Patent Application
20150196269
The present invention is directed to a system and method where a patient in a remote location records audio of their breathing/coughing sounds using a handheld device such as a smartphone, and then communicates that audio to a medical profession in another location whereby a preliminary diagnosis is made whether the patient has an acute respiratory infection by a comparison of the patient's audio to known signals contained in a database of signals associated with differing severities of various acute respiratory conditions.
Pneumonia is a major cause of mortality in young children. An acute respiratory infections (ARI) control program developed by the World Health Organization (WHO) has been implemented in various developing countries resulting in a significant decrease in pneumonia related deaths. However, the decrease in mortality is not yet sufficient to reach objectives set forth by the Millennium Developmental Goal, i.e., reduce by two thirds the mortality rate of children 5 years old or younger by the year 2015. Studies conducted by the WHO for Integrated Management of Childhood Illness (IMCI) in developing countries reveal that improvement in case management skills of health-care staff, family and community health practices can have significant impact on health worker performance and their quality of care and the reduction of under-five mortality and improved nutritional status. Their studies also emphasize that implementation of child survival interventions need to be supplemented by activities that strengthen the system support. Large-scale intervention coverage is a needed to achieve these goals. Moreover, the child must be recognized as needing clinical care as promptly as possible. In primary health care facilities, detection and referral of sick children to the required level of medical intervention is essential for further decrease in mortality rate of children with pneumonia. The teachings hereof are in furtherance of this effort.
Accordingly, what is needed in this art is a system and method which can facilitate the determination, by a medical professional, whether a patient in a remote location has an acute respiratory infection.
The following U.S. patents, U.S. patent applications, and Publications are incorporated herein in their entirety by reference.
What is disclosed is a system and method for remotely determining whether a patient has an acute respiratory infection. The sole device required on the patient side is a handheld device, preferably a cellphone with audio/video capture capability and enabled for wireless communication. Patients acquire audio of their breathing/coughing using the microphone built into the device. Audio signals acquired are transmitted by the handheld device to a remote computing device for analysis and preliminary diagnosis of acute respiratory cases with or without the advice of a medical specialist. The present invention leverages prevailing wired and wireless infrastructures which are increasingly reliable in most countries. Embodiments hereof enable infectious respiratory diseases to be identified, treated, tracked and studied.
In one embodiment, a handheld device such as, for example, a smartphone, a tablet, a notebook, and a laptop, is used to acquire an audio signal of a breathing sound of a respiratory patient in a remote location. The acquired audio signal of the patient's breathing sounds is communicated by the handheld device to a remote computing device, i.e., the location of the patient is different (perhaps substantially different) than the location of the computing device. For example, the patient may reside in a village away from a population center while the computing device is in a hospital in a faraway city. If the handheld device is a handheld cellular device then the acquired audio signals are wirelessly communicated to the remote computing device utilizing, for instance, a wireless cellular protocol. The remote computing device receives the acquired audio signal and retrieves, from a database, audio signals that are associated with various acute respiratory conditions. A comparison is then made between the patient's audio signal and the signals retrieved from the database. As a result of the comparison, a determination is made whether the patient has an acute respiratory condition. As used herein, an acute respiratory invention is an upper respiratory tract infection (URI) and/or a lower respiratory tract infection (LRI). The audio signal may be distributed to other medical professionals, secondary and tertiary service providers, governmental agencies, and disease control centers, for further analysis, longitudinal study, data compilation, and the like.
Many features and advantages of the above-described system and method will become readily apparent from the following detailed description and accompanying drawings.
The foregoing and other features and advantages of the subject matter disclosed herein will be made apparent from the following detailed description taken in conjunction with the accompanying drawings, in which:
What is disclosed is a system and method for determining whether a patient in a remote location has an acute respiratory infection.
A “patient” refers to a person for which a determination is intended to made whether or not they have an acute respiratory infection. The use of the term “patient” is not intended to limit the scope of the appended claims solely to people who are currently under the care of a physician. Rather, it refers to anyone to be diagnosed for an acute respiratory infection in accordance with the teachings hereof.
An “acute respiratory infection” refers to an upper respiratory tract infection and/or a lower respiratory tract infection, as are generally understood. Such infections may indicate a potentially life threatening respiratory condition such as pneumonia. Generally, an acute respiratory infection is considered pneumonia when the patient has a respiratory rate of either at least 60 bpm and the patient's age is less than 2 months, at least 50 bpm and the patient's age is between 2 to 12 months, and at least 40 bpm and the patient's age is between 12 to 60 months.
An “audio signal” is an electronic recording of the breathing/coughing sound made by the patient. The audio signal is communicated by the handheld device to a remote computing device and is used to determine whether the patient has an acute respiratory infection. The electronic recording can be edited, manipulated, transmitted, received, stored, and played. The audio signal may be processed to identify a breathing pattern for the patient which can help in the determination of the patient's respiratory condition.
A “breathing sound” is a sound of the patient breathing/coughing over a plurality of respiratory cycles.
A “cough” (also called “tussis”) is a rapid expulsion of air from the lungs typically in order to clear the lung airways of fluids, mucus, or other matter. Coughing can be voluntary or involuntary. Involuntary coughing is a reflexive event initiated by the lining of the airways. Coughing sounds include: a dry cough (also called a non-productive cough), a wet cough (also called a productive cough), a croup cough (also called a barking cough), a whooping cough (an infectious disease known as Pertussis), a psychogenic cough (also called a habit cough), and a reflex cough caused by having inhaled an irritant of some type from the environment. Each of these coughs is associated with a severity of acute respiratory infection. Different types of cough have different acoustic characteristics. The type of cough most associated with pneumonia is typically a productive/wet cough. Outbound air hits the mucus in the airways and so this type coughing sound typically will have a bulge at lower frequencies.
A “handheld device” is a device which is used to acquire an audio signal of the patient's breathing. The handheld device may be, for example, a smartphone, a tablet, a notebook, and a laptop. One such handheld device is shown and discussed with respect to
A “remote computing device” is a device which is used herein to facilitate a determination of the patient's respiratory condition. Example remote computing devices include: an ASIC, a smartphone, a tablet, a notebook, a laptop, a server, a mainframe, a computer workstation, or any combination thereof. In one embodiment, the computing device is configured to communicate back to the handheld device using either a wired or wireless protocol. In one embodiment hereof, a notification is communicated by to patient via the handheld device. The notification may be, for example, an audio message, a text message, an email, a phone call, a video, and an alert signal. Use of the term “remote” means that the computing device is remote from the handheld device, i.e., their locations are different. It can equally be said that the handheld device is remote from the computing device. The handheld device may be used by a patient in a remote village while the computing device is located in a city which has a medical facility or medical offices. Conversely, the handheld device may be used by a patient in the city while the computing device is in a remote village. The two devices may be located in the same village or city, or in different cities, or in different countries. As such, the term “remote computing device” should not be viewed as limiting the scope of the appended claims strictly to computing devices located in remote areas. Various handheld devices available in differing streams of commerce have a female audio-in port which receives a male audio jack. In one embodiment, a microphone is plugged into the audio-in port and used to capture the breathing sounds. In other embodiments, a stethoscope configured to have a male audio jack is plugged into the audio-in port of the handheld device and the stethoscope is used to receive breathing sounds therethrough. In some embodiments, the audio signal is a streaming audio signal that is acquired and communicated to the remote computing device in real-time.
“Communicating the audio signal” means electronically transmitting the audio signal to the computing device. If the handheld device is, for example, a smartphone capable of utilizing wireless cellular communication then the acquired audio signals are transmitted wirelessly over cell-towers. It should be appreciated that the audio signal being communicated by the handheld device to the computing device may utilize both wired and wireless pathways while traversing the distance therebetween.
An “audio playback device”, as is generally understood, is a device which is capable of receiving an audio signal and playing that signal through a speaker so that the signal can be heard by the human auditory system. Although one or both of the handheld device and the computing device may utilize audio playback functionality, the audio playback device may, at least partially, be a separate sound system.
A “database of known signals” that are associated with differing severities of various acute respiratory conditions can be readily generated by digitally recording the breathing sounds of patients who have already been diagnosed with a respiratory condition, and storing those signals in the database. Known signals can be processed, as needed, such that these are made more readily comparable to the audio signals acquired herein using the handheld device. Such processing may include: removing background noise and spurious anomalies, normalization, detrending, amplitude adjustment, frequency and/or phase shifting, linear response compensation (equalization), peak/valley detection, averaging, energy computation, converting to an FFT frequency representation, to name a few. Such methods are well understood in the signal processing arts. Signals or portions thereof may be weighted, as desired. The signals stored in the database are retrieved and compared to the audio signals of the patient. In the training phase, cough signals along with the corresponding ground truth labels (e.g., whether a cough or not and whether pneumonia or not) from health experts would be needed to derive salient acoustic features and/or to select discriminative features. A statistical classifier can then be trained to hypothesize presence or absence of an acute respiratory infection and a classification confidence can be used to estimate the severity of the condition.
“Comparing signals” is intended to be widely construed. The comparison of two signals can be effectuated in a variety ways. For example, two signals can be overlaid and a difference computed. This difference can be compared to a pre-defined threshold to determine whether there is a match therebetween sufficient for medical diagnostic purposes. Specialized circuitry, such as that in an ASIC, can perform quantitative analysis between two input signals and provide, as an output thereof, the differences between the two. For instance, an integral spectrum can be calculated for signal fragments using, for example, a discrete cosine transformation (DCT) and a level of spectrum energy determined and used for comparison purposes. Moreover, other data points such as, for instance, patient age, sex, race, symptoms such as fever, aches, pains, color of phlegm or sputum, persistence, duration, and health vitals, some or all of which have been associated with the audio signals can also be utilized as factors to facilitate a comparison between two audio signals. The method used for comparison will depend on the nature of the system wherein the teachings hereof find their implementation.
Reference is now being made to
Handheld device 100 is a mobile cellular device which utilizes in wireless cellular network.
It should be appreciated that the handheld device of
Reference is now made to the flow diagram of
At step 702, use a handheld device to acquire an audio signal of a breathing sound made by a patient. One example handheld device for acquiring an audio signal is shown and discussed with respect to
At step 704, communicate the acquired audio signal to a remote computing device over a wired or wireless connection. If the handheld device of
At step 706, retrieving a next signal from a database of signals associated with different severities of various acute respiratory conditions. On a first iteration hereof, the next signal retrieved is a first signal. On successive iterations, a next signal is retrieved until there are no more signals or until a matching signal has been found.
At step 708, compare the retrieved signal to the received audio signal.
At step 710, a determination is made whether, as a result of the comparison of step 708, there is a match sufficient for medical diagnostic purposes. If so then processing continues with respect to step 712. Otherwise, processing continues with respect to node B.
At step 712, determine that the patient has an acute respiratory infection.
Reference is now being made to the flow diagram of
At step 714, communicate a notification to the patient. Such a notification can be, for instance, what the patient needs to be doing next in terms of medicine, hospitalization, medical attention, and the like.
At step 716, a determination is made whether an alert condition exists. If so then, at step 718, initiate an alert signal to be sent out. The alert can be sent to, for example, another medical professional, a secondary or tertiary service provider, a government agency, and/or a disease control center. The alert may further include the received audio signal, the matching signal retrieved from the database, along with any other patient information that is deemed appropriate. If it is determined that an alert condition is not appropriate then processing continues with respect to node C.
If, at step 706, the signal retrieved from the database does not sufficiently match the audio signal for medical diagnostic purposes then, at step 720, a determination is made whether more signals remain in the database to be retrieved. If more signals remain in the database then processing continues with respect to node D wherein, at step 706, a next signal is retrieved from the database. This next signal is then compared to the patient's audio signal. A determination is made whether there is a sufficient match therebetween for medical diagnostic purposes. If so then a notification is provided to the patient. A determination is made whether an alert signal should be sent out. Processing repeats in such a manner until either a sufficiently matching signal has been found, or no more signals remain to be retrieved for comparison purposes. Thereafter, further processing stops.
It should be appreciated that the flow diagrams hereof are illustrative. One or more of the operations illustrated in the flow diagrams may be performed in a differing order. Other operations may be added, modified, enhanced, or consolidated. Variations thereof are intended to fall within the scope of the appended claims. Aspects of the flow diagrams will be implemented in hardware executing machine readable program instructions.
Reference is now being made to
In
The workstation implements a database 912 wherein signals associated with different severities of various acute respiratory conditions and other information are stored in a plurality of records (collectively at 913). As described with respect to steps 706 and 708 of
It should be appreciated that the remote computing device 907 has an operating system and other specialized software configured to display alphanumeric values, menus, scroll bars, dials, slideable bars, pull-down options, selectable buttons, and the like, for entering, selecting, modifying, and accepting information needed for processing video images and audio signals in a manner disclosed herein, and for enabling a medical practitioner to make a preliminary medical diagnosis based upon a comparison thereof. In other embodiments, results are communicated to one or more medical practitioners in various locations for their review and input. A practitioner may further communicate instructions back to the user via the handheld device, depending on the implementation. A user or technician may use the user interface of the workstation to set parameters, select image/signal portions for processing. These selections, including the received video images and audio signals, may be stored to storage 908 and 912. Default settings and initial parameters can be retrieved from either the storage devices, as needed.
A medical professional can distribute the video images 903 and/or the audio signals 904 to another medical professional, a tertiary service provider, a government agency, and a disease control center. Various kinds of aggregate summaries can be computed using the patient data. These include, but are not limited to: longitudinal analyses involving statistics of patient cases presented to the present system over a period of time; population-based studies of patients within sub-populations; geography-based studies involving patients in a specified geographical area; socio-economic community-based studies involving patients in a specified social or economic community; and epidemic studies wherein timelines of geographical spread (and severity) of different respiratory infections are formulated and analyzed. Rule based methods can be implemented on the workstation that alert registered government bodies when specific interventions are needed. For example, if the number of infectious cases in a given geography is more than a specified threshold, an alert can be sent out to contain a potential epidemic. Population based and socio-economic statistics sent out by the system can be used to derive healthcare policies by the government agencies. By combining the knowledge of genetic factors from public databases/literature, more sophisticated modeling and analyses can also be performed.
Although shown as a computer workstation, it should be appreciated that the remote computing system can be: an ASIC, a smartphone, a tablet, a notebook, a laptop, a server, a mainframe, and a workstation. The embodiment of the workstation of
The teachings hereof can be implemented in hardware or software using any known or later developed systems, structures, devices, and/or software by those skilled in the applicable art without undue experimentation from the functional description provided herein with a general knowledge of the relevant arts. One or more aspects of the methods described herein are intended to be incorporated in an article of manufacture. The article of manufacture may be shipped, sold, leased, or otherwise provided separately either alone or as part of a product suite or a service.
It will be appreciated that the above-disclosed and other features and functions, or alternatives thereof, may be desirably combined into other different systems or applications. Presently unforeseen or unanticipated alternatives, modifications, variations, or improvements may become apparent and/or subsequently made by those skilled in this art which are also intended to be encompassed by the following claims. The teachings of any publications referenced herein are each hereby incorporated by reference in their entirety.
