A wearable device configured to evaluate a user's breast region and provide a prediction

Abstract

A wearable device is provided that is configured to evaluate a user's breast region and provide a prediction associated with the user's breast region. The wearable device includes a garment insert removably coupled to a garment designed to at least partially contact the user's breast region, and a sensor configured to collect data associated with the user's breast region. The sensor may collect first breast data at a first time and second breast data at a second time different from the first time. The breast region prediction may be generated based on comparing the first breast data with the second breast data and may define an estimate of the breast region risk for the user. A feedback indicator may be provided to a user interface based on the breast region prediction, indicating whether the user should receive a breast region evaluation from a medical professional.

Description

Technical Field

[0001] Cross - Reference to Related Applications This disclosure claims priority to U.S. Provisional Patent Application No. 63 / 347,842, filed on June 1, 2022, entitled "WEARABLE DEVICE CONFIGURED TO EVALUATE A BREAST AREA OF A USER AND PROVIDE A PREDICTION ASSOCIATED WITH THE BREAST AREA", the disclosure of which is incorporated herein by reference.

[0002] This disclosure generally relates to breast health, and more specifically, to wearable devices configured to evaluate a user's breast area and provide a prediction associated with the breast area, and related technologies thereto.

Background Art

[0003] The background description provided herein is for the purpose of generally presenting the context of the present disclosure. Works of the presently named inventors in the context of the background art described herein, as well as aspects of this document that may not otherwise be eligible as prior art at the time of filing, are not admitted as prior art to the present disclosure, either expressly or implicitly.

[0004] Currently, screening for breast cancer and other breast health conditions is typically done via an annual mammogram. However, there is currently no standardized screening for breast health that occurs more frequently than an annual mammogram. Additionally, mammogram results regarding breast density may not be conclusive with respect to breast health for women who are born with high - density breast tissue.

[0005] Furthermore, mammograms require a doctor's examination and can, in some cases, be inconvenient and expensive. Additionally, mammograms are uncomfortable for many women. Additionally, breast self-examination can be performed at any time without the individual bearing the cost, but breast self-examination has not been shown to be effective in detecting cancer or improving the survival rate of women with breast cancer.

[0006] Accordingly, there is a need for wearable devices and associated methods for evaluating a user's breast region and providing predictions associated with the breast region, and related technologies thereto. SUMMARY OF THE INVENTION

[0007] The present disclosure provides a wearable device for evaluating a user's breast region (e.g., including the user's breast and associated breast tissue, breast implant material, and / or the user's chest region) and providing predictions associated with the user's breast region, and related technologies thereto. The wearable device including one or more sensors can be inserted into clothing such as a standard bra, sports bra, swimsuit, shirt, dress, or any other clothing designed to at least partially contact the user's breast region. The sensors of the wearable device can capture data associated with the user's breast region at various times, and this data can be analyzed to generate user-specific breast region predictions. The breast region predictions can be an estimation of the breast region risk for the user (e.g., the risk of breast cancer, the risk of breast implant rupture, etc.), which can be generated based on changes in the data associated with the user captured by the sensors over time. Feedback indicators can be provided via a user interface indicating the breast region predictions and recommendations regarding whether the user should receive further breast region evaluation from a medical professional.

[0008] Specifically, a clothing insert that fits inside the clothing can use on-board sensors to make regular measurements throughout the day, analyze the measurements, and detect small changes. In some examples, based on these changes, the wearable device can determine abnormalities associated with the user's breast area and generate a recommendation that the user should receive further breast area evaluation from a medical professional. The clothing insert can be used in multiple types of compatible clothing (including bras, sports bras, shirts, dresses, swimsuits, etc.) and can be removable and interchangeable between multiple pieces of clothing so that the user can use the insert with a second piece of clothing based on the first piece of clothing being washed or different pieces of clothing being used on different days.

[0009] Generally speaking, a clothing insert can be worn by a user throughout the day when the user wears the clothing, and can be measured over time (e.g., not only over the course of a day, but also over longer periods such as several days, a month, a year, etc.) to improve accuracy compared to a single scan. The on-board sensors can include multiple types of sensors to enhance accuracy. For example, in one instance, the sensors can measure temperature data in addition to other types of data. More specifically, with respect to various embodiments, a wearable device is provided that is configured to evaluate a user's breast region and provide a prediction associated with the user's breast region. The wearable device is a clothing insert configured to be removably coupled to the clothing, where the clothing is designed to at least partially contact the user's breast region, a clothing insert, one or more sensors configured to collect data associated with the user's breast region, one or more processors communicatively coupled to the one or more sensors, and a computer memory containing computing instructions. When the computing instructions are executed by the one or more processors, the one or more processors are caused to collect a first set of breast data sensed by the one or more sensors at a first time, collect a second set of breast data sensed by the one or more sensors at a second time, where the second time is different from the first time, compare the first set of breast data with the second set of breast data, generate a breast region prediction, where the breast region prediction defines an estimate of the breast region risk for the user, and provide a feedback indicator to the user interface indicating whether the user should receive a breast region evaluation from a medical professional based on the breast region prediction.

[0010] In an additional embodiment, a computer-implemented method in a wearable device for evaluating a user's breast region and providing a prediction associated with the user's breast region is provided. The method includes collecting, by one or more sensors of a garment insert configured to be removably coupled to a garment designed to at least partially contact the user's breast region, a first set of breast data associated with the user's breast region at a first time; collecting, by one or more sensors configured to collect data associated with the user's breast region, a second set of breast data associated with the user's breast region at a second time; generating, by one or more processors, a breast region prediction based on a comparison of the first set of breast data and the second set of breast data, wherein the breast region prediction defines an estimation of a breast region risk for the user; and providing, by one or more processors, to a user interface, a feedback indicator indicating whether the user should receive a breast region evaluation from a medical professional based on the breast region prediction.

[0011] In yet another embodiment, a tangible non-transitory computer-readable medium is provided that stores instructions for evaluating a user's breast region and providing a prediction associated with the user's breast region, the instructions, when executed by one or more processors, causing the one or more processors to collect a first set of breast data associated with the user's breast region sensed by one or more sensors of a clothing insert at a first time, wherein the clothing insert is configured to be removably coupled to clothing designed to at least partially contact the user's breast region, collect a second set of breast data associated with the user's breast region sensed by the one or more sensors at a second time, generate a breast region prediction based on a comparison of the first set of breast data and the second set of breast data, wherein the breast region prediction defines an estimation of the breast region risk for the user, and provide to a user interface a feedback indicator indicating whether the user should receive a breast region evaluation from a medical professional, based on the breast region prediction.

[0012] Representative embodiments of the systems and methods disclosed herein provide several advantages over commonly used methods such as mammograms in that a wearable device can be conveniently coupled to a user's clothing to conveniently collect a number of different types of data points over time without the need for a doctor's visit and associated discomfort, expense, or inconvenience. Further, the wearable device does not flag "abnormal" breast tissue, but rather detects user-specific changes in the breast region, and thus can detect changes in individual users that a mammogram may not be able to detect, particularly for users with naturally dense or otherwise atypical breast tissue. Accordingly, the present disclosure relates to an improvement over other technologies or technical fields in that at least the systems and methods shown herein can predict breast health risks with greater accuracy and efficiency than conventional techniques such as mammograms.

[0013] According to the above and the disclosure herein, the present disclosure at least describes improvements in computer functions or other technologies, such as when the intelligence or predictive ability of a computing device is enhanced by sensor data captured by multiple types of sensors of a wearable device worn by a user over time, for example, the computing device is improved. A breast region prediction application executed on a wearable device or an associated computing device can accurately predict a user-specific estimation of the breast region risk regarding the user based on sensor data captured by multiple types of sensors of the wearable device worn by the user over time. That is, a wearable device or other computing device can accurately predict, detect, or determine a user-specific breast region health risk, such as the risk of breast cancer, based on the changes over time in a specific user's breast region when the wearable device is worn daily, and is enhanced by sensor data captured by multiple types of sensors of the wearable device. Therefore, the present disclosure describes improvements in the function of the computer itself or in "any other technology or technical field". This is at least because existing systems lack such user-specific predictive ability and, as described herein, cannot capture these multiple types of sensor data over time from all-day wear to evaluate the user's breast region and provide predictions associated with the user's breast region, thus improving over the prior art.

[0014] For similar reasons, the present disclosure is at least related to improvements in other technologies or technical fields because the present disclosure describes or introduces improvements to computing devices in the field of breast health analysis. Thereby, a wearable device and / or a computing device can improve the field of breast health analysis by evaluating the user's breast region and providing predictions associated with the user's breast region based on multiple types of sensor data captured by the wearable device, as described herein.

[0015] Furthermore, the present disclosure includes applying certain aspects or features in or using a particular machine, such as a wearable device including one or more sensors, which can be inserted into clothing such as a standard bra, sports bra, swimsuit, shirt, dress, or any other garment designed to at least partially contact the user's breast area, configured to evaluate the user's breast area and provide a prediction associated with the user's breast area.

[0016] In addition, the present disclosure includes steps that are well understood, routines, conventional activities in the field, or not bound by the convention of limiting the claims to a particular useful application, such as evaluating the user's breast area based on multiple types of sensor data captured by a wearable device and providing a prediction associated with the user's breast area, including certain features other than this.

[0017] Advantages will become more apparent to those skilled in the art from the following description of the preferred embodiments illustrated and described by way of example. As will be understood, other different embodiments may be possible and their details may be modified in various respects. Accordingly, the drawings and description should be regarded as illustrative in nature and not restrictive.

Brief Description of the Drawings

[0018] The figures described below depict various aspects of the systems and methods disclosed herein. It should be understood that each figure depicts an embodiment of a particular aspect of the disclosed systems and methods and that each of the figures is intended to be consistent with its possible embodiments. Furthermore, to the extent possible, the following description refers to the reference numbers included in the following figures, and features depicted in multiple figures are designated by consistent reference numbers.

[0019] The arrangement under consideration is shown in the drawings, it being understood that the present embodiment is not limited to the exact arrangement and means shown.

[0020]

Figure 1

Figure 2

Figure 3

Figure 4

[0021] The systems and methods disclosed herein may be embodied in many different forms, but this disclosure should be regarded as an exemplification of the principles of the systems and methods disclosed herein, and it is not intended to limit the systems and methods disclosed herein to the specific embodiments illustrated. With this understanding, specific exemplary embodiments are shown in the drawings and described in detail herein. In this regard, before describing in detail at least one embodiment consistent with the systems and methods disclosed herein, it should be understood that the systems and methods disclosed herein are not limited in their application to the structural details and arrangements of components described above and below, illustrated in the drawings, or described in the examples. Methods and apparatuses consistent with the systems and methods disclosed herein may have other embodiments and may be implemented and executed in various ways. Also, it should be understood that the terminology and expression methods employed herein, as well as the abstract included below, are for the purpose of description and should not be regarded as limiting.

[0022] Referring now to the drawings, FIG. 1 is a block diagram of a system 100 for evaluating a user's breast region (e.g., including the user's breast and associated breast tissue, breast implant material, and / or the user's chest region) according to some examples provided herein and providing a prediction associated with the user's breast region. The high-level architecture illustrated in FIG. 1 may include both hardware applications and software applications, as well as various data communication channels for communicating data between various hardware components and software components, as described below.

[0023] System 100 may include garment inserts 102A, 102B, 102C, 102D, and / or 102E (i.e., 102A - 102E) configured to be removably coupled to respective garments 104A, 104B, 104C, 104D, and / or 104E (i.e., 104A - 104E). The garments may include clothing items such as bras, sports bras, shirts, dresses, swimsuits, undergarments, or other wearable apparel, lingerie, or other wearable dresses. The garment inserts are designed to at least partially contact the user's breast area. Each of the one or more garment inserts 102A - 102E is shown as including two inserts, but a garment insert may include a single insert. Additionally, each insert may be positioned on the garment in different regions or locations of the garment other than as shown.

[0024] One or more of the garment inserts 102A - 102E may each include one or more respective sensors 105A - 105E configured to collect data associated with the user's breast area, and the garment inserts 102A - 102E and / or one or more of the sensors 105A - 105E may communicate with a computing device 106 via, for example, a wired or wireless computer network 108, or via a cellular phone communication standard such as near field communication (NFC), Bluetooth (trademark) communication standard, Zigbee (trademark) communication standard, WIFI communication standard, LTE, 4G, 5G, or other cellular or mobile phone - based standard, or any other suitable communication technology. One computing device 106 is shown communicating with the plurality of garment inserts 102A - 102E and / or the plurality of sensors 105A - 105E of FIG. 1, but in some examples, each garment insert (or each set of garment inserts) or each sensor (or each set of sensors) may communicate with its own respective computing device 106.

[0025] In some embodiments, sensor data generated by any one or more of the garment inserts 102A-102E and / or one or more of the sensors 105A-105E may be transmitted to one or more servers 109. In various embodiments, the server 109 may comprise a plurality of servers, which may comprise multiple, redundant, or replicated servers as part of a server farm. In yet further embodiments, the server 109 may be implemented as a cloud-based server such as a cloud-based computing platform. For example, the server 109 may be any one or more cloud-based platforms such as MICROSOFT AZURE, AMAZON AWS. The server 109 may include one or more processors 112s (e.g., CPUs), as well as one or more computer memories 114s.

[0026] Memory 114s may include one or more forms of volatile and / or non-volatile, fixed and / or removable memory such as read-only memory (ROM), electronically programmable read-only memory (EPROM), random access memory (RAM), erasable electronically programmable read-only memory (EEPROM), and / or other hard drives, flash memory, MicroSD cards, etc. Memory 114s may store an operating system (OS) (e.g., Microsoft Windows, Linux, UNIX, etc.) that can facilitate functions, apps, methods, or other software as contemplated herein. Memory 114s may also store or be configured to access an artificial intelligence-based model such as a machine learning model trained on sensor data, or a breast region prediction application (app) 116s. Additionally, or alternatively, sensor data such as sensor data collected from any one or more of clothing inserts 102A-102E and / or one or more sensors 105A-105E may also be stored in a database 109d that is accessible to or otherwise communicatively coupled to server 109. In addition, memory 114s may also store machine-readable instructions that include any one of one or more applications, one or more software components, and / or one or more application programming interfaces (APIs), which may be implemented to facilitate or perform features, functions, or other disclosures herein such as any method, process, element or limitation, etc. illustrated, depicted, or described in various flowcharts, illustrations, graphics, diagrams, and / or other disclosures of this specification. It should be understood that one or more other applications may be contemplated and executed by processor 112s. Considering the state of advancement of mobile computing devices, it should be understood that all of the process functions and steps described herein may exist together on a mobile computing device (e.g., user computing device 106).

[0027] The processors 112s may be connected to the memory 114s via a computer bus responsible for transmitting electronic data, data packets, or other electronic signals between the processors 112s and the memory 114s to implement or execute machine-readable instructions, methods, processes, elements, or limitations illustrated, depicted, or described for various flowcharts, illustrative diagrams, graphics, figures, and / or other disclosures herein.

[0028] The processors 112s may interface with the memory 114s via a computer bus to execute an operating system (OS). The processors 112s may also interface with the memory 114s via a computer bus to create, read, update, delete, or otherwise access or interact with data stored in the memory 114s and / or the database 109d (e.g., a relational database such as Oracle, DB2, MySQL, or a NoSQL-based database such as MongoDB). The data stored in the memory 114s and / or the database 109d may include, for example, sensor data that may be used as training data for an artificial intelligence model, a machine learning model, etc., or may otherwise include all or part of any of the data or information described herein as described herein.

[0029] Server 109 may further include communication components configured to communicate (e.g., transmit and receive) data to one or more networks or local terminals such as computer network 108 and / or terminal 109 (for rendering or visualization) described herein via one or more external / network ports. In some aspects, server 109 may include client-server platform technologies such as ASP.NET, Java J2EE, Ruby on Rails, Node.js, web services, and / or online APIs, receive electronic requests, and respond thereto. Server 109 may implement client-server platform technologies that can interact with memory 114s (including applications, components, APIs, data, etc. stored therein) and / or database 109d to implement or execute various flowcharts, illustrative diagrams, figures, diagrams, and / or machine-readable instructions, methods, processes, elements, or limitations illustrated, depicted, or described for other disclosures herein via a computer bus.

[0030] In various aspects, server 109 may include or interact with one or more transceivers (e.g., WWAN, WLAN, and / or WPAN transceivers) that function according to IEEE standards, 3GPP standards, or other standards, and may be used for receiving and transmitting data via an external / network port connected to computer network 108. In some aspects, computer network 108 may comprise a private network or a local area network (LAN). Additionally, or alternatively, computer network 108 may comprise a public network such as the Internet.

[0031] Server 109 may further include or implement an operator interface configured to present information to and / or receive input from an administrator or operator. As shown in FIG. 1, the operator interface may provide a display screen (e.g., via terminal 109w). Server 109 may also provide I / O components (e.g., ports, capacitive or resistive touch sensing input panels, keys, buttons, lights, LEDs) that may be directly accessible via Server 109, or may be attached to Server 109, or may be indirectly accessible via terminal 109w, or may be attached to terminal 109w. According to some aspects, an administrator or operator may access Server 109 via terminal 109w to view information, make changes, manipulate sensor data, initiate training of an artificial intelligence or machine learning model, and / or perform other functions as described herein.

[0032] In some aspects, Server 109 may perform functions as contemplated herein as part of a "cloud" network, or alternatively, may communicate with other hardware or software components within the cloud to send, obtain, or otherwise analyze data or information described herein.

[0033] Generally, a computer program or computer system product, application, or code (e.g., a model such as an AI model, or other computing instructions described in this specification) can be stored in a computer-usable storage medium having such computer-readable program code or computer instructions embodied therein, or a tangible non-transitory computer-readable medium (e.g., standard random access memory (RAM), optical disk, universal serial bus (USB) drive, etc.), and the computer-readable program code or computer instructions can be installed in processors 112s (e.g., operating in association with respective operating systems in memory 114s) or otherwise adapted and executed to facilitate, implement, or carry out machine-readable instructions, methods, processes, elements, or limitations illustrated, depicted, or described for various flowcharts, illustrative diagrams, figures, graphs, and / or other disclosures of this specification. In this regard, the program code can be implemented in any desired programming language and can be implemented as machine code, assembly code, bytecode, interpretable source code, etc. (e.g., via Golang, Python, C, C++, C#, Objective-C, Java, Scala, ActionScript, JavaScript, HTML, CSS, XML, etc.).

[0034] As shown in FIG. 1, server 109 is communicatively connected to one or more of clothing inserts 102A-102E and / or one or more of sensors 105A-105E via computer network 108. Additionally, server 109 is communicatively connected to computing device 106 via computer network 108. In some embodiments, a base station comprising a cellular base station such as a cell tower may connect clothing inserts 102A-102E and / or one or more of sensors 105A-105E via wireless communication based on any one or more of various mobile phone standards including NMT, GSM, CDMA, UMMTS, LTE, 5G standards, etc. Additionally, or alternatively, the base station may comprise a router, wireless switch, or other such wireless connection point that communicates with clothing inserts 102A-102E and / or one or more of sensors 105A-105E via wireless communication based on any one or more of various wireless standards including, by way of non-limiting example, IEEE802.11a / b / c / g (WIFI), BLUETOOTH standards, etc.

[0035] Computing device 106 may comprise a mobile device and / or client device for accessing and / or communicating with server 109 and / or any one or more of clothing inserts 102A-102E and / or one or more of sensors 105A-105E. Computing device 106 may comprise a user interface 110 (e.g., a display screen, etc.), one or more mobile processors (e.g., processor 112), and memory 114. In various embodiments, computing device 106 may comprise, by way of non-limiting example, a mobile phone (e.g., a cellular phone), a tablet device, a personal data assistant (PDA), etc., including, for example, an APPLE iPhone or iPad device, or a GOOGLE ANDROID-based mobile phone or tablet.

[0036] In various aspects, the user computing device 106 may implement or execute an operating system (OS) or mobile platform, such as the APPLE iOS and / or Google ANDROID operating system. The user computing device 106 may include one or more processors (e.g., processor 112) and / or one or more memories (e.g., memory 114) for storing, implementing, or executing computing instructions or code, such as the breast region prediction application 116, as described in various aspects herein. As shown in FIG. 1, the breast region prediction application 116, or at least a portion thereof, may also be stored locally in a memory (e.g., memory 114) of the user computing device (e.g., computing device 106). Another portion of the breast region prediction application 116s app may be stored on a server 109 that is communicatively coupled to the breast region prediction application 116s via a computer network 108 by the breast region prediction application 116 running on the computing device 106. For example, the breast region prediction application 116s may communicate via an API and may transmit an output of sensor data, such as a prediction or classification as output by an artificial intelligence model. To facilitate such communication, the computer device 106 may include a wireless transceiver for receiving and transmitting wireless communication with a base station and may then be transmitted to and / or received from the server 100 via the computer network 108.

[0037] Referring further to FIG. 1, in some embodiments, the data collected by one or more of sensors 105A-105E may include data collected by one or more different types of sensors configured to collect data including one or more of temperature data, infrared data, ultrasonic data, visible light-based data, electromagnetic data, pressure data, inertial measurement unit (IMU) data, electromyogram (EMG) data, electrocardiogram (ECG) data, electrical impedance data, sweat-based data, blood oxygen data, breast density data, fat content data, vibration data, magnetomyogram (MaMG) data, mechanomyogram (MeMG) data, and / or voice data. Such data may be captured at one or more different times over one or more periods. The sensor data may be collected and transmitted to user device 106 and / or server 109.

[0038] Further, in some examples, the data collected by one or more of sensors 105A-105E may include data associated with other sounds generated by the user, such as vocalizations, breathing, coughing, laughing, etc. In particular, in some examples, the data collected by one or more of sensors 105A-105E may include different instances of the same type of sound generated by the user, such as different instances of the user breathing (e.g., at different times), or different instances of the user vocalizing the same phoneme (e.g., at different times). For example, changes in pitch, tone, timbre, etc. of sounds generated by the user as the sound travels through the user's breast region may be related to changes in breast density, breast health, and / or other breast biological markers. In some embodiments, the sensor data is collected when the user utters a specific word such as a trigger word. In such embodiments, the sensor data itself causes vibrations and / or changes in the user's breast region and / or chest. The trigger word may include, for example, commonly spoken words such as "yes" and / or "no", multiple words, and / or phrases. Additionally, or alternatively, the trigger word may include specific syllables, tones, and / or sounds (e.g., humming, whistling, etc.) of the user.

[0039] In some examples, one or more of sensors 105A - 105E may be configured to operate in a “sleep” or “idle” mode until activated, for example, by determining that the clothing (e.g., any one of clothing 104A - 104E) is at least partially in contact with the user's breast area by a user control signal from computing device 106, by analyzing voice data generated by the user, or by determining that the user has spoken a trigger word or the like. For example, one or more of sensors 105A - 105E that capture other types of data may remain idle until a sensor 105A - 105E that captures temperature data detects a temperature indicating that the user is wearing clothing 104A - 104E and / or until a sensor 105A - 105E that captures voice data detects a trigger word, which can cause one or more of sensors 105A - 105E to activate and begin capturing data that may include the same and / or other types of data. In some aspects, the trigger word may include commonly spoken words such as, for example, “yes” and / or “no”, multiple words, and / or phrases. Additionally, or alternatively, the trigger word may include specific syllables, tones, and / or sounds of the user (e.g., humming, whistling, etc.).

[0040] FIG. 2 illustrates exemplary clothing 104B and 104C and respective exemplary clothing inserts 102B and 102C of a wearable device for evaluating a user's breast area and providing predictions associated with the user's breast area, according to some examples provided herein.

[0041] FIG. 3 further illustrates exemplary clothing 104D and 104E and respective exemplary clothing inserts 102D and 102E of a wearable device for evaluating a user's breast area and providing predictions associated with the user's breast area, according to some examples provided herein.

[0042] As shown, garments 104B and 104D are sports undergarments, and garments 104C and 104E are bras. However, it should be understood that any garment to which a garment insert (e.g., respective garment inserts 102B - 102E) can be attached can be used. For example, as shown in FIGS. 2 and 3, in each of the various types of garments 104B - 104E, there are multiple possible placement locations for one or more of the garment inserts 102B - 102E. For example, in some instances, one or more of the garments 104B - 104E can include one or more pockets or pouches where the respective garment inserts 102B - 102E can be placed to capture data associated with the user's breast region from the locations shown in FIGS. 2 and 3. Of course, the locations of one or more of the garment inserts 102B - 102E shown in FIGS. 2 and 3 are merely exemplary, and many other possible locations for the garment inserts 102B - 102E are possible in various manners, including, for example, the garment insert 102A as shown in FIG. 1. Additionally, in some aspects, it should be understood that a single garment insert (e.g., not a pair of garment inserts as shown in 102B) can be used to collect sensor data for a single breast (e.g., breast tissue, breast implant material, etc.) or related regions of the breast. In such aspects, the sensor data of the single garment insert is used to generate a breast region prediction associated with the region of the garment insert that is associated with a single breast or, alternatively, analyzed by collecting sensor data for a single breast or its related regions.

[0043] Generally speaking, a clothing insert, such as any one or more of clothing inserts 102A - 102E, can be configured to be removably coupled to respective clothing (e.g., clothing 104A - 104E) designed to at least partially contact the user's breast area. For example, the clothing (e.g., any one or more of clothing 104A - 104E) can be a bra (or a shirt, swimsuit, dress, etc.) that includes a flexible portion configured to conform to the user's breast area. In some examples, the flexible portion can house one or more of sensors 105A - 104E. Additionally, in some examples, the flexible portion can house one or more processors and / or one or more memories. For example, FIG. 1 shows an exploded view of a block diagram of clothing insert 102A. The exploded view shows that the clothing insert can include a processor 112g and a memory 114g. The processor 112g and the memory 114g can be housed within a portion of the clothing insert, such as a flexible portion of the clothing insert. The processor 112g of the clothing insert (e.g., clothing insert 102A) can be communicatively coupled to a sensor (e.g., sensor 105A) to collect sensor data, to determine a period or time for collecting sensor data, and / or to communicate, transmit, or receive sensor data to / from server 109 and / or computing device 106 via computer network 108. The sensor (such as sensor 105A) can, in various examples, be positioned to contact the user's breast, subdermally to the user's breast, and / or proximate to the user's breast. The collected sensor data can vary based on the placement of the sensor relative to the user's breast. In various aspects, the sensor data can be stored within memory 114g. Additionally, in various aspects, memory 11g can store a breast area prediction app 116g, which can include a machine learning model, such as a breast area prediction model, that is pre-trained with sensor data of other individuals and downloaded or installed into the memory 114g of clothing insert 102A. Additionally, or alternatively, a machine learning model, such as a breast area prediction model, can be trained with sensor data of a single user (e.g., the user of the clothing).Such training can occur over time as the breast region prediction model is updated with the user (e.g., automatically and / or continuously). The model can output a feedback metric that indicates a change or delta in sensor data collected over time (e.g., between a first time and a second time) regarding the user's breast region when analyzed by sensor 105A. Such deltas and / or changes can indicate whether the user should receive a breast region evaluation from a medical professional.

[0044] In some examples, one or more garment inserts 102A - 102E can be configured to apply respective pressures to each of one or more sensors 105A - 105E positioned relative to the user's breasts based on detected movement of the user's breasts within or relative to the garment. For example, detecting movement of the user's breasts within or relative to the garment can include detecting a shift in the position of one or more sensors 105A - 105E and / or a change in the contact of one or more sensors 105A - 105E with the user's breast region. For example, a change in the contact of one or more sensors 105A - 105E with the user's breast region can be detected based on a change in the contact of one or more sensors 105A - 105E with the user's breast region, a change in the contact force of one or more sensors 105A - 105E with the user's breast region, etc. In some examples, the detected change in position of one or more sensors 105A - 105E can cause different data to be collected by the moved sensors 105A - 105E, such that different amounts of data are collected and / or different fidelity / quality data is collected.

[0045] Referring back to FIG. 1, computing device 106 may include a user interface 110, as well as one or more processors 112 and a memory 114. The user interface 110 may include a graphical user interface (GUI) configured to display breast region predictions, feedback metrics, and / or confidence level outputs. In some examples, the user interface 110 may include, for example, buttons, switches, and / or one or more LED indicators. The memory 114 (e.g., volatile memory, non-volatile memory) may be accessible by one or more processors 112 (e.g., via a memory controller). One or more processors 112 may interact with the memory 114 to obtain, for example, computer-readable instructions stored within the memory 114.

[0046] Additionally, although computing device 106 is shown as separate from clothing inserts 102A-102E, in some examples, computing device 106, or one or more of its components, may be incorporated into or attached to one or more of clothing inserts 102A-102E, or the clothing 104A-104E themselves. For example, the user interface 110, processor 112, and / or memory 114 may be incorporated into one or more of clothing inserts 102A-102E or the clothing 104A-104E themselves, and / or may communicate with or be attached to them and communicate with a user interface 110 of another computing device via either computer network 108 or any of the other communication technologies discussed above.

[0047] Furthermore, in some examples, the data captured by one or more of sensors 105A - 105E can be sent to another remote processor (e.g., separate from processor 112), which can be, for example, a processor on a cloud computing system, a processor of a medical professional's desktop computer, etc. For example, the remote processor can comprise processor 112s of server 109. In such an embodiment, the sensor data captured by sensors 105A - 105E can be sent and stored in memory 114s and / or database 109d. It should be understood that the sensor data can be sent and / or received over computer network 108 (e.g., via the Internet and / or other communications), wirelessly and / or wired, to a remote processor such as processor 112 of computing device 106 and / or processor 112s of the server.

[0048] In any case, the computer-readable instructions stored in the memory 114 are configured to cause one or more processors 112 to execute one or more applications including the breast region prediction application 116. Additionally, the computer-readable instructions stored in the memory 114s are configured to cause one or more processors 112s to execute one or more applications including the breast region prediction application 116s. Furthermore, the computer-readable instructions stored in the memory 114g are configured to cause one or more processors 112g to execute one or more applications including the breast region prediction application 116g. In some embodiments, computer-readable instructions such as computing instructions and / or applications that execute on a server (e.g., server 109), a computing device (e.g., computing device 106), and / or a garment insert (e.g., garment insert 102A) may be communicatively coupled to transmit and receive sensor data, analyze sensor data, output breast region predictions, and / or perform other functions described herein. For example, the processor 112g of the garment insert 112g may be communicatively coupled to one or more processors (e.g., processor 112s) of the server 109 via the computer network 108. The processors 112g and 1112s may each be communicatively coupled to the processor 112 of the user device 106 via a computer network (e.g., computer network 108). In such an embodiment, the breast region prediction application may include a device application portion (e.g., the breast region prediction application 116g configured to execute on the processor 112g of the garment insert 102A), a server application portion (e.g., the breast region prediction application 116s configured to execute on one or more processors of a server (e.g., server 102)), and a mobile application portion (e.g., the breast region prediction application 116) configured to execute on one or more processors of a computing device such as a mobile device (e.g., computing device 106).In such an embodiment, the server app portion, the mobile app portion, and / or the device app portion are configured to communicate with each other via the computer network 108. The server app portion, the mobile app portion, and / or the device app portion each implement, or are configured to partially implement, one or more of the following: (1) collecting a first set of breast data sensed by one or more sensors at a first time; (2) collecting a second set of breast data sensed by one or more sensors at a second time, where the second time is different from the first time; (3) generating a breast region prediction based on a comparison of the first set of breast data and the second set of breast data, where the breast region prediction defines an estimation of the breast region risk for the user; and / or (4) providing, to a user interface, a feedback indicator indicating whether the user should receive a breast region evaluation from a medical professional based on the breast region prediction. Additionally, or alternatively, the server app portion, the mobile app portion, and / or the device app portion are configured to communicate to implement, or partially implement, computing instructions for one or more other methods or computing functions as described herein. Partial implementation may include a distributed app network or codebase, where each app portion includes a portion of software instructions, code, or a machine learning model, and each communicates via the computer network 108 via an API (e.g., a RESTFUL API, etc.). For example, in some embodiments, the garment insert 102A may include a device app portion (e.g., a breast region prediction app 116g) that transmits sensor data to a server app portion (e.g., a breast region prediction app 116s) on the server 109. The server app portion (e.g., the breast region prediction app 116s) may include a breast region prediction model stored in the memory 114s of the server 109. The breast region prediction model stored on the server 109 outputs a feedback indicator that may be transmitted to a user interface (e.g., the user interface 110) indicating whether the user should receive a breast region evaluation from a medical professional.

[0049] Additionally, or alternatively, in other embodiments, a single application may handle all functions. For example, the breast region prediction application 116g may include a machine learning model such as a breast region prediction model. In such an embodiment, when the breast region prediction model is collected regarding the user's breast region, it receives sensor data, and the breast region prediction model outputs a feedback indicator indicating whether the user should receive a breast region evaluation from a medical professional to a user interface (e.g., the user interface 110 or another user interface of the clothing insert (not shown)). Such an interaction may occur without transmitting sensor data or otherwise communicating with the server 109.

[0050] Executing the breast region prediction application 116 and / or the breast region prediction application 116s may include analyzing data captured by one or more of any of 105A - 105E, including sensor data captured over time, to generate a breast region prediction. The breast region prediction may include an output defining an estimate of the breast region risk for the user, such as the risk of breast cancer or the risk of breast implant rupture. In particular, the breast region prediction application 116 and / or the breast region prediction application 116s may compare data captured by any one or more of sensors 105A - 105E at a first time with data captured by any one or more of sensors 105A - 105E at a second time to generate a breast region prediction. For example, a change in any of the breast data captured by any one or more of sensors 105A - 105E regarding a particular user may be associated with a change in breast density or breast biomarker regarding the particular user, and these types of changes may indicate the breast health risk for the particular user.

[0051] In some examples, breast region prediction may include an output of a confidence level for the estimation of breast region risk. The confidence level output may be based on the amount of data and / or the signal quality of the data of the breast data collected by any one or more of sensors 105A-105E. For example, the confidence level output may be higher when more breast data is collected by any one or more of sensors 105A-105E and may be lower when less breast data is collected by any one or more of sensors 105A-105E. Further, the confidence level output may be higher when the signal quality of the breast data collected by any one or more of sensors 105A-105E is higher and may be lower when the signal quality of the breast data collected by any one or more of sensors 105A-105E is lower.

[0052] In various aspects, executing the breast region prediction application 116 and / or the breast region prediction application 116s includes training a machine learning model to generate a breast region prediction based on data captured by one or more sensors (e.g., any one or more of 105A - 105E). Additionally, or alternatively, executing the breast region prediction application 116 and / or the breast region prediction application 116s includes using a previously trained machine learning model to generate and / or output a breast region prediction based on data captured by one or more sensors 105A - 105E. For example, the machine learning model can be trained with data from one or more sensors (e.g., one or more of sensors 105A - 105E) of multiple users to generate a machine learning-based breast region prediction model. Once trained, the breast region prediction model can then be provided with new sensor data (e.g., sensor data of the clothing insert 102A) to output a breast region prediction for a particular user (e.g., a user wearing clothing 104A). In this way, sensor data collected from multiple users is used via the breast region prediction model to define or output a feedback metric to the user interface indicating whether the user should receive a breast region evaluation from a medical professional, or to analyze the breast tissue, breast implant materials, and / or breast biological markers of the multiple users for which the breast region prediction model was trained. For example, in some examples, the breast region prediction application 116 and / or the breast region prediction application 116s can use data captured by respective sensors 105A, 105B, 105C, 105D, and / or 105E associated with respective users of respective clothing 104A, 104B, 105C, 105D, and / or 105E to train a breast region prediction model (e.g., a machine learning model). Of course, five such pieces of clothing 104A - 104E are shown in FIG. 1, but sensor data captured by sensors of any number of clothing items (e.g., thousands or tens of thousands of clothing items) can be used to train the machine learning model.

[0053] Additionally, or alternatively, the machine learning model can be trained on the collected sensor data of a single specific and / or individual user. In such an embodiment, training the breast region prediction model involves generating a new model and / or updating a previously trained baseline machine learning model to generate and / or output a breast region prediction based on data captured by sensors of a specific user's clothing insert (e.g., sensor 105A). For example, a machine learning model such as a breast region prediction model can be trained on data from sensors of a single user (e.g., one or more of sensors 105A) to generate a machine learning-based breast region prediction model specific to that user. Once trained, the breast region prediction model for a specific user can then be provided with new sensor data (e.g., sensor data collected by sensor 105A of clothing insert 102A) to output a breast region prediction for a specific user (e.g., a user wearing clothing 104A). In this way, sensor data collected from a single user can be used to define a feedback metric to a user interface indicating whether the user should receive a breast region evaluation from a healthcare provider via the breast region prediction model specific to the user, or can be used to analyze the breast tissue, breast implant material, or breast biological markers of the user for whom the breast region prediction model was trained. For example, in some examples, the breast region prediction application 116g can use data captured by sensors of a specific user's clothing insert (e.g., clothing insert 102A) (e.g., sensor 105A) to train a breast region prediction model for a specific user (e.g., a machine learning model). Such training can occur over time as the breast region prediction model is updated with the user (e.g., automatically and / or continuously). The model can output a feedback metric indicating a change or delta in the sensor data collected over time (e.g., between a first time and a second time) for the user's breast region when analyzed by sensor 105A. Such deltas and / or changes can indicate whether the user should receive a breast region evaluation from a medical professional.In some embodiments, the training and execution of the model may occur only with the garment insert (e.g., garment insert 102A) without interaction from server 109 and / or computing device 106. Additionally, or alternatively, the app portions located on server 109, computing device 106, and / or garment insert 102A may augment the training, execution, and / or output of the breast region prediction model as described herein.

[0054] In various embodiments, the breast region prediction model may include a machine learning program or algorithm that can be a deep learning neural network, trained by a neural network, and / or employ a neural network, or a combined learning module or program that learns in one or more features or feature datasets (e.g., breast data) in a particular area of interest. The machine learning program or algorithm may also include natural language processing, semantic analysis, automated inference, regression analysis, support vector machine (SVM) analysis, decision tree analysis, random forest analysis, k-nearest neighbor analysis, naive Bayes analysis, clustering, reinforcement learning, and / or other machine learning algorithms and / or techniques. In some embodiments, the artificial intelligence and / or machine learning-based algorithms used to train the breast region prediction model may include libraries or packages that are executed on server 109 and / or computing device 106 (or other computing devices not shown in FIG. 1). For example, such libraries may include TENSORFLOW-based libraries, PYTORCH libraries, and / or SCIKIT-LEARN Python libraries.

[0055] Machine learning can involve identifying and recognizing patterns in existing data (such as training a model based on sensor data measuring the breasts of multiple users, and breast health data, breast biological markers, breast cancer rates, etc. from those multiple users) in order to facilitate prediction or identification for subsequent data (for example, to determine user-specific breast health predictions, such as using a breast region prediction model for new or specific user or individual new breast data, such as determining the breast region predictions described herein).

[0056] A machine learning model can be created and trained based on exemplary data (such as "training data") inputs or data (which can be referred to as "features" and "labels") in order to make valid and reliable predictions about new inputs such as test-level or production-level data or inputs. In supervised machine learning, a machine learning program operating on a server, computing device, or other processor can, for example, determine and / or assign weights or other metrics to the model across its various feature categories so that the machine learning program or algorithm determines or discovers rules, relationships, patterns, or otherwise a machine learning "model" for mapping such inputs (such as "features") to outputs (such as labels). Such rules, relationships, or otherwise the model can then have subsequent inputs provided in order for the model executing on a server, computing device, or otherwise a processor to predict an expected output based on the discovered rules, relationships, or model.

[0057] In machine learning without a teacher, a server, a computing device, or otherwise a processor may be required to find its own structure with unlabeled exemplary inputs. For example, multiple training iterations are performed by a server, a computing device, or otherwise a processor until a satisfactory model is generated, such as a model that provides sufficient prediction accuracy when given test-level or production-level data or inputs are generated. The disclosure herein may use one or both of such supervised or unsupervised machine learning techniques.

[0058] Furthermore, executing the breast region prediction application 116 may further include providing a feedback indicator via the user interface 110 that indicates whether, based on the breast region prediction, the user should receive a breast region evaluation from a medical professional. That is, the feedback indicator may indicate whether an individual should seek further evaluation from a medical professional. Additionally, or alternatively, the feedback indicator may indicate that further evaluation from a medical professional is necessary and / or not necessary. For example, in some instances, the breast region prediction may be a numerical prediction (e.g., 75% risk, 5 / 10 risk, etc.) or otherwise a scaled prediction (e.g., orange-level risk in a color scale, A-level risk in an alphabetical scale, each indicating the degree of risk or severity of a breast problem). The breast region prediction application 116 may provide an indicator that the user should receive a breast region evaluation from a medical professional based on the breast region prediction exceeding a threshold level (e.g., risk exceeding 60%, risk exceeding 5 / 10, risk exceeding yellow, risk exceeding level C, etc.) and / or may provide an indicator that a breast region evaluation is not required based on the breast region prediction being lower than the threshold level. The feedback indicator may be provided to, for example, the user, a medical professional, and / or another authorized user (i.e., different from the user himself or herself).

[0059] The feedback indicator may include, for example, in various examples, visual, auditory, and / or tactile stimuli provided by one or more garment inserts 102A-102E and / or the computing device 106. For example, the visual stimulus may be a message, an application notification (e.g., provided by the breast region prediction application 106 of the computing device 106, another application stored in the memory 114 of the computing device 106, and / or another application of another computing device), a text message, or an email. The auditory stimulus may include an audible alert from a speaker of the user interface 110, etc. Additionally, the tactile stimulus may include vibrations from a vibrator, e.g., vibrations of one or more garment inserts 102A-102E and / or the computing device 106.

[0060] Further, in some examples, the computer-readable instructions stored in the memory 114 may include instructions for performing any of the steps of the method 400, which includes an algorithm configured to be executed on the processors 112s and / or 112 and is described in more detail below with respect to FIG. 4.

[0061] FIG. 4 is a flowchart of an exemplary method 400 for evaluating a user's breast region and providing a prediction associated with the user's breast region, as may be implemented within the system of FIG. 1, according to some examples provided herein. One or more of the steps of the method 400 may be implemented as a set of instructions stored in a computer-readable memory (e.g., memory 114 and / or 114s) and executable on one or more processors (e.g., processor 112 and / or processor 112s).

[0062] Block 402 may include collecting, by one or more sensors (e.g., sensor 105A) of a garment insert (e.g., 102A) configured to be removably coupled to a garment (e.g., garment 104A) designed to at least partially contact the user's breast area. This may be, for example, in or near the breast area of the garment insert, as shown for garment insert 102A. The first set of breast data is associated with the user's breast area at a first time.

[0063] Block 404 may include collecting, by one or more sensors (e.g., sensor 105A) configured to collect data associated with the user's breast area, a second set of breast data associated with the user's breast area at a second time.

[0064] Block 406 may include generating a breast area prediction, by one or more processors (e.g., processor 112 and / or processor 112s), based on a comparison of the first set of breast data and the second set of breast data. In such an aspect, the breast area prediction defines an estimate of the breast area risk for the user.

[0065] Block 408 may include providing, by one or more processors (e.g., processor 112 and / or processor 112s), to a user interface (e.g., user interface 110), a feedback indicator indicating whether the user should receive a breast area evaluation from a medical professional based on the breast area prediction.

[0066] Aspects of the present disclosure 1. A wearable device configured to evaluate a user's breast area and provide a prediction associated with the user's breast area, the wearable device comprising a garment insert configured to be removably coupled to a garment, the garment being designed to at least partially contact the user's breast area; one or more sensors configured to collect data associated with the user's breast area; one or more processors communicatively coupled to the one or more sensors; and a computer memory containing computing instructions that, when executed by the one or more processors, cause the one or more processors to collect, at a first time, a first set of breast data sensed by the one or more sensors, collect, at a second time different from the first time, a second set of breast data sensed by the one or more sensors, generate a breast area prediction based on a comparison of the first set of breast data and the second set of breast data, the breast area prediction defining an estimation of a breast area risk for the user, and provide to a user interface a feedback indicator indicating whether the user should receive a breast area evaluation from a medical professional.

[0067] 2. The wearable device of aspect 1, wherein the breast area prediction includes a confidence level output of an estimation of the breast area risk, the confidence level output being based on an amount and signal quality of one or more of the data of the first set of breast data or the second set of breast data.

[0068] 3. The wearable device of aspect 1 or 2, wherein the garment is a bra, the bra comprising a flexible portion configured to conform to the user's breasts, the flexible portion housing at least one of the one or more sensors and at least one of the one or more processors.

[0069] 4. The wearable device according to any one of aspects 1 to 3, wherein one or more sensors are positioned in at least one of contacting the user's breast, under the dermis of the user's breast, or adjacent to the user's breast.

[0070] 5. The wearable device according to any one of aspects 1 to 4, wherein when the clothing insert is positioned relative to the user's breast, it is configured to apply one or more pressures to each of one or more sensors, and the one or more applied pressures are based on a detected movement of the user's breast within or relative to the clothing.

[0071] 6. The wearable device according to aspect 5, wherein a change in the position of the moved sensor of one or more sensors causes different data to be collected by the moved sensor.

[0072] 7. The wearable device according to any one of aspects 1 to 6, wherein the breast data includes at least one of temperature data, infrared data, ultrasonic data, visible light-based data, electromagnetic data, pressure data, inertial measurement unit (IMU) data, electromyogram (EMG) data, electrocardiogram (ECG) data, electrical impedance data, sweat-based data, blood oxygen data, breast density data, fat content data, vibration data, or voice data.

[0073] 8. The wearable device according to any one of aspects 1 to 7, wherein the breast data includes user data including a sound generated by the user, a first set of breast data includes a first sound captured at a first time, a second set of breast data includes a second sound captured at a second time, and the first sound is different from the second sound.

[0074] 9. The wearable device according to aspect 8, wherein the first sound and the second sound are captured during respective first and second instances in which the user pronounces the same phoneme.

[0075] 10. The wearable device according to aspect 8, wherein the collection of the first set of breast data and the second set of breast data is initiated by one or more processors when the user utters a trigger word.

[0076] 11. The wearable device according to any one of aspects 1 to 10, comprising a graphical user interface (GUI) configured such that the user interface displays at least one of breast region prediction, feedback metrics, or confidence level output.

[0077] 12. The user interface according to any one of aspects 1 to 11, comprising at least one of a button, a switch, or one or more LED indicators.

[0078] 13. The wearable device according to any one of aspects 1 to 12, wherein at least one of the one or more processors comprises a remote processor communicatively coupled to the garment insert, and the first set of breast data and the second set of breast data are transmitted to the remote processor over a computer network.

[0079] 14. The wearable device according to any one of aspects 1 to 13, wherein the breast region prediction is output by a machine learning model pre-trained on training breast data, the training breast data being collected from a plurality of users and including sensor data defining breast tissue, breast implant material, or breast biological markers of the plurality of users.

[0080] 15. The wearable device according to any one of aspects 1 to 14, wherein one or more sensors are configured to initiate collection of data associated with the user's breast region based on a determination that the garment is at least partially in contact with the user's breast region.

[0081] 16. A computer-implemented method in a wearable device for assessing a user's breast area and providing a prediction associated with the user's breast area, the method comprising: collecting, by one or more sensors of a garment insert configured to be removably coupled to a garment designed to at least partially contact the user's breast area, a first set of breast data associated with the user's breast area at a first time; collecting, by one or more sensors configured to collect data associated with the user's breast area, a second set of breast data associated with the user's breast area at a second time; generating, by one or more processors, a breast area prediction based on a comparison of the first set of breast data and the second set of breast data, the breast area prediction defining an estimation of a breast area risk for the user; and providing, by one or more processors, to a user interface, a feedback indicator indicating whether the user should receive a breast area assessment from a medical professional based on the breast area prediction.

[0082] 17. A tangible non-transitory computer-readable medium storing instructions for evaluating a user's breast area and providing a prediction associated with the user's breast area, the instructions, when executed by one or more processors, causing the one or more processors to collect a first set of breast data associated with the user's breast area sensed by one or more sensors of a clothing insert at a first time, wherein the clothing insert is configured to be removably coupled to a garment designed to at least partially contact the user's breast area; collect a second set of breast data associated with the user's breast area sensed by the one or more sensors at a second time; generate a breast area prediction based on a comparison of the first set of breast data and the second set of breast data, wherein the breast area prediction defines an estimate of the breast area risk for the user; and provide to a user interface a feedback indicator indicating whether the user should receive a breast area evaluation from a medical professional.

[0083] Additional Considerations The methods or routines described herein may be at least partially processor-implemented. For example, at least a portion of the operations of a method may be performed by one or more processors or processor-implemented hardware modules. The execution of certain operations may exist within only a single machine or may be distributed among one or more processors deployed across several machines. In some embodiments, one or more processors may be located in a single location, while in other embodiments, the processors may be distributed across a number of locations.

[0084] The execution of certain operations can be distributed not only among processors that exist within a single machine but also among one or more processors that are spread across several machines. In some exemplary embodiments, one or more processors or processor-implemented modules can be located at a single geographical location (e.g., within a home environment, within a workplace environment, or within a server farm). In other embodiments, one or more processors or processor-implemented modules can be distributed across a number of geographical locations.

[0085] This detailed description is to be construed as illustrative only and is not intended to describe all possible embodiments. It is impractical, if not impossible, to describe all possible embodiments. Those skilled in the art can implement many alternative embodiments using either current technology or technology developed after the filing date of this application.

[0086] Those skilled in the art will recognize that various modifications, changes, and combinations can be made to the above-described embodiments without departing from the scope of the invention, and such modifications, changes, and combinations should be considered to be within the scope of the inventive concept.

[0087] Also, the claims at the end of this patent application are not intended to be construed under 35 U.S.C. § 112(f) unless traditional means-plus-function terms, such as "means for" or "steps for" that are expressly recited in the claims are explicitly recited. The systems and methods described herein are directed to improving computer functionality and the functionality of conventional computers.

Claims

**Claim 1** A wearable device configured to evaluate a user's breast region and provide a prediction associated with the user's breast region, a garment insert configured to be removably coupled to a garment, the garment being designed to at least partially contact the user's breast region, the garment insert; one or more sensors configured to collect data associated with the user's breast region; one or more processors communicatively coupled to the one or more sensors; a computer memory containing computing instructions that, when executed by the one or more processors, cause the one or more processors to collect a first set of breast data sensed by the one or more sensors at a first time; collect a second set of breast data sensed by the one or more sensors at a second time, the second time being different from the first time; generate a breast region prediction based on a comparison of the first set of breast data and the second set of breast data, the breast region prediction defining an estimate of a breast region risk for the user; provide to a user interface a feedback indicator indicating whether the user should receive a breast region evaluation from a medical professional, based on the breast region prediction. A wearable device comprising a computer memory. **Claim 2** The wearable device according to claim 1, wherein the breast region prediction includes a confidence level output of the estimate of the breast region risk, the confidence level output being based on an amount and signal quality of one or more of the data of the first set of breast data or the second set of breast data. **Claim 3** The wearable device according to claim 1, wherein the garment is a bra, the bra comprising a flexible portion configured to conform to the user's breast, the flexible portion housing at least one of the one or more sensors and at least one of the one or more processors. **Claim 4** The wearable device according to claim 1, wherein the one or more sensors are positioned in at least one of in contact with the breast of the user, under the dermis of the breast of the user, or proximate to the breast of the user.

5. The wearable device according to claim 1, wherein when the clothing insert is positioned relative to the breast of the user, it is configured to apply one or more pressures to each of the one or more sensors, and the one or more applied pressures are based on a detected movement of the breast of the user within or relative to the clothing.

6. The wearable device according to claim 5, wherein a change in the position of the moved sensor of the one or more sensors causes different data to be collected by the moved sensor.

7. The wearable device according to claim 1, wherein the breast data includes at least one of temperature data, infrared data, ultrasonic data, visible light-based data, electromagnetic data, pressure data, inertial measurement unit (IMU) data, electromyogram (EMG) data, electrocardiogram (ECG) data, electrical impedance data, sweat-based data, blood oxygen data, breast density data, fat content data, vibration data, magnetomyogram (MaMG) data, mechanomyogram (MeMG) data, or voice data.

8. The wearable device according to claim 1, wherein the breast data includes data of the user including a sound generated by the user, the first set of breast data includes a first sound captured at the first time, the second set of breast data includes a second sound captured at the second time, and the first sound is different from the second sound.

9. The wearable device according to claim 8, wherein the first sound and the second sound are captured during respective first and second instances in which the user pronounces the same phoneme.

10. The wearable device according to claim 8, wherein collection of the first set of breast data and the second set of breast data is initiated by the one or more processors when the user vocalizes a trigger word.

11. The wearable device according to claim 1, comprising a graphic user interface (GUI) configured such that the user interface displays at least one of the breast region prediction, the feedback metric, or the confidence level output.

12. The user interface according to claim 1, comprising at least one of a button, a switch, or one or more LED indicators.

13. The wearable device according to claim 1, wherein at least one of the one or more processors comprises a remote processor communicatively coupled to the garment insert, and the first set of breast data and the second set of breast data are transmitted to the remote processor across a computer network.

14. The wearable device according to claim 1, wherein the breast region prediction is output by a machine learning model pre-trained on training breast data, and the training breast data is collected from a plurality of users and includes sensor data defining breast tissue, breast implant material, or breast biological markers of the plurality of users.

15. The wearable device according to claim 1, wherein the one or more sensors are configured to initiate collection of data associated with the breast region of the user based on a determination that the garment is at least partially in contact with the breast region of the user.

16. A computer-implemented method in a wearable device for evaluating a user's breast region and providing a prediction associated with the user's breast region, comprising: collecting, by one or more sensors of a garment insert configured to be removably coupled to a garment designed to at least partially contact the breast region of the user, a first set of breast data associated with the breast region of the user at a first time; collecting, by the one or more sensors configured to collect data associated with the breast region of the user, a second set of breast data associated with the breast region of the user at a second time; Generating, by one or more processors, a breast region prediction based on a comparison of the first set of breast data and the second set of breast data, wherein the breast region prediction defines an estimation of a breast region risk for the user Providing, by the one or more processors, to a user interface, a feedback indicator indicating whether the user should receive a breast region evaluation from a medical professional based on the breast region prediction, the method comprising A tangible non-transitory computer-readable medium storing instructions for evaluating a user's breast region and providing a prediction associated with the user's breast region, the instructions, when executed by one or more processors, causing the one or more processors to Collect, at a first time, a first set of breast data associated with the user's breast region sensed by one or more sensors of a clothing insert, the clothing insert being configured to be removably coupled to clothing designed to at least partially contact the user's breast region Collect, at a second time, a second set of breast data associated with the user's breast region sensed by the one or more sensors Generate, based on a comparison of the first set of breast data and the second set of breast data, a breast region prediction, wherein the breast region prediction defines an estimation of a breast region risk for the user Provide, to a user interface, a feedback indicator indicating whether the user should receive a breast region evaluation from a medical professional based on the breast region prediction ​

Images