Enhanced detection and analysis of biological acoustic signals

Abstract

To provide the use of an intestinal audio analysis device for predicting gastrointestinal dysfunction prior to any clinical signs or symptoms occurring.SOLUTION: An intestinal audio analysis device is provided which has a patient interface adapted to attach to a surface of a patient's abdomen for a duration of time after surgery. The invention provides devices and methods for predicting the risk and likelihood of post-operative gastrointestinal dysfunction based on regression analysis of multiple spectral events related to intestinal sounds, with decreased or eliminated falsely elevated values of those events due to ambient noise.SELECTED DRAWING: Figure 17

Description

[Background technology]

[0001] Postoperative ileus (POI) is an acute paralysis of the digestive tract that develops 2-6 days after surgery, causing unwanted side effects such as nausea and vomiting, abdominal pain and distension. It occurs most frequently in gastrointestinal surgery. There is a lack of ability to predict which patients are likely to develop these bowel problems, which results in cases of postoperative complications, hospitalizations, and increased readmission rates. There is a further lack of bowel audio analysis devices and methods that provide more accurate risk level analysis by limiting and / or eliminating ambient noise that causes false data points, and devices and methods that are more self-contained.

[0002] Thus, there remains a need for devices and methods to reduce these problems, and for healthcare providers to be better equipped to reduce hospitalizations and re-admissions and avoid exacerbations through more accurate nutritional intake implementation, which can be achieved through an improved ability to obtain more accurate risk level information related to the likelihood that gastrointestinal dysfunction will occur in a patient, for example, post-surgery. [Brief description of the drawings]

[0003] [Figure 1] 1 illustrates an example of a device as described herein. [Diagram 2] 1 shows a top view of an example of a device described herein. [Diagram 3] 1 shows an exploded view of a device described herein. [Figure 4] 1 shows an exploded view of a device described herein. [Diagram 5] FIG. 2 shows a bottom view of an example of a device described herein. [Figure 6] 1 shows a front view of the separated housing of an example device described herein. [Figure 7] FIG. 2 shows a side view of the separated housing of an example device described herein. [Figure 8]1 illustrates a rear view of the separated housing of an example device described herein. [Figure 9] 1 shows the inside of the top of the housing without the user interface of an example device described herein. [Figure 10] 1 shows an inside view of the lower part of the housing of an example device described herein. [Figure 11] 1 shows a bottom view of the secondary audio collection device housing and the lower portion of the housing without the pedestal of an example device described herein. [Figure 12] FIG. 1 shows a side view of an example of a device described herein. [Figure 13] 1 shows a front view of an example of a device described herein. [Figure 14] 1 shows a rear view of a device as described herein. [Figure 15] 1 is an example spectrogram illustrating spectral events contained in recorded abdominal sounds; [Figure 16] 1 is a graph depicting the temporal evolution of a particular spectral event (MH4) in patients with and without functional gastrointestinal disorders. [Figure 17] FIG. 1 is a flow diagram of an embodiment of a method for predicting gastrointestinal dysfunction. [Figure 18] FIG. 15 is a block diagram of an embodiment of an architecture of a device such as those in FIGS. 1-14 that can process collected patient data to assist in prediction and risk assessment of gastrointestinal dysfunction. Summary of the Invention

[0004] The present invention relates to the use of a gut audio analysis device to predict gastrointestinal dysfunction before any clinical signs or symptoms occur.

[0005] In a particular embodiment, a bowel 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 following surgery. The device has a diaphragm that vibrates in response to bowel sounds to generate sound pressure waves that amplify bowel sounds emitted within the patient's abdomen. This allows audio data related to bowel sounds to be collected through an acoustic chamber that receives the amplified sounds, which are transmitted to an audio collection device located in or near the acoustic chamber. The bowel audio analysis device has an external housing and an internal computer, as well as a 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, and generate a slope of a linear regression analysis for comparison with a predetermined slope threshold to make a binary prediction related to the likelihood and risk of GII, the risk being communicated, for example, on a user interface display.

[0006] In other embodiments, methods of using the gut audio analysis device are provided. In certain implementations, methods are provided for predicting the likelihood and risk level of GII occurring prior to clinical symptoms. Bowel sounds are recorded to generate audio data of the patient's bowel sounds. The audio data is processed to identify certain predictive spectral events (e.g., MH4), and the audio data is analyzed for false signals due to ambient noise. Optionally, certain embodiments provide false signal mitigation to ensure obtaining a more accurate total number of predicted spectral events identified for the linear regression analysis. The resulting slope of the spectral event values ​​over time is used to correlate the slope with the likelihood of gastrointestinal dysfunction occurring (e.g., post-surgery), and based on the correlation, the user is provided with a likelihood-based risk level.

[0007] Embodiments of the present invention provide improved control over ambient noise, which increases the accuracy of the data used to perform correlations and thereby predict postoperative GII prior to clinical symptoms. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] Gastrointestinal dysfunction (GII) is a common concern following surgical procedures. Disclosed herein are systems and methods for predicting GII based on a patient's bowel sounds. As described below, the disclosed systems and methods identify discrete acoustic spectral events within bowel sounds that can be used to predict subsequent GII, and in some cases, post-operative GII. These spectral events are good indicators of bowel function and / or dysfunction, since the sounds are generated by motor activity in the bowel.

[0009] In the following disclosure, various embodiments are described, it being understood that these are merely illustrative implementations of the invention and that other embodiments are possible, all such other embodiments are intended to be within the scope of this disclosure.

[0010] Certain embodiments include a device that includes 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 the subject.

[0011] Figures 1-2 provide an example of an embodiment of the device. Figures 1 and 2 partially show an example of a device comprising a housing 101, at least one button 102 for a user to interact with the device and control its operation, and a user interface 103. The user interface may be a graphical user interface (GUI).

[0012] In certain embodiments, the device comprises a secondary audio collection device. In some embodiments, the secondary audio collection device may be a microphone or other sound receiving mechanism capable of collecting ambient noise. In other embodiments, a signal subtraction of ambient noise from the primary microphone data is performed to achieve true noise cancellation. In some embodiments, the device described herein may be used in a method for predicting or diagnosing GII. In certain embodiments, the systems and methods described herein may comprise predicting GII before symptoms develop. In some cases, the secondary audio collection device may remove interference associated with ambient noise that may interfere with the collection of bowel sounds. Such a configuration may provide surprising and unexpected results in more accurately predicting GII. In some cases, the GII prediction may be post-operative. In some embodiments, the ambient audio collection device further comprises a diaphragm.

[0013] Figures 3-4 show exploded views of example devices. Figures 3 and 4 show a device comprising a user interface 103, a separable top part 104 of the housing, a computer 105, a lower part 106 of the housing, at least one fastening means 107, a diaphragm 108, a gasket 109 and an adhesive wafer 110. Figure 5 shows an example of a device with a secondary audio collection device 111.

[0014] Figures 8-10 show different views of the top housing 104 and the bottom housing 106. Figure 9 shows an internal view of the top housing 104, and Figures 10-11 show different views of the bottom housing 106. Figures 12-14 show different views of one particular embodiment of the device of the present invention.

[0015] The GUI can be configured to allow a user to interact with the device and collect audio data from the subject. Certain embodiments include a housing. The housing can include a top and an adhesive wafer. The adhesive wafer can vary in size (width and length). For example, the wafer can be the same width and length as the bottom area of ​​the unit or smaller than the bottom area of ​​the unit. The wafer can be of different thicknesses. The wafer is shaped to best fit the unit to the patient for reliable monitoring / recording / collection of GII events. The housing can include a separable top and bottom.

[0016] In embodiments where the housing comprises separable top and bottom portions, the separable top and bottom portions are secured together using attachment means, which may comprise screws, fasteners, pins, brackets, pegs, rivets, clips, and the like.

[0017] An embodiment of the system can be used to predict gastrointestinal dysfunction. An embodiment of the system can include a data collection device, a patient interface, and a computer 105. The computer 105 or the data collection device can be separate devices that collect and / or store data retrieved from the patient interface and the computer 105. The patient interface can include any device capable of collecting audio data generated within the patient's intestinal tract. In some embodiments, the patient interface includes a portable (e.g., handheld) digital audio recorder. In such a case, the patient interface can include an integrated microphone (not shown) used to capture bowel sounds, which can be housed in or near an acoustic chamber. The acoustic chamber can be formed, for example, between the diaphragm 108 and the lower portion 106 of the housing. The acoustic chamber significantly increases data collection by amplifying the sounds of the patient's GI tract relative to ambient noise, increases the ability to reduce ambient noise at the time of audio collection, simplifies audio data collection through reduced inventory of extraneous components, and provides the capability for continuous audio data collection in combination with the patient interface, diaphragm, and audio data collection device, such as a microphone housed within the device of the present invention in or near the acoustic chamber.

[0018] The patient interface may be a device that can be applied directly to the patient's abdomen for the purpose of detecting bowel sounds. In some embodiments, the patient interface comprises a stethoscope head or is similar in design and function. The stethoscope head may comprise a diaphragm that is placed in contact with the patient and vibrates in response to sounds generated within the body. Those sounds may be delivered to a microphone that can transmit signals to the computer 105, which can optionally transmit data to a data collection device. In some embodiments, the patient interface may transmit sound through a tube that extends 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 may convert sound waves into a digital signal that can be processed by the computer 105. For example, sound pressure waves generated by the diaphragm vibrations may travel within the lumen of the tube to the microphone. In some embodiments, the patient interface may comprise a microphone or other device that converts sound pressure waves into a digital signal that can be processed and analyzed by the system to predict GII. By way of example, a microphone or other device for converting sound pressure waves into a digital signal may be housed in or in communication with an acoustic chamber positioned between the diaphragm 108 and the lower portion 106 of the housing. In some embodiments, all or a portion of the patient interface may be disposable to avoid cross-contamination between patients. The patient interface may be used with a disposable sheath or cover (not shown) that may be discarded after use.

[0019] The audio data collected by computer 105 may be stored in an internal memory provided by the computer. In some embodiments, the memory may be separate from computer 105, but in data communication with computer 105. In some embodiments, the audio data may be stored in non-volatile memory (e.g., flash memory) of the device. The data may then be transmitted to computer 105 for processing. In some embodiments, the data and data analysis are transmitted via wires or cables used to physically connect 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 to receive and communicate the data and data analysis. In some embodiments, the data and data analysis may be transmitted wirelessly from the device to a separate processor or computer via a suitable wireless protocol such as, for example, Bluetooth or Wi-Fi (IEEE 802.11), or via a suitable cellular protocol such as Global System for Mobile communication (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, 1xEV-DO), Short Message Service (SMS), and Wi-MAX.

[0020] The separate computer may, in some embodiments, comprise a desktop computer. However, it should be noted that virtually any computing device capable of receiving and processing the audio data collected by the computer 105 may be used. Thus, the separate computer may alternatively take the form of a mobile computer, such as a notebook computer, tablet computer, smartphone, or handheld computer. In some embodiments, the computer 105 may process any data generated from the acoustic sounds received from the patient and output information via the user interface 103. In some embodiments, the user interface may comprise a display capability and may also be a touch screen that allows the user to interact with 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.

[0021] 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 allows the interface to be temporarily adhered to the patient's skin similar to an electrocardiogram (EKG) lead. In certain 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.

[0022] In some embodiments, the patient interface may comprise a device with its own integrated microphone (not shown), and patient sounds picked up by the microphone may be electronically transmitted along a wire or cable to the device. In some embodiments, the device may comprise a component designed to dock with a patient monitoring system, which may be located near 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, the patient monitoring system may comprise a docking station and associated display. In certain embodiments, this allows alerts or notifications to be received at a secondary location, such as a nurse's station. The device may also be designed to dock in a free bay of the station prior to use. Other means of connecting the device of the present invention are via various ports known in the industry for these types of electronic systems, including, for example, PS / 2, serial ports (e.g., DB-25, DE-9 or RS-232, or COM Port), parallel ports or Centronics 36-pin ports, audio ports, S / PDIF, TOSLINK, video ports, Digital Video Interface (DVI) (e.g., mini-DVI, micro-DVI), display ports, RCA connectors, component video, S-Video, HDMI, USB (e.g., Type A, Type C), RJ-45, RJ-11, e-SATA, and the like. As will be appreciated, certain adapters for hard connecting the present invention to patient monitoring systems are also contemplated. Types of patient monitoring systems are known and include, for example, standard in-hospital patient monitoring systems for fixed location systems, as well as mobile and / or portable monitoring systems, remote and / or wireless, home systems, and / or combinations thereof.

[0023] In some embodiments, the device may not have an internal power source and therefore may only collect patient data when docked. In some embodiments, the device may have a power connection, such as an A / C connection, or may have an internal power source, such as a battery. In some embodiments, the device may have a photovoltaic and / or thermal power source, such as a solar cell. In some embodiments, the patient interface may have a power source, such as a battery, a photovoltaic device, and / or a thermoelectric device, that may be used to collect acoustic sound waves and / or process the acoustic sound waves into data that may be used to predict GII. By way of example, the device may have electrical pins that electrically couple the device to a patient monitoring system for the purposes of receiving power and transferring collected data to the patient monitoring system. The patient data may be stored in a memory of the patient monitoring system and / or transmitted to a central computer for storage in association with the patient record in an associated medical record database.

[0024] The device may include an electrical port capable of accepting a wire or cable plug, and may include one or more indicators, such as light emitting diode (LED) indicators, that communicate information to an operator, such as positive electrical connection with a patient monitoring system and patient signal quality.

[0025] The device can be coupled to a patient monitoring system. In some embodiments, instead of an external patient interface, the device can include an internal patient interface designed to collect sounds from within the peritoneal cavity. As an example, the patient interface can include a thin-diameter microphone catheter that is left in place after the procedure is completed, similar to a drainage catheter. Such a patient interface can be particularly useful when the patient is obese and it is more difficult to obtain a high-quality signal from the surface of the skin. To avoid passing electrical currents through the patient, the patient interface can include a laser microphone. In such a case, a laser beam is directed through the catheter and reflects off a target inside the body. The reflected optical signal can be received by a receiver that converts the optical signal into an audio signal. The minute differences in the distance the light travels as it reflects off the target are detected by interferometry. In one particular embodiment, the patient interface can include a microphone located at the tip of the catheter.

[0026] The device may comprise a central processing unit (CPU), such as a computer 105, or other processing device, such as a microprocessor or digital signal processor. The device may comprise memory, which may comprise any one or combination of volatile memory elements (e.g. RAM) and non-volatile memory elements (e.g. flash, hard disk, ROM).

[0027] The user interface 103 may comprise components by which a user interacts with the device. The user interface 103 may comprise, for example, 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 comprise one or more buttons 102 that may enable a user to use the device and operate the user interface 103, such as navigating menus, viewing data, etc. Alternatively or in addition, the user interface 103 may comprise one or more buttons and / or a touch screen. The 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, if the device is also collecting and / or processing data retrieved from the patient, the I / O devices may comprise a microphone.

[0028] 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 comprise one or more algorithms configured to analyze bowel audio data for the purpose of predicting the likelihood that a patient will develop GII. In some embodiments, the analyzer may perform analysis on correlation data stored in a database (such a database may be stored in the computer 105) and present a predictive index of GII risk to a user (e.g., a doctor, hospital staff, and / or clinician). In some embodiments, the analyzer may use a target signal parameter, a signal-to-noise ratio parameter, and a noise power estimation parameter to identify specific spectral events of interest. A decision tree analysis of the number of predicted spectral events during a specified time interval may then be used to communicate a high, medium, or low risk of GII. In some embodiments, the risk associated with each risk level is, or is about, 83%, 30%, and 0%, respectively.

[0029] In one particular method of using the device, the patient's bowel sounds can be recorded to generate audio data. As explained above, the sounds can be obtained non-invasively, for example, using a stethoscope head or other patient interface that is applied to the patient's skin on or near the abdomen. Alternatively, the sounds can be collected with a device that extends into the patient's peritoneal cavity. The sounds can be recorded early in the post-operative period, for example, on the day of surgery or the day immediately following surgery, and for any required length of time thereafter. In some embodiments, acoustic sounds are obtained immediately after surgery and can continue to be monitored and analyzed for hours, days, or weeks, as will be understood by those of skill in the art in view of this disclosure. In some embodiments, the sounds are collected continuously. In some embodiments, the sounds are collected for a period of time that is a predetermined interval. Regardless of when the sounds are recorded, they can be recorded for a duration of time sufficient to allow for the identification of spectral events predictive of bowel function and / or the onset of dysfunction. By way of example, the sounds are recorded for a period of about 4-6 minutes. In some embodiments, all sounds within the range of 20-20,000 Hz are recorded. In some embodiments, sounds outside the range audible to the human ear are collected and analyzed. Filters can be applied to reduce the range of frequencies recorded, thus reducing the amount of data analyzed. In some embodiments, the secondary audio collection device 111 can work in conjunction with the patient interface to provide improved analysis results. For example, the secondary audio collection device can include a microphone that can measure ambient noise in the vicinity of the patient. The ambient noise can then be subtracted from the acoustic sounds collected from the patient to ensure that any acoustic sounds analyzed by the device are actually collected from the patient and not from any external source. In certain embodiments, for example, the secondary microphone and the unit's integrated microphone collect audio data independently in a synchronized manner.Both sets of audio data are run through an MH4 detector to ascertain whether ambient noise is potentially triggering a false MH4 event count coming from the integrated microphone, and if certain criteria are met by the ambient sound(s), the ambient data count can be subtracted from the final count. In some embodiments, a filter can be used such that only sounds having frequencies between about 700-1500 Hz are recorded or analyzed, although filters can be incorporated that allow the device to analyze only sounds within a certain frequency range. As part of mitigating the effects of ambient noise, a warning indicator or alarm mechanism can be part of the device, for example, to notify a physician, caregiver, nurse, or clinician that the ambient noise(s) must be reduced. There are scenarios where the ambient noise level is too high for the device's noise reduction strategy to work. In such scenarios, a meaningful MH4 value cannot be obtained. A warning indicator, which can be any combination of light, noise, audible tone, or graphics on the device display, can be used to indicate to the user that the ambient noise needs to be reduced and / or controlled. The threshold for triggering the warning indicator may be based, for example, on the current ambient noise decibel level from the outward facing microphone, an analysis of the signal / noise ratio from the primary to the outward facing microphone, processing of sounds from the outward facing microphone for false triggering MH4 values ​​above a pre-set threshold. Although the sounds have been described as "recorded", it will be appreciated that the sounds may alternatively simply be captured and processed in real-time (as described below) without actually recording the sounds.

[0030] Once the audio data is generated, the data can be processed, for example, in real-time, to identify one or more predictive spectral signals. Real-time can mean, for example, that the data is processed while the sounds are being acquired through the device as they are generated by the patient. As explained above, sounds generated by the intestines can be the result of peristalsis, and from peristalsis, the device can predict the likelihood of GII, meaning that the device indicates (before GII) the likelihood that GII will occur after data collection and analysis. The sounds collected and / or analyzed by the device can thus provide an indication of how the intestines are functioning. For example, paralysis of a significant portion of the intestinal tract proportionally reduces the number of high energy propulsive contractions in the digestive tract, which results in some loss of the higher energy, and hence higher frequency, acoustic spectrum that is typical of a normally functioning intestine. As explained below, it has been found that certain predefined spectral events can be identified in the sounds that are highly predictive of whether or not GII is likely to occur. As also explained below, each of the predefined spectral events is defined by certain characteristics or parameters, such as their frequency, amplitude, duration, and temporal separation from other spectral events.

[0031] After the spectral events are identified, their number during a specified time duration (e.g., the total duration of the recording) can be summed. The total number of identified predicted spectral events 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, for example, in a physical memory storage used to temporarily store data, while the buffer can be in a fixed memory of hardware or as a virtual data buffer in software that points to a location in physical memory. At this point, the total number of spectral events can be compared to correlation data that correlates the number of spectral events with the likelihood of subsequent GII. As an example, a spectral event designated "MH4" was identified in the study described below. For MH4, a high risk of GII exists if the number of observed MH4 events is less than about 21 during a 4-minute recording, a medium risk of GII exists if the number of observed MH4 events is more than about 21 but less than about 131 during a 4-minute recording, and a low risk of GII exists if the number of observed MH4 events is more than about 131 during a 4-minute recording. The number of a given spectral event can therefore be used as an index to convey the magnitude of risk for the GII, with smaller numbers indicating higher risk and larger numbers indicating lower risk.

[0032] Once the likelihood of a later GII is ascertained, the risk can be communicated to the user. For example, the computer 105 or other device (such as a separate computer) can be used to perform the analysis and display the risk level on an associated display, such as the user interface 103, while the prediction can be shown on a separate display, such as a separate computer monitor. In some embodiments, the prediction can be automatically communicated to a hospital charting and / or recording system such that the prediction is automatically stored with the patient record. In some cases, the data can be anonymized and used as aggregate data. In some embodiments, the risk can be communicated as an index (i.e., a number). In other embodiments, the risk can be indicated as "high," "moderate," or "low." In either case, appropriate action can be taken in response to the indication, which may include allowing or prohibiting oral nutrition. Further recording and analysis can be performed on the patient in the days following surgery, particularly to assess bowel function and corroborate the initial patient evaluation.

[0033] Any of the features described herein can be combined or substituted as would be understood by one of ordinary skill in the art in light of the disclosure and explanations provided herein.

[0034] As can be seen from the methods described above, the risk of GII can be assessed in much the same way that the risk of heart problems can be assessed non-invasively using an EKG. In some embodiments, the risk assessment can be performed in real time.

[0035] A clinical study was conducted to evaluate the feasibility of the disclosed system and method. One objective of the study was to confirm that spectral events present in bowel sounds early in the postoperative period are indeed correlated with GII thereafter, before the onset of clinical signs and symptoms. Another objective of the study was to develop a model for predicting GII that can be implemented as a simple, non-invasive, point-of-care test that allows hospitals and other facilities to risk stratify patients for the development of clinically significant GII using analysis of bowel sounds.

[0036] Patients scheduled to undergo inpatient surgery were recruited for this 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.

[0037] For the study, a device was assembled to digitally record abdominal sounds using a dual-channel digital audio recorder (Microtrak II, M-Audio Corp., Irwindale, CA), a condenser microphone (ATR35s, Audio-Technica Ltd, Leeds, UK), stethoscope tubing, and a stethoscope head. To record bowel sounds, the stethoscope head was applied to the upper and lower anterior abdominal walls, and both channels were recorded simultaneously over a period of 5–6 min. Standardized tones were also applied to each recording to calibrate the audio levels.

[0038] Bowel sound recordings were performed by the research team immediately prior to surgery and then on each postoperative day. The research team also collected clinical outcome data daily. Variables associated with the development of GII are shown in Table 1. The clinical team providing patient care was blinded to the results of the audio recordings. [Table 1]

[0039] The audio recordings were then processed using a digital signal processing algorithm. The algorithm was applied in an iterative fashion focused on identifying spectral events preoperatively or early in the postoperative period that would predict the onset of GII during the remainder of the hospital stay. Five types of spectral events spanning different parts of the audible spectrum were ultimately used for the 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 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 for each are listed in Table 2. Spectral events were counted over a 4-minute time interval. GII was defined as the presence of vomiting, the need for nasogastric intubation, or reversal of eating and drinking. [Table 2]

[0040] RavenPro 1.4 software was used to visualize, analyze, and measure the recorded audio signals. Statistical analyses were performed using PASW 18 and Clementine 10.1.

[0041] Thirty-seven patients were recruited into the study. Five patients were excluded because of postoperative ICU admission. Two patients who were discharged on the day of surgery were excluded because no postoperative data were obtained. Of the remaining 30 patients, 11 were male and 19 were female. The mean age was 52 years (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 those patients, 4 started on POD1, 1 on POD2, and 4 on POD4.

[0042] Three examples of spectral events are shown in the spectrogram in FIG. 15. The mean number of each specified spectral event was calculated for patients who did or did not subsequently develop GII. A two-tailed t-test was then used to assess the significance of any differences. Spectral events obtained from POD0 did not correlate with the development of subsequent GII. Spectral events obtained from POD1, however, were found to correlate with the development of subsequent GII. Specifically, MH4 spectral events had a mean count of 154 in patients without subsequent GII and a mean count of 44 in patients who developed GII (p=0.004).

[0043] FIG. 16 shows an example of prediction of GII based on the collection of data as described herein, showing a graph depicting the temporal change in MH4 spectral events. The results of the study confirmed that the spectral events present in bowel sounds early in the surgical admission are indeed correlated with GII before the onset of clinical signs and symptoms. In particular, MH4 was found to be highly and significantly separated with the subsequent presence of GII. Thus, a predictive model based on MH4 measurements can be used to assess patients as being at high, medium, and low risk for GII. Significantly, patients in the low-risk group did not develop GII. In this study, the predictive value of the low-risk classification for no GII was 100%, while the predictive value of the high-risk classification for GII was 83%. Thirty percent (30%) of the medium-risk patients experienced GII.

[0044] As described herein and above for embodiments of the present invention, FIG. 17 provides a flow diagram of an embodiment of a method of the present invention for predicting GII. As illustrated, once the device of the present invention is positioned on the patient, in block 100, the patient's bowel sounds are recorded to generate audio data. As described herein, the sounds can be obtained non-invasively through a patient interface to the patient's skin at or virtually near the patient's abdomen. The recorded audio data from block 100 is then processed to identify predicted spectral events (e.g., MH4) in block 102. The processed audio data from block 102 is then analyzed for false signals due to ambient noise in block 104A. If the device of the present invention does not indicate that such false signals require mitigation, the total number of predicted spectral events identified is calculated in block 106. However, if the device of the present invention detects a number of false signals that exceeds a threshold in block 104A, mitigation of false signals due to ambient noise is performed by adjusting the number of predicted spectral events identified to take into account the false signals in block 104B, while alerting / alerts the user of the need to reduce or control the ambient noise, and the device recalculates. Once mitigation in block 104B is complete, a total number of identified predictive spectral events is provided in block 106, as described for the non-mitigation determination from block 104A discussed above. Using the total number of identified predictive events calculated in block 106, the timestamps and number of spectral events are written to a buffer in block 108A, and a slope of the spectral event values ​​over time is generated from a regression analysis of the buffered data in block 108B. The slope value is then compared in block 110 to data correlating the slope with the likelihood of a GI occurring in the future. This embodiment provides a significant improvement over other methods by analyzing the slope of two or more spectral event values ​​(i.e., MH4 values) over time. For example, MH4 values ​​between about 7 and about 12 hours post-surgery are obtained, and the slope of a linear regression analysis of these points is calculated.Rather than a single MH4 value collected at 12 hours post-op serving as a predictor, the calculated slope of the present invention is compared to a predefined slope threshold to make a binary prediction. While this aspect of the present invention corrects potential misinterpretations due to a single MH4 value that may be falsely elevated by ambient noise interference, the present invention provides an analysis based on multiple values ​​and outcomes with analysis results that are more resilient to external interference such as ambient noise. This ability to mitigate false signals significantly increases risk level analysis and strategies, especially when used with the device of the present invention comprising an acoustic chamber as defined herein. From the correlation of block 110, the device of the present invention indicates the risk level to the user in block 112 for decision-making regarding preparation, prevention, treatment, and other strategies to address the likelihood of the predicted GII event occurring. As discussed herein, devices and methods are provided that allow for real-time data collection, analysis, and correlation to provide results that predict that GII will occur at a particular risk level.

[0045] 18 illustrates an example architecture for a device 72 that can be used in a system for predicting gastrointestinal dysfunction to analyze collected patient data. By way of example, the architecture shown in FIG. 18 can be that of a device of the present invention, including, for example, the computer 105 and user interface 103 of FIGS. 3-4, as well as a data collection device, processing device, user interface, I / O device(s) (including microphones), memory (including operating system, bowel sound analyzer, database, etc.) as described herein. Moreover, it should be noted that the illustrated architecture can be distributed across one or more devices.

[0046] As shown in FIG. 18, device 72 generally 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.

[0047] The processing device 74 may include a central processing unit (CPU) or other processing device such as a microprocessor or digital signal processor. The memory 76 includes any one or combination of volatile memory elements (e.g., RAM) and non-volatile memory elements (e.g., flash, hard disk, ROM).

[0048] The user interface 78 comprises components with which a user interacts with the device 72. The user interface 78 may comprise, for example, a keyboard, a mouse, and a display device such as a liquid crystal display (LCD). Alternatively or additionally, the user interface 78 may comprise one or more buttons and / or a touch screen. The one or more I / O devices 80 are adapted to facilitate communication with other devices and may include one or more electrical connectors and wireless transmitters and / or receivers. Additionally, if the device 72 is a data collection device, the I / O devices 80 may comprise one or more of microphones 84.

[0049] 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, and preferably the memory 76, includes a data buffer into which time-stamped spectral events are written for analysis via one or more algorithms and / or other software for slope value comparison with data for correlation with slope and subsequent likelihood of GII, from which a risk level is determined. The bowel sound analyzer 88 includes one or more algorithms configured to analyze the bowel audio data for the purpose of predicting the likelihood that a patient will develop GII. In some embodiments, the analyzer 88 performs its analysis against the correlation data stored in the database 90 and presents a predictive index of GII risk to a user (e.g., a doctor or hospital staff). In some embodiments, the analyzer 88 uses a target signal parameter, a signal-to-noise ratio parameter, and a noise power estimation parameter to identify a particular spectral event of interest. A decision tree analysis of the number of predicted spectral events during a specified time interval can then be used to communicate a high, medium, or low risk of GII, in some embodiments, the risk associated with each risk level is, or is about, 83%, 30%, and 0%, respectively.

[0050] It is believed that powerful models can be generated from larger data sets of patients by monitoring bowel sounds during longer time intervals, such as a 24-hour period. Continuous recording with data averaging and the addition of additional types of spectral analysis may improve the predictive accuracy of the disclosed technique. Future studies are expected to focus on collecting larger sets of data, validating the proposed predictive models, refining the spectral events analyzed, evaluating alternative timing of data collection, and developing broadly applicable predictive models. In addition, further deployment of reliable techniques for rapid point-of-care data acquisition and analysis will be invaluable in expanding these investigations and ultimately in any clinical use. In any event, the studies described above support the feasibility and promise of using acoustic spectral analysis in the study of GII and other gastrointestinal disorders.

[0051] Colic is a leading cause of premature death in horses. Although colic refers to abdominal pain, it may reflect a number of underlying disorders affecting the large intestine, including blockage, spasm, or volvulus. Early diagnosis is key to preventing mortality, but early diagnosis in larger mammals such as horses is difficult. Because the underlying causes of colic reflect mechanical changes in the intestine, these are recognizable as subtle differences in the type of noise made from the regular contractions of the intestine.

[0052] The devices and systems of the present invention can be modified to perform audio spectral analysis of bowel sounds in large mammals such as horses. In another aspect of the present invention, a series of devices can be used to monitor multiple horses simultaneously or at overlapping times, with the devices networked to a gateway device for transmission of data and / or analysis to at least one other receiving system. The devices and systems would be configured to be attached (i.e., via straps, adhesives, elastic bands, other similar mechanisms, and / or combinations thereof) to the horse's body (e.g., trunk or abdomen / lower abdomen), with the device microphone positioned toward the body. Data collected by the devices can be analyzed by the devices. The resulting analysis can be accessed and reviewed from the devices as described herein, or the data analysis can be transmitted to a gateway device, for example, located in a barn, animal shelter, field, pasture, or essentially an area where the gateway device can receive information from devices attached to the horse and transmit the information to a device at another location where the zookeeper can review the analysis to determine the horse's required actions. The audio spectrum analysis algorithm should be specifically tuned for early identification of spectral events predicting the likelihood of colic beginning to occur or the early stages of colic, and would have a power consumption strategy that allows use for weeks to months before replacing the device. It should be appreciated that the ambient noise near and around a horse will differ from the ambient noise in a hospital or other location where humans are cared for, but the device of the present invention can be easily tuned to take into account the ambient noise near and around a horse. The use of warning indicators for notification and / or alerting of the need to control the ambient noise has been described herein above.

[0053] It should be noted that while the foregoing description is directed to preferred embodiments of the invention, other variations and modifications will be apparent to those skilled in the art and may be made without departing from the spirit or scope of the invention. Moreover, features described in connection with one embodiment of the invention may be used in conjunction with other embodiments even if not explicitly stated above.

Claims

1. a patient interface adapted for attachment to a surface of the patient's abdomen; a diaphragm that vibrates in response to bowel sounds to create acoustic pressure waves that amplify bowel sounds produced within the patient's abdomen and provide audio data for collection; an acoustic chamber adapted to receive acoustic pressure waves caused by diaphragm vibrations that amplify the bowel sounds; an audio collection device located in or near the acoustic chamber; a housing having a computer; a memory comprising one or more algorithms; a user interface having a display; 1. A gut audio analysis device comprising: At least one of the one or more algorithms analyzes the collected audio data for erroneous signals due to ambient noise; At least one of the one or more algorithms analyzes two or more spectral event values ​​over time; At least one of the one or more algorithms serves to generate a slope of a linear regression analysis of the two or more spectral event values ​​over time; The slope of the linear regression analysis is compared to a predetermined slope threshold to make a binary prediction.

2. The device of claim 1 , wherein the display comprises a graphical user interface.

3. 10. The device of claim 1, wherein the device is configured to collect and analyze audio signals from a patient to predict the likelihood of a gastrointestinal dysfunction before clinical signs of the dysfunction occur.

4. The device of claim 1 , wherein the housing comprises a top and a base.

5. The device of claim 1 , further comprising a secondary audio collection device.

6. The device of claim 5 , wherein the secondary audio collection device is configured to collect ambient noise.

7. The device of claim 1 , wherein the patient interface collects acoustic sound waves and the at least one audio collecting device collects processed audio data from the acoustic sound waves.

8. The device of claim 5 , wherein the secondary audio collection device further comprises a diaphragm.

9. The device of claim 1 , wherein the housing further comprises separable top and bottom portions.

10. 10. The device of claim 9, wherein the separable top and bottom portions are secured together using an attachment means.

11. 1. A method for predicting the likelihood of a functional gastrointestinal disorder occurring, the method comprising: recording bowel sounds to generate audio data of the patient; processing the audio data to identify predicted spectral events; analyzing the audio data for erroneous signals due to ambient noise and mitigating the erroneous signals if the analysis of the erroneous signals indicates a need for mitigation; Obtaining a total number of identified predicted spectral events; performing a linear regression analysis that yields a slope of the spectral event values ​​over time; Correlating the slope with the likelihood of a gastrointestinal dysfunction occurring; providing a user with a risk level based on said likelihood; 13. A method comprising:

12. 12. The method of claim 11, wherein the mitigating step comprises adjusting a number of identified predicted spectral events by taking into account the erroneous signals due to ambient noise, resulting in the total number of identified predicted spectral events.

13. The method of claim 11 , wherein the performing step comprises providing a timestamp and writing a total number of identified predicted spectral events to a buffer in the device.

14. The method of claim 13 , wherein the linear regression analysis is performed using data written to the buffer.

15. 12. The method of claim 11, wherein the correlating step is performed by comparing the slope value to data correlating slope with the likelihood of subsequent gastrointestinal dysfunction.

16. The method of claim 11 , further comprising the step of alerting a user if analysis of the false signal indicates a need for mitigation.

17. 17. The method of claim 16, wherein the warning comprises a warning indicator provided as part of the device, the warning indicator being selected from a list comprising a light, a noise, a graphic on a user interface display, or combinations thereof.

18. The warning step includes:

17. The method of claim 16, wherein the method is activated by: 1) a preset ambient noise decibel level from a secondary audio collection device; 2) an analysis of the signal-to-noise ratio from the primary audio collection device versus the secondary audio collection device; and 3) processing of noise received by the secondary audio collection device due to false triggering of a spectral event above a preset threshold.

19. The method of claim 11 , wherein the predicted spectral event is MH4.

20. The device of claim 1 , wherein the device comprises a warning indicator for false signals caused by excessive ambient noise.

Images