Wearable diagnostic devices

Abstract

A wearable diagnostic device that is worn on a user's body and is capable of providing various types of health-related information to the user is described. The wearable diagnostic device is capable of providing real-time, non-invasive, accurate, and continuous data about the user's heart rate, hemoglobin level, body temperature, oxygen level, glucose level, and blood pressure. In some embodiments, the wearable diagnostic device can also provide electrocardiogram (EKG) data or detection of Parkinson's symptoms, such as involuntary movements of the user's hands. The user can configure the wearable diagnostic device to provide information about one, more, or all of the health-related information listed above.

Description

[0001] background

[0002] As individuals become increasingly health-conscious, there is a growing demand for users to receive personal health information in a simple and convenient manner. Typically, a user may have to wear multiple devices, each of which provides information about a single aspect of the user's health. There is a need for devices that can provide information about multiple aspects of a user's health in a simple, non-invasive, and convenient manner.

[0003] Overview

[0004] Generally speaking, innovative aspects of the present subject matter describe wearable diagnostic devices, as well as methods and systems for performing one or more medical diagnostic tests.

[0005] In some embodiments, a system includes one or more computer devices and one or more storage devices storing instructions that, when executed by the one or more computer devices, cause the one or more computer devices to perform operations including receiving input corresponding to a request to initiate a non-invasive diagnostic test to detect a medical condition of a user; determining one or more sensors for performing the non-invasive diagnostic test; activating the determined one or more sensors based on the non-invasive diagnostic test; receiving signal data from the one or more sensors; obtaining a predicted value for the non-invasive diagnostic test based in part on a characteristic of the user; determining a test result based on the predicted value and the received signal data; and outputting the test result via a display or a speaker.

[0006] Embodiments can each optionally include one or more of the following features. For example, in some embodiments, the non-invasive diagnostic test includes one or more of the following: a glucose test, a cholesterol test, a hemoglobin test, an oxygen saturation level test, and an electrocardiogram monitoring test.

[0007] In some embodiments, the operations further include selecting a path based on raw data obtained from the received signal data, and obtaining a set of determined values based on the selected path.Determining the test result based on the predicted value and the received signal data includes determining the test result based on the determined values.

[0008] In some embodiments, the operations further include obtaining user clinical data and user demographic data from one or more databases; determining a clinical data set range based on the obtained user clinical data and user demographic data; and mapping the clinical data set range to a predictive value of the non-invasive diagnostic test.

[0009] In some embodiments, the operations further include determining a second non-invasive diagnostic test to be performed based on (i) a user pattern associating the second non-invasive diagnostic test with the non-invasive diagnostic test, and (ii) a medical history of the user; activating a second set of one or more sensors based on the second non-invasive diagnostic test; receiving second signal data through the one or more sensors of the second set; obtaining a second predicted value for the second non-invasive diagnostic test based in part on the user characteristics; and determining a second test result based on the second predicted value and the received second signal data.

[0010] In some embodiments, obtaining the predictive value of the non-invasive diagnostic test comprises determining the predictive value of the non-invasive diagnostic test using a second test result.

[0011] In some embodiments, when the non-invasive diagnostic test is a glucose test, the second non-invasive diagnostic test is a cholesterol test performed simultaneously therewith.

[0012] In some embodiments, the non-invasive diagnostic test and the second non-invasive diagnostic test are performed by a watch comprising one or more computer devices.

[0013] In some embodiments, the one or more sensors include one or more of: a wireless cardiac electrode, a piezoelectric vibration sensor, an infrared sensor, a temperature sensor, an accelerometer, and a micro-electro-mechanical system (MEMS) sensor.

[0014] According to aspects of the disclosed subject matter, a watch includes one or more computer devices and one or more storage devices storing instructions that, when executed by the one or more computer devices, cause the one or more computer devices to perform operations. The operations include selecting a glucose test and a cholesterol test based on a user characteristic; determining one or more sensors for performing the glucose test and the cholesterol test; activating the determined one or more sensors; receiving signal data from the one or more sensors; obtaining a first predicted value for the glucose test based in part on the user characteristic; determining a glucose test result and a cholesterol test result based on the first predicted value and the received signal data; and outputting the glucose test result and the cholesterol test result via a display or speaker of the watch.

[0015] In some embodiments, the one or more sensors include an infrared sensor and a piezoelectric vibration sensor. The operation includes selecting a path based on raw data obtained from the received signal data, and obtaining a set of determined values based on the selected path. Determining a glucose test result based on the first predicted value and the received signal data includes determining the glucose test result based on the determined values.

[0016] The above aspects and embodiments further described in this specification provide several advantages. For example, a single wearable diagnostic device can perform multiple non-invasive diagnostic tests, including a non-invasive glucose test, a non-invasive cholesterol test, and a non-invasive hemoglobin test. The wearable diagnostic device can also obtain electrocardiogram (EKG) data or detect Parkinson's symptoms, such as involuntary movements of the user's hand. Wearable diagnostic devices with wireless electrodes can record user history and medical conditions, and can utilize predictors, algorithms, and mapping databases to provide higher accuracy and reliable results for glucose, cholesterol, and / or hemoglobin tests. The predictors include clinical and demographic information of the user and can therefore make calculations more accurate, taking into account parameters such as skin color and age that may affect glucose or hemoglobin levels. The predictors can also be used to correlate the predictors with the user's susceptibility to certain diseases.

[0017] Other aspects include corresponding methods, systems, apparatus, computer-readable storage media, and computer programs configured to implement the actions of the above-described methods.

[0018] The details of one or more aspects described in this specification are set forth in the accompanying drawings and the description below. Other features, aspects, and advantages of the subject matter will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 、 2 , 3, 4 and 5 describe exemplary embodiments of wearable diagnostic devices.

[0021] Figure 6 An exemplary system implemented in a wearable diagnostic device is described.

[0022] Figure 7 A flow chart depicts an exemplary method of determining a user's glucose level.

[0023] Figure 8 A flow chart depicts an exemplary method of determining a glucose prediction value.

[0024] Figure 9 A flow chart depicts an exemplary method of determining a user's hemoglobin level.

[0025] Figure 10 A flow chart depicts an exemplary method of determining a predicted hemoglobin value.

[0026] Figure 11 A flow chart depicts an exemplary method of determining a user's blood pressure level.

[0027] Figure 12 A flow chart depicts an exemplary method of determining a predicted blood pressure value.

[0028] Figure 13 A flow chart depicts an exemplary method of determining a user's cholesterol level.

[0029] Like reference numbers and designations in the various drawings represent like elements.

[0030] Details

[0031] The present disclosure generally relates to wearable diagnostic devices that can be worn on a user's body to provide various types of health-related information to the user. In some embodiments, the wearable diagnostic device can perform one or more medical diagnostic tests and provide real-time, non-invasive, accurate, and continuous data about the user's heart rate, hemoglobin level, body temperature, oxygen level, glucose level, cholesterol, and blood pressure. In some embodiments, the wearable diagnostic device can also provide electrocardiogram (EKG) data and detection of Parkinson's symptoms, such as involuntary movements of the user's hand. The user can configure the wearable diagnostic device to provide information about one or more of the above-mentioned diagnostic tests. Embodiments of the wearable diagnostic device are described below with reference to the accompanying drawings.

[0032] Figure 1-5 In some embodiments, the wearable diagnostic device can be implemented in the form of a watch, such as Figure 1-5 shown. Figure 6 Further details of components included in a wearable diagnostic device according to some embodiments are shown. Generally, the wearable diagnostic device can be implemented in various suitable shapes, forms, and sizes and can be any electronic device that can be mounted to a user's left arm and is capable of obtaining a plurality of health diagnostic measurements of the user.

[0033] Reference Figure 1-5 The wearable watch may include a housing 101, a display 102, detachable wireless cardiac electrodes 103, 113, straps 104, 109, a piezoelectric vibration sensor 105, an infrared (IR) / light / laser sensor 106, a connector 107, a temperature sensor 108, control buttons 110, 111, a back cover 112, a strap connector 114, a strap fastener 115, a charging connector 116, a power supply 117, outer strap layers 118, 120, an insulated wire 119, an accelerometer 121, a power manager 122, a system on a chip (SoC) 123, and a power switch 124. The wearable watch may be worn on a user's left arm 150.

[0034] Housing 101 may include or be coupled to a display 102, a charging connector 116, control buttons 110, 111, and one or more electronic components, such as a processor, a printed circuit board (PCB), an integrated circuit (IC), a SoC 123, memory, and a wireless transceiver. Display 102 may be implemented using any suitable display, including, for example, a liquid crystal display (LCD), a light emitting diode (LED) display, or an organic LED display, to display various data. In some embodiments, display 102 may be a touch screen, such as a capacitive touch screen.

[0035] The display 102 can display a user interface configured to output data to the user and receive input from the user. The control buttons 110 and 111 can be used by the user to navigate the user interface, make selections, and perform one or more operations in the wearable diagnostic device. In some embodiments, the display 102 can receive selections from the user and provide information indicating the user selections to one or more processors in the wearable watch or network device. In some embodiments, the display 102 can receive data from one or more processors and provide the data to the display 102 for output to the user. For example, in some cases, the user can input a request to provide the user's glucose level through the user interface. After determining the user's glucose level, information indicating the user's glucose level can be output through the user interface displayed on the display 102.

[0036] The one or more processors in housing 101 may be implemented in a PCB or IC and may be electrically connected to other electronic components of the wearable diagnostic device, such as memory, display 102, and a wireless transceiver. For example, the processor may receive data indicating a user selection from display 102, determine the type of information requested by the user, and generate instructions to perform one or more operations based on the information requested by the user.

[0037] In some embodiments, one or more processors can transmit and receive data using a wireless transceiver. Data can be sent and received between the wearable diagnostic device and an auxiliary device. The auxiliary device can be a device selected by the user, a network server, or a device that the wearable watch is configured to communicate with. For example, the user can select another device owned by the user to send data from the wearable diagnostic device to. In another example, the wearable diagnostic device can be configured to send and receive data to one or more network servers based on user requests or a predetermined schedule for sending and receiving data.

[0038] One or more network servers may provide services for one or more networks, which may include one or more databases, access points, base stations, storage systems, cloud systems, and modules. The one or more servers may be a series of servers running a network operating system. The one or more servers may be used for and / or provide cloud and / or network computing.

[0039] The database in the network may include a cloud database or a database managed by a database management system (DBMS). The DBMS can be implemented as an engine that controls the organization, storage, management, and retrieval of data in the database. The DBMS generally provides query, backup and replication, execution rules, security, calculation, change and access logs, and automatic optimization capabilities. The DBMS generally includes a modeling language, data structure, database query language, and transaction mechanism. According to the database model, a modeling language can be used to define the schema of each database in the DBMS, and the database model may include a hierarchical model, a network model, a relational model, an object model, or some other applicable known or convenient organization. The data structure may include fields, records, files, objects, and any other applicable known or convenient structure for storing data. The DBMS may also include metadata about the stored data.

[0040] In some embodiments, the database may include a user database that may store user information such as the user's alias, medical history, and any medical conditions. The user database may also store data related to licenses, permissions, and certificates used to access various tools and software. In some cases, the user may select an option to anonymize user data, so that any information about the user is anonymized and user-identifying information is removed before the data is stored in the user database.

[0041] In general, various suitable wireless protocols can be used to transmit data to and from the wearable diagnostic device. For example, the wearable diagnostic device can use WiFi or Bluetooth communication to communicate with one or more networks, devices, or servers. In general, various types of networks can be communicated with and various communication protocols can be used.

[0042] Charging connector 116 may be a port configured to connect to a power cable, such as a universal serial bus (USB) or a wire. When connected to the power cable, charging connector 116 may function as a power interface to provide power from an external power source, thereby charging power supply 117 in the wearable watch. Power supply 117 may be any suitable battery and may provide power to any electronic components in the wearable diagnostic device.

[0043] The housing 101 also includes a power switch 124. In some embodiments, in response to selection of the power switch 124 such that the power switch 124 is in the power-off position, the one or more processors can send instructions to the power manager 122 to stop providing power to one or more components of the wearable diagnostic device, such as the display 102. In some embodiments, in response to selection of the power switch 124 such that the power switch 124 is in the power-on position, the power manager 122 can send instructions to the power supply 117 to provide power to one or more components of the wearable diagnostic device, such as the display 102.

[0044] Housing 101 is connected to bands 104, 109, connector 107, and band connector 114, which can be adjusted to secure the wearable diagnostic device around wrists of different sizes. For example, bands 104, 109, and band connector 114 can be wrapped around a user's wrist, and band fastener 115 can hold bands 104, 109, and band connector 114 in a fixed position. Back cover 112 and cardiac electrodes 113 can be disposed on the bottom of housing 101.

[0045] One or more insulated wires 119 may be integrated into the structure of the wearable diagnostic device and may provide electrical connections to various components of the wearable diagnostic device. Figure 6 As shown, one or more insulated wires 119 can be disposed along a central axis of the wearable diagnostic device and can provide electrical connections between the power source 117 and the housing 101 and between the power source 117 and the IR / light / laser sensor 106 .

[0046] The wearable diagnostic device may further include one or more sensors such as cardiac electrodes 103, 113, a piezoelectric vibration sensor 105, an infrared (IR) / light / laser sensor 106, a temperature sensor 108, an accelerometer 121, and an impedance sensor. In some embodiments, the piezoelectric vibration sensor 105 may include a micro-electromechanical system (MEMS) sensor.

[0047] The wireless cardiac electrodes 103, 113 may include a metallic conductive material configured to detect cardiac electrical potential waveforms, such as the voltage generated during cardiac contraction. The wireless cardiac electrodes 103 are disposed on an outer band layer 118 corresponding to the periphery of the wearable diagnostic device. The wireless cardiac electrodes 113 are disposed on or integrated within the back cover 112 so that they can contact the user's skin when the wearable diagnostic device is secured around the user's arm 150. The wireless cardiac electrodes 103, 113 can be removed and reattached to the wearable diagnostic device and can wirelessly transmit data to another electronic device.

[0048] The IR / light / laser sensor 106 may include a signal generator and a signal detector. The signal generator may generate and transmit an infrared signal having a wavelength in the range of, for example, 650-1400 nanometers (nm). This range is particularly useful for obtaining data indicating the presence of oxygen, glucose, and hemoglobin molecules in the user's blood. The signal detector may be configured to detect infrared signals received from the user's body.

[0049] In some embodiments, the IR / light / laser sensor 106 can detect pulse signals using the pulse wave transit time (PWTT) method of the artery method and process the detected signals. These pulse signals can be combined with data acquired by the piezoelectric vibration sensor 105 to non-invasively predict blood pressure. The IR / light / laser sensor 106 can also be used to non-invasively determine or obtain data indicating the oxygen saturation level (SpO2) in the user's blood.

[0050] The piezoelectric vibration sensor 105 and the accelerometer 121 can be used to measure vibrations in the user's hand. For example, the accelerometer 121 can detect changes in direction, speed, vibration, and rotation. The temperature sensor 108 can be used to measure the user's body temperature. The temperature sensor 108 can be implemented in various suitable ways. For example, the temperature sensor 108 can be a thermocouple, a silicon bandgap sensor, a thermometer, or a thermistor including one or more sensing resistors. Changes in resistance in the sensing resistors can correspond to changes in body temperature. In some embodiments, the temperature sensor can include active and passive components as well as resistors and semiconductor materials fabricated in a single IC package.

[0051] The sensors can be used to obtain one or more measurements as described in further detail below. Operation of the wearable diagnostic device to determine glucose levels, hemoglobin levels, blood pressure levels, EKG, heart rate levels, body temperature, and hand vibration is described in further detail below. Operation begins by a user placing the wearable diagnostic device on the user's left arm 150 and adjusting one or more of the straps 104, 109, strap connector 114, strap fastener 115, and outer strap layers 118, 120 to secure the wearable diagnostic device around the user's left arm 150.

[0052] When the wearable diagnostic device is attached to a user's left arm 150, the IR / light / laser sensor 106 can be brought into contact with the lower portion of the user's left wrist, just above the user's radial and ulnar arteries. As described above, the IR / light / laser sensor 106 can include a signal generator to generate and transmit an infrared signal. The signal can be transmitted from the IR / light / laser sensor 106 to the user's skin at the lower portion of the user's left wrist.

[0053] The IR / light / laser sensor 106 can detect the signal reflected from the user's skin. The detection signal, including the absorption spectrum data, can then be converted into a digital signal using an analog-to-digital converter (ADC). As a result of the conversion, raw digital data corresponding to the signal received from the user's skin is generated. This raw digital data can be processed to determine absorption spectra corresponding to the presence of various molecules in the user's blood, such as oxygen, glucose, and hemoglobin. By determining the absorption spectra, the presence and corresponding levels of specific molecules in the user's blood can be estimated.

[0054] In some embodiments, multiple signal measurements may be obtained to obtain multiple sets of raw digital data at various points in time. The different sets of raw digital data may be accumulated and averaged to generate a single set of raw data for the user.

[0055] In some embodiments, the wearable diagnostic device can obtain information related to the user's health. The information related to the user's health can include, but is not limited to, for example, the user's residential location, the user's doctor, the user's pharmacist, the user's medical record holder, the user's demographic association with one or more groups, the user's diet, an indication of how many children the user has, the user's medical history, one or more past or current medical conditions of the user (e.g., allergies, surgeries, genetic conditions), one or more health issues of the user, and one or more blood content levels for which the user is interested in obtaining detailed information. For example, the user can indicate that the user is particularly interested in the user's glucose or blood pressure levels. The user can also indicate how often the user wants to obtain information about the user's glucose or blood pressure levels.

[0056] Information related to the user's health can be used to create a user profile. The user profile can be stored locally in the wearable diagnostic device, or in a database or server remote from the wearable diagnostic device. In some embodiments, the user profile data can be processed in one or more ways before storage or use to remove personally identifiable information. For example, the user's identity can be processed so that personally identifiable information about the user cannot be determined, or the user's geographic location, identity, or demographic background can be generalized to the degree desired by the user so that specific details about the user cannot be determined. Thus, the user can control what information is collected and how it is used. To achieve this, the user can be provided with controls through the wearable diagnostic device that allow the user to select whether or when the systems, programs, or features described herein can collect or provide user information.

[0057] In some embodiments, a user may subscribe to or opt-in to a service through which the wearable diagnostic device may receive and update the user's medical information in real time. In particular, the wearable diagnostic device may update test results, doctor's visit results, diagnoses, or prescriptions. For example, a user may authorize the user's doctor, pharmacist, or medical record holder to publish the user's medical information to a server or database that stores the user's profile. The server or database may be managed by a subscription service that collects information from various sources to update the user's profile. The wearable diagnostic device may receive updates about the user's medical information in real time, periodically, or upon request by the user.

[0058] In some embodiments, a user can directly input information about the user's health and background using the user interface of the wearable diagnostic device. The input user medical information can then be stored remotely or on the wearable diagnostic device.

[0059] It should be understood that although Figure 1-6 The described features relate to a wearable diagnostic device that is worn on the user's left arm, but the wearable diagnostic device can have various other forms and, in some cases, can be worn or applied to other parts of the user's body. In addition, one or more additional components can be included in or coupled to the wearable diagnostic device. For example, in some embodiments, the wearable diagnostic device can include one or more speakers to output information using sound waves and a microphone to receive audio input corresponding to, for example, user instructions, requests, or feedback.

[0060] In some embodiments, the wearable diagnostic device may also be configured to perform one or more diagnostic tests to obtain one or more of a glucose level, a hemoglobin level, or a blood pressure level associated with a user wearing the wearable diagnostic device based on the received or obtained information related to the user's health. These processes are further described in Figure 7-12 middle.

[0061] Reference Figure 7 、 9and 13, the wearable diagnostic device can receive an indication that a test should be performed (702, 902, 1302). For example, the wearable diagnostic device can receive an indication that a glucose test (702), a hemoglobin test (902), or a cholesterol test (1302) should be performed. The indication that a test should be performed can include one or more of the following: a selection made by a user to perform a test; and a request made by one or more processors according to a predetermined time. For example, the wearable diagnostic device can be programmed to provide a blood pressure reading at certain times or after certain time periods. The wearable diagnostic device can then schedule when a specific reading should be provided to the user, such as a date and time for a blood pressure reading, and can begin the method of determining blood pressure and oxygen saturation levels at the predetermined time.

[0062] After receiving an indication that a test should be performed (702, 902, 1302), one or more processors of the wearable diagnostic device can determine the type of sensor to be used for the test and activate the determined sensor type, which in the case of a glucose or hemoglobin test can include one or more IR / light / laser sensors (704, 904). In the case of a cholesterol test, the activated sensors can include one or more of an IR / light / laser sensor, an impedance sensor, and an electromagnetic sensor. Activating the sensor can include operations including, but not limited to, providing increased power to the sensor, preheating the sensor to transmit or receive a signal (such as an IR signal), or configuring or calibrating the sensor.

[0063] The activated one or more sensors can obtain measurements that characterize the user (706, 906, 1306). For example, one or more IR / light / laser sensors can be configured to transmit an infrared signal or a pulsed signal for a short period of time, such as 30 seconds, and detect reflection of the transmitted signal from the user's skin. In some cases, reflection measurements and current measurements using impedance sensors can be obtained iteratively, or can be obtained under different environments, such as different pulse powers or magnetic fields. For example, for a cholesterol measurement, a first current or infrared signal measurement can be obtained without applying a magnetic field, and one or more additional current or infrared measurements can be taken after generating a magnetic field of various low power intensities for a period of time (e.g., 10 seconds).

[0064] In the case of glucose and hemoglobin testing, the detected signals are processed and a specific path is selected based on the raw data values (708, 908). In particular, each detected signal includes absorbance spectral data, which can be converted to raw digital data using an analog-to-digital converter (ADC). Processing can optionally include additional processing operations such as down-conversion, filtering, convolution, mixing, and any other suitable signal processing operations.

[0065] The raw digital data corresponding to the signal received from the user's skin is used as the basis for selecting a specific path and the corresponding predicted value and slope regression value (710, 910). For example, when performing a glucose test, the exemplary mapping shown in Table 1 can be used to select a specific path and the corresponding predicted value and slope regression value. If the raw value is greater than or equal to 500 and less than or equal to 700, path A and the corresponding glucose (G) predicted value of 917 and the G slope regression value of 0.838 are selected. If the raw value is greater than or equal to 701 and less than or equal to 850, path B and the corresponding G predicted value of 919 and the G slope regression value of 0.838 are selected. If the raw value is greater than or equal to 851 and less than or equal to 950, path C and the corresponding G predicted value of 1001 and the G slope regression value of 0.838 are selected. If the raw value is greater than or equal to 951 and less than or equal to 1100, path D and the corresponding G predicted value of 1004 and the G slope regression value of 0.838 are selected. If the raw value is greater than or equal to 1101, path E is selected with a corresponding G prediction value of 981 and a G slope regression value of 0.838.

[0066] Table I

[0067]

[0068] The obtained predicted value and slope regression value can then be used to determine the user's glucose level (712). To determine the glucose level, the wearable diagnostic device can apply generalization theory and G-slope regression to the original data set and determine a value indicative of the glucose level using [Equation 1] as shown below.

[0069] Glucose value = predicted value (G-临床取样回归) -(G regression slope)*(original data)

[0070] [Equation 1]

[0071] The determined glucose value can then be output 714 by various suitable methods. For example, the determined glucose value can be output on a display of the wearable diagnostic device or through a speaker of the wearable diagnostic device.

[0072] When performing a hemoglobin test, the exemplary examples shown in Table II can be used to select a specific path and the corresponding predicted value and slope regression value. If the original value is equal to or greater than 500 and less than or equal to 700, path A and the corresponding hemoglobin (Hb) predicted value of 31.5 and the Hb slope regression value of 0.114 are selected. If the original value is equal to or greater than 701 and less than or equal to 850, path B and the corresponding Hb predicted value of 67 and the Hb slope regression value of 0.114 are selected. If the original value is equal to or greater than 851 and less than or equal to 950, path C and the corresponding Hb predicted value of 81 and the Hb slope regression value of 0.114 are selected. If the original value is equal to or greater than 951 and less than or equal to 1100, path D and the corresponding Hb predicted value of 98 and the Hb slope regression value of 0.114 are selected. If the raw value is greater than or equal to 1101, path E is selected with a corresponding Hb prediction value of 100.5 and Hb slope regression value of 0.114.

[0073] Table II

[0074]

[0075] The obtained predicted value and slope regression value can then be used to determine the user's hemoglobin level (912). To determine the hemoglobin level, the wearable diagnostic device can apply Hb slope regression to the original data set and determine a value indicative of the hemoglobin level using [Equation 2] as shown below.

[0076] Hb value = ((Hb regression slope) * (original data)) - predicted value (Hb-临床取样回归)

[0077] [Equation 2]

[0078] The determined hemoglobin value can then be outputted by various suitable methods (914). For example, the determined hemoglobin value can be outputted on a display of the wearable diagnostic device or through a speaker of the wearable diagnostic device.

[0079] For raw data values less than 500 in a glucose or hemoglobin test, the wearable diagnostic device may determine that the value is erroneous and initiate additional attempts to obtain raw data values using one or more IR / light / laser sensors. If a value greater than 500 cannot be obtained after three attempts, the wearable diagnostic device may output an error message indicating that the glucose or hemoglobin test cannot currently be performed.

[0080] When a cholesterol test is performed to determine the cholesterol level (e.g., HDL, LDL, triglyceride molecules) associated with a user wearing a wearable diagnostic device, the lower portion of the user's left wrist is exposed to an infrared signal emitted from an IR / light / laser sensor. This area of the user's skin may also be exposed to a magnetic field for a short period of time, such as 10 or 30 seconds, after which, in addition to the cholesterol molecules, the blood particles arrange themselves according to the positive and negative polarity of the electromagnetic field. Data indicating the infrared absorption spectrum may be obtained before and after the application of the magnetic field (1306), and the obtained data may then be processed (1308). The processing of the obtained data may include converting the data into a digital signal using an analog-to-digital converter (ADC), and calculating the difference between the absorption spectrum values before and after the application of the magnetic field to produce a raw value.

[0081] Next, a predicted cholesterol level value is obtained from a database (1310). The database may include a mapping of cholesterol levels to raw values and may be organized according to demographic categories. The database may be generated based on testing of a plurality of human subjects as described below.

[0082] Initially, the subject's demographic characteristics can be recorded. Demographic characteristics can include various types of descriptive information about the subject, such as the subject's age, gender, race, skin color, marital status, and / or medical conditions. For example, a subject may have the following demographic characteristics: 48 years old, white, widowed, and has skin cancer. For each subject, an invasive cholesterol test can be performed using various suitable methods, and the test results can be added to the subject's characteristics.

[0083] Next, the resistance sensor and infrared sensor described above can be used to obtain current and infrared signal measurements of the subject, respectively. Current and infrared signal measurements can be taken before and after the magnetic field is applied for a certain period of time. The difference between the measured signals can be calculated and saved as a raw value. The raw value is mapped to the cholesterol level obtained from the invasive cholesterol test and stored in the subject's profile.

[0084] Hundreds and thousands of subjects may be tested so that a large sample size of subjects can be used to generate a database that maps raw values to cholesterol levels according to one or more demographic categories, such as sex, race, age, etc. In some embodiments, statistics can be extracted from the testing so that the mean, median, and mode values for the cholesterol levels and raw values for each demographic category can be determined.

[0085] Typically, various types of demographic categories can be formed. For example, in some cases, a demographic category may be subject to age, for example, the age restriction of a group of people in their 40s. In some cases, a demographic category may include multiple demographic characteristics, such as age and race, or age, race, and sex. Therefore, the database may include a mapping table that maps possible cholesterol levels based on the raw values associated with a specific demographic category. It should be noted that the database can be generated anonymously, thereby not revealing or knowing the identity of the object.

[0086] Return to reference Figure 13 , a predicted cholesterol level value is obtained from the database based on the original value obtained in operation 1308 (1310). In particular, the cholesterol level mapped to the original value obtained in operation 1308 and the demographic characteristics of the user wearing the wearable diagnostic device is obtained by referring to a mapping table in the database.

[0087] Next, the predicted cholesterol level value can be determined as the possible cholesterol level of the user wearing the wearable diagnostic device (1312). In some embodiments, the predicted cholesterol level value can be compared with a previously obtained cholesterol level of the user. If the difference between the predicted cholesterol level of the user and the last obtained cholesterol level of the user is greater than a threshold value, such as 3%, the wearable diagnostic device can repeat operations 1302 to 1310 to obtain a new predicted cholesterol level. Such iterations can continue until the predicted cholesterol level value is within a threshold difference of the last obtained cholesterol level of the user. In some cases, if three iterations are performed without meeting the threshold difference, the predicted cholesterol level value obtained at the third iteration can be determined as the possible cholesterol level of the user wearing the wearable diagnostic device. The determined possible cholesterol level of the user can then be displayed by the display 102 of the wearable diagnostic device.

[0088] In the exemplary embodiments described above, predicted values are used to determine glucose, hemoglobin, or cholesterol levels. Predicted values can be determined using a variety of different methods and based on several factors. Methods for obtaining predicted values for cholesterol levels are described above. Figure 8 and 10 Methods for obtaining predicted values for glucose and hemoglobin levels are further described.

[0089] Reference Figure 8To obtain a predicted value for the user's glucose level, the wearable diagnostic device may obtain user characteristic information (802). The user characteristic information may include one or more of the following: the user's residential location, the user's physician, the user's pharmacist, the user's medical record holder, the user's demographic association with one or more groups, the user's diet, an indication of the number of children the user has, the user's medical history, one or more past or current medical conditions of the user (e.g., allergies, surgeries, genetic conditions), one or more health concerns of the user, and one or more blood level levels for which the user is interested in obtaining detailed information.

[0090] Using information from the user's characteristics, the wearable diagnostic device can determine a clinically relevant information value (cCIG) for the user's glucose based on the user's blood pressure and temperature (804). In some embodiments, the cCIG can be a matrix representing possible blood pressure and temperature values. In general, various suitable methods can be used to obtain the user's blood pressure and temperature. In some embodiments, the cCIG can be obtained as described in the specification. Figure 11 and 12 Blood pressure may be obtained, and temperature may be obtained using a temperature sensor included in the wearable diagnostic device. In some cases, cCIG may be determined using clinical information obtained from user characteristics, such as the user's medical history, including data such as a doctor's report, past or current medical conditions, clinical diagnoses, and the like.

[0091] Next, the wearable diagnostic device can determine a clinically correlated demographic value (cLDG) for the user's glucose (806). The cLDG can be determined based in part on one or more user characteristics, such as the user's demographic group, the user's age, and other personal characteristics of the user. For example, if the raw glucose value described above is associated with a specific path, such as path A, or the user characteristics indicate a specific demographic origin or characteristic of the user, the cLDG value can be determined in such a way that the cLDG value corresponds to the raw glucose value or the specific demographic origin or characteristic of the user. In some embodiments, if the user has consented to provide this personal information, the cLDG can be a matrix of values representing various characteristics of the user, such as age, diet, and gender.

[0092] After obtaining the cCIG and cLDG, the wearable diagnostic device may determine a clinical data set range based on the cCIG and cLDG (810). The determined clinical data set range is mapped to a glucose prediction value for the user's glucose level (812). The determined clinical data set range may be used to query a database storing various clinical data set ranges and glucose prediction values, and a glucose prediction value mapped to the determined clinical data set range may be returned. The glucose prediction value may then be provided and used to determine the user's glucose level (814).

[0093] Reference Figure 10 To obtain a predicted value for the user's hemoglobin level, the wearable diagnostic device may obtain user characteristic information (1002). The user characteristic information may include one or more of the following: the user's residential location, the user's physician, the user's pharmacist, the user's medical record holder, the user's demographic association with one or more groups, the user's diet, an indication of the number of children the user has, the user's medical history, one or more past or current medical conditions of the user (e.g., allergies, surgeries, genetic conditions), one or more health concerns of the user, and one or more blood content levels for which the user is interested in obtaining detailed information.

[0094] Using information from the user's characteristics, the wearable diagnostic device can determine a clinically relevant information value (cCIHb) for the user's hemoglobin (1004). cCIHb can be determined using clinical information obtained from the user's characteristics, such as the user's medical history, including data such as doctor's reports, past or current medical conditions, clinical diagnoses, and the like. In some embodiments, if the user has consented to providing this personal information, cCIHb can be a matrix of values representing various aspects of the user's medical history.

[0095] Next, the wearable diagnostic device can determine a clinically relevant demographic value of the user's hemoglobin (cLDHb) by obtaining the user's oxygen saturation and temperature data (1006). In some embodiments, cLDHb can be a matrix representing possible oxygen saturation and temperature values for the user. Generally, various suitable methods can be used to obtain the user's oxygen saturation and temperature. In some embodiments, the user's oxygen saturation and temperature can be obtained by referring to the user's oxygen saturation and temperature data. Figure 11 The oxygen saturation is obtained, and the temperature can be obtained using a temperature sensor included in the wearable diagnostic device. In some embodiments, cLDHb can be determined based in part on information provided by user characteristics, such as one or more user characteristics, such as the user's demographic group, the user's age, and other personal characteristics of the user.

[0096] After obtaining cCIHb and cLDHb, the wearable diagnostic device may determine a clinical data set range based on cCIHb and cLDHb (1010). The determined clinical data set range may be mapped to a hemoglobin prediction value for the user's hemoglobin level (1012). The determined clinical data set range may be used to query a database storing various clinical data set ranges and hemoglobin prediction values, and the hemoglobin prediction value mapped to the determined clinical data set range may be returned. The hemoglobin prediction value may then be provided and used to determine the user's hemoglobin level (1014).

[0097] By utilizing predicted values in addition to blood pressure and temperature data to determine a user's glucose and hemoglobin levels, the user's glucose and hemoglobin levels can be determined with significantly greater accuracy than methods that do not utilize predicted values to determine glucose and hemoglobin levels. The predicted values include the user's clinical and demographic information and can therefore make calculations more accurate by taking into account parameters such as skin color and age that may affect glucose or hemoglobin levels. The predicted values can also be used to correlate the predicted values with the user's susceptibility to certain diseases, allowing the user to take preventative steps to minimize the likelihood of acquiring these diseases and improve the user's health and life expectancy. Furthermore, these multiple tests can be performed and results obtained from the tests as needed using a single device, providing a high degree of convenience for the user.

[0098] In addition to obtaining the user's glucose and hemoglobin levels, the wearable diagnostic device can also determine the user's blood pressure and oxygen saturation levels. A flowchart of an exemplary method of determining a user's blood pressure and oxygen saturation levels is depicted in FIG. Figure 11 Initially, the wearable diagnostic device may receive an indication that a blood pressure measurement should be performed (1102). The indication that a blood pressure measurement should be performed may include one or more of: a selection by a user to provide a blood pressure reading and a request by one or more processors based on a predetermined time. For example, the wearable diagnostic device may be programmed to provide a blood pressure reading at certain times or after certain time periods. The wearable diagnostic device may then schedule a date and time when a blood pressure reading should be provided to the user, and may begin the method of determining blood pressure and oxygen saturation levels at the predetermined time.

[0099] Upon receiving an indication that a blood pressure measurement should be performed (1102), the wearable diagnostic device may determine the type of sensor to use for the blood pressure test and activate the determined sensor type, which in the case of a blood pressure test may include a piezoelectric vibration sensor and an IR / light / laser sensor (1104). Activating the sensor may include several operations, including but not limited to providing increased power to the sensor and configuring or calibrating the sensor.

[0100] The activated piezoelectric vibration sensor and IR / light / laser sensor can obtain user measurement results (1106). For example, the piezoelectric vibration sensor is configured to sense or detect the movement, position, proximity, speed, and direction of the user's hand and generate an electrical signal corresponding to one or more of the detected touch, vibration, and impact movement. The IR / light / laser sensor is configured to transmit an infrared signal and detect the reflection of the emitted infrared signal from the user's skin. In some embodiments, a preamplifier can be used to amplify the weak pulse signal obtained by the piezoelectric vibration sensor.

[0101] The signals detected by the piezoelectric vibration sensor and the IR / light / laser sensor can be processed, for example, by performing analog-to-digital conversion (ADC) and filtering operations to generate infrared target detection (IRTD) values and piezoelectric vibration (PV) values (1108). Generally, various signal processing operations can be performed on the signals detected by the piezoelectric vibration sensor and the IR / light / laser sensor. In some embodiments, operations 1104-1108 can be repeated multiple times, and an average of the multiple IRTD and PV values can be determined.

[0102] The processing may also include comparing the determined IRTD and PV values with the predicted IRTD and PV values. The comparison produces two sets of blood pressure values. Each of the two sets of blood pressure values is averaged to produce a systolic pressure value and a diastolic pressure value, respectively (1112). The systolic pressure value and the diastolic pressure value can be used to determine the mean arterial pressure (MAP) using [Equation 3] as shown below.

[0103] MAP = diastolic blood pressure + (1 / 3) (systolic blood pressure – diastolic blood pressure)

[0104] [Equation 3]

[0105] See below Figure 12 The generation of predicted values for blood pressure measurement is explained. In some embodiments, the oxygen saturation level of the user's blood may also be determined using [Equation 4] (1110).

[0106] Oxygen saturation level = ((C HbO2 ) / (C HbO2 +C Hb ))*100

[0107] [Equation 4]

[0108] In [Equation 4], C HbO2 is equal to the concentration of oxygenated hemoglobin, and C Hb Equal to the concentration of deoxygenated hemoglobin. C can be obtained by using an infrared sensor Hb02 and C Hb The value of .

[0109] After operations 1110 and 1112, the blood pressure and oxygen saturation values are output (1114). For example, in some embodiments, the blood pressure and oxygen saturation values are displayed on a display. In some embodiments, the blood pressure and oxygen saturation values are output via a speaker. In some embodiments, the blood pressure and oxygen saturation values can be transmitted to another electronic device using a message, such as an email, SMS, or MMS. The information can be automatically generated and populated without any user input. The user can be prompted to confirm whether the blood pressure and oxygen saturation information should be transmitted to the other electronic device.

[0110] In the exemplary embodiment described above, the predicted value is used to determine the user's blood pressure. The predicted value can be determined using a variety of different methods and based on several factors. Figure 12 To obtain a predicted value of the user's blood pressure, the wearable diagnostic device may obtain user feature information (1202), as described in operations 802 and 1002. The wearable diagnostic device may obtain the user's clinical and demographic information from the user features.

[0111] Using information from the user characteristics, the wearable diagnostic device can determine the user's clinical correlate of blood pressure (cCIBP) and obtain EKG data (1204). cCIBP can be determined using clinical information obtained from the user characteristics (the user's medical history), including data such as a doctor's report, past or current medical conditions, clinical diagnoses, etc. The EKG data can be obtained from various suitable sources, such as, for example, the user's medical history.

[0112] Next, the EKG data is processed to determine the time differences between peaks, particularly R waves (1206). The wearable diagnostic device may also determine a clinically correlated demographic value (cLDBP) for the user's blood pressure (1206). In some embodiments, one or more processors in the wearable diagnostic device may execute one or more programs and algorithms that detect peaks in the user's EKG and the time differences between the detected peaks. In some embodiments, the cLDBP may be determined based in part on one or more user characteristics, such as the user's demographic group, the user's age, and other personal characteristics of the user. In some embodiments, if the user has consented to provide this personal information, the cLDBP may be a matrix of values representing various characteristics of the user, such as age, diet, and gender.

[0113] After obtaining cCIBP and cLDBP, the wearable diagnostic device may determine a clinical data set range based on cCIBP and cLDBP (1208). The determined clinical data set range is mapped to a blood pressure prediction value for the user's glucose level (1210). The determined clinical data set range may be used to query a database storing various clinical data set ranges and blood pressure prediction values, and a blood pressure prediction value mapped to the determined clinical data set range may be returned. The blood pressure prediction value may then be provided and used to determine the user's blood pressure level (1212).

[0114] In some implementations, the wearable diagnostic device may perform a process to obtain an EKG and heart rate level of a user wearing the wearable diagnostic device.

[0115] When the wearable diagnostic device is fixed on the user's left arm, the first cardiac electrode can be set on or within the bottom surface of the wearable diagnostic device and can contact the upper side of the user's left wrist. The second cardiac electrode is set on or within the upper surface of the wearable diagnostic device without contacting the skin on the user's left arm. The first cardiac electrode can obtain signals from the upper part of the wrist on the user's left arm, and the second cardiac electrode can obtain two signals using the second cardiac electrode placed on the user's chest. The obtained signals may include cardiac potential waveforms, such as the voltage generated during cardiac contraction. The data obtained from these three signals is converted into provocation, quality, radiation condition, severity, time (PQRST) waves. The PQRST waves can be used to generate Einthoven's triangle, EKG graphs, and calculate other information, such as the user's heartbeat. In some cases, the PQRST waves can be used to diagnose cardiac conditions.

[0116] In some embodiments, the wearable diagnostic device may perform a process for obtaining a body temperature associated with a user wearing the wearable diagnostic device. After the wearable diagnostic device is wrapped around the user's arm and in contact with the user's skin, a temperature sensor in the wearable diagnostic device may obtain the user's temperature based on the skin contact. For example, the temperature sensor may contact the wrist and may obtain body temperature data for the user over a specific time period. The temperature sensor provides the sensor data to one or more processors, which may convert the received data to Fahrenheit and average the temperature data collected over one or more time periods to generate a possible body temperature of the user.

[0117] In some embodiments, a wearable diagnostic device can perform a process for obtaining hand vibrations associated with a user wearing the wearable diagnostic device. One or more processors can perform operations using a timer and an accelerometer or piezoelectric vibration sensor to obtain hand vibration measurements. For example, upon receiving an indication that a user is interested in viewing hand vibrations, the processor can set a timer for a specific time period, such as 60 seconds, and instruct the accelerometer or piezoelectric vibration sensor to obtain vibration data for the specific time period. The accelerometer or piezoelectric vibration sensor can sense the number and intensity of hand vibrations of the user during the specific time period and provide data indicating the number of vibrations to the processor.

[0118] The processor may receive data indicating the number of vibrations and may determine the frequency of the vibrations. If the frequency of the vibrations is between 3 and 7 hertz (Hz), the vibrations may be classified as vibrations associated with Parkinson's tremor. The processor may also obtain amplitude information from an accelerometer or piezoelectric vibration sensor to determine the intensity of any vibrations associated with Parkinson's tremor. Data indicating the time, intensity, and frequency of the vibrations may be stored in a user profile in a storage device and / or may be presented to the user via a display.

[0119] The above-described processes of obtaining information about a user's glucose level, hemoglobin level, blood pressure level, EKG, heart rate level, body temperature, hand vibration, and cholesterol level may be performed in parallel, simultaneously, or at different times. The wearable diagnostic device may have sufficient processing power to perform any of these processes at any time and in response to a user request.

[0120] In some embodiments, multiple diagnostic tests can be run sequentially or simultaneously. For example, an EKG test can be performed before or during a blood pressure test. An oxygen saturation test and a temperature test can be performed before or during a hemoglobin test. A blood pressure test and a temperature test can be performed before or during a glucose test. Other variations and combinations are possible. For example, if a user has a medical history of a certain condition, such as diabetes, the wearable diagnostic device can periodically perform the test most relevant to the user's condition, such as a glucose diagnostic test, and can perform other tests, such as a blood pressure test, a cholesterol test, or an oxygen saturation test, before, after, or during the most relevant diagnostic test.

[0121] In some embodiments, although a user may input a request to perform one type of diagnostic test (e.g., a glucose test), the wearable diagnostic device may determine one or more tests, such as a blood pressure test, to be performed along with the diagnostic test requested by the user. Additional tests may be determined based on one or more criteria, such as tests typically selected by the user, default settings, manufacturer settings, or doctor recommendations to be performed simultaneously, sequentially, or in pairs. In some embodiments, additional tests may be determined based on the user's medical history. For example, if the user has diabetes and high blood pressure, the wearable diagnostic device may also perform a glucose test whenever the user selects a blood pressure test. If the user selects a glucose test, the wearable diagnostic device may also perform a blood pressure test.

[0122] The results obtained from performing one or more of the above-described processes can be stored in a memory in the wearable diagnostic device, or in a database or cloud account associated with the user. The results obtained from performing one or more of the above-described processes can also be displayed on a display. In some embodiments, if one or more of the determined glucose levels, hemoglobin levels, blood pressure levels, EKG, heart rate levels, body temperature, and hand vibrations indicates a serious medical condition, the wearable diagnostic device can output a visual, audible, or electronic alarm. For example, if, for example, the EKG includes some signs of abnormal heart movement or the body temperature exceeds 102 degrees Fahrenheit, the wearable diagnostic device can generate an audible output, such as a sound wave, suggesting that the user see a doctor.

[0123] It should be understood that the embodiments and / or actions described in this specification can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or any combination thereof. Embodiments can be implemented as one or more computer program products, such as one or more modules of computer program instructions encoded on a computer-readable medium for execution by or to control the operation of a data processing device. The computer-readable medium can be a machine-readable storage device, a machine-readable storage substrate, a memory device, a composition of matter that implements a machine-readable propagated signal, or any combination thereof. The term "data processing device" encompasses all devices, apparatus, and machines for processing data, including, for example, a programmable processor, a computer, or multiple processors or computers. In addition to hardware, a device may also include code that creates an execution environment for the computer program in question, such as code constituting processor firmware, a protocol stack, a database management system, an operating system, or any combination thereof. A propagated signal is an artificially generated signal, such as a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode information for transmission to a suitable receiving device.

[0124] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, and can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for a computing environment. A computer program does not necessarily correspond to a file in a file system. A program may be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language file), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files storing one or more modules, subroutines, or portions of code). A computer program may be executed on one computer, or on multiple computers located at one site or distributed across multiple sites and interconnected by a communications network.

[0125] The processes and logic flows described in this specification can be performed by one or more programmable processors executing one or more computer programs to perform actions by operating on input data and generating output. The processes and logic flows can also be performed by, and devices can also be implemented as, special purpose logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).

[0126] For example, a processor that executes a computer program in a computer includes both general-purpose and special-purpose microprocessors, as well as any one or more processors of any kind of digital computer. Typically, a processor will receive instructions and data from a read-only memory or a random access memory, or both.

[0127] Although this specification contains many details, these details should not be interpreted as limitations on the scope of the present disclosure or the scope of what is claimed, but rather as descriptions of specific features of specific embodiments. Certain features described in this specification in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments. Furthermore, although features may be described above as functioning in certain combinations and may even be claimed for this, one or more features from the combination may be stripped from the claimed combination in some cases, and the claimed combination may involve variations of sub-combinations or sub-combinations.

[0128] It should be understood that the phrases "one or more of" and "at least one of" include any combination of elements. For example, the phrase "one or more of A and B" includes A, B, or A and B. Similarly, the phrase "at least one of A and B" includes A, B, or A and B.

[0129] Thus, particular implementations have been described. Other implementations are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order and still achieve desirable results.

Claims

1. A system for performing a medical diagnostic test, comprising: One or more computer devices and one or more storage devices storing instructions, wherein the instructions, when executed by the one or more computer devices, cause the one or more computer devices to perform operations comprising: receiving input corresponding to a request to initiate a non-invasive glucose test or a non-invasive cholesterol test to detect a medical condition of a user; In response to receiving the input, determining that the non-invasive cholesterol test is to be performed concurrently with the non-invasive glucose test; determining one or more first sensors for performing the non-invasive glucose test and one or more second sensors for performing the non-invasive cholesterol test; activating the one or more first sensors and the one or more second sensors; receiving first signal data via the one or more first sensors and receiving second signal data via the one or more second sensors, the second signal data comprising data obtained at a first time without application of a magnetic field and data obtained at a second time different from the first time after application of a magnetic field; determining a first test result of the non-invasive glucose test based on the first signal data; determining a second test result of the non-invasive cholesterol test based on the second signal data, the second signal data including data obtained at a first time without applying a magnetic field and data obtained at a second time different from the first time after applying a magnetic field; as well as At least one of the first test result or the second test result is output through a display or a speaker.

2. The system of claim 1 , wherein determining the first test result and the second test result comprises: obtaining a first predicted value of the non-invasive glucose test and a second predicted value of the non-invasive cholesterol test; determining the first test result based on the first prediction value and the first signal data; as well as The second test result is determined based on the second predicted value and the second signal data.

3. The system of claim 2, wherein determining the first test result comprises: obtaining raw data from the first signal data; selecting a specific path from a group of known paths based on the raw data; obtaining the first prediction value based on the specific path, and The first test result is determined based on the first predicted value and the original data.

4. The system of claim 2, wherein determining the second test result comprises: obtaining raw data from the second signal data; Obtaining user characteristic information of the user; obtaining a specific cholesterol level value as the second predicted value from a plurality of predetermined cholesterol level values based in part on the raw data and the user characteristics; comparing the second predicted value to one or more previously obtained cholesterol levels of the user; as well as The second test result is determined based on comparing the second predicted value to one or more previously obtained cholesterol levels of the user.

5. The system of claim 1, wherein the non-invasive glucose test and the non-invasive cholesterol test are performed by a watch comprising the one or more computer devices.

6. The system of claim 1 , wherein the one or more first sensors comprise one or more of a light sensor, a laser sensor, or an infrared sensor, and wherein the one or more second sensors comprise one or more of a light sensor, a laser sensor, an infrared sensor, an impedance sensor, or an electromagnetic sensor.

7. The system of claim 4, wherein comparing the second predicted value to one or more previously obtained cholesterol levels of the user comprises: calculating a difference between the second predicted value and one or more previously obtained cholesterol levels; comparing the difference to a threshold value; In response to the difference being less than or equal to the threshold, setting the second prediction value as the second test result; and In response to the difference being greater than the threshold, performing the following operations (i)-(iii) in a plurality of iterations: (i) reactivating the one or more second sensors and receiving new second signal data through the one or more second sensors; (ii) obtaining a new second predictive value for the non-invasive cholesterol test based on the new second signal data; and (iii) comparing the new second predicted value to one or more previously obtained cholesterol levels; until the difference between the new second predicted value and one or more previously obtained cholesterol levels is less than or equal to the threshold, or the number of iterations reaches three; and The new second prediction value is set as the second test result.

8. The system of claim 6, wherein receiving the first signal data comprises: applying an infrared signal or a pulse signal on the skin area of the user for a first period of time using one or more of a light sensor, a laser sensor, or an infrared sensor; detecting reflection of one or more of an infrared signal or a pulse signal from the skin area; as well as The first signal data is obtained by processing reflections of one or more of an infrared signal or a pulse signal.

9. The system of claim 6, wherein receiving the second signal data comprises: applying a first infrared signal on the skin area of the user for a first period of time using one of a light sensor, a laser sensor, or an infrared sensor; detecting a first reflection of a first infrared signal from the skin area; determining first infrared absorption spectrum data based on the first reflection; applying a magnetic field on the skin area at a second time for a second period of time using an electromagnetic sensor; applying a second infrared signal to the skin area using one of a light sensor, a laser sensor, or an infrared sensor; detecting a second reflection of a second infrared signal from the skin area; determining second infrared absorption spectrum data based on the second reflection; as well as The second signal data is determined using the first infrared absorption spectrum data and the second infrared absorption spectrum data.

10. A computer-implemented method comprising: receiving input corresponding to a request to initiate a non-invasive glucose test or a non-invasive cholesterol test to detect a medical condition of a user; In response to receiving the input, determining, by one or more computer devices, that the non-invasive cholesterol test is to be performed concurrently with the non-invasive glucose test; determining, by one or more computer devices, one or more first sensors for performing the non-invasive glucose test and one or more second sensors for performing the non-invasive cholesterol test; activating the one or more first sensors and the one or more second sensors; receiving first signal data via the one or more first sensors and receiving second signal data via the one or more second sensors, the second signal data comprising data obtained at a first time without application of a magnetic field and data obtained at a second time different from the first time after application of a magnetic field; determining, by the one or more computer devices, a first test result based on the first signal data; determining, by the one or more computer devices, a second test result of the non-invasive cholesterol test based on the second signal data, the second signal data comprising data obtained at a first time without applying a magnetic field and data obtained at a second time different from the first time after applying a magnetic field; as well as At least one of the first test result or the second test result is output by the one or more computer devices through a display or a speaker.

11. The computer-implemented method of claim 10, wherein determining the first test result and the second test result comprises: obtaining a first predicted value of the non-invasive glucose test and a second predicted value of the non-invasive cholesterol test; determining the first test result based on the first prediction value and the first signal data; as well as The second test result is determined based on the second predicted value and the second signal data.

12. The computer-implemented method of claim 11 , wherein determining the first test result comprises: obtaining raw data from the first signal data; selecting a specific path from a group of known paths based on the raw data; obtaining the first prediction value based on the specific path, and The first test result is determined based on the first predicted value and the first signal data.

13. The computer-implemented method of claim 11 , wherein determining the second test result comprises: obtaining raw data from the second signal data; Obtaining user characteristic information of the user; obtaining a specific cholesterol level value as the second predicted value from a plurality of predetermined cholesterol level values based in part on the raw data and the user characteristics; comparing the second predicted value to one or more previously obtained cholesterol levels of the user; as well as The second test result is determined based on comparing the second predicted value to one or more previously obtained cholesterol levels of the user.

14. The computer-implemented method of claim 13, wherein the non-invasive glucose test and the non-invasive cholesterol test are performed by a watch comprising the one or more computer devices.

15. The computer-implemented method of claim 10, wherein the one or more first sensors include one or more of a light sensor, a laser sensor, or a CMOS sensor, and the one or more second sensors include one or more of a light sensor, a laser sensor, an infrared sensor, an impedance sensor, or an electromagnetic sensor; Receiving the first signal data includes: applying an infrared signal or a pulse signal on the skin area of the user for a first period of time using one or more of a light sensor, a laser sensor, or an infrared sensor; detecting reflection of one or more of an infrared signal or a pulse signal from the skin area; and obtaining said first signal data by processing reflections of one or more of an infrared signal or a pulse signal; and Receiving the second signal data includes: applying a first infrared signal on the skin area using one of a light sensor, a laser sensor, or an infrared sensor; detecting a first reflection of a first infrared signal from the skin area; determining first infrared absorption spectrum data based on the first reflection; applying a magnetic field on the skin area at the second time for a second period of time using an electromagnetic sensor; applying a second infrared signal to the skin area using one of a light sensor, a laser sensor, or an infrared sensor; detecting a second reflection of a second infrared signal from the skin area; determining second infrared absorption spectrum data based on the second reflection; and The second signal data is determined using the first infrared absorption spectrum data and the second infrared absorption spectrum data.

16. The computer-implemented method of claim 11 , wherein obtaining a first predicted value of a non-invasive glucose test comprises: Obtaining user characteristic information of the user; determining one or more of blood pressure or temperature of the user from the first signal data; determining a clinically correlated information value for glucose (cCIG) for the user using one or more of blood pressure or temperature; determining a clinically correlated demographic value of glucose (cLDG) for the user using the user characteristic information of the user; Determining the scope of the clinical dataset based on one or more of the cCIG or cLDG; mapping the clinical dataset range to glucose prediction values; as well as The glucose prediction value is provided as the first prediction value.

17. The computer-implemented method of claim 13, wherein comparing the second predicted value to one or more previously obtained cholesterol levels of the user comprises: calculating a difference between the second predicted value and one or more previously obtained cholesterol levels; comparing the difference to a threshold value; In response to the difference being less than or equal to the threshold, setting the second prediction value as the second test result; and In response to the difference being greater than the threshold, performing the following operations (i)-(iii) in a plurality of iterations: (i) reactivating the one or more second sensors and receiving new second signal data through the one or more second sensors; (ii) obtaining a new second predictive value for the non-invasive cholesterol test based on the new second signal data; and (iii) comparing the new second predicted value to one or more previously obtained cholesterol levels; until the difference between the new second predicted value and one or more previously obtained cholesterol levels is less than or equal to the threshold, or the number of iterations reaches three; and The new second prediction value is set as the second test result.

Images