Apparatus, system and method for non-invasive early warning for physical crisis

Abstract

A system, method and apparatus for providing a warning prior to a medical condition crisis is disclosed. The system, method and apparatus may include at least one Electro-Magnetic (EM) field related parameter sensor; at least one processor; and a communication unit. The processor may be configured to extract EM features from a signal received from the at least one EM sensor, compare to prestored signal EM features stored in a database, and diagnose a medical condition or issue a warning of an expected medical crisis based on the results of the comparison.

Description

APPARATUS, SYSTEM AND METHOD FOR NON-INVASIVE EARLY WARNINGFOR PHYSICAL CRISISCROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application is a PCT Patent Application which claims the benefit of priority under 35 U.S.C. § 119(e) of U.S. Provisional Patent Application No. 63 / 533,359, filed on 18 August 2023. The contents of the above applications are all incorporated by reference as if fully set forth herein in their entirety.FIELD OF INVENTION

[0002] The present innovation relates to apparatuses, systems and methods for early warning for physical crisis. More particularly, the present invention relates to a methodology of a non-invasive early warning prior to a physical / medical crisis, based on detection of changes in a subject’s magneto-physiology.BACKGROUND

[0003] Medical conditions often require timely and accurate diagnosis to ensure appropriate treatment and management. Traditional diagnostic methods, such as blood tests and imaging techniques, can be invasive, time-consuming, and may not provide real-time data. These methods often necessitate specialized equipment and trained personnel, which can limit their accessibility and frequency of use. Additionally, the interpretation of results from these traditional methods can be subjective, leading to potential inconsistencies in diagnosis.

[0004] Diabetes is a metabolic disease that causes high or low blood sugar. The hormone insulin moves sugar from the blood into your cells to be stored or used for energy. With diabetes, a human body either doesn’t make enough insulin or can’t effectively use the insulin it does make.

[0005] Untreated high blood sugar from diabetes can damage one’s nerves, eyes, kidneys, and other organs. Type 1 diabetes is an autoimmune disease. The immune system attacks and destroys cells in the pancreas, where insulin is made. It’s unclear what causes this attack. About 10 percent of people with diabetes have this type. Type 2 diabetes occurs when a human body becomes resistant to insulin, and sugar builds up in your blood.

[0006] Today, monitoring blood levels is done by direct blood sampling, which is extracted from the patient several times a day.

[0007] There are two main concerns regarding diabetic crisis. When sugar levels in the blood are too low or too high. This problem is even more acute in patients who have had the disease for a very long time as they may not even experience the associated symptoms.

[0008] Diabetic hypoglycemia occurs when someone with diabetes doesn't have enough sugar (glucose) in his or her blood. Glucose is the main source of fuel for the body and brain, so a person can't function well in case of an insufficient sugar level. Low blood sugar (hypoglycemia) is defined as a blood sugar level below 70 milligrams per deciliter (mg / dL), or 3.9 millimoles per liter (mmol / L). Initial signs and symptoms of diabetic hypoglycemia include: Shakiness, Dizziness, Sweating, Hunger, Fast heartbeat, Inability to concentrate, Confusion, Irritability or moodiness, Anxiety or nervousness and Headache.

[0009] Hyperglycemia doesn't cause symptoms until glucose values are significantly elevated — usually above 180 to 200 milligrams per deciliter (mg / dL), or 10 to 11.1 millimoles per liter (mmol / L). Symptoms of hyperglycemia develop slowly over several days or weeks. The longer blood sugar levels stay high, the more serious the symptoms become. Early signs and symptoms of hyperglycemia are: Frequent urination, Increased thirst, Blurred vision, Fatigue and Headache.

[0010] Both hypo and hyperglycemia can cause confusion, loss of consciousness, and even death. Hypoglycemia is one of the leading causes of nocturnal death in diabetic patients.

[0011] Thus, there is a need for non-invasive way for early detection and warning of an expected physical / medical crisis, such as hypoglycemia and hyperglycemia prior to its occurrence, to allow early treatment and prevention of acute outburst of a medical condition.SUMMARY OF THE INVENTION

[0012] Electromagnetic field (EMF) sensing can measure neuromuscular, metabolic / mitochondrial activity. Thus, can be a way to measure changes in body activity and serve as early warning for changes related to changes in blood glucose, or other medical conditions.

[0013] The proposed device may include the prediction and / or diagnosis capabilities of myriad other medical conditions not limited to Diabetes. Other medical conditions that may benefit from such a device may include but not limited to conditions that arise as the results of an attack or other change to the body’s homeostasis. Psychiatric conditions such as stress, anxiety, depression, schizophrenia, and the potential onset of psychosis. Epilepsy, a group ofneurological disorders characterized by seizures whose onset is often unpredictable and may result in bodily injury to the patient. Asthma an inflammatory disease of the lungs characterized by variable and recurring attacks of airway obstruction and bronchospasm. The onset of an infectious disease such as CO VID- 19 or influenza or bacterial infection may be measured prior to the onset of actual symptoms. Various cardiac arrythmias, prediction of flares of various autoimmune disorders such as Multiple Sclerosis, Lupus or Systemic Lupus Erythematosus, SLE or other inflammatory conditions. More longer-term variances may also be indicative of an oncological process.

[0014] Minor perturbations in electrophysiological activity may precede physiological changes that are measured by current modalities that are biochemistry or are more overtly electrical. For example when the blood sugar levels rise, mitochondrial activity slows down and this may reflect a decrease in EMF activity. Conversely, when insulin is administered, it may increase mitochondrial activity which may increase EMF activity with a subsequent drop in blood sugars.

[0015] Aspects of the present invention is a system, method, and apparatus for providing a warning prior to a medical condition crisis. The system, method and apparatus may include at least one Electro-Magnetic Field (EMF) related parameter sensor; at least one processor; and a communication unit.

[0016] According to some embodiments, the processor may be configured to extract EM features from a signal received from the at least one EM sensor, compare the extract EM features to prestored signal features stored in a database, and issue a warning of an expected crisis based on the results of the comparison.

[0017] According to some embodiments, the EMF related parameter sensor may be selected from a list consisting of an EMF sensor and other physiological measurements such as pulse, HRV, body temperature, blood pressure etc.

[0018] In some additional or alternative embodiments, an apparatus may further comprise an EM signal preprocessing module for digitizing and amplifying the EM signal to a signal readable by the processor.

[0019] The apparatus may be a non-invasive wearable device configured to be releasably attached to various sites (e.g., a limb) of a subject’s body.

[0020] The apparatus according to some embodiments, may further include a non-transitory computer-readable storage medium having stored thereon program instructions, the programinstructions executable by the at least one processor to: receive a signal indicative of an Electro- Magnetic Field (EMF) measured by an EMF related parameter sensor over a predefined time period; and at an inference stage, apply a trained machine learning model may diagnose a medical condition or may issue a warning prior to a medical condition crisis, based on the received signal.

[0021] The machine learning model may be trained to identify signal patters that are indicative of an expected medical crisis, wherein at a training stage, the machine learning model may be based on a training set that may include: signals from an EMF related parameter sensor(s), and labels indicating, with respect to each of said signals, a medical diagnosis or medical condition crisis event.

[0022] A method of issuing a warning prior to a medical condition crisis, according to some embodiments may include: receiving, by a processor of a signal analyzer, an Electromagnetic (EM) related signal measured during a predefined time period, from one or more EM Field related parameters sensors in proximity to a user’s body; extracting EM features from the received signals; compare the extracted EM features to prestored EM features to detect abnormalities in the extracted EM features; and issuing a warning when the detected abnormalities are associated with a predefined medical condition crisis.

[0023] Embodiments of the invention may include an apparatus for providing a warning prior to a medical condition crisis. The apparatus may include at least one Electro-Magnetic Field (EMF) sensor, adapted to measure at least one EMF-related parameter, at least one processor; and a communication unit. The at least one processor may be configured to extract one or more EM features from a signal received from the at least one EM sensor, compare the one or more extracted EM features to prestored signal features (e.g., stored in a database), and issue a diagnosis or a warning of an expected crisis based on the results of the comparison.

[0024] According to some embodiments, the at least one EMF sensor may be a magnetic sensor, and the EMF-related parameter may be an amplitude of a magnetic field.

[0025] Additionally, or alternatively, the apparatus may further include an EM signal preprocessing module, configured to digitize, and amplify the EM signal to generate a signal readable by the processor.

[0026] According to some embodiments, the apparatus may be wearable, and may be configured to be releasably attached to a limb of a user.

[0027] The apparatus may further include a non-transitory computer-readable storage medium having stored thereon program instructions. The program instructions may be executable by the at least one processor to receive a signal indicative of a measurement of the least one EMF-related parameter, by the at least one EMF sensor, over a predefined time period, and apply a trained machine learning model to issue a warning prior to a medical condition crisis, based on the received signal.

[0028] Additionally, or alternatively, the program instructions may be further configured to receive a training dataset. The training dataset may include: (i) one or more signals, indicative of a measurement of the least one EMF -related parameter, and (ii) labels indicating, with re spect to each of said one or more signals, a medical condition or a medical crisis event. During a training stage, the at least one processor may use the labels to train the machine learning model so as to identify, within said one or more signals, signal patterns that are indicative of an expected medical crisis.

[0029] Embodiments of the invention may include a method of issuing a medical diagnosis or medical warning prior to a medical condition crisis . Embodiments of the method may include receiving, by a processor of a signal analyzer, an EM-related signal, measured during a predefined time period, from one or more EM field related sensors in proximity to a user’s body. Embodiments of the method may further include extracting, by the processor, EM features from the received signals, and comparing the extracted EM features to prestored EM features, thereby detecting abnormalities in the extracted EM features. Embodiments of the method may subsequently issue a warning when the detected abnormalities are associated with a predefined medical condition crisis.

[0030] Embodiments of the invention may include a system for classifying a medical condition of a target patient. Embodiments of the system may include one or more magnetic sensors, each adapted to produce a magnetic sensor signal, indicating properties of a magnetic field at the target patient; a preprocessing module, adapted to produce a digitized, sampled version of the magnetic sensor signal; and at least one processor.

[0031] The at least one processor may be configured to, based on the digitized, sampled version of the magnetic sensor signal, calculate a value of at least one EM feature, representing temporal evolution of the magnetic sensor signal. The at least one processor may subsequently classify the condition of the target patient according to one or more health criteria, based on the at least one calculated EM feature value.

[0032] According to some embodiments, the at least one processor may be further configured to calculate a spectral distribution of at least one magnetic sensor signal of the one or more magnetic sensors. The at least one EM feature may thus represent temporal evolution of the spectral distribution within a predetermined period.

[0033] Additionally, or alternatively, the at least one processor may be further configured to decompose the digitized, sampled version of the magnetic sensor signal to constituent components selected from a list consisting of: a trend component, a seasonal component, and a residual component. The at least one EM feature may be selected from said list of constituent components (e.g., the trend, seasonal, and / or residual component).

[0034] Additionally, or alternatively, embodiments of the system may include a transmission module. The at least one at least one processor may be further configured to determine persistence of the condition of the target patient over a predefined period of time, and subsequent to said determined persistence, issue a notification of the condition of the target patient, to at least one computing device, via the transmission module.

[0035] According to some embodiments, the at least one processor may be configured to obtain at least one prestored EM feature value, pertaining to at least one respective subject of a cohort of subjects. At least one prestored EM feature value may be labeled according to the one or more health criteria. The at least one processor may compare the at least one prestored EM feature value with the calculated EM feature value of the target patient, and classify the condition of the target patient based on said comparison.

[0036] Additionally, or alternatively, the at least one processor may be configured to classify the condition of the target patient by: (a) obtaining an ML-based classification model, pretrained to classify condition of subjects according to the one or more health criteria, based on the at least one EM feature; and (b) inferring the ML-based classification model on at least one EM feature of the target patient, to classify the condition of the target patient according to the one or more health criteria.

[0037] Additionally, or alternatively, the at least one processor may be configured to obtain, from at least one biosensor, a measurement of concentration of a biological substance in a subject. Based on said measurement, the at least one processor may generate an annotation data element, labeling the subject according to the one or more health criteria. The at least one processor may subsequently use the annotation data element as supervisory information, to train the ML-based classification model.

[0038] According to some embodiments, the at least one biosensor may be a glucometer, adapted to measure a level of glucose in the subject’s blood. The one or more health criteria may be selected from a list consisting of: a rise in the level of glucose, a drop in the level of glucose, a stationary level of glucose, a hyperglycemic condition, a hypoglycemic condition, and a condition of normal level of glucose in the subject’s blood.

[0039] According to some embodiments of the system the at least one processor may be communicatively connected to a medical apparatus, such as an insulin pump. The at least one processor may be further configured to communicate with an associated insulin pump, to administer insulin based on the classification of the condition of the target patient.BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The subject matter regarded as the invention is particularly pointed out and distinctly claimed in the concluding portion of the specification. The invention, however, both as to organization and method of operation, together with objects, features, and advantages thereof, may best be understood by reference to the following detailed description when read with the accompanying drawings in which:

[0041] Fig. 1 shows high level block diagram of an exemplary computing device according to embodiments of the present invention;

[0042] Fig. 2A is a block diagram depicting an overview of a system, and an apparatus according to embodiments of the present invention;

[0043] Fig. 2B is a block diagram depicting components of an analysis module, that may be included in the system and / or apparatus of the present invention;

[0044] Fig. 3 shows a flowchart of a method according to an embodiment of the present invention;

[0045] Figs. 4A and 4B are illustrations of a single spectrogram and stitched spectrograms according to some embodiments of the invention;

[0046] Fig. 4C is a real data acquisition spectrogram according to some embodiment of the invention;

[0047] Figs. 5 A and 5B include show time-frequency maps of an empty room and a healthy patient, respectively, according to some embodiments of the invention;

[0048] Fig. 6A is a graph showing timewise evolution of (i) glucose level measurements, and (ii) a trend of a magnetic sensor’s measurement, according to some embodiments of the invention;

[0049] Fig . 6B is a graph showing cross-correlation between the glucose level measurement and trend of the magnetic sensor’s measurement of Fig. 6A; and

[0050] Fig. 7 is a table showing performance parameters of embodiments of the invention, in predicting glucose-related health conditions such as hypoglycemia and hyperglycemia.

[0051] It will be appreciated that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity. Further, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements.DETAILED DESCRIPTION OF THE PRESENT INVENTION

[0052] In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be understood by those skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, and components have not been described in detail so as not to obscure the present invention.

[0053] Although embodiments of the invention are not limited in this regard, discussions utilizing terms such as, for example, “processing,” “computing,” “calculating,” “determining,” “establishing”, “analyzing”, “checking”, or the like, may refer to operation(s) and / or process(es) of a computer, a computing platform, a computing system, or other electronic computing device, that manipulates and / or transforms data represented as physical (e.g., electronic) quantities within the computer’s registers and / or memories into other data similarly represented as physical quantities within the computer’s registers and / or memories or other information non-transitory storage medium that may store instructions to perform operations and / or processes. Although embodiments of the invention are not limited in this regard, the terms “plurality” and “a plurality” as used herein may include, for example, “multiple” or “two or more”. The terms “plurality” or “a plurality” may be used throughout the specification to describe two or more components, devices, elements, units, parameters, or the like. The term set when used herein may include one or more items. Unless explicitly stated, the methodembodiments described herein are not constrained to a particular order or sequence. Additionally, some of the described method embodiments or elements thereof can occur or be performed simultaneously, at the same point in time, or concurrently.

[0054] An apparatus, system and method according to embodiments of the invention may monitor changes in electromagnetic field (EMF) and / or other physiological manifestations, such as pulse, heart rate variability (HRV), BP, pulse ox, body temperature etc. also referred herein as EMF related physiological parameters of a user, and based on the identified changes predict one or more medical diagnoses or medical condition crisis, and provide a diagnosis or alert prior to the crisis.

[0055] Reference is made to Fig. 1, showing a high-level block diagram of an exemplary computing device according to embodiments of the present invention. Computing device 100 may include at least one processor or controller 105 such as a central processing unit processor (CPU). For example, the at least one processor or controller 105 can be a single high- performance CPU or a combination of a CPU and a specialized digital signal processor (DSP) to enhance computational efficiency.

[0056] Computing device 100 may further include a chip or any suitable computing or computational device, that may accommodate an operating system 115, a memory 120, an executable code 125, a storage 130, input devices 135 and output devices 140.

[0057] The at least one processor or controller 105 may be configured to carry out methods described herein, and / or to execute or act as the various modules, units, etc. More than one computing device 100 may be included, and one or more computing devices 100 may act as the various components, for example the components shown in Figs. 2A, 2B. For example, analysis module 203 in Figs. 2A, 2B described herein may include components of computing device 100, and may be implemented as a software component, a hardware component, or any combination thereof.

[0058] For example, by executing executable code 125 stored in memory 120, controller 105 may be configured to carry out a method of predicting and alerting of a medical condition crisis as described herein. For example, controller 105 may be configured to analyze amplified electromagnetic signals received from EM sensors on users’ body, and / or EMF related physiological signals, received from current standard body monitoring sensors, and use the communication unit to issue a warning or alert to a user and / or a caregiver when a change inthe electromagnetic field and or EMF / physiological measurements (and / or in other EMF related parameters) is indicative of a medical diagnosis or expected crisis or seizure as described herein.

[0059] Operating system 115 may be or may include any code segment (e.g., one similar to executable code 125 described herein) designed and / or configured to perform tasks involving coordination, scheduling, arbitration, supervising, controlling or otherwise managing operation of computing device 100, for example, scheduling execution of software programs or enabling software programs or other modules or units to communicate. Operating system 115 may be a commercial operating system.

[0060] Memory 120 may be or may include, for example, a Random Access Memory (RAM), a read only memory (ROM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a double data rate (DDR) memory chip, a Flash memory, a volatile memory, a nonvolatile memory, a cache memory, a buffer, a short-term memory unit, a long term memory unit, or other suitable memory units or storage units. Memory 120 may be or may include a plurality of, possibly different memory units. Memory 120 may be a computer or processor non-transitory readable medium, or a computer non-transitory storage medium, e.g., a RAM.

[0061] Executable code 125 may be any executable code, e.g., an application, a program, a process, task or script. Executable code 125 may be executed by controller 105 possibly under control of operating system 115. For example, executable code 125 may be an application that extracts EM features from the EM signal received from the EM sensor(s) and / or from other EMF related parameters signals, , compare the extracted EM features to a database and if the extracted EM features are associated with features indicative of a medical diagnosis or expected medical crisis, issue a warning or an alert as further described herein.

[0062] Although, for the sake of clarity, a single item of executable code 125 is shown in Fig. 1, a system according to embodiments of the invention may include a plurality of executable code segments similar to executable code 125 that may be loaded into memory 120 and cause controller 105 to carry out methods described herein. For example, units or modules described herein (e.g., analysis module 203 in Fig. 2) may be, or may include, controller 105 and executable code 125.

[0063] Storage 130 may be, or may include, for example, a hard disk drive, a floppy disk drive, a Compact Disk (CD) drive, a CD-Recordable (CD-R) drive, a Blu-ray disk (BD), a universal serial bus (USB) device or other suitable removable and / or fixed storage unit. Content may be stored in storage 130 and may be loaded from storage 130 into memory 120 where itmay be processed by controller 105. In some embodiments, some of the components shown in Fig. 1 may be omitted. For example, memory 120 may be a non-volatile memory having the storage capacity of storage 130. Accordingly, although shown as a separate component, storage 130 may be embedded or included in memory 120.

[0064] According to some embodiments, computing device 100 may include a cloud-based computer or server, adapted to provide online storage and / or analysis to data of system 10.

[0065] Input devices 135 may be or may include a mouse, a keyboard, a touch screen or pad or any suitable input device. It will be recognized that any suitable number of input devices may be operatively connected to computing device 100 as shown by block 135. Output devices 140 may include one or more displays or monitors, speakers and / or any other suitable output devices. It will be recognized that any suitable number of output devices may be operatively connected to computing device 100 as shown by block 140. Any applicable input / output (I / O) devices may be connected to computing device 100 as shown by blocks 135 and 140. For example, a wired or wireless network interface card (NIC), a printer, a universal serial bus (USB) device or external hard drive may be included in input devices 135 and / or output devices 140.

[0066] Embodiments of the invention may include an article such as a computer or processor non-transitory readable medium, or a computer or processor non-transitory storage medium, such as for example a memory, a disk drive, or a USB flash memory, encoding, including or storing instructions, e.g., computer-executable instructions, which, when executed by a processor or controller, cany out methods disclosed herein. For example, an article may include a storage medium such as memory 120, computer-executable instructions such as executable code 125 and a controller such as controller 105.

[0067] Some embodiments may be provided in a computer program product that may include a non-transitory machine -readable medium, stored thereon instructions, which may be used to program a computer, controller, or other programmable devices, to perform methods as disclosed herein. Embodiments of the invention may include an article such as a computer or processor non-transitory readable medium, or a computer or processor non-transitory storage medium, such as for example a memory, a disk drive, or a USB flash memory, encoding, including or storing instructions, e.g., computer-executable instructions, which when executed by a processor or controller, carry out methods disclosed herein. The storage medium may include, but is not limited to, any type of disk including, semiconductor devices such as read-only memories (ROMs) and / or random access memories (RAMs), flash memories, electrically erasable programmable read-only memories (EEPROMs) or any type of media suitable for storing electronic instructions, including programmable storage devices. For example, in some embodiments, memory 120 is anon-transitory machine-readable medium.

[0068] A system 10 according to embodiments of the invention may include components such as, but not limited to, a plurality of CPUs or any other suitable multi-purpose or specific processors or controllers (e.g., controllers similar to controller 105), a plurality of input units, a plurality of output units, a plurality of memory units, and a plurality of storage units. System 10 may additionally include other suitable hardware components and / or software components.

[0069] In some embodiments, System 10 may include or may be, for example, a personal computer, a desktop computer, a laptop computer, a workstation, a server computer, a network device, or any other suitable computing device. For example, system 10 as described herein may include one or more devices such as computing device 100.

[0070] Reference is now made to Fig. 2 which is a block diagram depicting an overview of apparatus 200, or system 10, adapted to perform non-invasive monitoring of a subject’s magneto-physiology, according to embodiments of the present invention. As elaborated herein, embodiments of the invention may subsequently provide early warning prior to a physical or medical crisis, based on detection of changes in the subject’s monitored magneto-physiology.

[0071] Apparatus 200 may include one or more electrophysiological sensor(s) 201, such as an Electro Magnetic (EM) sensor, adapted to measure an electrophysiological signal 20 IS. Additionally, or alternatively, sensor 201 may measure an EMF-related signal or parameter 20 IS, as elaborated herein.

[0072] According to some embodiments, EMF sensor(s) 201 may include low-frequency EMF sensors, such as currently available Nivio or xMR modules, which may include multiple ultrasensitive magnetic sensors. EMF sensor(s) 201 may be placed in an array to detect biomagnetism, in a subject, an organ, or a tissue of the subject. Such ultrasensitive magnetic sensors 201 may be capable of detecting changes of less than one pico-tesla in the EMF of the subject, the tissue, or the organ.

[0073] The arrangement of the one or more EMF sensors, such as the abovementioned magnetic sensors 201 in the apparatus, may enable non-invasive detection of properties of a magnetic field at the target patient, which can be indicative of various physiological conditions, as elaborated herein.

[0074] Sensor 201 may be operatively connected to a signal preprocessing module 202, adapted to produce a digital representation 202D of signal 201 S, readable by an analysis module 203 for digital analysis. For example, preprocessing module 202 may employ adaptive amplification, to amplify the EM or EM-related signal 201 S so as to conform to required signal amplitude and dynamic range. Preprocessing module 202 may sample the amplified signal(s) 20 IS according to a predetermined sampling rate. Additionally, or alternatively, preprocessing module 202 may use different types of analog-to-digital converters (ADCs) and / or filters, to accommodate required signal characteristics and noise levels, thereby generating the digital representation 202D of signal 20 IS.

[0075] As shown in Fig. 2A, apparatus 200 may further include an analysis module 203, adapted to analyze the preprocessed EMF-related signal 202D, so as to identify a condition 203C of a subject.

[0076] Reference is also made to Fig. 2B, which is a block diagram depicting components of analysis module 203 (e.g., same as analysis module 203 of Fig. 2A), that may be included in the system 10 and / or apparatus 200 of the present invention.

[0077] As elaborated herein, analysis module 203 may implemented as a software module, a hardware module, or any combination thereof. For example, analysis module 203 may include at least one processor or controller (e.g., 105 of Fig. 1), configured to implement a method of classifying a condition of a target patient, as elaborated herein.

[0078] According to some embodiments, analysis module 203 may be configured to calculate one or more EM features (e.g., 22F, 24F) that represent a temporal evolution of sensor signals 20 IS (the digital representation 202D of signal 20 IS), including for example, parameters such as amplitude, frequency, and phase changes overtime.

[0079] Analysis module 203 may subsequently classify the target patient's condition based on these EM features (e.g., 22F, 24F), using predefined health criteria 28C, which can be tailored to detect a range of medical conditions.

[0080] For example, embodiments of the invention may be adapted to classify a medical condition related to a level of glucose in the blood of a target patient which describes a clinical state. In this example, the one or more health criteria 28C may include, for example an expected rise in the level of glucose, an expected drop in the level of glucose, an expected stationary level of glucose, an expected hyperglycemic condition, an expected hypoglycemic condition, and an expected condition of normal level of glucose in the subject’s blood.

[0081] According to some embodiments, analysis module 203 may be configured to calculate a spectral distribution 22F of at least one sensor signal 20 IS (the digital representation 202D of signal 20 IS) of the one or more magnetic sensors 201. For example, and as shown in Fig. 2B, analysis module 203 may include a spectrogram generation module 22. Spectrogram generation module 22 may be adapted to calculate a spectral distribution 22F of at least one sensor signal 20 IS as a spectrogram, based on the digital representation 202D of measured signal(s) 20 IS.

[0082] As known in the art, a spectrogram may be a data structure, e.g., a matrix of values, representing the spectrum of frequencies of a signal as it varies with time. For example, a horizontal axis of the spectrogram may represent time, a vertical axis of the spectrogram may represent frequency, and a value of entries in the matrix may represent an amplitude of the signal at each corresponding frequency and time point.

[0083] It may be appreciated that spectrogram 22F (or any derivative thereof) may be, or represent a temporal evolution of the calculated spectral distribution 22F within a predetermined period. As elaborated herein, analysis module 203 may subsequently use spectrogram 22F (e.g., evolution of spectral distribution 22F) as a distinguishing EM feature, to classify a condition 203C of the target patient.

[0084] As known in the art, decomposing a signal into components, namely a trend component, a seasonal component, and a residual component, may refer to the process of breaking down atime series signal into three distinct parts: the trend component, which captures the long-term progression or direction of the data; the seasonal component, which captures repeating patterns or cycles within the data over a specific period; and the residual component, which captures the remaining variability in the data that is not explained by the trend or seasonal components. Such decomposition may facilitate analyzing and understanding the underlying patterns and behaviors within the signal.

[0085] As shown in Fig. 2B, analysis module 203 may include a signal decomposition module 24, configured to decompose (e.g., produce a decomposition 24F of) the digitized, sampled version 202D of sensor signal(s) 20 IS, to constituent components. The constituent components 24F may include for example, a trend component 24F-1, a seasonal component 24F-2, and a residual component 24F-3.

[0086] As elaborated herein, analysis module 203 may subsequently use one or more constituent components 24F (e.g., 24F-1, 24F-2, 24F-3) as distinguishing EM features for classifying a condition 203C of the target patient.

[0087] As shown in Fig. 2B, analysis module 203 may include, or may be associated with a database 30DB. Database 30DB may maintain prestored EM feature values (e.g., 22F, 24F), pertaining to at least one respective subject (e.g., a human subject) of a cohort of subjects. Prestored EM feature values 22F, 24F may be labeled, or annotated (e.g., by a human expert) according to the one or more health criteria 28C.

[0088] Pertaining to the example of monitoring diabetic patients, the prestored EM feature values of database 30DB may include values of spectral distribution 22F and / or values of decomposition constituent components 24F, labeled according to a diagnosed condition of a respective subject (e.g., normal, hypoglycemic, and hyperglycemic).

[0089] According to some embodiments, analysis module 203 may compare the at least one pre stored EM feature value (22F, 24F) with the calculated EM feature value (22F, 24F), of the target patient, and categorize or classify the condition of the target patient 203 C based on this comparison. Examples of such comparisons are provided herein (e.g., in relation to Fig. 7).

[0090] Additionally, or alternatively, and as shown in Fig. 2B, analysis module 203 may include at least one ML-based classification model 28, which may be configured to classify the condition 203 of the target patient based on one or more EM feature values (e.g., 22F and / or 24F), according to the one or more health criteria.

[0091] According to some embodiments, ML-based classification model 28 may be based on the application of genetic algorithms, an evolutionary computation methodology, to identify the most appropriate sequence of computational operations and machine learning models for accurately and effectively detecting correlation signals.

[0092] Embodiments of the invention may apply various preprocessing operations to the data, such as filters, transformations, and statistical tests, to prepare it for the machine learning stage. There are numerous tools available, each with its parameters, and sometimes several tools may be combined hierarchically. The output from this preprocessing stage is then fed into the second stage, where machine learning model 28 may be built. Here too, many tools are available, each with specific parameters.

[0093] To find the best combination of parameters, the inventors have performed an iterative search process of trial-and-error, aimed at finding the best combinations out of trillions ofpossible options. The genetic algorithm may oversee this stage, optimizing the search process intelligently, rather than exhaustively testing all possibilities, by brute force, which would be infeasible within a reasonable time frame.

[0094] When applied to the available data, the iterative search process identified preprocessing techniques such as trend detection, seasonality detection, anomaly detection, and data normalization tools as beneficial. In the machine learning stage, supervised machine learning methods for time series forecasting proved to be effective.

[0095] Additionally, or alternatively, ML-based classification model 28, which may be configured to classify the condition 203 of the target patient based on the digitized, sampled version 202D of sensor signal(s) 20 IS.

[0096] According to some embodiments (and as shown in Fig. 2B), ML-based classification model 28 may include a plurality of separate models (e.g., denoted 28-1, 28-2), each dedicated to classification of target subjects based on a unique, respective type of EM feature, or input (e.g., 22F, 24F, 202D). The outcome of the individual models (e.g., 28-1, 28-2) may be subsequently summarized (e.g., weighted by a classification confidence value), resulting in classification value 203 C. Alternatively, ML-based classification model 28 may include a unified classification model, adapted to produce classification value 203 C based on EM feature values of various types (e.g., 22F and / or 24F) and / or digitized sensor signal 202D.

[0097] As known in the art, the term “feature” in an ML-based model may refer to an individual measurable property or characteristic of a phenomenon being observed.

[0098] In this context, “features” may include values of input EM features (e.g., 22F, 24F) used by the ML model to make predictions or classifications, and / or values of digitized sensor signal 202D.

[0099] Additionally, or alternatively, the term “feature” may further refer to any derivation ofthe input variables (e.g., derivation of EM features 22F, 24F). For example, in the context of a Neural-Network (NN) based classifier, the term “feature” 22F, 24F may also refer to any combination of input variables (22F, 24F), e .g., as manifested in by weights of individual nodes in the NN.

[0100] ML-based classification model 28 may be implemented using various machine learning algorithms such as decision trees, support vector machines, or neural networks, depending on the specific requirements and complexity of the classification task. ML-basedmodel 28 can be trained on a diverse dataset that includes a wide range of patient data, ensuring robustness and generalizability across different patient populations.

[0101] According to some embodiments, system 10 may incorporate a federated learning approach, where ML-based classification model 28 may be trained across multiple decentralized devices or servers 100 holding local data samples, without exchanging them, to enhance data privacy and security while benefiting from a large and diverse dataset. The decentralized devices or servers may include, for example, an on-board computing device, such as computing device 100 of Fig. 1.

[0102] In another example, the decentralized devices or servers 100 may include at least one local computing device 100, such as a smartphone device which is associated with the specific target subject.

[0103] In yet another example, the decentralized devices or servers 100 may include an online (e.g., a cloud-based) server, that may be adapted to provide personalized analysis services for a plurality of apparatuses.

[0104] Apparatus 200 may be designed to support a continuous learning scheme, by which ML-based model 28 may be periodically updated with new data to improve accuracy and adapt to evolving medical knowledge. Additionally, apparatus 200 may include a user interface (UI, e.g., input device 135 of Fig. 1) that may allow healthcare providers to input additional patient information or adjust the health criteria, providing a customizable and interactive diagnostic tool.

[0105] According to some embodiments, apparatus 200 may include, or be associated with one or more biosensors 40, configured to measure 40M biomedical parameter of the subject.

[0106] For example, biosensor 40, may be configured to measure 40M a concentration of a biological, or chemical substance in a subject. In such embodiments, biosensor 40 may be a glucometer, adapted to measure glucose concentration in the subject’s blood, a pulseoxygenation sensor, adapted to measure oxygenation in the subject’s blood, and the like.

[0107] In another example, biosensor 40, may be configured to measure 40M parameters of electrical signals, associated with the subject’s heart, including for example a pulse rate, a pulse shape, Heartrate variation (HRV), and the like. In yet another example, biosensor 40, may be configured to measure 40M physical parameters such as body temperature.

[0108] According to some embodiments, system 10 (e.g., apparatus 200) may include a diagnosis module 220. Diagnosis module 220 may receive EMF-related signals and parameters(e.g., features 22F, 24F) and / or physiological measurements 40M as inputs, and compare these inputs with baseline values, to arrive at a diagnosis 220D of a subject (e.g., diabetic) or a warning 205 / 206 (e.g., an upcoming critical condition).

[0109] For example, a cancer patient is hypothesized to exhibit elevated levels of EMF- related signals (e.g., 202D) or parameters (e.g., features 22F, 24F), in relation to a cohort of similar (e.g., similar age, gender and build) subjects. Diagnosis module 220 may therefore compare the measured EMF-related signals and / or parameters to predetermined baseline values of a cohort of healthy or sick subjects, to derive a diagnosis 220D of cancer, and output that diagnosis to a relevant computer device as a notification 207.

[0110] In another example an epileptic subject is hypothesized to exhibit changing levels of EMF-related signals (e.g., 202D) or parameters (e.g., features 22F, 24F), prior to, and during onset of a seizure. Analysis module 203 may therefore compare the measured EMF-related signals and / or parameters to a previously established baseline value of that patient, to issue a warning 205 / 206 against an upcoming seizure.

[0111] Additionally, or alternatively, ML model 28 may receive physiological measurements 40M in conjunction with EMF-related signals and parameters (e.g., features 22F, 24F), as inputs, to classify the condition 203C of the subject.

[0112] Additionally, or alternatively, system 10 may use physiological measurements 40M as supervisory data, to train ML model 28, so as to classify the condition 203C of the subject based on EMF-related parameters (e.g., features 22F, 24F).

[0113] For example, biosensors 40 may include a glucometer, adapted to measure blood glucose levels 40M the blood of diabetic patients. During a training stage, apparatus 200 may receive a measurement 40M of the concentration of substance (e.g., glucose), and generate an annotation data element 40L, labeling the subject according to the one or more health criteria (e.g., normal, hypoglycemic, hyperglycemic). Analysis module 203 may subsequently employ a training scheme, such as a backward propagation training scheme, and use the annotation data element 40L as supervisory information, to train the ML-based classification model.

[0114] In a subsequent inference stage, analysis module 203 may be configured to classify the condition of the target patient by obtaining the trained ML-based classification model 28, and inferring it on at least one EM feature of the target patient (e.g., 22F, 24F or any derivation thereof), to classify the condition 203 C of the target patient according to the one or more health criteria 28C.

[0115] According to some embodiments, apparatus 200 may include a power source (not shown), and a transmission module 204, such as a wireless communication unit, adapted to transmit one or more notifications or warnings 204T of the monitored subject’s condition 203C (e.g., to a computing device of a physician or caretaker).

[0116] According to some embodiments, apparatus 200 may communicate with a computing device such as the computing device 100 in Fig. 1 via a dedicated application for further data analysis, and generating warnings should it be needed.

[0117] For example, apparatus 200 may determine a persistence (e.g., over a predefined period of time) of the condition 203 of the target patient. Subsequent to this determined persistence, apparatus 200 may issue notification 204T of the condition 203C of the target patient, to at least one computing device 100, via transmission module 204.

[0118] Sensor or sensors 201, preprocessing module 202, analysis module 203, the power source and transmission unit 204 (also referred to herein as a “communication unit”) may be placed within a wearable mount 208 that may be removably attachable to a patient, e.g., around a limb or a muscle. For example, wearable mount 208 may attach sensors 201 to the biceps, a wrist, a calf or a thigh of a monitored subject or patient.

[0119] According to some embodiments, sensors 201 may be placed at more than one site over the patient’s body, e.g., by using two or more wearable mounts 208, or by using a wearable mount having a plurality of sensors 201 located at different sites.

[0120] Apparatus 200 may sense the patient’s electrophysiological activity for a given time frame, and subsequently analyze that activity for either learning or monitoring parameters of the subjects electrophysiological activity.

[0121] According to some embodiments, noninvasive warning apparatus 200 may be placed in a vicinity of a patient, e.g., by wearable mount 208. EMF related sensors, such as EM sensor(s) and / or HRV sensor(s) 201 may measure signals 20 IS representing the patient’s magnetic field and / or HRV.

[0122] Preprocessing module 202 may amplify signals 20 IS, and / or convert the physiological signal readings 20 IS received from sensor(s) 201 into readable, digitized EMF signals or data 202D for a processor or controller (e.g., 105 of Fig. 1) of analysis module 203.

[0123] Processor 105 may be adapted to analyze digitized EMF signals or data 202D, to determine a condition of the patient. For example, analysis module 203 may be, or may include a machine learning (ML) model, configured to predict and / or indicate, based on digitized EMFsignals 202D, whether the patient exhibits signals that represent early signs of a medical condition crisis, hyperglycemia or hypoglycemia (i.e., high or low glucose concentration in the blood).

[0124] Should such indication occur, the apparatus 200 may transmit, via transmission module (e.g., a wireless communication module) 204, a warning or notification 204T of condition 203C to one or more computing devices (e.g., 100 of Fig. 1).

[0125] For example, apparatus 200 may transmit notification 204T of condition 203C to a local application 205, installed on the same computing device (e.g., a smartphone) as analysis module 203.

[0126] Additionally, or alternatively, apparatus 200 may transmit notification 204T of condition 203 C to an application 206 of a remotely connected computing device 100, so as to alert the patient and / or a caregiver to the abnormal conditions 203C developing for further treatment, so as to re-stabilize the patient (e.g., stabilize the glucose levels in the patient’s blood).

[0127] According to some embodiments, system 10 may include apparatus 200 and / or one ormore remote computing devices 100 (e.g., of a user / patient, a caregiver etc.). System lO may inform 204T the patient’s physician regarding the current situation 203 C, allowing an intervention should the alert not being treated, or the treatment is ineffective.

[0128] According to some embodiments, analysis module 203 may read digital signal or data 202D from the preprocessing module 202, and use a patient database 30DB, to compare the current reading and former crisis data. Analysis module 203 may thereby determine the current condition 203 C of the patient.

[0129] Additionally, or alternatively, apparatus 200 may examine condition 203 further based on persistence of appearance. For example, transmission module 204 may issue warning notification 204T when condition 203C appears, or persists for a predetermined duration of time.

[0130] Changes in EM signal may be changes in the Pico Tesla range with very low to low frequencies such as 0.1 Hz - 10 KHz.

[0131] According to some embodiments, an ML algorithm may be trained on EM signals and / and / or other physiological parameters, obtained prior to a medical diagnosis, event or crisis. In the training stage, the ML model is provided with signals obtained a predefined time prior to a known medical event as well as signals that are not associated with a medical event.Unsupervised training may be used in order to train the ML model to identify signals (e.g., EMF signals) that are associated with, or predictive of a medical diagnosis or event of the patient.

[0132] According to some embodiments, system 10 may include, or be associated with (e.g., communicatively connected to) an insulin pump 50. The at least one processor 105 may be configured to communicate with the associated insulin pump 50, to administer insulin to the subject, based on the classification 203C of the condition of the target patient, e.g., when classification 203C indicates an expected condition of hyperglycemia.

[0133] The following method described in Fig. 3 herein, can describe but not limit the functionality of the analysis module 203.

[0134] Reference is now made to Fig. 3 which is a flowchart of a method of issuing a warning prior to a medical condition crisis, such as a hyperglycemic crisis, according to some embodiments of the present invention. At step 305 a patient may be monitored for a given period of time in which the patient maintains normal life activities while maintaining normal sugar levels, the stage called “data gathering” or training stage. In this stage, EM signals and patterns 202D may be collected, as well as other measurements, from sensors 40 such as blood glucose sensors 40.

[0135] EM signals and patterns 202D may be labeled 40L according to the physiological measurements 40M received from the sensors 40S, e.g., as patterns associated with normal or abnormal condition 203C.

[0136] In the example or diabetic subjects, label data 40L may include a “normal activity” of the patient (e.g., normal glucose level), or “abnormal activity” (e.g., “hyperglycemia” or “hypoglycemia”).

[0137] According to some embodiments of the invention, analysis module 203 may use ML techniques to extract EM features from EM signal 202D (step 310), to define patterns that represent the patient’s normal and / or abnormal activities.

[0138] According to some embodiments, analysis module 203 may use unsupervised machine learning techniques to divide the patterns to different activities, which the patient is accustom in performing. When the algorithm classifications reaches high enough accuracy, (e.g., when the correlation between sensed signal or pattern is in correlation higher than 0.5 (r> 0.5) with a medical event), the patterns gathered may be stored as reference for the further analysis.

[0139] As shown in step 305, in an inference stage, system 10 may record the patient’s electrophysiological condition for given time intervals (e.g., 1 minute). System 10 may subsequently extract the relevant EM patterns which may indicate the patient for each of the predefined activities (step 310).

[0140] According to some embodiments, Al algorithms may be used in order to define to which of the pre-defined activity the current condition matches as seen in step 315. Should the current condition deviate from the pre-defined activities (e.g., an indication of possible crisis step 320), and this finding will repeat itself through a number of observations (steps 325-340), or should deviation increase with time, the system may issue a warning 204T (step 345) to the patient.

[0141] Should these deviations persist for a longer period of time, the system may also issue a warning 204T to a computing device 100 associated with a predetermined person, such as a family member, a physician of the patient, or medical aid.

[0142] The inventors have performed the following experiments to demonstrate efficacy of the present invention in ascertaining a subject’s condition.

[0143] In these experiments, a sensors 201 included a pair of commercially available detectors (e.g., TDK, Nivio xMR). The Nivio -based sensor 201 was operational under geomagnetism of ±60 pT or below de field range by using the recommended circuit. Sensor 201 was able to measure with high sensitivity of pico-tesla level, i.e., below under 1 / 1,000,000 of the geomagnetic field.

[0144] Sensor 201 was sensitive to a frequency range of between 0.1 Hz and 1 kHz, and the achieved measurable AC magnetic field was up to ±250 nano-tesla (nT).

[0145] packed within a plastic casing, and isolated from external magnetic fields in all directions except one. Sensors 201 were fixed by a soft bandage to a body of a patient, such that the non-isolated face could detect a magnetic signal 20 IS from as close as possible to the body. Preprocessing module 202 acquired signals 201S in a differential mode, e.g., indicating a difference in reading of the two detectors, to eliminate the effect of ambient noise sources.

[0146] Two reference measurements were performed.

[0147] In a first reference measurements, apparatus 200 was operated in an empty patient’s room. Additional electronic equipment in the surrounding was measured apart. No signals at the range of interest were detected.

[0148] In a second reference measurement, a patient who is not afflicted with diabetes was monitored, as a reference to a diabetic patient, who was the subject of the experiment.

[0149] The sampling rate of signal 202D was 20 Kilo-Hertz (KHz). The measurement were taken at intervals of 6 hours. A one-dimension continuous wavelet transform was applied on signal 202D.

[0150] Reference is now made to Figs. 4 A and 4B which are schematic illustrations of spectrograms. As known in the art, spectrograms depict temporal changes in spectral (e.g., frequency-related) properties of a signal over time.

[0151] It may be appreciated that long -period spectrograms may undergo global normalization and adaptation. Therefore, spectrograms observed at short intervals, may possess high granularity frequency data, in comparison to spectrograms of longer intervals. Embodiments of the invention may therefore employ a process referred to herein as “spectrogram stitching”, to support analysis of spectral data over long periods of time.

[0152] Figs. 4A depicts a single spectrogram, whereas Fig. 4B depicts a stitched spectrogram, allowing continuous representation of the signal’s spectral properties, according to some embodiments of the invention.

[0153] Reference is also made to Fig. 4C, which is an image depicting a stitched spectrogram of real data, acquired by embodiments of the invention.

[0154] In order to process this volume of data, the measurement intervals were divided into 50 equal intervals. Each one was processed apart, and the results were stitched together on a time-frequency map. The maps are a mosaic of 50 spectrograms.

[0155] Reference is now made to Figs. 5A and 5B which show time-frequency maps of an empty room and a healthy patient, respectively, which serve as reference maps. By comparing Figs. 5 A and 5B, it may be understood that in absence of a patient, the acquired data is almost featureless. In other words, the bulk of acquired signals 20 IS was acquired from a human subject, and was not a result of ambient noise.

[0156] Reference is also made to Figs. 6A and 6B. Fig. 6A is a graph showing timewise evolution of (i) glucose level measurements 40M, and (ii) atrend 24F-1 of amagnetic sensor’s 201 measurement, according to some embodiments of the invention. Fig . 6B is a graph showing a cross-correlation between the glucose level measurement 40M and the trend 24F-1 of the magnetic sensor’s 201 measurements depicted in Fig. 6A.

[0157] As shown in Fig. 6A, at point A, the monitored subject was administered a bolus of insulin, without food. Between points A and B, the subject reported they were feeling unwell, and in point B the EMF-related parameter (e.g., feature 22F / 24F, in this example, trend feature 24F-1) began rising. Approximately 400 seconds afterwards, in point C, the level of glucose in the subject’s blood began to drop.

[0158] In other words, at point B, the EMF-related parameter (e.g., feature 24F) has predicted an upcoming change in the subject’s blood glucose by approximately 7 minutes. Embodiments of the invention may therefore produce a predicted change in the subject's condition 203C, i.e., an expected drop in blood glucose.

[0159] Between points C and D, embodiments of the invention may generate a prediction of the subject’s condition 203C, as an expected medical crisis. In this case, the medical crisis 203C was a condition of hypoglycemia (e.g., blood glucose concentration below 70 milligram (mg) / Deci-liter (dl)), which indeed was manifested at point D.

[0160] In other words, the EMF-related parameter (e.g., feature 24F) has also been shown to predict an upcoming condition of crisis, such as a hypoglycemic state, approximately 35-40 minutes before onset of that state. Embodiments of the invention may therefore produce a warning against an expected condition 203 C such as a state of crisis, well before that crisis has materialized.

[0161] At point D, the subject was provided with food, resulting in another prediction of a change in the subject’s medical condition 203C, i.e., a steep rise in blood glucose, which indeed occur between points D and E. As shown in point F, this rise in blood glucose resulted in another predicted crisis condition 203C, this time - a condition of hyperglycemia (e.g., blood glucose concentration exceeding 180 mg / dl).

[0162] By observing Figs. 6A and 6B, it may be appreciated that significant crosscorrelation exists between the EMF-related parameter (in this case feature 24F, e.g., trend 24F- 1 ) of the measured EM or magnetic field, provided by EM or magnetic sensor 201, and groundtruth glucose values provided by biosensor 40 (e.g., glucometer), following injection of insulin, and intake of food.

[0163] In addition, it may also be appreciated that significant changes in the monitored feature 24F (e.g., trend 24F-1) well precede the expected changes (e.g., drop and rise) in the subject’s condition (e.g., blood glucose levels).

[0164] Reference is also made to Fig. 7, which is a table showing performance parameters of embodiments of the invention, in predicting glucose-related crisis health conditions 203 C (e.g., hypoglycemia and hyperglycemia).

[0165] As shown in Fig. 7, a gap of approximately 1000 seconds (between 1078 and 886) was typically observed between prediction 203C of a crisis by system 10 and an actual onset of that crisis. Performance parameters (e.g., accuracy, specificity and Fl) of system 10 in generating these predictions are also provided.

[0166] The “Threshold” values of each condition (hypoglycemic and hyperglycemic crisis conditions) were obtained from database 30, representing a plurality of measurements. This plurality of measurements may pertain to a single subject, e.g., historical measurements of the target subject of interest. Additionally, or alternatively, plurality of measurements may pertain to a cohort of subjects of similar characteristics (e.g., gender, age, weight, and health condition or disposition). Embodiments of the invention may calculate the threshold values of Fig. 7 so as to predict 203C with the aforementioned parameters of performance.

[0167] According to some embodiments, analysis module 203 of Fig. 2A may analyze EMF-related parameters or features (e.g., 22F, 24F, 202D) of measured EM signal 20 IS by comparing values of these features with threshold values of Fig. 7. Analysis module 203 may thereby conclude, or determine a condition 203C of the subject based on this comparison. Pertaining to the example of Fig. 7, when feature value 24F (e.g., 24F-1) exceeds the value of 0.13439, analysis module 203 may conclude that the subject is expected to enter a state of hypoglycemia. In another example, when feature value 24F (e.g., 24F-1) drops below the value of -0.01496, analysis module 203 may conclude that the subject is expected to enter a state of hyperglycemia.

[0168] As elaborated herein, it is made clear that embodiments of the invention may provide a practical application in the technological field of assistive diagnostics, preventive treatment and wellbeing. Embodiments of the invention may thus provide an improvement over currently available diagnostic technology, by generating non-invasive, reliable, and predictive indications of a patient’s condition.

[0169] The non-limiting examples provided herein relate mainly to health conditions associated with blood glucose levels. The inventors hypothesize that the observed changes to EM and / or magnetic fields of a subject, e.g., as shown in Fig. 6 A, correlate to cellular-level, and / or organelle -level (e.g., Mitochondrial) metabolic activity.

[0170] Therefore, it may be appreciated that embodiments of the invention should not be limited to identification of glucose-related conditions. In other words, any indication that involves metabolic, neuromuscular, metabolic oncologic, inflammatory, infectious diseases may be detected with changes in a persons EMF or EMF fingerprint as expressed by MF, frequencies, wave forms etc.

[0171] may also be identified, or predicted by embodiments of the invention, by analyzing EM or magnetic signals, given sufficient training data.

[0172] Unless explicitly stated, the method embodiments described herein are not constrained to a particular order in time or chronological sequence. Additionally, some of the described method elements may be skipped, or they may be repeated, during a sequence of operations of a method.

[0173] While certain features of the invention have been illustrated and described herein, many modifications, substitutions, changes, and equivalents will now occur to those of ordinary skill in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention.

[0174] Various embodiments have been presented. Each of these embodiments may of course include features from other embodiments presented, and embodiments not specifically described may include various features described herein.

Claims

CLAIMS1. An apparatus for providing a warning prior to a medical condition crisis comprising: at least one Electro-Magnetic Field (EMF) sensor, adapted to measure at least one EMF- related parameter; at least one processor; and a communication unit, wherein the processor is configured to extract one or more EM features from a signal received from the at least one EM sensor, compare the one or more extracted EM features to prestored signal features stored in a database, and issue a diagnosis or a warning of an expected crisis based on the results of the comparison.

2. The apparatus of claim 1, wherein the at least one EMF sensor is a magnetic sensor, and wherein the EMF-related parameter is an amplitude of a magnetic field.

3. The apparatus according to any one of claims 1-2, further comprising an EM signal preprocessing module, configured to digitize, and amplify the EM signal to generate a signal readable by the processor.

4. The apparatus according to any one of claims 1-3, wherein the apparatus is a wearable apparatus configured to be releasably attached to a limb of a user.

5. The apparatus according to any one of claims 1-4, further comprising a non-transitory computer-readable storage medium having stored thereon program instructions, the program instructions executable by the at least one processor to: receive a signal indicative of a measurement of the least one EMF-related parameter, by the at least one EMF sensor, over a predefined time period; and apply a trained machine learning model to issue a warning prior to a medical condition crisis, based on the received signal.

6. The apparatus of claim 5 wherein the program instructions are further configured to:receive a training dataset comprising: (i) one or more signals, indicative of a measurement of the least one EMF-related parameter, and (ii) labels indicating, with respect to each of said one or more signals, a medical condition or a medical crisis event; and during a training stage, use said labels to train the machine learning model so as to identify, within said one or more signals, signal patterns that are indicative of an expected medical crisis.

7. A method of issuing a medical diagnosis or medical warning prior to a medical condition crisis, comprising: receiving, by a processor of a signal analyzer, an Electromagnetic (EM) related signal measured during a predefined time period, from one or more EM field related sensors in proximity to a user’s body; extracting EM features from the received signals; comparing the extracted EM features to prestored EM features, to detect abnormalities in the extracted EM features; and issuing a warning when the detected abnormalities are associated with a predefined medical condition crisis.

8. A system for classifying a medical condition of a target patient, the system comprising: one or more magnetic sensors, each adapted to produce a magnetic sensor signal, indicating properties of a magnetic field at the target patient; a preprocessing module, adapted to produce a digitized, sampled version of the magnetic sensor signal; and at least one processor, wherein the at least one processor is configured to: based on the digitized, sampled version of the magnetic sensor signal, calculate a value of at least one EM feature, representing temporal evolution of the magnetic sensor signal; and classify the condition of the target patient according to one or more health criteria, based on the at least one calculated EM feature value.

9. The system of claim 8, wherein the at least one processor is further configured to calculate a spectral distribution of at least one magnetic sensor signal of the one or more magneticsensors, and wherein the at least one EM feature represents temporal evolution of said spectral distribution within a predetermined period.

10. The system according to any one of claims 8-9, wherein the at least one processor is further configured to decompose the digitized, sampled version of the magnetic sensor signal to constituent components selected from a list consisting of: a trend component, a seasonal component, and a residual component, and wherein the at least one EM feature is selected from said list of constituent components.

11. The system according to any one of claims 8-10, further comprising a transmission module, and wherein the at least one at least one processor is further configured to: determine persistence of the condition of the target patient over a predefined period of time; and subsequent to said determined persistence, issue a notification of the condition of the target patient, to at least one computing device, via the transmission module.

12. The system according to any one of claims 8-11, wherein the at least one processor is configured to: obtain at least one prestored EM feature value, pertaining to at least one respective subject of a cohort of subjects, wherein at least one prestored EM feature value is labeled according to the one or more health criteria; compare the at least one prestored EM feature value with the calculated EM feature value of the target patient; and classify the condition of the target patient based on said comparison.

13. The system according to any one of claims 8-12, wherein the at least one processor is configured to classify the condition of the target patient by: obtaining an ML-based classification model, pretrained to classify condition of subjects according to the one or more health criteria, based on the at least one EM feature; and inferring the ML-based classification model on at least one EM feature of the target patient, to classify the condition of the target patient according to the one or more health criteria.

14. The system according to any one of claims 8-13, wherein the at least one processor is configured to: obtain, from at least one biosensor, a measurement of concentration of a biological substance in a subject; based on said measurement, generate an annotation data element, labeling the subject according to the one or more health criteria; and using the annotation data element as supervisory information, to train the ML-based classification model.

15. The system of claim 14, wherein the at least one biosensor is a glucometer, adapted to measure a level of glucose in the subject’s blood, and wherein the one or more health criteria are selected from a list consisting of: a rise in the level of glucose, a drop in the level of glucose, a stationary level of glucose, a hyperglycemic condition, a hypoglycemic condition, and a condition of normal level of glucose in the subject’s blood.

16. The system of claim 15, wherein the at least one processor is further configured to communicate with an associated insulin pump, to administer insulin based on the classification of the condition of the target patient.

Images