A computer implemented method for determining a probability of the diseases and functional states of homeostatsis systems by deviations in the function of the lymphovenous junction

Abstract

A computer implemented method for determining a probability of a presence of pathology and / or functional disorder based on an acoustic recording of a lymphovenous junction, the method comprising; extracting a set of characteristic features from the acoustic recording, determining a set of quantitative values, such that, for each characteristic feature in the set of characteristic features, a quantitative value in the set of quantitative values indicate the characteristic feature's significance for the presence of pathology and / or functional disorder.

Description

[0001] A COMPUTER IMPLEMENTED METHOD FOR DETERMINING A PROBABILITY OF THE DISEASES AND FUNCTIONAL STATES OF HOMEOSTATSIS SYSTEMS BY DEVIATIONS IN THE FUNCTION OF THE LYMPHO VENOUS JUNCTION

[0002] Technical field

[0003] The present invention relates to risk assessment of the occurrence or presence of diseases. More particularity, it relates to a method for determining the probability of occurrence or presence of a pathology and / or functional disorder based on an acoustic recording, wherein the recording may be represented e.g., by a curve, of the sphincter apparatus and the valves of a lymphovenous junction (LVJ).

[0004] Background of the invention

[0005] The application of new technologies within the MedTech industry has seen great improvements during the last couple of years. More and more advanced technologies are now available for doctors, for example when conducting medical examination and assistance in decision making.

[0006] However, improvements need to be made in this area. At least with regard to the early diagnosis of diseases, as well as, not excluding, disturbances in the homeostasis system in the body, which can lead to the development of diseases. Thus, there is a need for simpler and more effective methods accessible to general practitioners and even ordinary people, based on the use of Al computer applications for smartphones and computers.

[0007] The scientific group led by Professor Shamil Gantsev has been conducting fundamental research in the field of studying the lymphatic system, including states in cancer, for more than 25 years; the quintessence of the research results was the Atlas of Lymphatic System in Cancer: Sentinel Lymph Node, Lymphangiogenesis and Neolymphogenesis (Sh. Gantsev, K. Gantsev, Sh Kzyrgalin (Springer, Cham, 2020). These studies made it possible to come to an understanding of the importance of the lymphatic system for human health and the role of LVJ in the regulation of the homeostasis of hydrodynamic processes (Gantsev Sh.Kh., Kzyrgalin Sh.R., Gantsev K.Sh., Mansurova A.V. et al. Functional and anatomical features of the lymphovenous anastomosis / / Avicenna Bulletin. - 2022. - No. 24 (3). - P. 369-78). Further in- depth studies led to the identification of the significance of the functioning of the lymphovenous junction (LVJ) for the early detection of pathologies and functional disorders in the body, such as, but not limited to, changes in the physicochemical characteristics of lymph, lymphedema, lymphostasis, lymphangitis, chylothorax, ascites, dehydration, overhydration, hematocrit deviations.

[0008] Summary of the invention

[0009] In view of the above, the objective of the present invention is to create a method for determining the probability of the presence of pathologies and functional disorders in the body based on data obtained from recording the operation of a LVJ (left and right ones).

[0010] After fundamental research, it became clear that by assessing many characteristics and elements of the LVJ of a human being, or any mammal, without limitation, it is possible to accurately and effectively determine the probability of the presence of pathologies and functional disorders in the body. The advantage of the method is that it is not invasive and can be used not only at a hospital or a clinic, but at home and field conditions (it is not necessary to carry out it at an equipped medical institution).

[0011] This invention presents a computer-implemented method for determining the probability of the presence of pathologies and functional disorders in the body using an acoustic recording of the lymph, blood and their mixture movement through the LVJ.

[0012] Graphical representations may be plotted, based on the acoustic recording, both for separate LVJ operation and for synchronous or asynchronous operation of the LVJ with the heart.

[0013] Elements of the LVJ and some of their parameters (not limited to those listed) that are significant for identifying the probability of pathologies are:

[0014] ■ veins (subclavian vein, internal jugular vein, brachiocephalic vein);

[0015] ■ thoracic lymphatic duct (has anatomical heterogeneity in the terminal section, which flows into the veins);

[0016] ■ valves and sphincter apparatus;

[0017] ■ lymph, blood and their mixtures.

[0018] Original photos (inventors' own data - autopsy material) of anatomical preparations of the LVJ are presented in Fig. 1-2.

[0019] The main hydrodynamic load falls on the left LVJ, which is connected with the lymphatic and blood circulatory systems.

[0020] The method may further comprise: determining a weighted sum of the quantitative values of the at least one element of each identified feature of the acoustic recording of LVJ operation, wherein each weight relates to a significance that the corresponding element has when assessing a grade of the disease, comparing the weighted sum with a set of predetermined sums with known grades of the disease, and obtaining the grade of the disease as the known grade of the predetermined sum that best matches the weighted sum.

[0021] The term “grade of the disease” may be interpreted as a severity of the disease. Alternatively, it may be interpreted as a stage or degree of the disease. In other words, how far progressed the disease are.

[0022] A possible related advantage of the method described above is that the development of a disease or substrate for the development of a disease can be monitored, for example to see if there is a reason to start treatment or to see if current treatment works or to make recommendations for change lifestyle to avoid the development of pathology.

[0023] The proposed method for predicting and preventing diseases, based on studies of the functioning of the sphincter apparatus and valves of LVJ, has the potential advantage of being able to monitor the progression of pathology. This approach allows the evolution of the disease to be tracked, which may be important for determining the need to initiate treatment or assessing the effectiveness of current therapy. In other words, the development of an identified disease or functional disorder can be monitored. Thus, disease monitoring using this method can be effective in terms of optimizing costs and time, since it does not require regular visits to medical institutions.

[0024] Further, an advantage of weighting the elements may be that different element may be more indicative of the disease than others. Thus, a more accurate results may be achieved. This approach reduces the number of false positive and false negative results.

[0025] The act of determining the probability of the disease may be based on a dataset of images representative of an acoustic recording of LVJ operation. The dataset may comprise of multiple subsets of images. Each subset of images may be related to a specific disease and / or functional state.

[0026] The act of determining the probability of the disease may be performed by a machine learning, ML, model, such as a neural network. The ML model may be trained using the dataset of images representative of an acoustic recording of LVJ operation, with or without disease / diseases, but not limited to.

[0027] The neural network may be a combined convolutional and recurrent neural network, but not limited to. The method may further comprise receiving a user input indicating what disease to look for and selecting only the identified features that are relevant for the disease. Relevant for the disease may be that they are indicative of the occurrence of the disease.

[0028] A possible associated advantage may be that computational resources may be saved, and less data transferred by knowing what features and elements is to be analyzed.

[0029] A user device configured to determine the probability of a disease using the proposed method can be presented in at least 3 options, without limitation.

[0030] Option 1 , Screening for the mass user

[0031] The user device comprises a mobile phone with an installed software application to determine the probability of LVJ operation deviation from the normal state.

[0032] This option can be used both by the common user without medical education for personal purposes of screening for the probability of abnormalities in the body’s functioning, and by medical professionals.

[0033] Option 2, Screening to assess the probability of various diseases

[0034] The user device contains:

[0035] ■ a mobile phone with an installed software application to determine the probability of various diseases based on deviations in the LVJ operation;

[0036] ■ additional acoustic sensors.

[0037] This option can be used both by the common user without medical education for personal purposes of screening for the of abnormalities in the body’s functioning, and by medical professionals.

[0038] Option 3, Accurate screening

[0039] The user device contains:

[0040] ■ a specialized computer device with ultra-sensitive acoustic sensors, developed for this method, with an installed software application for determining the probability of various diseases based on deviations in the LVJ operation.

[0041] This option can be used by doctors in medical institutions only. A schematic diagram of the user device (using the example of implementation option 1) and options for projection of acoustic recording points onto the anterior chest wall are presented in Fig. 3 and Fig. 4.

[0042] Brief description of the figures

[0043] Examples of the present disclosure will be described in more detail with reference to the appended drawings. In the following drawings like reference numbers are used to refer to like elements. Although the following figures depict various examples, one or more implementations are not limited to the examples depicted in the figures.

[0044] FIG. 1 illustrates a macroscopic specimen of LVJ

[0045] FIG. 2 illustrates a macroscopic specimen of LVJ, isolated by ultrasonic treatment of tissues

[0046] FIG. 3 illustrates an example of user device with implementation according to Option 1

[0047] FIG. 4 illustrates an example of projection points of the heart and LVJ for an acoustic recording

[0048] FIG. 5 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; a2 - right LVJ is normal; b - heart is normal (mitral valve)

[0049] FIG. 6 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl -left LVJ of patient with ascites; a2 - right LVJ is normal; b2 - right LVJ of patient with ascites

[0050] FIG. 7 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of patient with heart failure; a2 - right LVJ is normal; b2 - right LVJ of patient with heart failure

[0051] FIG. 8 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of cancer patients with metastasis; a2 - right LVJ is normal; b2 - right LVJ of cancer patients with metastasis

[0052] FIG. 9 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of patient who suffered from myocardial infarction, 6 months after the acute state; a2 - right LVJ is normal; b2 - right LVJ of patient who suffered from myocardial infarction, 6 months after the acute state

[0053] FIG. 10 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of pregnant woman (25 weeks) with lower extremities edema; a2 - right LVJ is normal; b2 - right LVJ of pregnant woman (25 weeks) with lower extremities edema FIG. 11 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl- LVJ in dehydrated body; a2 - right LVJ is normal; b2 - right LVJ in dehydrated body

[0054] FIG. 12 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of healthy young person after 5 minutes intense physical activity; a2 - right LVJ is normal; b2 - right LVJ of healthy young person after 5 minutes intense physical activity

[0055] FIG. 13 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of patient with type II diabetes mellitus; a2 - right LVJ is normal; b2 - right LVJ of patient with type II diabetes mellitus

[0056] FIG. 14 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; b2 - left LVJ of patient after an acute cerebrovascular accident; a2 - right LVJ is normal; b2 - right LVJ of patient after an acute cerebrovascular accident

[0057] FIG. 15 illustrates a graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of patient with type II diabetes mellitus and malignant neoplasm; a2 - right LVJ is normal; b2 - right LVJ of patient with type II diabetes mellitus and malignant neoplasm

[0058] Detailed Description

[0059] Together with the attached drawings, the technical contents and description of the present invention are described hereinafter according to examples that are not intended to limit the claimed scope. This invention may be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these examples are provided to facilitate the understanding of the inventive concepts, and to convey the scope of the invention to the skilled person.

[0060] According to a first aspect, there is provided a computer implemented method for determining a probability of a presence of pathology and / or functional disorder based on an acoustic recording of a lymphovenous junction, the method comprising extracting a set of characteristic features from the acoustic recording, determining a set of quantitative values, such that, for each characteristic feature in the set of characteristic features, a quantitative value in the set of quantitative values indicate the characteristic feature’s significance for the presence of pathology and / or functional disorder.

[0061] The acoustic recording may comprise acoustics of lymphovenous junction activity, and separate acoustics of lymphovenous junction activity being synchronous and / or asynchronous with a heart activity. The method may further comprise determining a weighted sum of quantitative values from the set of quantitative values, wherein each weight relates to a significance that the corresponding element in the set of characteristic features has when assessing a grade of the pathology and / or functional disorder, comparing the weighted sum with a set of predetermined sums with known grades of the pathology and / or functional disorder, and obtaining the grade of the pathology and / or functional disorder as the known grade of the predetermined sum that best matches the weighted sum.

[0062] The acoustic recording may be represented in a set of graphical representations, such that extracting a set of characteristic features from the acoustic recording comprises extracting characteristic features from the set of graphical representations.

[0063] An acoustic recording may be effectively represented through a set of graphical representations, transforming the acoustic information into visual formats. This transformation process may involve converting the acoustic signal into a digital format, which allows for detailed analysis and visualization. The digital acoustic data can be processed to extract various features, such as amplitude, frequency, and time, which are then represented graphically. Common graphical representations include waveforms, spectrograms, and frequency spectra. A waveform graph displays the acoustic signal's amplitude over time, providing a clear view of the sound's dynamics. Spectrograms offer a three-dimensional view, showing how the frequency content of the acoustic signal evolves over time, with intensity indicated e.g., by color or brightness. Frequency spectra illustrate the distribution of signal power across different frequencies at specific time intervals. These graphical representations may facilitate a deeper understanding and analysis of acoustic recordings, allowing for the identification of patterns, anomalies, and other characteristics. The visual approach may enhance the ability to interpret, compare, and manipulate acoustic data.

[0064] Determining the probability of the presence of pathology and / or functional disorder may performed by a machine learning model, such as a neural network, decision tree, support vector machine, random forest, and / or ensemble model.

[0065] Extracting a set of characteristic features from the acoustic recording is performed by a machine learning model, such as a neural network, decision tree, support vector machine, random forest, and / or ensemble model.

[0066] The machine learning model may be configured e.g., to receive and process input data, thereby transforming raw inputs into a format suitable for analysis; extract relevant features from the input data, identifying key characteristics and patterns that are critical for accurate modeling; learn patterns and relationships within the data through training on a dataset, where the model iteratively adjusts its parameters to improve its understanding and performance; apply the learned model to make predictions or classifications based on new input data, utilizing the insights gained during training to provide accurate and reliable outputs; continuously improve its performance through iterative learning and adaptation, incorporating new data and feedback to refine its accuracy and effectiveness over time; optimize the overall efficiency and accuracy of the method through advanced data analysis techniques, employing sophisticated algorithms to enhance the model's predictive power and reduce computational overhead; and / or to integrate results from multiple models to enhance robustness and reliability, combining the strengths of various approaches to mitigate individual model weaknesses and improve overall decision-making.

[0067] At least one characteristic feature in the set of characteristic features may be based on acoustics of lymph, blood and / or the mixture of lymph and blood moving through the lymphovenous junction (LVJ). A characteristic feature may be based e.g., on flow rate, flow velocity, pressure, temperature, viscosity, and / or fluid density. A characteristic feature may further be based on turbulence characterization, including e.g., turbulence intensity and / or scale. Acoustic parameters that may serve as a base for a characteristic feature may include sound pressure level (SPL), frequency, wavelength, speed of sound, acoustic impedance, attenuation, reflection and transmission coefficients, and / or acoustic power. Combining flow and acoustic measurements may require attention to factors such as flow-induced noise, measurement accuracy, signal interference, calibration of equipment, and the physical properties of lymph, blood and / or the mixture of lymph and blood. At least one characteristic feature in the set of characteristic features may be based on at least one of Peak systolic velocity, End-diastolic velocity, Time-averaged maximum velocity, Flow acceleration, Pulsatility index, Resistive index, Waveform shape, Systolic upstroke time, Diastolic decay, Dicrotic notch, Mean velocity, Flow volume, Spectral broadening, Anterograde and / or retrograde flow and Vessel wall motion.

[0068] - Peak systolic velocity (PSV): The maximum flow velocity during the cardiac systole.

[0069] - End-diastolic velocity (EDV): The flow velocity at the end of the cardiac diastole.

[0070] Time-averaged maximum velocity (TA V): The average of the maximum velocities over the cardiac cycle.

[0071] - Flow acceleration: The rate of change in flow velocity, particularly important in early systole. - Pulsatility index (PI): A measure of the variability in flow velocity, calculated as (PSV - EDV) / TAMV.

[0072] - Resistive index (RI): A measure of resistance within the vessel, calculated as (PSV - EDV) / PSV.

[0073] - Waveform shape: The overall contour of the waveform, indicating the type of flow (laminar or turbulent).

[0074] Systolic upstroke time: The time it takes for the flow velocity to reach its peak from the onset of systole.

[0075] - Diastolic decay: The rate at which the flow velocity decreases during diastole.

[0076] - Dicrotic notch: A small downward deflection in the waveform following the systolic peak, representing the closure of the aortic valve.

[0077] - Mean velocity: The average flow velocity over the cardiac cycle.

[0078] - Flow volume: The total volume flowing through the vessel per unit time.

[0079] Spectral broadening: The widening of the range of velocities present in the waveform, often indicating turbulent flow.

[0080] Anterograde and retrograde flow: The presence and pattern of forward (anterograde) and backward (retrograde) flow during the cardiac cycle.

[0081] Vessel wall motion: Changes in the waveform that might indicate movement or compliance of the vessel wall.

[0082] The characteristic features listed above provide critical insights into the hemodynamic behavior within vessels and may be important for diagnosing vascular conditions and assessing treatment outcomes. By analyzing these characteristics, such as peak systolic velocity, end-diastolic velocity, and pulsatility index, a detailed understanding of vascular health may be facilitated. This analysis may enable the identification of potential abnormalities, such as variations in flow velocity, pressure gradients, and vessel wall motion.

[0083] The data derived can be compared against established normal values and patterns. This comparison may facilitate the determining of a probability of a presence of pathology and / or functional disorder.

[0084] The method may further comprise receiving a user input indicating at least one pathology and / or functional disorder, selecting only characteristic features that are associated with the indicated at least one pathology and / or functional disorder.

[0085] Receiving a user input indicating at least one pathology and / or functional disorder may comprise obtaining input from a user that specifies at least one pathology and / or functional disorder. This input can be gathered through various means such as a graphical user interface, voice command, or any other suitable method that allows the user to convey their preferences effectively. Upon receiving the user input, only characteristic features that are associated with the indicated at least one pathology and / or functional disorder may be selected. The term "selecting" in this context refers to the process of filtering and isolating relevant features from a larger set of characteristic features, based on their association with the user's preferences. This involves matching the user's preferences against a predefined mapping or database that links preferences to specific characteristic features. The system ensures that only the characteristic features relevant to the user’s input are chosen, thereby tailoring the output or response to the user's indicated preferences.

[0086] According to a second aspect, there is provided a device comprising a processor and a memory, the device being configured to determine a probability of a presence of pathology and / or functional disorder based on an acoustic recording according to any one of claims 1 to 8.

[0087] A device comprising a processor and a memory, such as a computer, mobile phone, tablet, or smartwatch, configured to determine a probability of a presence of pathology and / or functional disorder based on an acoustic recording, enables users to obtain accurate indications of potential pathological conditions. This capability enhances diagnostic accuracy and efficiency, allowing healthcare professionals and patients to make informed decisions based on reliable data. The device may facilitate early detection and monitoring of health conditions, which may be important for effective treatment and management.

[0088] The device may be a mobile device, such as a smartphone or tablet, offering the advantage of portability and ease of use. This allows for continuous health monitoring in various settings, providing users with immediate access to health assessments regardless of their location. The mobility ensures that patients can monitor their health in real-time and receive timely updates, which is particularly beneficial in managing chronic conditions or tracking the progression of symptoms.

[0089] Alternatively, the device may be a computer system configured to perform more sophisticated computing tasks. Such a system can leverage greater processing power and advanced algorithms to analyze complex health data, offering more detailed and comprehensive health insights. This configuration is ideal for healthcare facilities and research institutions where in-depth analysis and high computational resources are required to support advanced diagnostics and personalized treatment plans. The device may further comprise at least one acoustic sensor.

[0090] The at least one acoustic sensor may be positioned on regions of the body near and / or directly above the lymphovenous junction. This may enable the detection and amplification of sound waves generated by the lymphovenous junction. The acoustic sensor may provide valuable acoustic information that can be recorded and analyzed to assess a probability of a presence of pathology and / or functional disorder.

[0091] The recorded acoustic data may be normalized, e.g., to ensure consistent amplitude levels and to provide a standardized basis for analysis. Artifacts, which may include unwanted noise and interference from various sources, may be removed to enhance the quality of the signal. Spectral analysis may be used to identify and isolate non-physiological frequency components, which may then be filtered out through adaptive filtering methods. Specific noise frequencies may be suppressed using notch filters. Machine learning algorithms may be employed to distinguish between genuine physiological sounds and extraneous noise based on patterns learned from large datasets. Additionally, other sound enhancement techniques such as smoothing, dynamic range compression, and signal amplification may be utilized to further improve the clarity and fidelity of the recorded data, ensuring that the resulting acoustic signal is both accurate and reliable for assessing a probability of a presence of pathology and / or functional disorder.

[0092] Acoustic sensors, e.g., microphones and / or sound sensors, are configured for detecting sound waves and transforming the sound waves into electrical signals for further processing, storage, and / or transmission. Acoustic sensors can range from basic transducers integrated into mobile devices and / or external devices, to sophisticated arrays connected to sophisticated computing systems. In the former case, these sensors are typically designed for general acoustic capture, and may be optimized for portability and power efficiency. When attached to sophisticated computing systems, the acoustic sensors may be configured for more advanced signal processing. The acoustic sensors may serve in high-fidelity recording with a greater sensitivity and a broader dynamic range. The device configured to determine a probability of a presence of pathology and / or functional disorder based on an acoustic recording, may comprise at least one acoustic sensor. For example, the device may be a mobile device wherein an integrated microphone serve as acoustic sensor. An external acoustic sensor may further be connected to the mobile device. Alternatively, the device may be a computer system configured to perform more sophisticated computing, wherein an external acoustic sensor is connected to the sophisticated computing system. The external acoustic sensor may e.g., be adapted for general acoustic capture. Alternatively, external acoustic sensor may be adapted for high-fidelity recording.

[0093] A gel may be used with the at least one acoustic sensor. The application of gel with an acoustic sensor may be used to ensure optimal contact and signal transmission between the sensor and the skin. The gel serves as a coupling medium, reducing the impedance mismatch at the interface and minimizing air gaps that can cause signal degradation. By providing a continuous medium for sound waves to travel through, the gel enhances the quality and clarity of the recorded acoustic data.

[0094] According to a third aspect, there is provided a computer program having instructions which when executed by a data-processing system cause the data-processing system to perform the method presented herein.

[0095] The computer program may be a standalone program or a module within a larger software ecosystem. It can be written in any suitable programming language and can be executed on various types of computing systems, including but not limited to personal computers, servers, mobile devices, embedded systems, and cloud-based virtual machines.

[0096] The computer program may be stored on a physical storage medium, such as a hard disk drive or a solid-state drive, or it may be hosted on a network server and accessed over the internet. The instructions of the software application can be loaded into the memory of the computing system and executed by the processing unit of the system.

[0097] According to a fourth aspect, there is provided computer-readable non-transitory medium comprising instructions which, when executed by a computer, cause the computer to carry out the method presented herein.

[0098] The computer-readable non-transitory medium can be any form of storage device that can retain data for a period of time, even when power is not supplied. Examples include, but are not limited to, hard disk drives, solid-state drives, USB flash drives, memory cards, ROM, and optical discs like CD, DVD, and Blu-ray.

[0099] The instructions may be read and executed by the processing unit of the computer. This allows the computer to carry out the method as described herein.

[0100] The inventive concept has mainly been described with reference to a limited number of examples. However, as is readily appreciated by a person skilled in the art, other examples than the ones disclosed above are equally possible within the scope of the inventive concept, as defined by the appended claims. EXAMPLES

[0101] Example 1. Differences in graphical representations of acoustic recordings of LVJ and the heart

[0102] Comparative graphical representations of acoustic recordings of LVJ in normal state and of the heart (projection of the mitral valve) and are shown in Fig. 5. There are significant differences in amplitude and shape of signal.

[0103] Fig. 5. Graphical representations of acoustic recordings: al - left LVJ is normal; a2 - right LVJ is normal; b - heart is normal (mitral valve).

[0104] Example 2, Differences in graphical representations of acoustic recordings of the LVJ in normal state and in ascites

[0105] Comparative graphical representations of acoustic recordings of LVJ operation in normal state and in ascites are shown in Fig. 6. There are significant differences in amplitude and shape of signal.

[0106] Fig. 6. Graphical representations of acoustic recordings: al - left LVJ is normal; bl -left LVJ of patient with ascites; a2 - right LVJ is normal; b2 - right LVJ of patient with ascites

[0107] Example 3, Differences in graphical representations of acoustic recordings of the LVJ in normal state and in heart failure

[0108] Comparative graphical representations of acoustic recordings of LVJ operation in normal state and in heart failure are shown in Fig. 7. There are significant differences in amplitude and shape of signal.

[0109] Fig. 7. Graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of patient with heart failure; a2 - right LVJ is normal; b2 - right LVJ of patient with heart failure.

[0110] Example 4, Differences in graphical representations of acoustic recordings of LVJ in normal state and in cancer Comparative graphical representations of acoustic recordings of LVJ in normal state and in cancer are shown in Fig. 8. There are significant differences in amplitude and shape of signal.

[0111] Fig. 8. Graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of cancer patients with metastasis; a2 - right LVJ is normal; b2 - right LVJ of cancer patients with metastasis.

[0112] Example 5, Differences in graphical representations of acoustic recordings of the LVJ in normal state and after myocardial infarction

[0113] Comparative graphical representations of acoustic recordings of LVJ in normal state and after myocardial infarction are shown in Fig. 9. There are significant differences in amplitude and shape of signal.

[0114] Fig. 9. Graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of patient who suffered from myocardial infarction, 6 months after the acute state; a2 - right LVJ is normal; b2 - right LVJ of patient who suffered from myocardial infarction, 6 months after the acute state.

[0115] Example 6, Differences in graphical representations of acoustic recordings of the LVJ in normal state and in a pregnant woman with edema of the lower extremities

[0116] Comparative graphical representations of acoustic recordings of LVJ operation in normal state and in a pregnant woman with edema of the lower extremities are presented in Fig. 10. There are significant differences in amplitude and shape of signal.

[0117] Fig 10. Graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of pregnant woman (25 weeks) with lower extremities edema; a2 - right LVJ is normal; b2 - right LVJ of pregnant woman (25 weeks) with lower extremities edema.

[0118] Example 7, Differences in graphical representations of acoustic recordings of LVJ in normal and in dehydrated body Comparative graphical representations of acoustic recordings of LVJ in normal state and with dehydration of the body are shown in Fig. 11. There are significant differences in amplitude and shape of signal.

[0119] Fig 11. Graphical representations of acoustic recordings: al - left LVJ is normal; bl- LVJ in dehydrated body; a2 - right LVJ is normal; b2 - right LVJ in dehydrated body.

[0120] Example 8, Differences in graphical representations of acoustic recordings of LVJ in normal state and in a healthy young person after intense physical exercise

[0121] Comparative graphical representations of acoustic recordings of LVJ in normal state and after intense physical activity are shown in Fig. 12. There are significant differences in amplitude and shape of signal.

[0122] Fig. 12. Graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of healthy young person after 5 minutes intense physical activity; a2 - right LVJ is normal; b2 - right LVJ of healthy young person after 5 minutes intense physical activity.

[0123] Example 9, Differences in graphical representations of acoustic recordings of LVJ in normal state and in type II diabetes mellitus

[0124] Comparative graphical representations of acoustic recordings of LVJ in normal state and in type II diabetes mellitus are shown in Fig. 13. There are significant differences in amplitude and shape of signal.

[0125] Fig.13. Graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of patient with type II diabetes mellitus; a2 - right LVJ is normal; b2 - right LVJ of patient with type II diabetes mellitus.

[0126] Example 10. Differences in graphical representations of acoustic recordings of LVJ in normal state and after acute cerebrovascular accident Comparative graphical representations of acoustic recordings of LVJ in normal state and after acute cerebrovascular accident are shown in Fig. 14. There are significant differences in amplitude and shape of signal.

[0127] Fig. 14. Graphical representations of acoustic recordings: al - left LVJ is normal; b2 - left LVJ of patient after an acute cerebrovascular accident; a2 - right LVJ is normal; b2 - right LVJ of patient after an acute cerebrovascular accident

[0128] Example 11. Differences in graphical representations of acoustic recordings of LVJ in normal state and in a combination of type II diabetes mellitus and malignant neoplasm with distant metastases

[0129] Comparative graphical representations of acoustic recordings of LVJ in normal state and in type II diabetes mellitus, as well as malignant breast neoplasm are shown in Fig. 15. There are significant differences in amplitude and shape of signal.

[0130] Fig. 15. Graphical representations of acoustic recordings: al - left LVJ is normal; bl - left LVJ of patient with type II diabetes mellitus and malignant neoplasm; a2 - right LVJ is normal; b2 - right LVJ of patient with type II diabetes mellitus and malignant neoplasm.

[0131] Fig. 1. illustrates a macroscopic specimen of LVJ: TLD - thoracic lymphatic duct, IJV - internal jugular vein, SV - subclavian vein, BCV - brachiocephalic vein. 3 lymphovenous anastomosis are shown in the lumen of the veins (indicated by arrows), 2 of which are divided into 2 additional passages equipped with valves.

[0132] Fig. 2. Illustrates a macroscopic specimen of LVJ, isolated by ultrasonic treatment of tissues. The outer side of the vein is shown, into which 3 branches (trunks) of the thoracic lymphatic duct go obliquely and open (indicated by an arrows). 2 main trunks of the TLD are shown, one of which (right), immediately before entering the vein, is divided into 2 small trunks.

[0133] Fig. 3 illustrates a diagram of a user device with implementation according to Option 1.

[0134] Fig. 4 illustrates a diagram of projection points of the heart and LVJ for an acoustic recording:

[0135] 1 - projection point of the apical impulse of the heart, the left border of the heart at the level of the 5th intercostal space; 2 - projection point of the aortic valve and the aortic orifice, II intercostal space directly at the right edge of the sternum; 3 - projection point of the pulmonary valve, II intercostal space directly at the left edge sternum; 4 - point of projection of the tricuspid valve and the right atrioventricular orifice, base of the xiphoid process; 5 - additional, point of projection of the mitral valve, place of attachment of the IV rib to the left edge of the sternum; 6 - additional projection of the aortic valve point, III intercostal space at the left edge of the sternum; 7, 8 - LVJ projection zones on the left and right, respectively, highlighted by a pentagon in color, but does not impose restrictions on listening at other points.

Claims

Claims1. A computer implemented method for determining a probability of a presence of pathology and / or functional disorder based on an acoustic recording of a lymphovenous junction, the method comprising; extracting a set of characteristic features from the acoustic recording, determining a set of quantitative values, such that, for each characteristic feature in the set of characteristic features, a quantitative value in the set of quantitative values indicate the characteristic feature’s significance for the presence of pathology and / or functional disorder.

2. The method according to claim 1, wherein the acoustic recording comprises acoustics of lymphovenous junction activity, and separate acoustics of lymphovenous junction activity being synchronous and / or asynchronous with a heart activity.

3. The method according to any one of the preceding claims, further comprising; determining a weighted sum of quantitative values from the set of quantitative values, wherein each weight relates to a significance that the corresponding element in the set of characteristic features has when assessing a grade of the pathology and / or functional disorder, comparing the weighted sum with a set of predetermined sums with known grades of the pathology and / or functional disorder, and obtaining the grade of the pathology and / or functional disorder as the known grade of the predetermined sum that best matches the weighted sum.

4. The method according to any one of the preceding claims, wherein the acoustic recording is represented in a set of graphical representations, such that extracting a set of characteristic features from the acoustic recording comprises extracting characteristic features from the set of graphical representations.

5. The method according to any one of the preceding claims, wherein determining the probability of the presence of pathology and / or functional disorder is performed by a machine learning model, such as a neural network, decision tree, support vector machine, random forest, and / or ensemble model.

236. The method according to any one of the preceding claims, wherein extracting a set of characteristic features from the acoustic recording is performed by a machine learning model, such as a neural network, decision tree, support vector machine, random forest, and / or ensemble model.

7. The method according to any one of the preceding claims, wherein at least one characteristic feature in the set of characteristic features is based on at least one of Peak systolic velocity, End-diastolic velocity, Time-averaged maximum velocity, Flow acceleration, Pulsatility index, Resistive index, Waveform shape, Systolic upstroke time, Diastolic decay, Dicrotic notch, Mean velocity, Flow volume, Spectral broadening, Anterograde and / or retrograde flow and Vessel wall motion.

8. The method according to any one of the preceding claims, further comprising; receiving a user input indicating at least one pathology and / or functional disorder, selecting only characteristic features that are associated with the indicated at least one pathology and / or functional disorder.

9. A device comprising a processor and a memory, the device being configured to determine a probability of a presence of pathology and / or functional disorder based on an acoustic recording according to any one of claims 1 to 8.

10. A device according to claim 9, the device further comprising at least one acoustic sensor.

11. A computer program having instructions which when executed by a data-processing system cause the data-processing system to perform the method according to any one of claims 1 to 8.

12. A computer-readable non-transitory medium comprising instructions which, when executed by a computer, cause the computer to carry out the method of any one of claims 1 to 8.

Images