Wearable devices for monitoring uterine activity

Abstract

Systems, devices, and methods are described for monitoring uterine activity, the system comprising: a sensor module coupled to a belly region of a female, the sensor module including at least one inertial measurement unit; a processor communicatively coupled to the sensor module, the processor being configured to execute instructions comprising: acquiring inertial motion data from the sensor module; processing the inertial motion data to differentiate uterine motion data from other physiological motion data; generating, based on the uterine motion data, a uterine activity signal by transforming the uterine motion data from a first signal domain to a second signal domain; and generating, based on the generated uterine activity signal, an output representing at least one uterine contraction within the generated uterine activity signal or activity indicating a lack of uterine contraction.

Description

WEARABLE DEVICES FOR MONITORING UTERINE ACTIVITYCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the priority benefit of U.S. Provisional Application No. 63 / 618, 414, filed on January 8, 2024, the disclosure of which is herein incorporated by reference in its entirety.INCORPORATION BY REFERENCE

[0002] All publications and patent applications mentioned in this specification are herein incorporated by reference in their entirety, as if each individual publication or patent application was specifically and individually indicated to be incorporated by reference in its entirety.TECHNICAL FIELD

[0003] This disclosure relates generally to the field of women’s health, and more specifically to systems and methods for monitoring uterine activity.BACKGROUND

[0004] Pregnancy is an incredibly stressful time for an expectant mother. As her body changes in many ways during the pregnancy process, she must begin to discern between bodily changes that insinuate that her body is progressing in her pregnancy and preparing for labor. Understanding what a contraction feels like and differentiating uterine activity from other physiological phenomena such as the baby moving, the baby kicking, digestive track activity can be difficult for an expectant mother, especially a first-time mother. Tracking the evolution of uterine activity over time during the pregnancy is an additional burden for the expectant mother at a time where her attention should go to caring for herself and her baby.

[0005] Early conventional uterine activity and contraction monitoring devices introduced for remote monitoring at the expectant mother’s home, for example Home Uterine Activity Monitors or more recently wireless Cardiotocographs (CTG), are cumbersome and require the patient to remember to wear the device daily for short periods of time, collect the data, and transmit the data to a center. Such systems are based on tocodynamometry (TOCO), the current standard-of-care for monitoring uterine activity, which measures the pressure at the abdominal surface induced by a contraction. These conventional systems rely on the patient to accuratelyposition the probes. These probes tend to fall off or move, and the patient has to reposition the probes to avoid losing the signal. This makes it difficult for patients and clinicians to obtain a reliable trace. Poor or lack of data prevents the providers from making their clinical assessment, failing the purpose of remote monitoring. Poor usability also negatively impacts adherence and patient acceptance, as pregnant women become concerned about not doing the test correctly and causing harm to the fetus. In addition, such conventional devices do not provide any feedback to the pregnant woman and could therefore create additional anxiety with regards to the outcome of the monitoring.

[0006] These technology limitations are one of the reasons behind the development of newer technologies for uterine activity monitoring based on electrophysiology. These newer technologies measure the electrical muscle activity (EMG) of the uterus, also known as electrohysterography. Other electrophysiology-based techniques use variations on maternal ECG or maternal heart rate to extract information about uterine activity. These solutions are usually less position dependent when compared to TOCO. However, they have been reported to detect more uterine activity than the standard-of-care TOCO device. When used clinically this means a doctor will see more contractions than they would expect to see and can result in frequent misdiagnosis of symptomatic preterm labor and / or unnecessary and expensive trips to emergency care.

[0007] Other conventional systems for monitoring labor include invasive probes or devices inserted into the uterus (post membrane rupture) or on the cervix to monitor uterine contractions. Such systems are not safe for continuous use and are not suitable for in-home and / or personal use (i.e., without a healthcare provider).SUMMARY

[0008] Described herein are systems, devices, and techniques for monitoring uterine activity. In some aspects, the techniques described herein relate to a system for monitoring uterine activity, the system including: a sensor module coupled to a belly region of a female, the sensor module including at least one inertial measurement unit; a processor communicatively coupled to the sensor module, the processor being configured to execute instructions including: acquiring inertial motion data from the sensor module; processing the inertial motion data to differentiate uterine motion data from other physiological motion data; generating, based on the uterine motion data, a uterine activity signal by transforming the uterine motion data from a first signal domain to a second signal domain; and generating, based on the generated uterineactivity signal, an output representing at least one uterine contraction within the generated uterine activity signal or activity indicating a lack of uterine contraction.

[0009] In some aspects, the techniques described herein relate to a system, wherein transforming the uterine motion data from the first signal domain to the second signal domain includes: determining, in the uterine motion data, a plurality of angles between axes defined by the at least one inertial measurement unit; correcting the uterine motion data; refining the corrected uterine motion data; converting the corrected uterine motion data to identify at least two displacement measurements according to the axes; and combining the at least two displacement measurements.

[0010] In some aspects, the techniques described herein relate to a system, wherein differentiating uterine motion data from other physiological motion data includes: decomposing the inertial motion data into a plurality of signals based on a determined source associated with generation of each portion of the inertial motion data.

[0011] In some aspects, the techniques described herein relate to a system, wherein the instructions further include: performing a data trust analysis during the monitoring; and using the data trust analysis to attenuate or amplify a portion of the generated uterine activity signal.

[0012] In some aspects, the techniques described herein relate to a system, wherein the instructions further include: classifying the output as one of: a non-pregnant contraction, an antepartum contraction, an intrapartum contraction, a postpartum contraction, a Braxton-Hicks contraction, or a state of no contraction; performing a data trust analysis during the monitoring; and using the data trust analysis to determine an accuracy likelihood of the classifying of the output; and

[0013] In some aspects, the techniques described herein relate to a system, wherein the instructions further include generating an output indicating the accuracy likelihood.

[0014] In some aspects, the techniques described herein relate to a system, wherein the at least one inertial measurement unit includes two or more inertial measurement units coupled to the belly region and arranged according to a pattern.

[0015] In some aspects, the techniques described herein relate to a system, wherein the pattern is selected based at least in part on a gestational age of a fetus associated with the female and a body mass index of the female, wherein the female is pregnant.

[0016] In some aspects, the techniques described herein relate to a system, where the at least one inertial measurement unit is placed on the belly region in a configuration that is based atleast in part on a gestational age of a fetus associated with the female or a body mass index of the female.

[0017] In some aspects, the techniques described herein relate to a system, wherein the instructions further include: detecting outlier portions within the inertial motion data; classifying each outlier portion according to movement source; and modifying the generated uterine activity signal based on the classifying.

[0018] In some aspects, the techniques described herein relate to a system, wherein the classifying applies a label for each detected outlier portion, the labels indicating a source for each outlier portion selected from: a pregnant female movement, a postpartum female movement, a non-pregnant female movement, a belly deformation movement, a muscle movement, a placental movement, and a fetal movement.

[0019] In some aspects, the techniques described herein relate to a system, wherein the instructions further include converting the generated uterine activity signal into a signal that emulates a tocography signal representing the uterine activity or an electrohysterography signal representing the uterine activity.

[0020] In some aspects, the techniques described herein relate to a system, wherein the sensor module is held within or forms a portion of: a patch, a belt, a strap, a band, a t-shirt, elastic of a pair of pants, or other clothing or other wearable accessory.

[0021] In some aspects, the techniques described herein relate to a computer-implemented method for monitoring uterine activity, the method including: providing at least one motion sensor module coupled to a belly region of a female, the sensor module including at least one inertial measurement unit; providing a processor communicatively coupled to the at least one sensor module, the processor being configured to execute instructions including: acquiring inertial motion data from the sensor module; processing the inertial motion data to differentiate uterine motion data from other physiological motion data; generating, based on the uterine motion data, a uterine activity signal by transforming the uterine motion data from a first signal domain to a second signal domain; and generating, based on the generated uterine activity signal, an output representing at least one uterine contraction within the generated uterine activity signal or activity indicating a lack of uterine contraction.

[0022] In some aspects, the techniques described herein relate to a computer-implemented method, wherein transforming the uterine motion data from the first signal domain to the second signal domain includes: determining, in the uterine motion data, a plurality of angles between axes defined by the at least one inertial measurement unit; correcting the uterinemotion data; refining the corrected uterine motion data; converting the corrected uterine motion data to identify at least two displacement measurements according to the axes; and combining the at least two displacement measurements.

[0023] In some aspects, the techniques described herein relate to a computer-implemented method, wherein differentiating uterine motion data from other physiological motion data includes: decomposing the inertial motion data into a plurality of signals based on a determined source associated with generation of each portion of the inertial motion data.

[0024] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the instructions further include: performing a data trust analysis during the monitoring; and using the data trust analysis to attenuate or amplify a portion of the generated uterine activity signal.

[0025] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the instructions further include: classifying the output as one of: a nonpregnant contraction, an antepartum contraction, an intrapartum contraction, a postpartum contraction, a Braxton-Hicks contraction, or a state of no contraction; performing a data trust analysis during the monitoring; and using the data trust analysis to determine an accuracy likelihood of the classifying of the output; and

[0026] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the instructions further include generating an output indicating the accuracy likelihood.

[0027] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the at least one inertial measurement unit includes one or more inertial measurement units coupled to the belly region and arranged according to a pattern.

[0028] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the pattern is selected based at least in part on a gestational age of a fetus associated with the female and a body mass index of the female, wherein the female is pregnant.

[0029] In some aspects, the techniques described herein relate to a computer-implemented method, where the at least one inertial measurement unit is placed on the belly region in a configuration that is based at least in part on a gestational age of a fetus associated with the female or a body mass index of the female.

[0030] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the instructions further include: detecting outlier portions within the inertialmotion data; classifying each outlier portion according to movement source; and modifying the generated uterine activity signal based on the classifying.

[0031] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the classifying applies a label for each detected outlier portion, the labels indicating a source for each outlier portion selected from: a pregnant female movement, a postpartum female movement, a non-pregnant female movement, a belly deformation movement, a muscle movement, a placental movement, and a fetal movement.

[0032] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the instructions further include: converting the generated uterine activity signal into a signal that emulates a tocography signal representing the uterine activity or an electrohysterography signal representing the uterine activity.

[0033] In some aspects, the techniques described herein relate to a computer-implemented method, wherein the sensor module is held within or forms a portion of: a patch, a belt, a strap, a band, a t-shirt, elastic of a pair of pants, or other clothing or other wearable accessory.

[0034] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium for monitoring uterine activity including instructions that, when executed by at least one processor, cause the at least one processor to perform operations including: receiving inertial motion data from a sensor module, wherein the sensor module includes at least one inertial measurement unit; processing the inertial motion data to differentiate uterine motion data from other physiological motion data; generating, based on the uterine motion data, a uterine activity signal by transforming the uterine motion data from a first signal domain to a second signal domain; and generating, based on the generated uterine activity signal, an output representing at least one uterine contraction within the generated uterine activity signal or activity indicating a lack of uterine contraction.

[0035] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein transforming the uterine motion data from the first signal domain to the second signal domain includes: determining, in the uterine motion data, a plurality of angles between axes defined by the at least one inertial measurement unit; correcting the uterine motion data; refining the corrected uterine motion data; converting the corrected uterine motion data to identify at least two displacement measurements according to the axes; and combining the at least two displacement measurements.

[0036] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein differentiating uterine motion data from other physiological motiondata includes: decomposing the inertial motion data into a plurality of signals based on a determined source associated with generation of each portion of the inertial motion data.

[0037] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the operations further include: performing a data trust analysis during the monitoring; and using the data trust analysis to attenuate or amplify a portion of the generated uterine activity signal.

[0038] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the instructions further include: classifying the output as one of: a non-pregnant contraction, an antepartum contraction, an intrapartum contraction, a postpartum contraction, a Braxton-Hicks contraction, or a state of no contraction; performing a data trust analysis during the monitoring; and using the data trust analysis to determine an accuracy likelihood of the classifying of the output; and

[0039] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the instructions further include generating an output indicating the accuracy likelihood.

[0040] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the at least one inertial measurement unit includes one or more inertial measurement units coupled to a belly region of a female and arranged according to a pattern.

[0041] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the pattern is selected based at least in part on a gestational age of a fetus associated with the female and a body mass index of the female, wherein the female is pregnant.

[0042] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the operations further include: detecting outlier portions within the inertial motion data; classifying each outlier portion according to movement source; and modifying the generated uterine activity signal based on the classifying.

[0043] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the classifying applies a label for each detected outlier portion, the labels indicating a source for each outlier portion selected from: a pregnant female movement, a postpartum female movement, a non-pregnant female movement, a belly deformation movement, a muscle movement, a placental movement, and a fetal movement.

[0044] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the operations further include converting the generated uterine activity signal into a signal that emulates a tocography signal representing the uterine activity or an electrohysterography signal representing the uterine activity.

[0045] In some aspects, the techniques described herein relate to a non-transitory computer- readable medium, wherein the sensor module is held within or forms a portion of: a patch, a belt, a strap, a band, a t-shirt, elastic of a pair of pants, or other clothing or other wearable accessory.BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The foregoing is a summary, and thus, necessarily limited in detail. The above- mentioned aspects, as well as other aspects, features, and advantages of the present technology are described below in connection with various embodiments, with reference made to the accompanying drawings.

[0047] FIG. 1 illustrates a schematic diagram of an example system for performing uterine activity monitoring.

[0048] FIG. 2A illustrates an example embodiment of a positioning of a sensor module on an abdomen of a user.

[0049] FIG. 2B illustrates an example fundal height over the course of a pregnancy.

[0050] FIG. 2C illustrates various regions of an abdomen.

[0051] FIG. 2D illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0052] FIG. 2E illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0053] FIG. 2F illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0054] FIG. 2G illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0055] FIG. 2H illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0056] FIG. 21 illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0057] FIG. 2J illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0058] FIG. 2K illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0059] FIG. 2L illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0060] FIG. 2M illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0061] FIG. 2N illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0062] FIG. 20 illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0063] FIG. 2P illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0064] FIG. 2Q illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0065] FIG. 2R illustrates an example embodiment of various sensor module positions over time on an abdomen of a user.

[0066] FIG. 3 illustrates a block diagram of an example system for performing uterine activity monitoring.

[0067] FIG. 4 illustrates a flow diagram of an example system for performing uterine activity monitoring.

[0068] FIG. 5A illustrates a flow diagram of an example process for performing uterine activity monitoring in combination with a trust analysis.

[0069] FIG. 5B illustrates a flow diagram of an example process for performing a transformation of captured inertial measurement unit (IMU) signals.

[0070] FIGS. 6A-6B illustrate pictorials of examples of using the systems described herein to monitor uterine activity.

[0071] FIG. 7 is an example output generated by the monitoring system.

[0072] FIG. 8 illustrates a flow diagram of an example process for monitoring uterine activity.

[0073] FIG. 9 illustrates a flow diagram of an example process for performing uterine activity monitoring in combination with a trust analysis.

[0074] FIG. 10 illustrates a flow diagram of an example process for generating a uterine activity trace based on at least one accelerometer or IMU signal.

[0075] The illustrated embodiments are merely examples and are not intended to limit the disclosure. The schematics are drawn to illustrate features and concepts and are not necessarily drawn to scale.DETAILED DESCRIPTION

[0076] The foregoing is a summary, and thus, necessarily limited in detail. The above- mentioned aspects, as well as other aspects, features, and advantages of the present technology will now be described in connection with various embodiments. The inclusion of the following embodiments is not intended to limit the disclosure to these embodiments, but rather to enable any person skilled in the art to make and use the claimed subject matter. Other embodiments may be utilized, and modifications may be made without departing from the spirit or scope of the subject matter presented herein. Aspects of the disclosure, as described and illustrated herein, can be arranged, combined, modified, and designed in a variety of different formulations, all of which are explicitly contemplated and form part of this disclosure.

[0077] Disclosed herein are systems and methods for monitoring uterine activity. In general, the system may include one or more wearable devices with sensors and processors for monitoring uterine activity. For example, described herein are devices, systems, and methods for monitoring uterine activity during pregnancy and labor. Such systems may be used to detect and measure uterine activity before pregnancy (e.g. to assist with in-vitro fertilization or other assisted reproduction techniques), during pregnancy, during an antepartum time period, during labor, and / or post-partum. The systems and methods described herein address the technical problem of providing reliable and accurate uterine activity monitoring in a noninvasive manner. This technical problem is relevant since uterine activity is a signal that is used by health care providers to assess the health of the pregnant female and the fetus (or of a nonpregnant female), in the context of assisted reproduction, antepartum fetal monitoring, fetal non-stress tests (NST), during labor monitoring, and / or post-partum.

[0078] Monitoring uterine activity by the systems and devices described herein is not limited to the pregnant state. In general, uterine contractions represent muscle contractions of the uterine smooth muscle that can occur at various intensities in both the non-pregnant and pregnant uterine state. The non-pregnant uterus undergoes minor and / or spontaneous contractions in addition to stronger, coordinated contractions during the menstrual cycle andorgasm. The pregnant uterus only contracts strongly during orgasms, labor, and in the postpartum stage to return to its natural size. Thus monitoring uterine activity may be of clinical relevance during all phases of a female’s life. Conventional measurement of uterine activity may include the use of technologies such as Intra-Uterine Pressure Catheter (IUPC), tocography (TOCO), and Uterine EMG (uEMG), or electrohysterography (EHG). However, in a typical setting each of these technologies are employed as ad-hoc techniques based on physician choice, pregnancy status, or technology availability at a particular clinic. In examples that indicate a pregnant female throughout this disclosure, a non-pregnant female may be substituted when a fetus or pregnancy do not exist for the specific non-pregnant female at a time of monitoring.

[0079] The systems described herein may combine such conventional techniques and new techniques described herein with one or more trust metrics, as a basis to detect and analyze measurements of displacement / deformation in service of assessing uterine activity during any stage of pregnancy including the third stage of labor or soon thereafter, during assisted reproduction, and / or postpartum. Such analysis may be used to detect pregnant female movement, a postpartum female movement, a belly deformation movement, a muscle movement, a placental movement, and / or a fetal movement. The systems described herein may analyze signals in combination for a non-pregnant female (or a pregnant female) to determine a state or indication of an antepartum contraction, an intrapartum contraction, a non-pregnant female movement, a postpartum contraction, a Braxton-Hicks contraction, or a state of no contraction. In some embodiments, the analysis performed by the systems described herein may include assessment of any combination of data based on one or more of: IUPC signals, TOCO signals, uEMG signals, EHG signals, IMU signals, and direct accelerometer signals.

[0080] IUPC generally uses invasive sensors mounted on the tip of a catheter to measure internal pressure changes inside the uterus that results from uterine contraction. IUPC is available for use once the membrane is ruptured and therefore is typically suitable for monitoring uterine activity during labor, not during pregnancy. In addition, IUPC is an invasive method and has risks associated with infection. TOCO uses a non-invasive pressure sensor to measure pressure changes induced by contractions. The measurements may be captured at a certain point of the lower abdomen. When compared to IUPC, TOCO has the advantage that it is noninvasive and can thus be used to monitor uterine activity during pregnancy and during labor. It is however known to be less accurate with less sensitivity than IUPC. Uterine EMG (uEMG) or electrohysterography (EHG) has recently been introduced as an alternative toTOCO with the goal to provide a more accurate and noninvasive alternative. EHG-based uterine activity monitoring has been shown to be more accurate than TOCO when compared to IUPC. It has also been reported to lead to detection of many more contractions when compared to TOCO. This represents a challenge for the clinical adoption of EHG-based uterine activity during pregnancy where the medical community is accustomed to using TOCO systems, wherein, by comparison, EHG-based systems can lead to an over detection of contractions (i.e., false positives).

[0081] While these conventional systems and methods may be useful in a clinical setting to give an approximate labor or contraction status when performed by a healthcare provider, such systems may not accurately capture the real physiological phenomenon behind contractions that is represented as the electrical activity of the uterine muscle. Consequently, these conventional monitoring technologies may fail to distinguish Braxton-Hicks contractions from labor inducing contractions.

[0082] The systems and methods described herein provide an improved approach to uterine activity monitoring over conventional systems. For example, the systems and methods described herein combine the use of one or more inertial measurement unit (IMU) sensors to assess contraction activity, which utilizes a different sensing principle than conventional pressure sensing (e.g., TOCO) or surface EMG sensing (e.g., EHG). The systems and methods described herein may solve a technical problem of capturing the electrical activity and response of the uterine muscle during contractions (preterm or term). For example, the systems described herein may provide a technical solution including a device capable of performing accurate and reliable uterine activity monitoring by capturing and analyzing uterine deformation and movement and the underlying electrical activity of the uterine muscle during assisted reproduction, pregnancy and labor, and / or postpartum and may do so in a clinical setting (by medical staff) and in a home-based setting (by non-medical staff, the pregnant female, etc.).

[0083] In some embodiments, the systems and methods described herein utilize one or more IMUs to measure uterine activity from inertial motion data. The systems may acquire local and global movement from the lower abdomen of a pregnant woman, sense the movement data, processing the data, transmit the data, and visualize the data in a user interface. In some embodiments, additional sensor outputs are used in combination with the one or more IMUs including, but not limited to, one or more EMG sensors, one or more EHG sensors, one or more strain gauge, and one or more electrodes.

[0084] In some embodiments, the systems and methods described herein may provide a number of advantages over conventional systems and practices in monitoring uterine activity and contractions during assisted reproduction, pregnancy and labor, and / or post-partum. The systems and methods described herein may provide an improved, precise way to monitor uterine activity. For example, the systems described herein may incorporate advanced sensing technology and signal processing algorithms to enhance the accuracy and precision of uterine activity monitoring. This allows for a more reliable assessment of contraction duration and frequency compared to conventional methods.

[0085] In some embodiments, the systems and methods described herein include multiple algorithms for converting IMU signals into a signal representation of the uterine activity. The different algorithms can be used in a staging process in which outputs from each stage are fed into another stage or are independently calculated and then combined in a final stage of processing. Some of the stages are used for cleaning the signals of interest such as filtering, down sampling, or de-noising.

[0086] The systems and methods described herein further provide an advantage of enhanced patient comfort because the sensor modules described herein are compact in size, which minimizes the physical presence on the maternal abdomen, thereby contributing to increased comfort for the laboring mother. Unlike bulkier or invasive conventional devices, the unobtrusive nature of the sensor modules described herein allow for greater freedom of movement during labor.

[0087] The systems and methods described herein further provide an advantage of facilitating remote monitoring. For example, the systems and methods described herein may provide for wireless connectivity that allows for remote monitoring capabilities, enabling healthcare providers to access real-time data from the sensors even when not physically present. This feature can be advantageous in situations where immediate on-site presence is not feasible or for remote monitoring of at-risk pregnancy.

[0088] The systems and methods described herein further provide an advantage of reducing the obstruction to healthcare providers. For example, the systems and methods described herein may provide for a streamlined, compact sensor design that reduces interference with healthcare providers during labor management. This advantage may be helpful in dynamic healthcare environments by allowing providers greater flexibility and ease of access to the patient.

[0089] The systems and methods described herein further provide an advantage of wireless connectivity for mobility. For example, the systems and methods described herein may providefor a wireless connection between the sensors and the monitoring device (and / or display device), which adds a layer of mobility to the system. This enables the laboring mother to move freely, maintaining a natural and comfortable birthing environment, while ensuring continuous and reliable data transmission to the monitoring system.

[0090] The systems and methods described herein further provide for ease of sensor / device application and removal. For example, the systems and methods described herein may provide a compact sensor design that facilitates easy application and removal of the monitoring device thereby streamlining the overall monitoring process. This can assist both medical staff and patients during the hectic and time-sensitive circumstances of labor and delivery.

[0091] The systems and methods described herein further provide an advantage of minimizing disruption to workflow. For example, the systems and methods described herein may provide a wireless connection that eliminates cumbersome cables or wires, thereby reducing the risk of tangling and disruption to the workflow of medical staff. This contributes to an efficient and organized labor management process.

[0092] The systems and methods described herein further provide an advantage of an improved aesthetic. For example, the wireless nature of the sensor contributes to an aesthetically pleasing monitoring setup. This can positively impact the overall experience for the laboring mother, thereby creating a less intimidating and more patient-friendly environment.

[0093] The systems and devices described herein may function as compact wireless sensors that prioritize patient comfort while minimizing disruption to healthcare providers. Such devices introduce a level of mobility and flexibility to the field and process of uterine contraction monitoring. The devices include programmatic code to enable a patient-centered, efficient approach to risk assessment in pregnancy and labor management. The systems and devices described herein is described for use with monitoring pregnancy and labor, but can additionally or alternatively be used for any suitable applications, clinical or otherwise. Such applications may include monitoring uterine activity during assisted reproduction and postpartum. The systems and devices can be configured and / or adapted to function for any suitable surface deformation monitoring task.

[0094] In operation, the systems and devices described herein may be used at home by a patient and in a clinical or hospital setting. The data generated by the systems and devices described herein may be converted into graphical content that may be displayed in a user interface and / or provided via messaging to a pregnant woman, by her care team (OB-GYN.MFM, nurse, midwife, etc.). In some embodiments, the systems and devices described herein may function as an alerting system that automatically detects when contractions are becoming more regular and may be indicative of upcoming labor. Such a system may send the data indicating such a labor state to the pregnant woman and / or a care team for the pregnant woman.

[0095] FIG. 1 illustrates a schematic diagram of an example monitoring system 100 for performing uterine activity monitoring. The system 100 includes a sensor module 102 that may perform the uterine activity monitoring. In some embodiments, the sensor module 102 is communicatively coupled to an optional computing device 104, which may optionally perform additional uterine activity monitoring and / or processing of data captured by sensor module 102. Computing device 104 may depict visual information about the uterine activity monitoring on a display 106 and / or audio information via a speaker (not shown) of device 104. In some embodiments, the computing device 104 may further provide tactile information using mechanisms (e.g., sensors, speakers, motors, piezo devices, or the like) to produce haptic feedback from device 104 responsive to data obtained during uterine activity monitoring. In some embodiments, the sensor module 102 is communicatively coupled to an optional cloud computing server 108, which may optionally perform additional uterine activity monitoring and / or processing of data captured by sensor module 102.

[0096] In some embodiments, the system 100 may include sensor module 102 without additional computing device 104 and server 108. For example, the sensor module 102 may include processors, memory, and programming to execute uterine activity monitoring without assistance from external devices. In such embodiments, the system 100 may include a display or speaker to provide feedback to a user or may instead provide circuitry for wired (not shown) or wireless connection (e.g., via wireless antenna 110) to other computing devices capable of receiving feedback from sensor module 102.

[0097] The sensor module 102 may represent a wearable sensor module that may carry out the methods described herein when worn by a user. The wearable sensor module 102 may connect to or form a portion of: a patch, a belt, a strap, a band, a t-shirt, the elastic of a pair of pants, or other clothing or other wearable accessory. In some embodiments, the sensor module 102 may represent a wearable sensor patch (e.g., wearable device 302 of FIG. 3 and sensor placement indicated in FIGS. 2A-2R) integrated in a textile or clothing accessory. Examples of clothing accessories can include, but are not limited to: a shirt, T-shirt, a belly-band, a pregnancy support belt, or a belt.

[0098] As shown in FIG. 1, the sensor module 102 includes one or more sensors 112, one or more processors 114, and memory 116, each positioned on or within the sensor module 102. An electronic circuit 118 and wireless antenna 110 may also be provided on or in the sensor module 102. In such embodiments, one or more sensors 112 may sense signals and electronic circuit 118 may amplify, filter, digitize, and / or otherwise process the signals. The one or more processors 114 may analyze the sensed signals and / or analyze the processed signals. Execution of instructions stored in memory 116 may cause the one or more processors 114 to perform one or more of the methods of monitoring uterine activity described elsewhere herein. Analyzed data may be transmitted via the antenna 110 to one or both of the computing device 104 and the server 108 for visual or audio presentation to a user, for additional analysis, and / or for storage.

[0099] In some embodiments, the sensors 112 are positioned on or in the sensor module 102 with the electronic circuit 118 and wireless antenna 110, while the computing device 104 houses the processor 114 that performs a uterine activity monitoring and the memory 116 that stores instructions for performing such monitoring. In such embodiments, signals are sensed by the sensors 112 and amplified, filtered, digitized and / or otherwise processed by the electronic circuit 118, and the processed signals are transmitted via the antenna 110 to the computing device 104 and / or server 108. One or more processors (not shown) on the computing device 104 (and / or server 108) may analyze the processed signals and determine uterine activity associated with deformation of a portion of the belly region, contraction count or activity, and a likelihood of labor state changes, as described elsewhere herein. The analyzed data may be saved, shared with contacts, or presented to a user via the computing device 104 or other connected device. In some such embodiments, some of or all the analyzed data may be transmitted from the computing device 104 to the server 108 for storage.

[0100] The one or more sensors 112 may include one or more IMU sensors 120, one or more optional EHG sensors 122, one or more optional EMG sensors 124, one or more optional electrodes 126, and / or one or more optional strain gauge sensors 128, one or more piezoelectric sensors, one or more piezo-resistive sensors, one or more capacitive sensors, one or more pressure sensors, and / or one or more stretch sensors.

[0101] In some embodiments, the sensors 112 (e.g., electrodes) may sense one or more biopotential signals. In some embodiments, the sensors 112 may measure one or more of: a maternal heart rate, a maternal heart rate variability, a maternal respiration rate, a maternal respiration intensity, a deformation of a belly region of the pregnant woman, a maternal skinor body temperature, a maternal skin conductance (i.e., galvanic skin response), and an electrohysterography (EHG) or electromyography (EMG) signal.

[0102] In some embodiments, one or more of the sensors 112 may include non-contact sensors. For example, the sensors 112 may further include one or more visual sensors (e.g., image / video sensor), magnetic resonance sensors, mmWave sensors, PIR sensors, or other infrared, light, magnetic, or electromagnetic sensors. Such sensors may function alone or in combination to measure displacement or deformations associated with the belly or other sensed portion of the female.

[0103] In some embodiments, the system 100 includes at least three sensors. In one nonlimiting example, the sensors 112 include a measurement electrode and a reference electrode. In some embodiments, the system includes more than three sensors, for example four, five, six, or seven sensors including electrodes (e.g., optional electrodes 340), IMUs, and / or EHG sensors. In some such embodiments, the sensors 112 include at least one reference electrode and a plurality of measurement electrodes. In one non-limiting embodiment, the sensors 112 may include: an EHG sensor, an electrocardiogram (ECG) sensor, an accelerometer, a gyroscope, and one or more IMUs. In another non-limiting embodiment, the sensors 112 may include: an EHG sensor, an accelerometer, and a gyroscope. In yet another non-limiting embodiment, the sensors 112 may include: an EHG sensor and one or more IMUs. In one nonlimiting embodiment, the sensors 112 may include: a plurality of electrodes and one or more IMUs.

[0104] In some embodiments, the sensors 112 may include one or more IMU and / or one or more non-contact sensor that may be used to improve heart rate detectability and / or measurement of displacement or deformations from a female or a fetus. In some embodiments, a single sensor 112 may be used to monitor heart rate including, but not limited to an mmWave sensor, a video / image sensor, a magnetic resonance sensor, a PIR sensor, or other infrared, light, magnetic, or electromagnetic and / or non-contact sensor. In some embodiments, such sensors may be used as a basis in which to analyze vascular pressure differentials to obtain improved heart rate measurements.

[0105] In some embodiments, the electronic circuit 118 may include an operational amplifier; a low-pass, high-pass, or band-pass filter; an analog-to-digital (AD) converter; and / or other signal processing circuit components configured to amplify, filter, digitize, and / or otherwise process the signals. The electronic circuit 118 may additionally include a power supply or power storage device, such as a battery or capacitor to provide power to the otherelectronic components. For example, the electronic circuit 118 may include a rechargeable (e.g., lithium ion) or disposable (e.g., alkaline) battery.

[0106] In some embodiments, the antenna 110 includes one or both of a receiver and a transmitter. The receiver receives and demodulates data received over a communication network. The transmitter prepares data according to one or more network standards and transmits data over a communication network. In some embodiments, a transceiver antenna 110 acts as both a receiver and a transmitter for bi-directional wireless communication. As an addition or alternative to the antenna 110, in some embodiments, a data bus (not shown) is provided within the sensor module 102 so that data can be sent from, or received by, the sensor module 102 via a wired connection.

[0107] In some embodiments, there is one-way or two-way communication between the sensor module 102 and the computing device 104, the sensor module 102 and the server 108, and / or the computing device 104 and the server 108. The sensor module 102, computing device 104, and / or server 108 may communicate wirelessly using Bluetooth, low energy Bluetooth, near-field communication, infrared, WLAN, Wi-Fi, CDMA, LTE, other cellular protocol, other radiofrequency, or another wireless protocol. Additionally or alternatively, sending or transmitting information between the sensor module 102, the computing device 104, and the server 108 may occur via a wired connection such as IEEE 1394, Thunderbolt, Lightning, DVI, HDMI, Serial, Universal Serial Bus, Parallel, Ethernet, Coaxial, VGA, or PS / 2.

[0108] In some embodiments, the computing device 104 is a computational device wrapped in a chassis that includes a visual display with or without touch responsive capabilities (e.g., Thin Film Transistor liquid crystal display (LCD), in-place switching LCD, resistive touchscreen LCD, capacitive touchscreen LCD, organic light emitting diode (LED), Active- Matrix organic LED (AMOLED), Super AMOLED, Retina display, Haptic / Tactile touchscreen, or Gorilla Glass), an audio output (e.g., speakers), a central processing unit (e.g., processor or microprocessor), internal storage (e.g., flash drive), n number of components (e.g., specialized chips and / or sensors), and n number of radios (e.g. , WLAN, LTE, Wi-Fi, Bluetooth, GPS, etc.). In some embodiments, the computing device 104 is a mobile or portable computing device, such as a mobile phone, smartphone, smart watch, smart glasses, smart contact lenses, or other wearable computing device, tablet, laptop, netbook, notebook, or any other type of mobile computing device. In some embodiments, the computing device 104 is a stationary computing device, such as a desktop computer or workstation.

[0109] In some embodiments, the server 108 is a database server, application server, internet server, cloud server, or other remote server. In some embodiments, the server 108 may store user profile data, historical user data, historical community data, algorithms, machine learning models, software updates, or other data. With appropriately configured user permissions, the server 108 may share this data with the computing device 104 or the sensor module 102, and the server 108 may receive newly acquired user data from the sensor module 102 and / or the computing device 104.

[0110] FIGS. 2A-2R illustrate example sensor module placement for performing uterine activity monitoring. Sensor module placement may be substantially constant (e.g., may be intermittently removed and then repositioned in a similar position; may be adjusted slightly for comfort during the time of sensor module use; may be temporarily repositioned for a background, reference, or calibration; etc.). Alternatively, sensor module placement may be periodically adjusted during the time of sensor module use. For example, sensor module placement may be periodically adjusted based on a gestational age of the fetus, fetal orientation, fetal presentation, anatomical curvature of the abdomen of the mother, body mass index of the mother, or other features of the fetus or mother. For example, sensor module placement may be periodically adjusted based on empirical data that has determined placement over time to maximize a signal-to-noise ratio. Periodic adjustment of sensor module placement may occur on a weekly basis, a trimester basis, a monthly basis, or otherwise.

[0111] FIG. 2A illustrates an example embodiment of a positioning of a sensor module 202a on an abdomen 212 of a user. The sensor module 202a may be positioned below a naval or belly button 204 of the user. For example, the sensor module 202a may be aligned with a frontal axis 206 of the user. More particularly, the frontal axis 206 may intersect with a centroid 210 of the sensor module 202a. For example, the sensor module 202a may be positioned below a transverse axis 208 of the user that bisects a belly button 204 of the user. The sensor module 202a may be positioned, as shown in FIG. 2A, substantially constantly or periodically as described above. In general, placement or positioning of the sensor modules described herein, but particularly in FIGS. 2A-2R, may be based on a distance from the belly button 204, the fundus, a pubis distance, and / or a relationship based on the female being in a particular position (e.g., standing, sitting, angled from the waist / hips, etc.).

[0112] FIG. 2B illustrates an example fundal height over the course of a pregnancy. The fundal height is used to estimate fetal growth and position. The fundal height is the distance from the top of the mother's pubic bone 214 to the top of the uterus (fundus) 216 (shown asmultiple lines depending on gestational age). For example, at 12 weeks, the fundal height 216a is just above the pubic bone 214. At 14-16 weeks, the fundal height 216b is below the belly button 204 but above the pubic bone 214 and above the 12-week fundal height 216a. At 20 weeks, the fundal height 216c is approximately at the belly button 204. At 24 weeks, the fundal height 216d is above the belly button 204 in the umbilical region of the abdomen (shown in FIG. 2C). At 26 weeks and 32 weeks, the fundal heights 216e, 216f, respectively, are above the belly button in the epigastric region of the abdomen (shown in FIG. 2C). At 36-38 weeks, the fundal height 216g may be right up under the sternum 218. At 40 weeks (40+ weeks if the fetus is overdue), the fundal height 216h drops below the 38-week level as presenting part drops down into the pelvis.

[0113] FIG. 2C illustrates various regions of an abdomen. Region 201cl is the dextral hypochondriac region. Region 201c2 is the dextral lumbar region. Region 201c3 is the dextral iliac region. Region 201c4 is the epigastric region. Region 201c5 is the umbilical region. Region 201c6 is the hypogastric region. Region 201c7 is the sinistral hypochondriac region. Region 201c8 is the sinistral lumbar region. Region 201c9 is the sinistral iliac region. These regions are used in describing FIGS. 2D-2R to describe potential sensor module positions on an abdomen of a user.

[0114] FIGS. 2D-2R illustrate various example embodiments of sensor module positions on an abdomen of a user during a pregnancy or that changes over time. In some embodiments, a sensor module may be used in a position during the pregnancy. In some embodiments, two or more or a plurality of sensor modules may be used, each in a position during the pregnancy. In some embodiments, a sensor module may be used in two or more of a plurality of positions during the pregnancy. In some embodiments, two or more or a plurality of sensor modules may be used, each in two or more or a plurality of positions during the pregnancy. In these examples, like or same numbers refer to like or same objects or axes. Further, although numerical and alphabetical designations are used for various sensor modules in a figure, the numerical and alphabetical designations should not be construed as designating an order or sequence.

[0115] FIG. 2D illustrates an example embodiment of various sensor module positions 202dl-d7 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202dl-d7 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus ormother. For example, sensor module position or reposition 202dl may be proximate to or near fundal height 216b (shown in FIG. 2B) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202dl may be aligned with a frontal axis 206 below a naval 204 of the user. The sensor module position or reposition 202d2 may be proximate to or near fundal height 216d (shown in FIG. 2B) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202d2 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202d3 may be proximate to or near fundal height 216e, proximate to or near fundal height 216f or between fundal height 216e and 216f (shown in FIG. 2B) at about 26 weeks of pregnancy or between about 24 weeks and 32 weeks of pregnancy. Sensor module position or reposition 202d3 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202d4 may be proximate to or near fundal height 216g or 216h (shown in FIG. 2B) at about 36 to 38 weeks of pregnancy or between about 32 weeks and 40+ weeks of pregnancy. Sensor module position or reposition 202d4 may be aligned with a frontal axis 206 above a naval 204 of the user. Alternatively, or additionally, sensor module position or reposition 202d5 may be at a horizontal offset from frontal axis 206 on a sinistral side of the user. Sensor module positions or repositions 202d6, 202d7 may be horizontally offset from frontal axis 206 on a dextral side of the user. Sensor module positions or repositions 202d5, 202d6 may be in a sinistral and dextral umbilical region (shown in FIG. 2C), respectively, of the user and at about a fundal height 216e to 216f between about 25 weeks to about 35 weeks of pregnancy. Sensor module position or reposition 202d7 may be in a dextral lumbar region (shown in FIG. 2C) of the user and above a fundal height 216f or between fundal height 216f and 216g or 216h.

[0116] FIG. 2E illustrates an example embodiment of various sensor module positions 202el-e7 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202el-e7 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202el may be proximate to or near fundal height 216b (shown in FIG. 2B) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks ofpregnancy. Sensor module position or reposition 202el may be aligned with a frontal axis 206 below a naval 204 of the user. The sensor module position or reposition 202e2 may be proximate to or near fundal height 216d (shown in FIG. 2B) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202e2 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202e3 may be proximate to or near fundal height 216e, proximate to or near fundal height 216f or between fundal height 216e and 216f (shown in FIG. 2B) at about 26 weeks of pregnancy or between about 24 weeks and 32 weeks of pregnancy. Sensor module position or reposition 202e3 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202e4 may be proximate to or near fundal height 216g or between fundal height 216f and 216g or 216h (shown in FIG. 2B) at about 36 to 38 weeks of pregnancy or between about 32 weeks and 40+ weeks of pregnancy. Sensor module position or reposition 202e4 may be aligned with a frontal axis 206 above a naval 204 of the user. Sensor module positions or repositions 202e5, 202e6, 202e7 may be at a horizontal offset from frontal axis 206 on a dextral side of the user. Sensor module position or reposition 202e5, 202e6 may be in an umbilical region (shown in FIG. 2C) of the user. Sensor module position or reposition 202e7 may be in a dextral lumbar region (shown in FIG. 2C) of the user. Sensor module position or reposition 202e5 may be at a fundal height of about 216e (shown in FIG. 2B) between about 25 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202e6 may be at a fundal height between about 216e to 216f (shown in FIG. 2B) between about 25 weeks and about 35 weeks of pregnancy. Sensor module position or reposition 202e7 may be at a fundal height above 216f, for example between about fundal height 216f and 216g or 216h at about 30 weeks to about 40+ weeks of pregnancy.

[0117] FIG. 2F illustrates an example embodiment of various sensor module positions 202fl- f7 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor modules 202fl-f7 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202f 1 may be proximate to or near fundal height 216b (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202fl may bealigned with a frontal axis 206 below a naval 204 of the user. The sensor module position or reposition 202f2 may be proximate to or near fundal height 216d (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202f2 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202f3 may be proximate to or near fundal height 216e, proximate to or near fundal height 216f or between fundal height 216e and 216f (shown in FIG. 2B) at about 26 weeks of pregnancy or between about 24 weeks and 32 weeks of pregnancy. Sensor module position or reposition 202f3 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202f4 may be above fundal height 216f or proximate to or near fundal height 216g (shown in FIG. 2B) in an epigastric region (shown in FIG. 2C) at about 36 weeks to 38 weeks of pregnancy or between about 32 weeks and 40+ weeks of pregnancy. Sensor module position or reposition 202f4 may be aligned with a frontal axis 206 above a naval 204 of the user. Sensor module positions or repositions 202f5, 202f6, 202f7 are horizontally offset from frontal axis 206 on a dextral side of the user. Sensor module position or reposition 202f5, 202f6 may be in an umbilical region (shown in FIG. 2C) of the user. Sensor module position or reposition 202e7 may be in a dextral lumbar region (shown in FIG. 2C) of the user. Sensor module position or reposition 202f5 may be approximately between fundal height 216d and 216e (shown in FIG. 2B) between about 20 weeks to about 26 weeks of pregnancy. Sensor module position or reposition 202f6 may be approximately at a fundal height of 216e (shown in FIG. 2B) between about 25 weeks to about 32 weeks of pregnancy. Sensor module position or reposition 202f7 may be approximately at a fundal height 216g or between fundal height 216f and 216h (shown in FIG. 2B) between about 30 weeks to about 40+ weeks of pregnancy.

[0118] FIG. 2G illustrates an example embodiment of various sensor module positions 202g l-g7 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202g l-g7 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202gl may be proximate to or near fundal height 216a (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. For example, sensormodule position or reposition 202g2 may be proximate to or near fundal height 216b (shown in FIG. 2B) or between fundal height 216b and 216c in the hypogastric region (shown in FIG. 2C) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202g2 may be aligned with a frontal axis 206 below a naval 204 of the user. The sensor module positions or repositions 202g3, 202g4, 202g5 may be horizontally offset from frontal axis 206. For example, sensor module positions or repositions 202g3, 202g4, 202g5 may be along an arcuate path or curved path relative to the frontal axis 206. Sensor module position or reposition 202g3 may be horizontally aligned with sensor module position or reposition 202g2 or slightly below sensor module position or reposition 202g2 in a hypogastric region between fundal height 216b and 216c (shown in FIG. 2B) between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202g4 may be an umbilical region at approximately fundal height 216d. Sensor module position or reposition 202g5 may be in a dextral lumbar region between about fundal height 216e and 216f at about 25 weeks to about 25 weeks of pregnancy. Sensor module position or reposition 202g6 may be proximate to or near fundal height 216d (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202g6 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202g7 may be proximate to or near fundal height 216f or fundal height 216h or between fundal height 216e and 216h or 216f (shown in FIG. 2B) at about 32 weeks of pregnancy or between about 26 weeks and 40+ weeks of pregnancy. Sensor module position or reposition 202g7 may be aligned with a frontal axis 206 above a naval 204 of the user.

[0119] FIG. 2H illustrates an example embodiment of various sensor module positions 202hl-h7 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202hl-h7 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202hl may be proximate to or near fundal height 216a (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. For example, sensor module position or reposition 202h2 may be proximate to or near fundal height 216b (shownin FIG. 2B) or between fundal height 216b and 216c in the hypogastric region (shown in FIG. 2C) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202h2 may be aligned with a frontal axis 206 below a naval 204 of the user. Sensor module position or reposition 202h4 may be proximate to or near fundal height 216d (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202h4 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or repositions 202h3, 202h5 may be horizontally offset from frontal axis 206. For example, sensor module position or reposition 202h3 may be between fundal height 216e and 216f in the dextral umbilical region at about 25 weeks to about 35 weeks of pregnancy. Sensor module position or reposition 202h5 may be horizontally offset from the frontal axis 206. Sensor module position or reposition 202h5 may be between fundal height 216e and 216f in the sinistral umbilical region at about 25 weeks to about 35 weeks of pregnancy. The sensor module position or reposition 202h6 may be proximate to or near fundal height 216e, proximate to or near fundal height 216f or between fundal height 216e and 216f (shown in FIG. 2B) at about 26 weeks of pregnancy or between about 24 weeks and 32 weeks of pregnancy. Sensor module position or reposition 202h6 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202h7 may be proximate to or near fundal height 216g or fundal height 216h or between fundal height 216f and 216g or 216h (shown in FIG. 2B) at about 36 to 38 weeks of pregnancy or between about 26 weeks and 40+ weeks of pregnancy. Sensor module position or reposition 202h7 may be aligned with a frontal axis 206 above a naval 204 of the user.

[0120] FIG. 21 illustrates an example embodiment of various sensor module positions 202i 1 - i7 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202il-i7 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202i 1 may be proximate to or near fundal height 216a (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. For example, sensor module position or reposition 202i2 may be proximate to or near fundal height 216b (shown in FIG.2B) in a hypogastric region (shown in FIG. 2C) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202i2 may be aligned with a frontal axis 206 below a naval 204 of the user. The sensor module position or reposition 202i3 may be proximate to or near fundal height 216d (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202i3 may be aligned with a frontal axis 206 above a naval 204 of the user. Sensor module position or reposition 202i4 may be at a horizontal offset from frontal axis 206, parallel to transverse axis 208. Sensor module position or reposition 202i4 is horizontally offset from frontal axis 206 on a dextral side of the user. Sensor module position or reposition 202i4 may be in an umbilical region (shown in FIG. 2C) of the user. Sensor module position or reposition 202i4 may be aligned (parallel to transverse axis 208) to fundal height 216d (shown in FIG. 2B) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. The sensor module position or reposition 202i5 may be between fundal heights 216f and 216g or 216h in the dextral lumbar region (shown in FIG. 2C) of the user. The sensor module position or reposition 202i6 may be proximate to or near fundal height 216e, proximate to or near fundal height 216f or between fundal height 216e and 216f (shown in FIG. 2B) at about 26 weeks of pregnancy or between about 24 weeks and 32 weeks of pregnancy. Sensor module position or reposition 202i6 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202i7 may be proximate to or near fundal height 216g (shown in FIG. 2B) in an epigastric region (shown in FIG. 2C) at about 36 to 38 weeks of pregnancy or between about 32 weeks and 40+ weeks of pregnancy. Sensor module position or reposition 202i7 may be aligned with a frontal axis 206 above a naval 204 of the user.

[0121] FIG. 2 J illustrates an example embodiment of various sensor module positions 202j 1 - j7 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202j 1 -j 7 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202j 1 may be proximate to or near fundal height 216a (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. For example, sensor moduleposition or reposition 202j2 may be proximate to or near fundal height 216b (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202i2 may be aligned with a frontal axis 206 below a naval 204 of the user. Sensor module positions or repositions 202j3, 202j4 may be in a dextral umbilical region and sinistral umbilical region, respectively, along transverse axis 208. Sensor module positions or repositions 202j3, 202j4 may be horizontally or laterally offset from belly button 204 approximately between fundal heights 216c and 216d (shown in FIG. 2B). The sensor module position or reposition 202j5 may be proximate to or near fundal height 216d or between fundal height 216d and 216e (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202j5 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202j6 may be proximate to or near fundal height 216f or between fundal height 216e and 216f or between fundal height 216e and 216g or 216h (shown in FIG. 2B) at about 32weeks of pregnancy or between about 30 weeks and 40+ weeks of pregnancy. Sensor module position or reposition 202i6 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202i7 may be proximate to or near fundal height 216g or 216h (shown in FIG. 2B) in an epigastric region (shown in FIG. 2C) at about 36 to 38 weeks of pregnancy or between about 32 weeks and 40+ weeks of pregnancy. Sensor module position or reposition 202j7 may be aligned with a frontal axis 206 above a naval 204 of the user.

[0122] FIG. 2K illustrates an example embodiment of various sensor module positions 202k l-k7 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202k l-k7 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202kl may be proximate to or near or below fundal height 216a (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 12 weeks or between about conception and about 12 or 16 weeks of pregnancy. Sensor module position or reposition 202k2 may be in a dextral hypogastric region (shown in FIG. 2C) around or between fundal height 216c and 216d (shown in FIG. 2B) between about 18 weeks to about 25 weeks. Sensor module position or reposition 202k3 may be proximate to ornear fundal height 216b or below fundal height 216c (shown in FIG. 2B) in a sinistral hypogastric region (shown in FIG. 2C) at about 14 weeks to 16 weeks. Sensor module position or reposition 202k4 may be offset from the belly button 204 along transverse axis on a sinistral side of the umbilical region at about 20 weeks to about 30 weeks of pregnancy at fundal height 216d. Sensor module position or reposition 202k5 may be in a dextral umbilical or lumbar region between approximately fundal height 216e and 216f (shown in FIG. 2B) between about 25 weeks and about 35 weeks of pregnancy. Sensor module positions or repositions 202k6, 202k7 are between fundal height 216f and 216g or 216h. However, sensor module position or reposition 202k6 is on a sinistral side and 202k7 is on a dextral side. Further, sensor module position or reposition 202k6 is more laterally offset from frontal axis 206 than sensor module position or reposition 202k7. For example, sensor module position or reposition 202k6 may be positioned in a sinistral lumbar region while sensor module position or reposition 202k7 may be positioned in a dextral epigastric region.

[0123] FIG. 2L illustrates an example embodiment of various sensor module positions 202L1-L9 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202L1-L9 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202L1 may be proximate to or near fundal height 216a (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. For example, sensor module position or reposition 202L2 may be proximate to or near fundal height 216b (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202L2 may be aligned with a frontal axis 206 below a naval 204 of the user. The sensor module position or reposition 202L3 may be between fundal height 216c and 216d (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) between about 20 weeks to about 25 weeks of pregnancy. The sensor module position or reposition 202L4 may be between fundal height 216d and 216e (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202L4 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202L5 maybe between fundal height 216f and 216g or 216h (shown in FIG. 2B) in an epigastric region (shown in FIG. 2C) between about 30 weeks and about 40+ weeks of pregnancy. Sensor module position or reposition 202L5 may be aligned with a frontal axis 206 above a naval 204 of the user. Sensor module positions or repositions 202L6, 202L7, 202L8, 202L9 may be at a horizontal offset from frontal axis 206, parallel to transverse axis 208. Sensor module positions or repositions 202L6, 202L7 are horizontally offset from frontal axis 206 on a dextral side of the user. Sensor module positions or repositions 202L8, 202L9 are horizontally offset from frontal axis 206 on a sinistral side of the user. Sensor module positions or repositions 202L6, 202L9 may be between fundal height 216d and 216e at about 22 weeks to about 28 weeks of pregnancy. Sensor module positions or repositions 202L7, 202L8 may be between fundal height 216f and 216g or 26h at about 30 weeks to about 40+ weeks of pregnancy.

[0124] FIG. 2M illustrates an example embodiment of various sensor module positions 202m l-m9 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202m l-m9 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202ml may be proximate to or near fundal height 216a (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. For example, sensor module position or reposition 202m2 may be proximate to or near fundal height 216b or between fundal height 216b and 216c (shown in FIG. 2B) in a hypogastric region (shown in FIG. 2C) at about 14-16 weeks of pregnancy or between about 12 weeks and about 24 weeks of pregnancy or between about 12 weeks and about 20 weeks of pregnancy. Sensor module position or reposition 202m2 may be aligned with a frontal axis 206 below a naval 204 of the user. The sensor module position or reposition 202m3 may be at fundal height 216d (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) between about 20 weeks to about 30 weeks of pregnancy. The sensor module position or reposition 202m4 may be at fundal height 216e (shown in FIG. 2B) in an umbilical region (shown in FIG. 2C) between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202m4 may be aligned with a frontal axis 206 above a naval 204 of the user. The sensor module position or reposition 202m5 may be between fundal height 216f and 216g or 216h (shown in FIG. 2B) in an epigastric region (shown in FIG. 2C) between about 30 weeks and about 40+ weeks ofpregnancy. Sensor module position or reposition 202m5 may be aligned with a frontal axis 206 above a naval 204 of the user. Sensor module positions or repositions 202m6, 202m7, 202m8, 202m9 may be at a horizontal offset from frontal axis 206, parallel to transverse axis 208. Sensor module positions or repositions 202L6, 202L7 are horizontally offset from frontal axis 206 on a sinistral side of the user. Sensor module positions or repositions 202L8, 202L9 are horizontally offset from frontal axis 206 on a dextral side of the user. Sensor module positions or repositions 202m7, 202m9 may be between fundal height 216c and 216d at about 15 weeks to about 25 weeks of pregnancy. Sensor module positions or repositions 202L6, 202L8 may be between fundal height 216d and 216e at about 32 weeks to about 28 weeks of pregnancy.

[0125] In some embodiments, the embodiments described in FIGS. 2A-2M may additionally include optional electrodes or other sensors within the sensor modules. In some embodiments, the sensor modules may include any number of sensor modules attached at different locations of the abdomen, in which case the output of each patch may be combined into a single uterine activity signal.

[0126] FIG. 2N illustrates an example embodiment of various sensor module positions over time on an abdomen of a user. In particular, various sensor module positions 202n2-202n4 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202n2-202n4 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202n2 may be between fundal height 216d and fundal height 216c (shown in FIG. 2B) in the umbilical region 201c5 (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. Sensor module position or reposition 202n2 may be aligned proximate or near to transverse axis 208 and may be horizontally offset from frontal axis 206 on a dextral side of the user. The sensor module position or reposition 202n4 may be between fundal height 216d and fundal height 216c (shown in FIG. 2B) in the umbilical region 201c5 (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. Sensor module position or reposition 202n4 may be aligned proximate or near to transverse axis 208 and may be horizontally offset from frontal axis 206 on a sinistral side of the user.

[0127] FIG. 20 illustrates an example embodiment of various sensor module positions over time on an abdomen of a user. In particular, various sensor module positions 202o2-202o4 overtime on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202o2-202o4 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. For example, sensor module position or reposition 202o2 may be between fundal height 216d and fundal height 216c (shown in FIG. 2B) in the umbilical region 201c5 (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. Sensor module position or reposition 202o4 may be aligned with a frontal axis 206 below a naval 204 of the user.

[0128] FIG. 2P illustrates an example embodiment of various sensor module positions over time on an abdomen of a user. In particular, various sensor module positions 202p2-202p4 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202p2-202p4 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. The sensor module position or reposition 202p2 may be aligned with a frontal axis 206 below a naval 204 of the user. The sensor module position or reposition 202p4 may be proximate to or near fundal height 216d (shown in FIG. 2B) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. Sensor module position or reposition 202p2 may be aligned with a frontal axis 206 below a naval 204 of the user.

[0129] FIG. 2Q illustrates an example embodiment of various sensor module positions over time on an abdomen of a user. In particular, various sensor module positions 202q2-202q6 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202q2-202q6 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother.

[0130] The sensor module position or reposition 202q2 may be between fundal height 216d and fundal height 216c (shown in FIG. 2B) in the umbilical region 201c5 (shown in FIG. 2C) at about 12 weeks or between about conception and about 16 weeks of pregnancy. The sensor module position or reposition 202q4 may be proximate to or near fundal height 216d (shownin FIG. 2B) at about 24 weeks of pregnancy or between about 20 weeks and about 30 weeks of pregnancy. The sensor module position or reposition 202q6 may be aligned with a frontal axis 206 below a naval 204 of the user.

[0131] FIG. 2R illustrates an example embodiment of various sensor module positions over time on an abdomen of a user. In particular, various sensor module positions 202r2-202r6 over time on an abdomen of a user. The positions of the sensor module are with respect to frontal axis 206 and transverse axis 208 (centered on belly button or naval 204). The position or reposition of the sensor module 202r2-202r6 may be based on one or more of: a gestational age of the fetus, a fetal orientation, a fetal presentation, an anatomical curvature of the abdomen of the mother, a body mass index of the mother, or other features of the fetus or mother. The sensors module position or reposition 202r2 may be along the frontal axis 206 and above the naval 204 in the umbilical region. The sensor module position or reposition 202r4 may be aligned with the frontal axis 206 and below the naval 204 of the user.

[0132] The sensor module position or reposition 202r6 may be on or near to an iliac region including on a portion of a hip, an upper thigh, or the like. The sensor module 202r6 may capture or detect patient movements. In some embodiments, movements captured by sensor module 202r6 may include physical abdominal or leg movements of the patient, but may not include the fetus and not contraction movements. The movements captured by sensor module 202r6 may be correlated to any number of other sensor module data including contraction data, fetal movement, maternal movement, etc.

[0133] FIG. 3 illustrates a block diagram of the example monitoring system 100 for performing uterine activity monitoring. The system 100 may measure uterine activity over time to monitor a patient during assisted reproduction, pregnancy, labor, and / or post-partum. For example, the system 100 may be used to measure uterine activity and process such activity via a signal processing unit 300 when it is medically indicated, e.g. in parallel to the use of assisted reproductive technologies, in the case of possible preterm labor, in the case of a risk of postpartum hemorrhage, or when uterine contractions represent a clinical risk to the pregnant patient or her baby. The system 100 may also be used as part of an antepartum fetal monitoring system (not shown) where uterine activity information is combined with maternal heart rate and fetal heart rate measurements.

[0134] As shown, the monitoring system 100 may optionally receive data from an optional wearable device 302 that is communicatively coupled to system 100. The optional wearable device 302 may include sensors 304 and a display 306 for providing graphical output to a useror obtain or receive patient data. In some embodiments, the system 100 may optionally receive patient data 308 from a medical system or the patient from wearable device 302 and / or prior input into the system 100. In some embodiments, the system 100 may utilize training data 310 with rules 312 to enhance machine learning (ML) models and / or other artificial intelligence algorithms used by the signal processing unit 300, a trust management unit 324, a data transmission unit 326, ML models 328 (or other Al model, generative Al model, or the like), and / or classifiers 330.

[0135] In general, the monitoring system 100 may utilize ML models (or other Al models, generative Al models, or the like that employ regression analysis, random forest analysis with different quality metrics or other detected contraction feature. Unsupervised learning or statespace modeling may be used to assess and monitor contractions and movements of a female captured by one or more sensor modules 102.

[0136] The monitoring system 100 may utilize any number of sensors 112 of sensor module 102 to determine belly deformation and / or other physiological contraction indicators for a pregnant female. The sensors 112 may include, for example, one or more IMU sensors 120, one or more optional EHG sensors 122, one or more optional EMG sensors 124, one or more optional electrodes 126, one or more optional strain gauge sensors 128, and any combination thereof.

[0137] While any combination of IMUs are described herein to obtain deformation characteristics of the belly to identify contractions or contraction patterns, any combination of sensors may be utilized. For example, in some embodiments, a plurality of signals may be obtained by system 100 when attached to a belly region of a female. The system 100 may further process the plurality of signals to extract a deformation of the belly region of the female. In some such embodiments, the deformation may be measured by IMUs (e.g., with any combination of gyroscopes, accelerometers, magnetometers), and / or any combination of a piezo- electric sensor, a piezo-resistive sensor, a capacitive sensor, a pressure sensor, or a stretch sensor. In one non-limiting example, as uterine electrical activity moves from the top of the belly (e.g., fundus region) to the bottom of the belly (e.g., cervix region), the belly may temporarily deform at the location or position of the uterine electrical activity as the uterine electrical activity propagates. Such deformation may be detected and measured by one or more IMUs and correlated with additional uterine electrical activity characteristics (e.g., frequency, amplitude, etc.).

[0138] In some embodiments, the system 100 may include one or more IMU sensors 120 that may be in communication with or otherwise correlated to one another. In some embodiments, the system 100 may include one or more IMU sensors 120 and an EMG / EHG sensor (e.g., uterine EMG (or EHG) data). In some embodiments, the system 100 may include one or more IMU sensors and a strain gauge. In some embodiments, the system 100 may include one or more IMU sensors 120 and a maternal heart rate sensor. In some embodiments, the system 100 may include one or more IMU sensors 120 and a fetal heart rate sensor. In some embodiments, the system 100 may measure fetal kicks and fetal movement in addition to uterine activity, using the same IMU sensor 120 or a plurality of IMU sensors. In some embodiments, the system 100 may measure labor progression contraction timing in addition to uterine activity, using the same IMU sensor 120 or a plurality of IMU sensors.

[0139] In some embodiments, the system 100 may include one or more non-contact sensor, as described elsewhere herein, to detect deformations of the abdomen of a female before, during, and after labor. For example, the system 100 may use multiple non-contact sensors and a processor to assess orientation or directionality of a contraction (e.g., a contraction wave) when viewing the data with the multiple sensors and / or other sensor modalities.

[0140] In some embodiments, the system 100 may utilize one or more IMU sensors 120 to monitor the overall movement of a pregnant woman or the movements of the abdomen induced by fetus movement and kicks. Alternatively, or additionally, the one or more IMU sensors 120 may be used to measure the local movement of the sensor module 102. In some embodiments, the system 100 may utilize one or more IMU sensor 120 to detect fetal activity timing and duration based on fetal movement and fetal kicks.

[0141] In some embodiments, the system 100 may measure maternal health parameters in addition to uterine activity. In some embodiments, the system 100 may combine uterine activity with maternal heart rate and / or fetal heart rate, thus providing the data to perform antepartum fetal monitoring or a non-stress test (NST).

[0142] The signal processing unit 300 can be implemented in one or more digital signal processor (DSP), one or more micro-controller unit (MCU), one or more field programmable gate array (FPGA), one or more application specific integrated circuit (ASIC), and / or one or more application specific processor (ASP), etc. In the example of FIG. 3, the signal processing unit 300 includes a pre / post processing unit 314, a transformation generator 316, a deformation analyzer 318, and an optional EMG / EHG analyzer 320.

[0143] In some embodiments, the pre / post processing unit 314 is a combined unit. In some embodiments, the pre / post processing unit 314 includes separate pre-processing and postprocessing units. The pre / post processing unit 314 may include pre-processing logic. The preprocessing may include any processing that occurs after sensor capture. In some embodiments, pre-processing may include determining trustworthiness of particular signal outputs and analysis performed by the system 100. In some embodiments, pre-processing may include outlier removal using a statistical model, for example, to remove outlier data points from a particular IMU signal. In some embodiments, pre-processing may include noise cancellation, noise removal (e.g., filtering, smoothing, etc.), signal translations, signal boosting, etc.

[0144] The pre / post processing unit 314 may also include post-processing logic. Postprocessing may include signal combining or signal transformation to provide cohesive images of the captured data for a user to view and / or interpret. In some embodiments, post-processing may include generating graphs, pictorials, tables, and / or other data representing the captured sensor output.

[0145] In some embodiments, post-processing may include motion artifact removal. For example, sensor signals may be corrupted with movement artifacts, resulting in noise in the signal that can affect signal interpretation. Movement artifacts are especially present in the case of ambulatory settings. The system 100 may perform automatic identification of motion artifacts. Such artifacts may be removed by pre / post processing unit 314 to exclude excerpts of the sensor signals that are corrupted with artifacts.

[0146] In some embodiments, the post-processing may include motion artifact filtering. Motion artifact filtering can be performed in the analog domain before amplifying the sensor signals, and / or in the digital domain. Motion artifact filtering detects and removes artifacts from the sensor signals, in order to increase the signal quality and signal-to-noise ratio of the sensor signals. Motion artifact filtering can be achieved using a variety of signal processing techniques, including but not limited to: band-pass filters, linear filters, adaptive filters, wavelet filters, or blind source separation techniques. In some embodiments, motion artifact filtering can be achieved using an additional motion artifact signal that is measured in parallel to the sensor signals. The additional signal may carry information about the artifacts. For example, the motion artifact signal can be measured using an accelerometer or IMU attached to or integrated into the sensor module 102 or a separate accelerometer or IMU that is used for motion artifact sensing. In another example, the motion artifact signal may include measuring contact impedance using the optional electrodes 340. In some embodiments, the motion artifactsignal can be used as an input to a motion artifact filter. For example, the motion artifact signal can be used as the input to an adaptive filter representing an estimation of the noise. The adaptive filter can then function to remove the noise estimation from the sensor signals, yielding cleaner and more accurate signals than the initial signal.

[0147] The transformation generator 316 may function to determine a maximum displacement and rotation of an IMU signal to maximize impact of a particular contraction by transforming from local coordinates into other coordinates. For example, the transformation generator 316 may transform pre-processed IMU data into a distance (i.e., displacement) measurement (e.g., in millimeters) and / or a rotation measurement to enable contraction assessment. In some embodiments, transforming the IMU signals includes transforming uterine motion data obtained from the IMU signals from a first signal domain to a second signal domain by determining, in the uterine motion data, a plurality of angles between axes defined by the at least one IMU sensor, correcting the uterine motion data, refining the corrected uterine motion data, converting the corrected uterine motion data to identify at least two displacement measurements according to the axes, and combining the at least two displacement measurements. From the transformed IMU signals, the deformation analyzer 318 may determine what the identified displacements and / or rotations indicate for a particular contraction. For example, a transformation that results in a displacement above a predefined displacement threshold level may indicate a large contraction and thus active labor and / or imminent birth. In some embodiments, the transformation generator 316 may use divergence and / or similarity measurements, theoretic information, and / or frequency-domain measurements to determine particular displacements and / or rotations of an IMU signal with respect to one or more contractions occurring at the uterus.

[0148] The deformation analyzer 318 may assess what the displacements and / or rotations determined by transformation generator 316 indicate about a status of the female, a status of labor, a status of the fetus, etc. In some embodiments, the deformation analyzer 318 may include an algorithm to automatically detect and count contractions based on the uterine activity signal. Such counts may be used to identify a preterm labor contraction, a labor contraction, a Braxton-Hicks contraction, and a state of no contraction, based at least in part on the IMU signals.

[0149] The optional EMG / EHG analyzer 320 may analyze electrical activity of the uterus captured by one or more optional electrodes 340. For example, analysis of the electrical activity of the uterus, or electrohystergraphy (EHG), may reflect a source of a uterine contraction.Uterine contractions are generated by the electrical activity originating from the depolarization- repolarization of smooth muscle myometrial cells, thus, creating intermittent bursts of spikelike action potentials. This electrical activity is low and uncoordinated early in gestation, but becomes intense and synchronized later in pregnancy, peaking at term, and as such the use of EHG measurements to detect changes can be another way to analyze contractions. In some embodiments, the optional EMG / EHG analyzer 320 may use data coming from the one or more IMU sensors of sensor module 102 to fdter artifacts from the signals captured by one or more optional electrodes 340.

[0150] The monitoring system 100 also includes a trust management unit 324. The trust management unit 324 may employ a statistical analysis to determine a trustworthiness of any modification to a signal. For example, modifications that occur at pre-processing steps, transformation steps, post-processing steps, gain determination steps, and modulation steps may be assessed according to a trust analysis. Each step of a process may be assessed by the trust management unit 324 to determine a trust index for the step. For example, the trust index can be calculated using raw incoming data and / or calculated on combined data from different transformation steps, denoising steps, detection steps, and / or smoothing stages. As each of these steps can provide input into the trust index, a merged trust metric may be used to provide qualitative information for the underlying and converted signals or could be directly applied to the resulting signal as a way to dynamically adapt the output. In some embodiments, determined trust indices may be presented to clinicians, medical staff, etc. For example, the trust management unit 324 may utilized the UI generator 334 to generate and mark signals of interest within a user interface and may further provide within the user interface signal segments with contractions and / or fetal kicks with a trust index value to indicate a level of trust to place in the presented signal / user interface.

[0151] In some embodiments, the trust analysis may include using a Poisson-based statistical model to analyze all or portions of a biological signal to ensure the changes to the signal do not violate particular rules. In particular, the trust analysis may include the use of a multi-state trust index or a joint trust index that utilizes any number of signals from one or more sensor modules 102 and / or user input. For example, if the signals are IMU signals that represent contraction movement of a pregnant female, then example rules may include assessments about particular parameters such as gestational age, BMI of patient, age of the patient, number of prior pregnancies, length of contraction, amplitude of contraction, shape of contraction, contraction frequency, EXG energy, EHG energy, signal-to-noise ratio (SNR) of IMU, gyroscopeinformation, magnetometer information (e.g., quaternions as input), respiratory information, and change of position of the pregnant female, etc. Such rules may include setting minimum and maximum limits on contraction times, acceleration limits for IMU sensors, etc. The system 100 may use such rules to generate trust indices for signals being output at particular processing steps to generate a probabilistic measure of how much trust to assign a signal being output from each processing step and to determine how the signal reflects the physiology of the contraction.

[0152] In some embodiments, the system 100 may classify generated output as one of: an antepartum contraction, an intrapartum contraction, a non-pregnant contraction, a postpartum contraction, a non-pregnant female movement, a Braxton-Hicks contraction, or a state of no contraction. Upon completion of classification, the system 100 may perform a data trust analysis during the monitoring, as described elsewhere herein, and may use the data trust analysis to determine an accuracy likelihood of the classifying of the output. For example, if the trust analysis indicates that a trust index associated with the output is above a predefined threshold, then the data may be indicated as trustworthy. If the trust analysis instead indicates that the trust index associated with the output is at or below the predefined threshold, then the data may be indicated as untrustworthy. In some embodiments, the determined trustworthiness may be used to generate an output indicating the accuracy likelihood. Such output may take the form of any or all of an audio indicator, a visual indicator, an alarm indicator, a vibratory indicator, etc. In some embodiments, the system 100 may generate postpartum hemorrhaging predictions utilizing one or more of the contraction detection techniques and data described herein.

[0153] The monitoring system 100 also includes a data transmission unit 326. The data transmission unit 326 may transmit at least one of the signals generated by the signal processing unit 300 to a user personal device or other computing device. The user personal device can be a smartphone (e.g., device 104), a tablet, a smart watch, smart glasses, a personal computer, and / or any multimedia device that is equipped with wired, wireless, or optical communication. Wired communication can be achieved using USB, Ethernet, HDMI, FireWire, Thunderbolt, RS232 or any other wired communication protocol. Wireless communication can be achieved using Bluetooth, Bluetooth low-energy, Wi-Fi, Zigbee, NFC or any other wireless communication protocol. In some embodiments, the data transmission unit 326 can transmit at least one of the signals generated by the signal processing unit 300 to a clinician computing device.

[0154] The system 100 may further include a power management unit 332. The power management unit 332 can deliver power to the different modules of the monitoring system 100. In some embodiments, the power management unit 332 can include power management circuitry, a battery and on / off circuitry. The power management circuitry can convert the battery voltage to the right level of input voltage for the different modules of the device. The power management unit 332 can deliver an input voltage that is specific and may be different for each module. The battery can be rechargeable or alkaline and can be of different chemistry and shape. In the case of a rechargeable battery, the power management circuitry can also include charging circuitry. The on / off circuitry can be a switch that allows the user to switch the device on and off. In some embodiments, the on / off circuitry can advantageously include electronic circuitry to detect when the sensors of module 102 and / or optional electrodes 340 are connected to the system 100. In some embodiments, the on / off circuitry can advantageously include electronic circuitry to detect when the monitoring system 100 and / or sensors or module 102 and / or optional electrodes 340 are attached to the body.

[0155] The system 100 may further include a user interface (UI) generator 334 for generating output data from captured sensor data. The output data may include any combination of user interface content such as graphs and data representing contractions, uterine activity, fetus status, maternal status, or the like. The system 100 may further include an optional display 342 for depicting any of the UI interfaces as well as data and UI content associated with system 100 and / or optional wearable device 302.

[0156] The system 100 may include one or more neural networks (not shown) associated with one or more machine learning (ML) models 328. The neural networks may include one or more activation functions executable by the ML models 328 of system 100. The ML models 328 may utilize training data 310, classifiers 330, and one or more rules 312. For example, the neural networks and resulting ML models 328 may be trained using training data 310 and may be executed to classify data using classifiers 330 and the rules 312. In some embodiments, the ML models 328 may include one or more feed-forward models that may weight any or all of the IMU signals. In some embodiments, the ML models 328 may further include postcombining any of the axes associated with the IMUs.

[0157] In some embodiments, one or more classifiers 330 may be trained or updated based on user input. The user input may be used to improve or refine output from the system 100 including, but not limited to contraction state, uterine activity, fetus status, maternal status, or the like. For example, if a user provides an input to the system 100 with a time of known fetuskick (or lack thereof) or a location of fetus kick (or lack thereof), then system 100 may analyze other sensed movements or signals with respect to one or more sensors 102 worn on the user and correlate such sensed movements / signals with a definitive fetus kick (or lack thereof). Such correlations can be used for future analysis to determine a likelihood of the fetus kick or other fetus status. Similarly, other aspects may be provided as input and correlated to signal data to improve future physiological observations determined by the system. Other aspects may include, but are not limited to an orientation or measurement with respect to the user sitting location, fetus sitting location or another physical change associated with the user or the fetus.

[0158] The training data 310 may include historical contraction and labor data for any number of patients. In some embodiments, the data 310 may be anonymized to comply with the Health Insurance Portability and Accountability Act (HIPAA) ) or the General Data Protection Regulation (GDPR).

[0159] In some embodiments, the rules 312 may include a number of definitions and instruction for handling and processing data in system 100. For example, the rules 312 may include trust analysis rules for trust management unit 324, sensor data handling rules, UI generator rules, signal processing rules, ML model rules, power rules, user permission rules, user or physician entered rules, or the like.

[0160] The system 100 may further include processors 336 and memory 338. The processors 336 may include one or more processors that include one or more devices capable of executing instructions, such as instructions stored by the memory 338, to perform communications amongst signal processing unit 300, trust management unit 324, data transmission unit 326, power management unit 332, sensor module 102, wearable device 302, ML models 328, user devices (not shown), and other modules of system 100.

[0161] The memory 338 can include one or more non-transitory computer-readable storage media. The memory 338 may store instructions and data that are usable in combination with processors 336 to execute the processes and / or algorithms described herein as well as to execute or interface with ML models 328, signal processing unit 300, trust management unit 324, data transmission unit 326, and power management unit 332. The memory 338 may also function to store or have access to the ML models 328, patient data 308, and / or data from optional wearable device 302.

[0162] In some embodiments, the monitoring system 100 may further include or be communicatively coupled to input devices (not shown), output devices (not shown), and / orsensor interfaces such as sensor module 102. The input devices may interact with one or more processors 336, memory 338, and / or wearable device 302.

[0163] In some embodiments, the system 100 may further include or be communicatively coupled to output devices (not shown). The output devices may interact with one or more processors 336 and memory 338. In some embodiments, the output devices may include, for example, an external display for depicting user interfaces generated by UI generator 334 and / or system 100.

[0164] In some embodiments, the sensor data output by system 100 may be used to identify contractions of the pregnant female (or recently previously pregnant female, or female looking to become pregnant). The contraction data may be fed into any number of additional algorithms. For example, the contraction data identified by system 100 may be combined with extracted EXG signals and / or fetal heart rate signals to perform a non-stress test in any location, including the home. This information can then be shared remotely with a clinical trained staff for data interpretation.

[0165] In some embodiments, the contraction data may be used in combination with maternal activity to correlate contractions with maternal activity. Maternal activity can be achieved using an activity sensor embedded in a smartphone, for example, using a dedicated activity tracker or using an activity sensor embedded in the sensor module 102 of system 100. Activity measures can include, but are not limited to: steps, activity time, activity types, time spent in different activity types, energy expenditure, calorie burned, sleep duration, sleep quality, etc. The activity sensor can track maternal activity over time, for specific recording sessions, or continuously.

[0166] In some embodiments, the system 100 may provide user feedback. Providing user feedback can provide recommendations or suggestions to the pregnant woman based on the contraction data determined by analyzing uterine activity. User feedback can be provided to help women reduce the pain associated with contractions, or to attempt to reduce the number or the frequency of contractions. User feedback can, for example, include recommendations for a better body position, for specific food, for specific activities (e.g. take a warm bath), etc. The feedback can also include tips to help the user relax, or exercises that the user may be able to do to decrease stress levels. In some embodiments, providing user feedback can provide recommendations or suggestions to the pregnant woman based on the correlation between contractions and maternal activity. For example, if an elevated number of contractions and an elevated activity level are detected simultaneously, feedback can be provided to the woman toreduce activity and relax for a predefined time period. The user feedback can take the form of a message displayed in an App for smartphone, tablets, smart watch, or smart glasses, or a text message, and / or feedback during monitoring on an external display. Alternatively, or additionally, the feedback can take the format of a message, graph, picture, figure, or any multimedia messages transmitted to the partner, family, or friends of the pregnant woman. Alternatively or additionally, the user feedback can take the form of a report with graphs, tables or text, sent to an obstetrician or a clinically trained staff for further interpretation.

[0167] In some embodiments, the system 100 may also be used as part of an antepartum fetal monitoring system, where the uterine activity information is combined with maternal heart rate and fetal heart rate.

[0168] In some embodiments, the system 100 may be used to measure arterial stiffness in conjunction with contraction information. For example, one or more sensor modules 102 may include a pulse oximeter sensor and another of the one or more sensor modules 102 may include one or more electrodes for capturing EXG signals. The system 100 may assess arterial stiffness during a contraction by analyzing the EXG signals in combination with the pulse oximeter data captured by the pulse oximeter sensor.

[0169] In some embodiments, the wearable device 302 may provide sensed data to the monitoring system 100. However, it will be appreciated that the wearable device 302 may be integrated into the monitoring system 100 as a single device that performs other health tracking with uterine activity monitoring. In some embodiments, the wearable device 302 may instead share data with system 100 via the cloud (e.g., server 108).

[0170] The sensor modules 102 (e.g., sensors 112) depicted in FIGS. 2A-2M can take many different form factors. In some embodiments, the sensor module 102 of various embodiments has many different shapes, sizes, colors, materials, and levels of conformability to the body. The sensor module 102 may connect to, be embedded within, or form a portion of: a patch; a strap, belt, or band; a blanket / cover; t-shirt; pants; underwear; or other article of clothing or wearable accessory. In some embodiments, the sensor module 102 is attached to the body using an adhesive layer. In some embodiments, the adhesive layer can be replaceable and / or disposable. In some embodiments, the sensor module 102 can be attached to the body using a strap or a piece of textile that can maintain the device in contact with the body. In some embodiments, the sensor module 102 may have an embedded display that visualizes the uterine activity.

[0171] FIG. 4 illustrates a flow diagram of an example system 400 for performing uterine activity monitoring. The system 400 includes a sensor module 402, a sensing unit 404, a signal processing unit 300, a data transmission unit 326, and a user interface 406. In some embodiments, the sensor module 402 may be an adhesive sensor module that may be coupled to the belly of a pregnant woman. While there is a flow shown to system 400, any combination of data flow may be possible.

[0172] The sensor module 402 may include a wearable device, as described elsewhere herein. In some embodiments, the sensor module 402 may be an adhesive patch having sensors 112. In some embodiments, the adhesive sensor module 402 may be an adhesive patch that includes the monitoring system 100 and is couplable to the belly of a woman. The sensor module 402 may take any shape for attaching to a lower abdomen of a woman. The sensor module 402 may be formed in such a way that the local (e.g. deformation, rotation, translation movements) and global movements of the lower abdomen are transferred to the sensor module 402.

[0173] In some embodiments, the module 402 may include the sensors 112 of module 102, the data transmission unit 326, and optionally the signal processing unit 300. In some embodiments, the module 402 may be composed of a single disposable piece. In some embodiments, the module 402 may be composed of two pieces (i.e., one disposable adhesive, and one reusable electronics module attached to the adhesive). Optionally the patch may also include electrodes (e.g., electrodes 340) to acquire uterine EMG signals.

[0174] The sensing unit 404 may incorporate one or more IMUs to detect uterine contractions, belly deformations, and other physiologically derived pregnancy signals. For example, one or more non-invasive IMU sensors may be strategically placed on the maternal abdomen to capture uterine activity, as described elsewhere herein. Optionally, the sensing unit 404 may also include an analog front-end to measure EMG signals.

[0175] The signal processing unit 300 may include signal processing algorithms and, optionally, machine learning or artificial intelligence algorithms. The signal processing unit 300 may interpret signals from the sensing unit 404 to distinguish uterine contractions from other physiological signals, ensuring accuracy and reliability in uterine activity monitoring. The data processing unit 300 may be embedded in the sensor module 402, or may be distributed between the sensor module 402 and a cloud server, or may be fully executing in the cloud server.

[0176] The data transmission unit 326 may transmit data from the monitoring system 100, for example, to the user interface 406 generated by UI generator 334. In some embodiments, the data that is transmitted may be raw sensor module data, e.g. in the case that the data processing is performed in a cloud server. In some embodiments, the data that is transmitted may be the uterine activity signal(s), e.g. in the case that the data processing is performed locally in the system 100.

[0177] The user interface 406 may include graphically displayed uterine activity. The user interface 406 may be used by a woman or her medical staff (e.g. nurse, midwife, physician, etc.). In some embodiments, the user interface 406 may include any number of updateable content to display captured uterine activity. User interface 406 described herein may include IMU data, contraction data, uterine activity signals, patient data, or the like. The content depicted in the user interface 406 may be displayed and / or updated in real time or near real time.

[0178] FIG. 5A illustrates a flow diagram of an example process 500 for performing uterine activity monitoring in combination with a trust analysis. The process 500 performs a flow of signal processing of IMU signals 502 in blocks 504-514 while performing trust index analysis in parallel in blocks 516-522. The trust index analysis may be based on trust index metrics that are generated by system 100 at one or more steps of signal processing. The trust index represents how reliable or accurate is the signal that is output from a particular block in the signal processing with respect to a raw signal and / or with respect to a signal generated from a prior block analysis or output. In the example with trust analysis occurring for each block in the process 500, for example, a number of intermediate trust indices can be generated to track the reliability or accuracy of the signals through the signal processing steps. In this way, the system 100 can track the trustworthiness of a signal at each step of signal processing.

[0179] In some embodiments, the trust index analysis may be performed at each signal processing step and the end decisions during modulation block 512 may be combined to generate a uterine activity signal. In some embodiments, the trust index analysis is performed with respect to one or more of the blocks 502-510. In some embodiments, the trust index analysis is performed with respect to the modulation block 512 without performing additional trust analysis in other prior blocks.

[0180] In some embodiments, the trust index analysis may include using a Poisson-based statistical model to analyze all or portions of a biological signal to ensure the changes to the signal do not violate particular rules. In particular, the trust analysis may include the use of amulti-state trust index or a joint trust index that utilizes any number of signals from one or more sensor modules 102 and / or user input. For example, if the signals are IMU signals that represent contraction movement of a pregnant female, then example rules may include assessments about particular parameters such as gestational age, BMI of patient, age of the patient, number of prior pregnancies, length of contraction, amplitude of contraction, shape of contraction, contraction frequency, EXG energy, EHG energy, signal-to-noise ratio (SNR) of IMU, gyroscope information, magnetometer information (e.g., quaternions), respiratory information, and change of position of the pregnant female, etc.

[0181] At block 504, the process 500 may include pre-processing the IMU signals 502. For example, the pre / post processing unit 314 may perform any or all of detecting, within the IMU signals, a change of position of the pregnant female at block 524, smoothing portions of the IMU signals at block 526, and one or more outlier removal processes of the IMU signals at block 528, as described elsewhere herein. Any output from block 504 may be used as input to the trust index analysis at block 516. For example, the trust management unit 324 may use a probabilistic model to assess whether the steps of preprocessing carried out in block 524, block 526, and block 528 are trustworthy with respect to the original IMU signals 502. The system 100 may determine to perform the pre-processing again on the IMU signals 502 if it is determined that the trust index is below a predefined threshold level. For example, the system 100 may normalize a probability between zero and one as a basis for finding a threshold level. The predefined threshold level may be set at or above about 60 to about 80 percent of the highest threshold of one. The system 100 may additionally scale the probabilities and thresholds to ensure that the IMU data or other output is trustworthy. In one non-limiting example, the system 100 may utilize a trust index, as described elsewhere herein to indicate a state of the data being used in a contraction state determination. For example, a contraction state versus a rest / refractory state may be determined using a joint probability (e.g., exclusive or logic).

[0182] In some embodiments, other or additional data manipulations can be included in the pre-processing block 504, such as baseline removal, smoothing, inversion, detection and correction of female movement and change of position, detection of baby / fetus movement and fetal kicks, just to name a few examples.

[0183] The system 100 may instead determine to provide the output from block 504 to the next block in the process 500 if it is determined that the trust index meets or exceeds the predefined threshold level.

[0184] In some embodiments, the pre-processing may include determining a change of position of the female to indicate that the system 100 determined not to trust the next section or time period of data until there is stability in the system. The probabilistic version of that may depend on the distribution of events and event impact on uterine activity output in order to determine how to modulate or attenuate particular output. In some embodiments, preprocessing may include outlier removal techniques to remove data that may be providing noise or anomalies on the signal.

[0185] At block 506, the process 500 may include transforming raw IMU signals into a different space. For example, the system 100 may utilize signal processing unit 300 to convert each IMU signal from raw signals to a different space. The transformation may occur from a first signal domain to a second signal domain. In some embodiments, the transformation may assess angles and displacements associated with changes in the IMU signals and convert the raw data to displacement data to assess how a particular accelerometer sensor is moving over time. In some embodiments, the transformation performed at block 506 finds a maximum displacement and rotation to maximize impact of a particular contraction by transforming from local coordinates into other coordinates. For example, the transformation generator 316 may transform pre-processed IMU data into a distance (i.e., displacement) measurement (e.g., in millimeters) and / or a rotation measurement to enable contraction assessment.

[0186] In some embodiments, the transformations may include determining a distribution of observed displacements and / or angles from prior training data. Given a signal determined to be clean, the probability of seeing a particular displacement or angular change could be incorporated into the trust index. This could be a static measure or a dynamic measure within the patient’s observed signals.

[0187] In some embodiments, transformations performed in block 506 may include combining multidimensional signals into a single dimensional signal as a basis in which to determine overall displacement and / or rotation associated with maternal movement / uterus contractions.

[0188] Any output from block 506 may be used as input to the trust index analysis at block 518 in addition to output from block 516. For example, the trust management unit 324 may use a probabilistic model to assess whether the steps of transformation analysis carried out in block 506 is trustworthy with respect to the output at block 504. The system 100 may determine to perform transformations of block 506 again if it is determined that the trust index for block 506 is below a predefined threshold level. For example, if the trust index is allocated into a lowerquartile (e.g., lower than about 50 percent (e.g., about 43 percent to about 49 percent or lower)), then the system 100 may remove or negatively weight the data associated with the trust index. If the trust index is allocated into a higher quartile (e.g., between about 50 percent and about 100 percent), then the system 100 may allow a gain or positively weight the data associated with the trust index. The particular predefined threshold level may be selected and / or normalized / dynamically scaled, or the like based at least in part on other patient data such as calibration data, physiological data (BMI, GA, pregnancy status, heart rate, fetus status, contraction state, etc.)

[0189] The system 100 may instead determine to provide the output from block 506 to the next block in the process 500 if it is determined that the trust index meets or exceeds the predefined threshold level.

[0190] In some embodiments, transforming the IMU signals 502 includes transforming uterine motion data obtained from the IMU signals 502 from a first signal domain to a second signal domain by determining, in the uterine motion data, a plurality of angles between axes defined by the at least one IMU sensor, correcting the uterine motion data, refining the corrected uterine motion data, converting the corrected uterine motion data to identify at least two displacement measurements according to the axes, and combining the at least two displacement measurements, as described elsewhere herein

[0191] At block 508, the process 500 may include performing post-processing on the output from block 506 including any or all of inversion at block 530, smoothing at block 532, and / or outlier removal at block 534. The inversion may account for IMU or other sensor data changes. Similar to the pre-processing block, the post-processing may include determining noise characteristics from outlier analysis or post smoothing functions. These signal changes could directly feed a probabilistic trust index. Additionally inversion calculations could inform quadrant rotation and other observed factors that bias the trust index. For example, particular orientations may be notoriously troublesome and the system 100 may include one or more rules to assign less weight to such signals taken during the orientations.

[0192] Any output from block 508 may be used as input to the trust index analysis at block 520 in addition to output from block 518. For example, the trust management unit 324 may use a probabilistic model to assess whether the steps of transformation analysis carried out in block 508 is trustworthy with respect to the output at block 506. The system 100 may determine to perform additional or repeat post-processing of output from block 508 again if it is determined that the trust index for block 508 is below a predefined threshold level, as described elsewhereherein. The system 100 may instead determine to provide the output from block 508 to the next block in the process 500 if it is determined that the trust index meets or exceeds the predefined threshold level.

[0193] At block 510, the process 500 may combine the displacements determined from signal outputted from block 508 to determine how the belly is transformed during the uterine activity. Any output from block 510 may be used as input to the trust index analysis at block 522 in addition to output from block 518. For example, the trust management unit 324 may use a probabilistic model to assess whether the steps of gain analysis carried out in block 510 are trustworthy with respect to the output at block 508. The system 100 may determine to perform gain analysis of block 510 again if it is determined that the trust index for block 510 is below a predefined threshold level. The system 100 may instead determine to provide the output from block 510 to the next block in the process 500 if it is determined that the trust index meets or exceeds the predefined threshold level.

[0194] In some embodiments, the trust index may operate as a gating function to use or not use particular data. In some embodiments, the trust index may operate as a gain / loss or weighted function to modulate particular output to ensure trustworthiness and accuracy of the output.

[0195] At block 512, the process 500 may include performing modulation on the output signal from block 510. The modulation may include attenuations or amplifications of particular signal portions based on information received from the trust analysis performed in block 522. In some embodiments, the modulation may be performed dynamically or statically to attenuate or amplify particular uterine activity output for a trustworthy signal output. This could be done with multiplication, using a joint-probability attenuation, correlation, or other functional combination and / or weighting. For example, the system 100 may learn a feed-forward model that weights the different IMU signals or post-combines the different axes to obtain an improved signal. The output at block 514 is based on the original one or more IMU signals 502 and represents the uterine activity signal generated at block 512.

[0196] In some embodiments, the signal processing unit 300 may include an algorithm to incorporate outlier detection to help understand different classes of data, such as patient movement versus physiologically derived signals. The outlier detection may use statistical methods and / or ML techniques to determine the outlier properties. Further, these outliers may be used to inform modifications to the input signal such as dynamic scaling and / or other signal processing parameters.

[0197] In some embodiments, the signal processing unit 300 may include an algorithm to transform either raw data and / or denoised data from one signal domain to another domain. These transformations may be applied in parallel or independently. Transformations may include wavelet combinations, angular calculations, Fourier series, information-theoretic, or other broad signal processing transformations. Other transformations may include the conversion of IMU output units to mmHG, bias weightings, or other units of measure.

[0198] In some embodiments, the signal processing unit 300 may include an algorithm to smooth the outputs from the transformation and denoising algorithms to make signals appear similar to how uterine activity is currently displayed for clinicians in TOCO and / or EHG. This algorithm may leverage adaptable parameters that are tuned from prior stages in the algorithm and / or use a trust index (e.g., quality index, signal quality measures, signal quality indicators, etc.) to help inform the smoothing function(s). Other measures of smoothness may be applied to the signal output to act as a feedback loop to dynamically adapt the signal.

[0199] In some embodiments, the signal processing unit 300 may include an algorithm to detect signal features of interest to adaptively tune parameters for the respective signal processing stages. These adaptive tunings can occur independently for the signal processing stages or in parallel. Some of the features of interest may be related to physiologically derived signals such as uterine activity, fetal movements, local muscle deformations, and / or uterine pressure changes. In some embodiments, the signal processing unit 300 may utilize a temporal variable in the data to assess or smooth data over moving time windows, for example.

[0200] FIG. 5B illustrates a flow diagram of an example process 550 for performing a transformation of captured IMU signals. In operation, the system 100 may obtain one or more IMU signals from IMU sensors (e.g., sensor module 102) placed on a belly of a female. At block 552, the system 100 may use the captured signals to identify uterine motion data and calculate, from the uterine motion data, angles between axes for each defined IMU that captured a portion of the motion data. For each IMU that detected motion and contributed to the motion data, a set of three axes are defined and provide six degrees of freedom. For example, for each IMU, an x-axis, a y-axis, and a z-axis are defined perpendicular to one another. The system 100 may calculate angles between axes for one IMU and / or angles between axes for any two or more IMUs. The angles may be calculated to provide a baseline for later determining an amount of uterine activity movement (in yaw, pitch, or roll) during monitoring of a pregnant female. The angle(s) may range between -180 degrees and +180 degrees (e.g., - K to + n).

[0201] At block 554, the system 100 may perform a baseline removal to correct the uterine motion data for motion artifacts or other outlier signal portions. For example, one or more accelerometers of the one or more IMUs may be used to measure body movement that may have occurred at a same time the uterine motion data was captured. This body movement may be removed from the uterine motion data.

[0202] At block 556, the system 100 may perform fdtering and / or smoothing to further refine the uterine motion data. The resulting output may represent linear displacement measurements for the one or more IMUs. The linear displacement measurements represent a distance that the belly of the pregnant female moved from a previous position. For example, the displacement measurements described herein may be used to determine and depict a signal representation of deformation of the belly during uterine contractions. In some embodiments, additional measurements including tilt and rotation measurements with respect to the previous position may also be determined. The displacement, tilt, and rotation measurements may be determined by system 100 for each of the one or more IMUs capturing movement based measurements of the belly region. In some embodiments, outlier movement may be removed and / or corrective actions may be performed on data transformations by system 100.

[0203] At block 558, the system 100 may convert the determined displacement for the one or more axes. For example, the system 100 may convert the uterine motion data to displacement and velocity measurements for each of the axes of each of the IMUs capturing data from the belly surface of the pregnant female.

[0204] At block 560, the system 100 may combine the determined displacements. For example, each displacement measurement from a respective IMU may represent a distance of movement (e.g., belly deformation, muscle contraction, etc.) captured from a first time until a second time. The distances may be combined to result in a magnitude that may indicate a total distance for a particular movement.

[0205] FIG. 6A illustrates a pictorial 600 of an example use of the systems described herein to monitor uterine activity. As shown, an example patch 602 is attached to a belly 604 of a pregnant female. In some embodiments, the patch 602 may be an adhesive patch couplable to the belly of a woman (pregnant or non-pregnant). The patch 602 may include any or all of the monitoring system 100 including any combination of sensors described herein. For example, the patch 602 may include at least one IMU sensor representing three inertial signals providing 3-axis acceleration measurements. The captured signals may be provided to processor 336, which may utilize signal processing unit 300 to process and analyze (e.g., 606) the IMU signalsand extract (e.g., and / or generate representations of) uterine activity from such signals, as shown by uterine activity output 608. The graphed units of output 608 may include mmHG (“y”) over time (“x”) or a transformation with respect to a pressure measurement measured in mmHG (“y”) over time (“x”).

[0206] FIG. 6B illustrates a pictorial 650 of an example use of the systems described herein to monitor uterine activity. In this example, another example patch 652 is shown attached to a belly 654 of a pregnant female. The patch 652 may include any or all of the monitoring system 100 including any combination of sensors described herein. For example, the patch 652 may include at least one IMU sensor representing three inertial signals providing 3 -axis acceleration measurements and one or more electrodes for capturing EXG signals, for example. The captured signals may be provided to processor 336, which may utilize signal processing unit 300 to process and analyze (e.g., 656) the IMU signals and the EXG signals and extract (e.g., and / or generate representations of) uterine activity from such signals, as shown by uterine activity output 658. The graphed units of output 658 may include mmHG (“y”) over time (“x”) or a transformation with respect to a pressure measurement measured in mmHG (“y”) over time (“x”).

[0207] FIG. 7 is an example output 700 generated by the monitoring system. In this example, a strip of contractions 702, 704, and 706 are shown. Other outputs may indicate fetal kicks, labor progression, contraction timing, or the like. The graphed units of the signal shown in FIG. 7 may include mmHG (“y”) over time (“x”) or a transformation with respect to a pressure measurement measured in mmHG (“y”) over time (“x”).METHODS

[0208] FIG. 8 illustrates a flow diagram of an example process 800 for monitoring uterine activity. The process 800 functions to determine contraction information and belly deformation information from a plurality of biological signals including IMU sensor data, electrode sensor date, and / or other sensor data. The process 800 may be used for uterine monitoring, but can additionally, or alternatively, be used for any suitable applications, clinical or otherwise. The process 800 can be configured and / or adapted to function for any suitable surface monitoring technology for analyzing biological movements or function.

[0209] In some embodiments, process 800 is executed by one or more sensor module 102. In some embodiments, the process 800 is executed by monitoring system 100 using signals and data received from one or more sensor modules 102, or the like. For example, one or moresensor modules may determine contraction information, belly deformation information, movement data, or the like. The monitoring system 100 may perform any number of operations on such information / data to generate output representing uterine contractions and / or uterine activity signals.

[0210] The process 800 may be performed based on data obtained from a system including a processor (e.g., one or more processors 114 and / or one or more processors 336) and a sensor module 102 coupled to a belly region of a pregnant female. In some embodiments, the sensor module 102 may include one or more IMU sensors 120, one or more optional EHG sensors 122, one or more optional EMG sensors 124, one or more optional electrodes 126, one or more optional strain gauge sensors 128, or any combination thereof. In some embodiments, the process 800 may be performed in a cloud server, such as server 108 or another device such as smart phone device (e.g., computing device 104) or wearable device 302 in communication with the sensor module 102. In some embodiments, the processor 336 is communicatively coupled to the sensor module 102, the processor being configured to execute the instructions of blocks 802, 804, 806, and 808. In some embodiments, the process 800 may include generating postpartum hemorrhaging predictions utilizing one or more of the contraction detection techniques and data described herein.

[0211] At block 802, the process 800 includes acquiring inertial motion data from the sensor module. For example, the sensor module 102 (e.g., sensors 112) may sense data output by one or more sensors (e.g., at least one IMU, electrodes, EHG sensor, etc.) placed on a belly of a pregnant female. In some embodiments, the one or more sensors may include, one IMU, two or more IMUs (e.g., two IMUs; three IMUs; four IMUs; five IMUs; six IMUs; seven IMUs; eight IMUs; nine IMUs; ten IMUs, etc.). The inertial motion data may be captured and further analyzed by system 100. In some embodiments, the sensors may include one to nine IMUs coupled to the belly region and arranged according to a pattern. The pattern may be selected based at least in part on a gestational age of a fetus associated with the pregnant female, as described with reference to FIGS. 2A-2M. In some implementations, the pattern may be selected based on both the gestational age of the fetus and a body mass index of the pregnant female. In some embodiments, the pattern may be predefined or predetermined according to one or more of: maternal parameters, fetal parameters, prior measurements, or the like. The sensor module 102 may be held within or form a portion of: a patch, a belt, a strap, a band, a t- shirt, the elastic of a pair of pants, or other clothing or other wearable accessory.

[0212] In some embodiments, the pattern may be selected or determined based at least in part on a gestational age of a fetus associated with the pregnant female and / or a body mass index of the pregnant female. In some embodiments, the pattern may be selected or determined based at least in part on the body mass index of a non-pregnant female. In some embodiments, the at least one inertial measurement unit may be placed on the belly region of a pregnant female in a configuration that is based at least in part on a gestational age of a fetus associated with the female or a body mass index of the female.

[0213] At block 804, the process 800 includes processing the inertial motion data to differentiate uterine motion data from other physiological motion data. For example, the deformation analyzer 318 may determine which signal portions of the inertial motion data are generated by uterine movement and which signal portions of the inertial motion data are generated by maternal movement or other non-uterine initiated movement. To do so, the deformation analyzer 318 and / or other signal module of signal processing unit 300 may differentiate uterine motion data from other physiological motion data by decomposing the inertial motion data into a plurality of signals according to a determined source associated with generation of each respective portion of the inertial motion data. In some embodiments, the signal processing unit 300 may utilize ML models 328 and / or training data 310 to differentiate amongst signals in the inertial motion data. For example, the process 800 (e.g., using one or more sensor modules 102 and / or monitoring system 100) may determine particular signal sources associated with inertial motion data based on measured displacement and / or deformations captured by one or more sensor modules 102 placed on a body of a woman. In a non-limiting example, the system 100 may assess myometrium contorting and / or twisting to determine particular localized or global pressure changes measured by detecting displacements and / or deformations. At block 804, the process 800 includes generating, based on the uterine motion data, a uterine activity signal by transforming the uterine motion data from a first signal domain to a second signal domain, as described with reference to FIGS. 5A-5B. In some embodiments, transforming the uterine motion data from the first signal domain to the second signal domain includes: determining the non-uterine related movement in the uterine motion data, correcting the uterine motion data, aggregating the multidimensional uterine motion data into one-dimensional uterine motion data, and refining the corrected uterine motion data. Aggregating the multidimensional uterine motion data may include averaging, summing, summing with weight, anyway of measuring the displacement in the uterine motion data or the energy in the uterine motion data or the acceleration in the uterine motion data, using allmultidimensional signals from one or more IMUs (e.g., within one or more sensor modules 102).

[0214] At block 804, the process 800 includes generating, based on the generated uterine activity signal, an output representing at least one uterine contraction within the generated uterine activity signal and / or activity indicating a lack of uterine contraction, as described with reference to FIG. 6A, FIG. 6B, and FIG. 7.

[0215] In some embodiments, the process 500 further includes performing a data trust analysis during the monitoring. For example, the trust management unit 324 may perform trust analysis, as described with respect to FIG. 5 A. The signal processing unit 300 may use the data trust analysis to attenuate or amplify a portion of the generated uterine activity signal.

[0216] In some embodiments, the process 800 further includes detecting outlier portions within the inertial motion data, classifying each outlier portion according to movement source, and modifying the generated uterine activity signal based on the classifying. The classifying may include applying a label for each detected outlier portion. The labels may indicate a source for each outlier portion selected from: a pregnant female movement, a postpartum female movement, a female movement, a non-pregnant female movement, a belly deformation movement, a muscle movement, a placental movement, and / or a fetal movement.

[0217] In some embodiments, the process 800 further includes converting the generated uterine activity signal into a signal that emulates a TOCO signal representing the uterine activity or an EHG signal representing the uterine activity. In some embodiments, the process 800 may further include assessing postpartum contractions. For example, detecting postpartum contractions may include using one or more accelerometer and / or EHG signal (on separate or disparate sensor modules 102, for example).

[0218] The systems described herein may generate requisite warnings to protect the information contained in data accessed and / or stored by such systems in compliance with the Health Insurance Portability and Accountability Act (HIPAA) and / or the General Data Protection Regulation (GDPR). Accordingly, the systems and methods described herein provide compliance with HIPAA and / or GDPR, and other privacy requirements regarding patient medical data, or other personal information. For example, the processes described herein are executed in such a fashion to be HIPAA and / or GDPR compliant and requisite warnings are provided to protect the information contained in system 100 in compliance with HIPAA and / or GDPR.

[0219] FIG. 9 illustrates a flow diagram of an example process 900 for performing uterine activity monitoring in combination with a trust analysis. At block 1A, the process 900 may include performing the steps associated with block 504 (FIG. 5A), which includes at least change of position (COP) data 524, smoothing data 526, and outlier removal data 528. Output from block 1A is then provided as input to block IB and block 2A.

[0220] At block IB, the process 900 may include transforming raw IMU signals into a different space. For example, the system 100 may utilize signal processing unit 300 to convert each IMU signal from raw signals to a different space. The transformation may occur from a first signal domain to a second signal domain. In some embodiments, the transformation may assess angles and displacements associated with changes in the IMU signals and convert the raw data to displacement data to assess how a particular accelerometer sensor is moving over time. In some embodiments, the transformation may find a maximum displacement and rotation to maximize impact of a particular contraction by transforming from local coordinates into other coordinates. For example, the transformation generator 316 may transform pre- processed IMU data into a distance (i.e., displacement) measurement (e.g., in millimeters) and / or a rotation measurement to enable contraction assessment.

[0221] In block 1C, the transformations / combinations may be dynamically adjusted based on an objective function. The dynamic nature is shown as a two way arrow 902 allowing any statistical / signal information being fed into the objective function at block 1C from the COP data of block 3 A.

[0222] In block ID, the process 900 may include performing post-processing on the output from block 1C including any or all of inversion 530, smoothing 532, and / or outlier removal 534 (FIG. 5A). The inversion may account for IMU or other sensor data changes. Similar to the pre-processing block, the post-processing may include determining noise characteristics from outlier analysis or post smoothing functions. These signal changes could directly feed a probabilistic trust index. Additionally inversion calculations could inform quadrant rotation and other observed factors that bias the trust index. For example, particular orientations may be notoriously troublesome and the system 100 may include one or more rules to assign less weight to such signals taken during the orientations. The output of block ID may undergo modulation at block IE, similar to processes carried out by both blocks 510 and 512 (FIG. 5A). Block IE may also receive input from a bias / weight block 2D as well as the multi-state trust index calculation from block 3B.

[0223] In block 2A, raw IMU data may be received and / or preprocessed data (e.g., COP data output data, smoothing data, outlier removal data, etc.). The combination of data may be used to calculate a signal quality measure (e.g., one or more signal quality indicators). The signal quality indicators may be both pre-processing (e.g., block 2A) and post-processing (e.g., block 2C). This information may function as an input to the change of position (COP) detection block 3A and the multi-state trust index calculation block 3B. This information can be used to modify parameters associated with block 3A and / or block 3B. For example, a post signal quality indicator block 2C may receive raw transformed data from block ID (e.g., newly postprocessed data) to calculate the signal quality measure pre- and post-processing, which functions as an input into the multi-state trust index calculation block 3B and can be used to modify parameters.

[0224] In block 2D, the multi-state trust index may statically or dynamically tune a bias weight / parameter for input into the modulation block IE. The weighting / biasing can help tune the modulation output for either dynamic scaling based on prior processing block analysis and / or adjust baseline offset (i.e.. 20mmHg, etc.).’

[0225] In block 3 A, multiple processing steps may be spanned in the pipeline of process 900 because different changes of positions may have impact across pre-processing / transformation and / or the objective function. The feedback from block 3 A may assist the objective function for determining a best transformation respective to a particular COP.

[0226] In block 3B, the processes ofblocks 516, 518, 520, and 522 (FIG. 5A) may be carried out in a single block. Output from block 3B may be provided back to the modulation block IE through a bias / weighting block. Some embodiments may have the bias / weighting block acting as a simple pass-thru for the multi-state trust index. Another modification to block 3B may include having the index be indicative of multiple states being seen in the uterine activity. For example, a contraction state, a rest period, a refractory period, a Braxton-Hicks episode, stages of labor, postpartum periods, reproductive periods, etc.

[0227] FIG. 10 illustrates a flow diagram of an example process 1000 for generating a uterine activity trace 1002 based on at least one accelerometer or IMU signals (e.g., from 3-axes accelerometer 1004). Signals from one or more three-axes accelerometers may be received at block 1006. Block 1006 may function to remove change of positions from the signal(s). The modified data from block 1006 may be provided to block 1008 to highlight deviations in orientations from baseline cross product signals with baseline signals and / or computation of baseline signals using a moving median filter. Output from block 1008 may be provided toblock 1010 to reverse negative contraction signals, which may be provided to block 1012 to combine axis data and compute Euclidian normalizations on the received signal. Output from block 1012 may be provided to block 1014 to remove a mean from the signal, which may be provided to block 1016 to scale the signal by a fixed gain and shift the scaled signal by a fixed baseline.

[0228] The systems and methods of the embodiments described herein and variations thereof can be embodied and / or implemented at least in part as a machine configured to receive a computer-readable medium storing computer-readable instructions. The instructions are executed by computer-executable components integrated with the system and one or more portions of the processor on the sensor module 102 and / or computing devices 104 and / or 108. The computer-readable medium can be stored on any suitable computer-readable media such as RAMs, ROMs, flash memory, EEPROMs, optical devices (e.g., CD or DVD), hard drives, floppy drives, or any suitable device. The computer-executable component may be a general or application-specific processor, but any suitable dedicated hardware or hardware / firmware combination can alternatively or additionally execute the instructions.

[0229] References to an IMU or IMU sensor may refer to a one -dimension, two-dimension, or 3-dimension accelerometer, a one-dimension, two-dimension, or 3-dimension, gyroscope, one-dimension, two-dimension, or 3-dimension magnetometer, or any combination thereof.

[0230] References in the specification to “one embodiment,” “an embodiment,” “an illustrative embodiment,” “some embodiments,” etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may or may not necessarily include that particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to effect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0231] As used in the description and claims, the singular form “a”, “an” and “the” include both singular and plural references unless the context clearly dictates otherwise. For example, the term “sensor” may include, and is contemplated to include, a plurality of sensors. At times, the claims and disclosure may include terms such as “a plurality,” “one or more,” or “at least one;” however, the absence of such terms is not intended to mean, and should not be interpreted to mean, that a plurality is not conceived.

[0232] The term “about” or “approximately,” when used before a numerical designation or range (e.g., to define a length or pressure), indicates approximations which may vary by ( + ) or ( - ) 5%, 1% or 0. 1%. All numerical ranges provided herein are inclusive of the stated start and end numbers. The term “substantially” indicates mostly (i.e., greater than 50%) or essentially all of a device, substance, or composition.

[0233] As used herein, the term “comprising” or “comprises” is intended to mean that the devices, systems, and methods include the recited elements, and may additionally include any other elements. “Consisting essentially of’ shall mean that the devices, systems, and methods include the recited elements and exclude other elements of essential significance to the combination for the stated purpose. Thus, a system or method consisting essentially of the elements as defined herein would not exclude other materials, features, or steps that do not materially affect the basic and novel characteristic(s) of the claimed disclosure. “Consisting of’ shall mean that the devices, systems, and methods include the recited elements and exclude anything more than a trivial or inconsequential element or step. Embodiments defined by each of these transitional terms are within the scope of this disclosure.

[0234] The examples and illustrations included herein show, by way of illustration and not of limitation, specific embodiments in which the subject matter may be practiced. Other embodiments may be utilized and derived therefrom, such that structural and logical substitutions and changes may be made without departing from the scope of this disclosure. Such embodiments of the inventive subject matter may be referred to herein individually or collectively by the term “invention” merely for convenience and without intending to voluntarily limit the scope of this application to any single invention or inventive concept, if more than one is in fact disclosed. Thus, although specific embodiments have been illustrated and described herein, any arrangement calculated to achieve the same purpose may be substituted for the specific embodiments shown. This disclosure is intended to cover any and all adaptations or variations of various embodiments. Combinations of the above embodiments, and other embodiments not specifically described herein, will be apparent to those of skill in the art upon reviewing the above description.

Claims

WHAT IS CLAIMED IS:

1. A system for monitoring uterine activity, the system comprising: a sensor module coupled to a belly region of a female, the sensor module including at least one inertial measurement unit; a processor communicatively coupled to the sensor module, the processor being configured to execute instructions comprising: acquiring inertial motion data from the sensor module; processing the inertial motion data to differentiate uterine motion data from other physiological motion data; generating, based on the uterine motion data, a uterine activity signal by transforming the uterine motion data from a first signal domain to a second signal domain; and generating, based on the generated uterine activity signal, an output representing at least one uterine contraction within the generated uterine activity signal or activity indicating a lack of uterine contraction.

2. The system of claim 1, wherein transforming the uterine motion data from the first signal domain to the second signal domain comprises: determining, in the uterine motion data, a plurality of angles between axes defined by the at least one inertial measurement unit; correcting the uterine motion data; refining the corrected uterine motion data; converting the corrected uterine motion data to identify at least two displacement measurements according to the axes; and combining the at least two displacement measurements.

3. The system of claim 1, wherein differentiating uterine motion data from other physiological motion data comprises: decomposing the inertial motion data into a plurality of signals based on a determined source associated with generation of each portion of the inertial motion data.

4. The system of claim 1, wherein the instructions further comprise: performing a data trust analysis during the monitoring; and using the data trust analysis to attenuate or amplify a portion of the generated uterine activity signal.

5. The system of claim 1, wherein the instructions further comprise: classifying the output as one of: a non-pregnant contraction, an antepartum contraction, an intrapartum contraction, a postpartum contraction, a Braxton-Hicks contraction, or a state of no contraction; performing a data trust analysis during the monitoring; and using the data trust analysis to determine an accuracy likelihood of the classifying of the output; and6. The system of claim 5, wherein the instructions further comprise generating an output indicating the accuracy likelihood.

7. The system of claim 1, wherein the at least one inertial measurement unit comprises two or more inertial measurement units coupled to the belly region and arranged according to a pattern.

8. The system of claim 7, wherein the pattern is selected based at least in part on a gestational age of a fetus associated with the female and a body mass index of the female, wherein the female is pregnant.

9. The system of claim 1, where the at least one inertial measurement unit is placed on the belly region in a configuration that is based at least in part on a gestational age of a fetus associ ted with the female or a body mass index of the female.

10. The system of claim 1, wherein the instructions further comprise: detecting outlier portions within the inertial motion data; classifying each outlier portion according to movement source; and modifying the generated uterine activity signal based on the classifying.

11. The system of claim 10, wherein the classifying applies a label for each detected outlier portion, the labels indicating a source for each outlier portion selected from: a pregnant female movement, a postpartum female movement, a non-pregnant female movement, a belly deformation movement, a muscle movement, a placental movement, and a fetal movement.

12. The system of claim 1, wherein the instructions further comprise converting the generated uterine activity signal into a signal that emulates a tocography signal representing the uterine activity or an electrohysterography signal representing the uterine activity.

13. The system of claim 1, wherein the sensor module is held within or forms a portion of: a patch, a belt, a strap, a band, a t-shirt, elastic of a pair of pants, or other clothing or other wearable accessory.

14. A computer-implemented method for monitoring uterine activity, the method comprising: providing at least one motion sensor module coupled to a belly region of a female, the sensor module including at least one inertial measurement unit; providing a processor communicatively coupled to the at least one sensor module, the processor being configured to execute instructions comprising: acquiring inertial motion data from the sensor module; processing the inertial motion data to differentiate uterine motion data from other physiological motion data; generating, based on the uterine motion data, a uterine activity signal by transforming the uterine motion data from a first signal domain to a second signal domain; and generating, based on the generated uterine activity signal, an output representing at least one uterine contraction within the generated uterine activity signal or activity indicating a lack of uterine contraction.

15. The computer-implemented method of claim 14, wherein transforming the uterine motion data from the first signal domain to the second signal domain comprises: determining, in the uterine motion data, a plurality of angles between axes defined bythe at least one inertial measurement unit; correcting the uterine motion data; refining the corrected uterine motion data; converting the corrected uterine motion data to identify at least two displacement measurements according to the axes; and combining the at least two displacement measurements.

16. The computer-implemented method of claim 14, wherein differentiating uterine motion data from other physiological motion data comprises: decomposing the inertial motion data into a plurality of signals based on a determined source associated with generation of each portion of the inertial motion data.

17. The computer-implemented method of claim 14, wherein the instructions further comprise: performing a data trust analysis during the monitoring; and using the data trust analysis to attenuate or amplify a portion of the generated uterine activity signal.

18. The computer-implemented method of claim 14, wherein the instructions further comprise: classifying the output as one of: a non-pregnant contraction, an antepartum contraction, an intrapartum contraction, a postpartum contraction, a Braxton-Hicks contraction, or a state of no contraction; performing a data trust analysis during the monitoring; and using the data trust analysis to determine an accuracy likelihood of the classifying of the output; and19. The computer-implemented method of claim 18, wherein the instructions further comprise generating an output indicating the accuracy likelihood.

20. The computer-implemented method of claim 14, wherein the at least one inertial measurement unit comprises one or more inertial measurement units coupled to the bellyregion and arranged according to a pattern.

21. The computer-implemented method of claim 20, wherein the pattern is selected based at least in part on a gestational age of a fetus associated with the female and a body mass index of the female, wherein the female is pregnant.

22. The computer-implemented method of claim 14, where the at least one inertial measurement unit is placed on the belly region in a configuration that is based at least in part on a gestational age of a fetus associated with the female or a body mass index of the female.

23. The computer-implemented method of claim 14, wherein the instructions further comprise: detecting outlier portions within the inertial motion data; classifying each outlier portion according to movement source; and modifying the generated uterine activity signal based on the classifying.

24. The computer-implemented method of claim 23, wherein the classifying applies a label for each detected outlier portion, the labels indicating a source for each outlier portion selected from: a pregnant female movement, a postpartum female movement, a non-pregnant female movement, a belly deformation movement, a muscle movement, a placental movement, and a fetal movement.

25. The computer-implemented method of claim 14, wherein the instructions further comprise: converting the generated uterine activity signal into a signal that emulates a tocography signal representing the uterine activity or an electrohysterography signal representing the uterine activity.

26. The computer-implemented method of claim 14, wherein the sensor module is held within or forms a portion of: a patch, a belt, a strap, a band, a t-shirt, elastic of a pair of pants, or other clothing or other wearable accessory.

1. A non-transitory computer-readable medium for monitoring uterine activity comprising instructions that, when executed by at least one processor, cause the at least oneprocessor to perform operations comprising: receiving inertial motion data from a sensor module, wherein the sensor module includes at least one inertial measurement unit; processing the inertial motion data to differentiate uterine motion data from other physiological motion data; generating, based on the uterine motion data, a uterine activity signal by transforming the uterine motion data from a first signal domain to a second signal domain; and generating, based on the generated uterine activity signal, an output representing at least one uterine contraction within the generated uterine activity signal or activity indicating a lack of uterine contraction.

28. The non-transitory computer-readable medium of claim 27, wherein transforming the uterine motion data from the first signal domain to the second signal domain comprises: determining, in the uterine motion data, a plurality of angles between axes defined by the at least one inertial measurement unit; correcting the uterine motion data; refining the corrected uterine motion data; converting the corrected uterine motion data to identify at least two displacement measurements according to the axes; and combining the at least two displacement measurements.

29. The non-transitory computer-readable medium of claim 27, wherein differentiating uterine motion data from other physiological motion data comprises: decomposing the inertial motion data into a plurality of signals based on a determined source associated with generation of each portion of the inertial motion data.

30. The non-transitory computer-readable medium of claim 27, wherein the operations further comprise: performing a data trust analysis during the monitoring; and using the data trust analysis to attenuate or amplify a portion of the generated uterine activity signal.

31. The non-transitory computer-readable medium of claim 27, wherein the instructions further comprise: classifying the output as one of: a non-pregnant contraction, an antepartum contraction, an intrapartum contraction, a postpartum contraction, a Braxton-Hicks contraction, or a state of no contraction; performing a data trust analysis during the monitoring; and using the data trust analysis to determine an accuracy likelihood of the classifying of the output; and32. The non-transitory computer-readable medium of claim 31, wherein the instructions further comprise generating an output indicating the accuracy likelihood.

33. The non-transitory computer-readable medium of claim 27, wherein the at least one inertial measurement unit comprises one or more inertial measurement units coupled to a belly region of a female and arranged according to a pattern.

34. The non-transitory computer-readable medium of claim 33, wherein the pattern is selected based at least in part on a gestational age of a fetus associated with the female and a body mass index of the female, wherein the female is pregnant.

35. The non-transitory computer-readable medium of claim 27, wherein the operations further comprise: detecting outlier portions within the inertial motion data; classifying each outlier portion according to movement source; and modifying the generated uterine activity signal based on the classifying.

36. The non-transitory computer-readable medium of claim 35, wherein the classifying applies a label for each detected outlier portion, the labels indicating a source for each outlier portion selected from: a pregnant female movement, a postpartum female movement, a non- pregnant female movement, a belly deformation movement, a muscle movement, a placental movement, and a fetal movement.

37. The non-transitory computer-readable medium of claim 27, wherein the operations further comprise converting the generated uterine activity signal into a signal that emulates a tocography signal representing the uterine activity or an electrohysterography signal representing the uterine activity.

38. The non-transitory computer-readable medium of claim 27, wherein the sensor module is held within or forms a portion of: a patch, a belt, a strap, a band, a t-shirt, elastic of a pair of pants, or other clothing or other wearable accessory.

Images