicator for the false signal due to the ambient noise.

19. The apparatus of claim 1, further comprising: buffer, wherein at least one of the one or more algorithms analyzes two or more spectral event values ​​of the collected audio data and provides a timestamp and a total number of identified spectral events to the buffer, and Wherein, at least one of the one or more algorithms is used to generate a slope of the linear regression analysis using the buffered data.

20. A method for predicting the possibility of occurrence of gastrointestinal damage, the method comprising: utilizing the device of claim 1 to record intestinal sounds emitted from the patient's abdomen to collect said audio data from said sound pressure waves collected by said primary audio collection device; Analyzing the collected audio data for erroneous signals due to the environmental noise using the computer; mitigating the error signal if analysis of the collected audio data for the error signal indicates that mitigation is needed, using the computer; processing, using the computer, the collected audio data to identify the two or more spectral event values; utilizing the computer, obtaining a total number of the identified two or more spectral event values; Using the computer, performing a linear regression analysis on the processed audio data to obtain a slope of the two or more spectrum event values ​​over time; using the computer, correlating the slope with the likelihood of occurrence of the gastrointestinal injury; as well as Using the display, a risk level based on the likelihood is provided to the user.

21. The method according to claim 20, wherein: One of the two or more spectral event values ​​comprises a predefined signal parameter, wherein the predefined signal parameter further comprises: a duration in the range of 5 to 600 milliseconds; and The minimum time separation between one spectrum event value and other spectrum event values, wherein the minimum time separation is 20 milliseconds; The signal-to-noise ratio is 70%; and The signal-to-noise ratio threshold is 10 dB.

22. The method according to claim 20, wherein: The mitigation steps include: The number of identified predicted spectral events is adjusted by taking into account the error signal due to the environmental noise, thereby obtaining a total number of identified predicted spectral events.

23. The method according to claim 20, wherein: The execution steps include: providing a timestamp and writing the total number of identified spectral events to a buffer of the device, and Wherein, the linear regression analysis is performed using the buffered data.

24. The method according to claim 20, wherein: The correlating step is performed by comparing the slope to data correlating the slope with the likelihood of a subsequent gastrointestinal injury.

25. The method according to claim 20, wherein: The method further comprises the following steps: If analysis of the error signal indicates that mitigation is necessary, the user is alerted.

26. The method according to claim 25, wherein: The alarm is provided with an alarm indicator as part of the device, wherein, The alarm indicator is selected from a list consisting of a light, a noise, a graphic on the display of the user interface, or a combination thereof.

27. The method according to claim 25, wherein: The alarm step is activated by: 1) A preset ambient noise decibel level from the auxiliary audio collection device; 2) analysis of the signal-to-noise ratio from the primary audio collection device compared to the secondary audio collection device; as well as 3) Processing the ambient noise received by the auxiliary audio collection device in response to false triggering of spectrum events above a preset threshold.

Images