An artificial intelligence (AI)-integrated childbirth assisting and training system

Abstract

An Artificial intelligence (AI)-integrated childbirth assisting and training system has been developed. The exemplary AI-integrated exoskeleton childbirth-assisting system comprises a passive force transmission assembly to amplify hand grip force, wherein the system is designed to operate without external motorized power source, utilizing a user's natural mechanobiological forces to achieve the precision, delicacy, and safety required for childbirth maneuvers; A plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor; an AI-driven advisory system for real-time force modulation and feedback; and a built-in augmented reality (AR) interface providing a visual guidance and biomechanical data during a childbirth maneuver. wherein the system is further configured to digitize and quantify childbirth maneuvers, enabling real-time feedback for practitioners.

Description

An Artificial intelligence (AI)-integrated childbirth assisting and training system

[0001] The present disclosure application claims priority from United States Patent and Trademark Office No. 63 / 848,822, filed on 22 July 2025, entitled "An Artificial intelligence (AI)-integrated childbirth assisting and training system", which is incorporated by reference herein in its entirety.

[0002] The present invention relates to an AI-integrated exoskeleton system for childbirth assistance, particularly designed to support obstructed childbirth cases while also serving as a training tool for obstetric procedures.

[0003] Natural childbirth, as one of the most complex biological processes, requires precise and delicate maneuvers by midwives or obstetricians. However, traditional methods primarily rely on the physical abilities, experience, and individual judgment of the practitioner, with no precise auxiliary tools to measure and control applied forces. This can lead to human errors, maternal or neonatal tissue damage, and inconsistent care quality. Recent advances in soft robotics and medical exoskeletons, inspired by biological structures and using flexible materials, enable enhanced hand strength and improved movement precision. These technologies have found broad applications in minimally invasive surgery and limb rehabilitation. Passive exoskeletons and mechanical force transmission systems, without external motors, use cables, pulleys, and levers to amplify manual force while preserving tactile feedback. Given the critical role of midwives and specialists in childbirth, designing systems to reduce muscle fatigue and weakness while maximizing the utilization of their expertise is essential. Such technologies can standardize care quality by maintaining tactile sensitivity and precision, preventing experienced professionals from leaving due to physical strain. Passive mechanical force transmission approaches can provide the necessary power for safer, more accurate maneuvers during delivery.

[0004] Recent advances in sensing technologies (e.g., force, pressure, and angle sensors) enable real-time monitoring of biomechanical data during childbirth. Coupled with AI, this data can provide immediate feedback and personalized recommendations to midwives. Machine learning models can identify optimal force patterns and issue warnings if deviations occur. Augmented reality (AR) and digital simulators further enhance training by allowing midwifery students to practice maneuvers in a controlled environment, with real-time visual guidance reducing errors. However, challenges persist in force control, tactile feedback, and adaptation to diverse maternal anatomies.

[0005] Existing tools like vacuum extractors and forceps (e.g., GB2485967A, EP1638478B1) mitigate physical strain but lack integrated sensors to quantify forces or angles. For instance, forceps with pull-sensing grips alert users to excessive force but fail to generate actionable data for analysis or training. Hydrogel-based devices (e.g., GB2615312A) improve lubrication but offer no feedback on maneuver execution. These tools operate in isolation, unable to log traction patterns or simulate scenarios for trainees, perpetuating reliance on subjective mentorship and hindering standardized training.

[0006] Wearable robotics, such as exoskeletons used in rehabilitation, demonstrate how mechanized assistance can enhance human precision while capturing kinematic data. In obstetrics, such systems could translate a midwife’s movements into calibrated forces, digitizing maneuvers (e.g., force vectors, fetal descent rates) for real-time AI analysis. This data could provide clinicians with corrective feedback and create anonymized datasets for training modules. Students could practice in immersive simulations, benchmarking their technique against evidence-based standards—addressing gaps in current apprenticeship models.

[0007] Current devices like vacuum extractors and forceps are static, offering no feedback loops for technique refinement. Hydrogel devices, while innovative, cannot adapt to variable fetal positions or document outcomes. These limitations are acute in training, where students need iterative feedback to master maneuvers like Rubin or McRoberts techniques. The absence of reproducible scenarios also limits preparedness for rare emergencies (e.g., shoulder dystocia), underscoring the need for dynamic, data-driven tools.

[0008] An AI-integrated exoskeleton system could unify human expertise with robotic precision. Sensors would track grip strength, traction angles, and fetal descent velocity, while AI adjusts assistive forces and generates procedural summaries. For training, a "digital twin" feature could reconstruct deliveries in virtual reality, enabling post-hoc analysis. The exoskeleton’s ergonomic design would reduce midwife fatigue, and predictive models could preempt high-risk scenarios. By quantifying intangible skills and standardizing protocols, this system bridges the gap between theory and practice, transforming obstetrics and midwifery education.

[0009] This summary is intended to provide an overview of the subject matter of this disclosure, and is not intended to identify essential elements or key elements of the subject matter, nor is it intended to be used to determine the scope of the claimed implementations. The proper scope of this disclosure may be ascertained from the claims set forth below in view of the detailed description below and the drawings.

[0010] In a general aspect, the present disclosure is directed to an exemplary Artificial intelligence (AI)-integrated childbirth assisting and training system. The exemplary AI-integrated childbirth assisting and training system may comprise A passive force transmission assembly to amplify a hand grip force, wherein the assembly configured to operate under a manual human control without an external motorized power source, utilizing a user's natural mechanobiological forces to assist in fetal extraction from a birth canal; A plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor; an AI-driven advisory system configured to suggest real-time force modulation, feedback, and recommendations, including predictive alerts based on biomechanical patterns, detection of abnormal force applications, and identification of potential risks during fetal extraction; wherein the system continuously learns from aggregated and anonymized childbirth data to improve decision support accuracy over time, and concurrently contributes to the development of a centralized big data repository intended for future clinical research, practitioner education, and refinement of obstetric techniques; all while ensuring that operational decisions and actions remain under the direct authority and discretion of a midwife or a practitioner; a built-in augmented reality (AR) interface providing a visual guidance and biomechanical data during childbirth maneuver; An embedded educational module for training midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees through a simulated childbirth scenario and analysis of historical procedure data; and a coordinated control architecture integrating components (a) through (e), configured to ensure fine-tuned biomechanical precision and safety during assisted delivery maneuvers, by dynamically modulating force application, monitoring tissue interaction parameters, and enabling practitioner-supervised, low-risk extraction of the fetus while minimizing mechanical trauma to neonatal structures; wherein the system is configured to digitize and quantify the childbirth maneuver for the practitioner review and an educational purpose, operate under a full human oversight with no autonomous machine control, and enable selective utilization of components (a), (b), (c), (d), and (e) only when explicitly authorized by the midwife or the practitioner based on situational necessity.

[0011] In an exemplary implementation, the passive force transmission assembly may comprise an exoskeleton structure comprises a plurality of interconnected pulleys and levers configured to amplify the hand grip force, while preserving tactile feedback via a plurality of low-friction cables interlinking the pulleys and levers.

[0012] In an exemplary implementation, the exoskeleton structure may comprise a plurality of adjustable straps and a plurality of support elements configured to be securely fastened between a shoulder and an elbow region of a user, thereby minimizing obstruction and ensuring unrestricted movement during the childbirth maneuver.

[0013] In an exemplary implementation, the exoskeleton structure may comprises at least one lightweight, cost-effective composite material selected from materials including glass fiber-reinforced polypropylene, recycled carbon fiber-polyamide composites, cellulose-reinforced thermoplastic polyurethane and other polymers with comparable mechanical properties and medical-grade sterilizability, wherein said material provides an optimal balance of ergonomic flexibility, force transmission capability, and clinical durability while maintaining cost efficiency for disposable or reusable applications in obstetric settings.

[0014] In an exemplary implementation, the exoskeleton structure may comprise a plurality of actuators providing a controlled assistance for the childbirth maneuver, wherein the actuators are integrated into the exoskeleton structure and are configured to generate a controlled mechanical force to support and facilitate the childbirth maneuver

[0015] In an exemplary implementation, the exoskeleton structure may comprise a lower limb-driven force augmentation system configured to capture a mechanical energy from a user’s lower limb muscles and transfer it to the exoskeleton to amplify the hand grip force during the childbirth maneuver.

[0016] The above general aspect may have one or more of the following features. In an exemplary implementation, the lower limb-driven force augmentation system comprises a pneumatic actuator or a spring-based actuator configured to store the mechanical energy generated by an ankle dorsiflexion, a knee extension, or a posterior leg muscle contraction. In an exemplary implementation, the lower limb-driven force augmentation system utilizes a force-controlled cable transmission system to transfer the stored mechanical energy to the exoskeleton.

[0017] In an exemplary implementation, the plurality of sensors may integrate into a glove.

[0018] In an exemplary implementation, the plurality of sensors may wirelessly connect to the AI-driven advisory system, enabling real-time data transmission without obstructing the practitioner movement.

[0019] In an exemplary implementation, the AI-driven advisory system may monitor the applied force via the plurality of sensor, compares them with historical optimal ranges, and issue the practitioner alerts when a deviation occurs.

[0020] In an exemplary implementation, The exemplary AI-driven advisory system is developed using a dataset that includes maternal biometric parameters (weight, pelvic dimensions, medical history), fetal biometric parameters (estimated weight, positioning), contextual metadata (ethnicity, gestational age, childbirth progression metrics), and additional data points (maternal oxygen saturation, uterine activity, fetal heart rate variability), which are analyzed to provide personalized guidance and optimize the childbirth maneuver.

[0021] In an exemplary implementation, the AI-driven advisory system may employ a machine learning model trained on historical childbirth maneuver data.

[0022] In an exemplary implementation, the AR interface may comprise an interactive AR display unit supporting a visual control, a voice control, a haptic input control, or a combination thereof, configured to dynamically render real-time biomechanical data including applied force, and joint angles while providing context-aware procedural guidance including fetal extraction vectors or overpressure alerts that auto-adapts to operator skill level and childbirth complexity wherein the AR interface synergizes with the plurality of sensors and the AI-driven advisory system to enable AR-simulated practice scenarios with live feedback, all outputs remaining under full supervisory control of the attending midwife or obstetrician.

[0023] In an exemplary implementation, The AR interface is configured as an adaptive training module for midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees and comprises a virtual patient simulator dynamically responsive to applied forces and maneuvers, replicating biomechanical behaviors of maternal and fetal anatomy during childbirth.

[0024] In an exemplary implementation, The AI-integrated childbirth assisting and training system may further comprise a feedback mechanism selected from the group comprising a visual feedback mechanism, an auditory feedback mechanism, a haptic feedback mechanism, or a combination thereof, wherein said feedback mechanism is integrated with the passive force transmission assembly and configured to alert the practitioner when an applied force exceed a predetermined threshold.

[0025] In an exemplary implementation, The AI-integrated childbirth assisting and training system may further comprise a smart garment worn by the mother, embedded with a plurality of sensors to monitor uterine contractions and pelvic alignment, wirelessly transmitting data to the AI system for real-time correlation with the practitioner maneuvers, while at least one AR marker on the garment project maternal anatomical guidance onto the practitioner’s interface.

[0026] In an exemplary implementation, the present disclosure is directed to an exemplary AI-integrated childbirth assisting and training device. The exemplary AI-integrated childbirth assisting and training device may comprise a passive force transmission assembly to amplify a hand grip force, wherein the assembly configured to operate under a manual human control without an external motorized power source, utilizing a user's natural mechanobiological forces to assist in fetal extraction from the birth canal; a plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor; an AI-driven advisory system configured to suggest real-time force modulation, feedback, and recommendations, including predictive alerts based on biomechanical patterns, detection of abnormal force applications, and identification of potential risks during fetal extraction; wherein the system continuously learns from aggregated and anonymized childbirth data to improve decision support accuracy over time, and concurrently contributes to the development of a centralized big data repository intended for future clinical research, practitioner education, and refinement of obstetric techniques; all while ensuring that operational decisions and actions remain under the direct authority and discretion of a midwife or a practitioner; a built-in augmented reality (AR) interface providing a visual guidance and biomechanical data during a childbirth maneuvers; an embedded educational module for training midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees through a simulated childbirth scenarios and analysis of historical procedure data; and a coordinated control architecture integrating components (a) through (e), configured to ensure fine-tuned biomechanical precision and safety during assisted delivery maneuvers, by dynamically modulating force application, monitoring tissue interaction parameters, and enabling practitioner-supervised, low-risk extraction of the fetus while minimizing mechanical trauma to neonatal structures.

[0027] In an exemplary implementation, the present disclosure is directed to an exemplary method for performing and training AI-integrated childbirth assisting maneuvers using the AI-integrated childbirth assisting and training system. The exemplary method may comprise a) positioning a practitioner's or a trainee's hand correctly under a fetal head during an actual or a simulated childbirth; b) passively capturing a mechanical energy from the practitioner's or the trainee's ankle flexion, knee motion, or posterior leg muscle contractions via a passive force transmission assembly, wherein the assembly transfers the captured mechanical energy to a spring-based or a pneumatic actuator to amplify a hand grip force without an external motorized power source; c) applying the amplified hand grip force under a manual human control to provide a controlled assistance during the childbirth maneuvers; d) monitoring, via a plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor, and transmitting data to a AI-driven advisory system and a built-in AR interface for real-time feedback and a guidance; e) adjusting the hand orientation and the applied force based on the practitioner's or the trainee's expertise level and the AI-driven advisory system's recommendations, while maintaining full human oversight to safely deliver the fetus from the birth canal or execute a training scenario; and f) recording the maneuver data for the AI training, real-time feedback, and structured educational assessment, wherein all operational decisions remain under the direct authority of the supervising practitioner.

[0028] The drawing figure only demonstrates one or more embodiments in accordance with the present teaching, by way of example only, not by way of limitation. Therefore, the drawing figure does not limit the extent of the present disclosure. Also, reference numerals with similar numbers in the figures demonstrate similar or the same elements.Fig.1

[0029] illustrates a schematic overview of an exemplary AI-integrated childbirth assisting and training system, consistent with one or more exemplary embodiments of the present disclosure.Fig.2a

[0030] illustrates an isometric view of an exemplary exoskeleton structure being worn by a user, consistent with one or more exemplary embodiments of the present disclosure.Fig.2b

[0031] illustrates an isometric view of an exemplary exoskeleton structure, consistent with one or more exemplary embodiments of the present disclosure.Fig.3

[0032] illustrates a schematic view of an exemplary glove, consistent with one or more exemplary embodiments of the present disclosure.Fig.4

[0033] illustrates a schematic overview of an exemplary AI-integrated childbirth assisting and training device consistent with one or more exemplary embodiments of the present disclosure.Fig.5

[0034] illustrates a flowchart of an exemplary method for performing and training AI-integrated childbirth assisting maneuvers using the exemplary AI-integrated childbirth assisting and training system, consistent with one or more exemplary embodiments of the present disclosure.

[0035] The following detailed description is presented to enable a person skilled in the art to make and use the processes and devices disclosed in exemplary embodiments of the present disclosure. For purposes of explanation, specific nomenclature is set forth provide a thorough understanding of the present disclosure. However, it will be apparent to one skilled in the art that these specific details are not required to practice the disclosed exemplary embodiments. Descriptions of specific exemplary embodiments are provided only as representative examples. Various modifications to the exemplary implementations will be readily apparent to one skilled in the art, and the general principles defined herein may be applied to other implementations and applications without departing from the scope of the present disclosure. The present disclosure is not intended to be limited to the implementations shown, but is to be accorded the widest possible scope consistent with the principles and features disclosed herein.

[0036] The present disclosure describes an exemplary AI-integrated childbirth assisting and training system. The system may comprise a passive force transmission assembly to amplify a hand grip force, wherein the assembly is configured to operate under a manual human control without an external motorized power source, utilizing a user's natural mechanobiological forces to assist in fetal extraction from a birth canal; a plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor; an AI-driven advisory system configured to suggest real-time force modulation, feedback, and recommendations, including predictive alerts based on biomechanical patterns, detection of abnormal force applications, and identification of potential risks during fetal extraction; wherein the system continuously learns from aggregated and anonymized childbirth data to improve decision support accuracy over time, and concurrently contributes to the development of a centralized big data repository intended for future clinical research, practitioner education, and refinement of obstetric techniques; all while ensuring that operational decisions and actions remain under the direct authority and discretion of a midwife or a practitioner; a built-in augmented reality (AR) interface providing a visual guidance and biomechanical data during childbirth maneuver; An embedded educational module for training midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees through a simulated childbirth scenario and analysis of historical procedure data; and a coordinated control architecture integrating components (a) through (e), configured to ensure fine-tuned biomechanical precision and safety during assisted delivery maneuvers, by dynamically modulating force application, monitoring tissue interaction parameters, and enabling practitioner-supervised, low-risk extraction of the fetus while minimizing mechanical trauma to neonatal structures;. wherein the system is configured to digitize and quantify the childbirth maneuver for the practitioner review and an educational purpose, operate under a full human oversight with no autonomous machine control, and enable selective utilization of components (a), (b), (c), (d), and (e) only when explicitly authorized by the midwife or the practitioner based on situational necessity.

[0037] Some benefits of using the exemplary AI-integrated childbirth assisting and training system, as described in the present disclosure, compared to conventional childbirth assisting and training systems, may include, but are not limited to, improved delivery safety and precision through real-time biomechanical monitoring, AI-driven adjustments, and AR / VR simulations. It continuously tracks force, pressure, and fetal positioning to optimize maneuvers and prevent injuries, with multi-sensory alerts (visual / auditory / haptic) warning of unsafe deviations. Machine learning algorithms, trained on clinical datasets, provide probabilistic guidance for complex scenarios like shoulder dystocia, particularly aiding less-experienced practitioners in low-resource settings. For education, the system offers a risk-free, adaptive training environment with realistic simulations, instant corrective feedback, and competency-based assessments, allowing trainees to practice indefinitely on hybrid physical-digital models. Adaptive learning personalizes modules based on progress, while tele-education connects learners with global experts. By combining intelligent assistance with ergonomic design, the system reduces obstetric complications, standardizes training quality, and bridges skill gaps between advanced and underserved medical centers, potentially transforming global maternal care. In modern obstetric technologies, the ethical collection and usage of physiological and procedural data during childbirth maneuvers remains a critical consideration. The proposed system is designed to comply with established medical data ethics, ensuring that all captured information is anonymized, securely stored, and processed only with explicit consent. Beyond clinical applications, the digitized sensory and biomechanical data may also serve an additional human-centered purpose: enabling avatar-based visualization of the birth process. Such representations, developed under strict ethical oversight, can offer a meaningful, respectful, and emotionally resonant record of the childbirth experience, intended as a digital memory for the mother and child. This dual-purpose approach aligns clinical utility with emotional value, while maintaining rigorous ethical standards throughout data handling and presentation.

[0038] Conventional childbirth assisting tools like forceps and vacuum extractors present several limitations. They rely heavily on practitioner skill, with inexperienced users having higher complication rates (e.g., 3x more neonatal injuries). Static designs cannot adapt force application to real-time maternal-fetal biomechanics, risking tissue trauma from excessive traction. They lack integrated feedback systems, preventing early detection of unsafe force thresholds (>100N). Motorized robotic systems introduce latency (200-500ms delays) and remove tactile feedback critical for delicate maneuvers. Disposable variants (e.g., plastic vacuum cups) often fail under high-load scenarios (15-20% detachment rates). Most tools address only fetal extraction without supporting concurrent maternal positioning or fatigue management during prolonged childbirth.

[0039] In contrast, the exemplary AI-integrated childbirth assisting and training system overcomes these limitations by Reducing skill dependency through real-time AR guidance and AI-powered force recommendations, narrowing the performance gap between novice and expert practitioners; Dynamically adapting force application via continuous sensor monitoring of maternal-fetal biomechanics, preventing tissue trauma through micro-adjustments; Providing multi-sensory feedback (visual / haptic / auditory alerts) when forces approach unsafe thresholds, enabling immediate correction; Preserving tactile sensitivity via passive force transmission (non-motorized) while eliminating robotic system delays; Ensuring mechanical reliability through reinforced, sterilizable exoskeleton materials tested to withstand 3x typical delivery forces; Addressing holistic delivery challenges by simultaneously mitigating practitioner fatigue (via ergonomic support) and optimizing maternal positioning through integrated AR postural guidance. Additionally, the system serves as an advanced training platform, offering risk-free, adaptive simulations with real-time corrective feedback for midwifery students. Through AI-driven competency assessments and personalized learning modules, it standardizes education quality, reduces reliance on live patient training, and bridges skill gaps between high- and low-resource medical settings.

[0040] In an exemplary embodiment, aspects and features of an exemplary AI-integrated childbirth assisting and training system, an exemplary AI-integrated childbirth assisting and training device, and an exemplary method for performing and training AI-integrated childbirth assisting maneuvers using the AI-integrated childbirth assisting and training system will be described in greater detail, below.

[0041] An AI-integrated childbirth assisting and training system

[0042] To address the challenges of traditional childbirth-assisting systems, enhance maternal and neonatal safety, reduce midwives' muscle fatigue and weakness, and digitize childbirth maneuvers for therapeutic and educational purposes, the design and development of an AI-integrated childbirth assisting and training system is imperative. In a general aspect, the present disclosure is directed to an exemplary Artificial intelligence (AI)-integrated childbirth assisting and training system.illustrates a block diagram of an exemplary AI-integrated childbirth assisting and training system, consistent with one or more exemplary embodiments of the present disclosure. The exemplary AI-integrated childbirth assisting and training system100comprises a) a passive force transmission assembly101to amplify a hand grip force, wherein the assembly configured to operate under a manual human control without an external motorized power source, utilizing a user's natural mechanobiological forces to assist in fetal extraction from a birth canal; b) a plurality of sensors102including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor, provide real-time biomechanical data monitoring; c) an AI-driven advisory system103configured to suggest real-time force modulation, feedback, and recommendations, including predictive alerts based on biomechanical patterns, detection of abnormal force applications, and identification of potential risks during fetal extraction; wherein the system continuously learns from aggregated and anonymized childbirth data to improve decision support accuracy over time, and concurrently contributes to the development of a centralized big data repository intended for future clinical research, practitioner education, and refinement of obstetric techniques; all while ensuring that operational decisions and actions remain under the direct authority and discretion of a midwife or a practitioner; d) a built-in augmented reality (AR) interface104providing a visual guidance and biomechanical data during a childbirth maneuver; e) an embedded educational module105for training midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees through a simulated childbirth scenario and analysis of historical procedure data; and f) a coordinated control architecture integrating components (a) through (e), configured to ensure fine-tuned biomechanical precision and safety during assisted delivery maneuvers, by dynamically modulating force application, monitoring tissue interaction parameters, and enabling practitioner-supervised, low-risk extraction of the fetus while minimizing mechanical trauma to neonatal structures; Wherein the system is configured to digitize and quantify the childbirth maneuver for the practitioner review and an educational purpose, operate under a full human oversight with no autonomous machine control, and enable selective utilization of components (a), (b), (c), (d), and (e) only when explicitly authorized by the midwife or the practitioner based on situational necessity.

[0043] In an exemplary implementation, the passive force transmission assembly101may comprise an exoskeleton structure200comprises a plurality of interconnected pulleys and levers configured to amplify the hand grip force, while preserving tactile feedback via a plurality of low-friction cables interlinking the pulleys and levers.

[0044] illustrates a schematic view of an exemplary exoskeleton structure, consistent with one or more exemplary embodiments of the present disclosure. In an exemplary implementation, the exemplary exoskeleton structure200may comprise a plurality of adjustable straps and a plurality of support elements201configured to be securely fastened between a shoulder and an elbow region of a user, thereby minimizing obstruction and ensuring unrestricted movement during the childbirth maneuver.

[0045] In an exemplary implementation, the exemplary exoskeleton structure200may comprises at least one lightweight, cost-effective composite material selected from materials including glass fiber-reinforced polypropylene, recycled carbon fiber-polyamide composites, cellulose-reinforced thermoplastic polyurethane and other polymers with comparable mechanical properties and medical-grade sterilizability, wherein said material provides an optimal balance of ergonomic flexibility, force transmission capability, and clinical durability while maintaining cost efficiency for disposable or reusable applications in obstetric settings.

[0046] In an exemplary implementation, the exemplary exoskeleton structure200may comprise a plurality of actuators providing a controlled assistance for the childbirth maneuver, wherein the actuators are integrated into the exemplary exoskeleton structure200and are configured to generate a controlled mechanical force to support and facilitate the childbirth maneuver

[0047] In an exemplary implementation, the exemplary exoskeleton structure200may comprise a lower limb-driven force augmentation system202configured to capture a mechanical energy from a user’s lower limb muscles and transfer it to the exoskeleton to amplify the hand grip force during the childbirth maneuver.

[0048] The above general aspect may have one or more of the following features. In an exemplary implementation, the lower limb-driven force augmentation system202comprises a pneumatic actuator or a spring-based actuator203configured to store the mechanical energy generated by an ankle dorsiflexion, a knee extension, or a posterior leg muscle contraction. In an exemplary implementation, the lower limb-driven force augmentation system utilizes a force-controlled cable transmission system204to transfer the stored mechanical energy to the exoskeleton.

[0049] illustrates a schematic view of an exemplary glove, consistent with one or more exemplary embodiments of the present disclosure. In an exemplary implementation, the plurality of sensors102may integrate into an exemplary glove300.

[0050] In an exemplary implementation, the plurality of sensors102may wirelessly connect to the AI-driven advisory system103, enabling real-time data transmission without obstructing the practitioner movement.

[0051] In an exemplary implementation, the AI-driven advisory system103may monitor the applied force via the plurality of sensors102, compares them with historical optimal ranges, and issue the practitioner alerts when a deviation occurs.

[0052] In an exemplary implementation, The exemplary AI-driven advisory system103is developed using a dataset that includes maternal biometric parameters (weight, pelvic dimensions, medical history), fetal biometric parameters (estimated weight, positioning), contextual metadata (ethnicity, gestational age, childbirth progression metrics), and additional data points (maternal oxygen saturation, uterine activity, fetal heart rate variability), which are analyzed to provide personalized guidance and optimize the childbirth maneuver.

[0053] In an exemplary implementation, the AI-driven advisory system103may employ a machine learning model trained on historical childbirth maneuver data.

[0054] In an exemplary implementation, the AR interface104may comprise an interactive AR display unit supporting a visual control, a voice control, a haptic input control, or a combination thereof, configured to dynamically render real-time biomechanical data including applied force, and joint angles while providing context-aware procedural guidance including fetal extraction vectors or overpressure alerts that auto-adapts to operator skill level and childbirth complexity wherein the AR interface104synergizes with the plurality of sensors102and the AI-driven advisory system103to enable AR-simulated practice scenarios with live feedback, all outputs remaining under full supervisory control of the attending midwife or obstetrician.

[0055] In an exemplary implementation, The AR interface104is configured as an adaptive training module for midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees and comprises a virtual patient simulator dynamically responsive to applied forces and maneuvers, replicating biomechanical behaviors of maternal and fetal anatomy during childbirth.

[0056] In an exemplary implementation, The AI-integrated childbirth assisting and training system100may further comprise a feedback mechanism selected from the group comprising a visual feedback mechanism, an auditory feedback mechanism, a haptic feedback mechanism, or a combination thereof, wherein said feedback mechanism is integrated with the passive force transmission assembly101and configured to alert the practitioner when an applied force exceed a predetermined threshold.

[0057] In an exemplary implementation, The AI-integrated childbirth assisting and training system100may further comprise a smart garment worn by the mother, embedded with a plurality of sensors to monitor uterine contractions and pelvic alignment, wirelessly transmitting data to the AI advisory system103for real-time correlation with the practitioner maneuvers, while at least one AR marker on the garment project maternal anatomical guidance onto the practitioner’s interface.

[0058] An AI-integrated childbirth assisting and training device

[0059] illustrates a schematic overview of an exemplary AI-integrated childbirth assisting and training device consistent with one or more exemplary embodiments of the present disclosure. In an exemplary implementation, the present disclosure is directed to an exemplary AI-integrated childbirth assisting and training device400. The exemplary AI-integrated childbirth assisting and training device may comprise a passive force transmission assembly to amplify a hand grip force401, wherein the assembly configured to operate under a manual human control without an external motorized power source, utilizing a user's natural mechanobiological forces to assist in fetal extraction from the birth canal; A plurality of sensors402including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor; An AI-driven advisory system404configured to suggest real-time force modulation, feedback, and recommendations, including predictive alerts based on biomechanical patterns, detection of abnormal force applications, and identification of potential risks during fetal extraction; wherein the system continuously learns from aggregated and anonymized childbirth data to improve decision support accuracy over time, and concurrently contributes to the development of a centralized big data repository intended for future clinical research, practitioner education, and refinement of obstetric techniques; all while ensuring that operational decisions and actions remain under the direct authority and discretion of a midwife or a practitioner; A built-in augmented reality (AR) interface405providing a visual guidance and biomechanical data during a childbirth maneuvers; an embedded educational module406for training midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees through a simulated childbirth scenarios and analysis of historical procedure data; and a coordinated control architecture integrating components (a) through (e), configured to ensure fine-tuned biomechanical precision and safety during assisted delivery maneuvers, by dynamically modulating force application, monitoring tissue interaction parameters, and enabling practitioner-supervised, low-risk extraction of the fetus while minimizing mechanical trauma to neonatal structures.

[0060] A method for performing and training AI-integrated childbirth assisting maneuvers using the AI-integrated childbirth assisting and training system

[0061] illustrates a flowchart of an exemplary method for performing and training AI-integrated childbirth assisting maneuvers500using the exemplary AI-integrated childbirth assisting and training system100, consistent with one or more exemplary embodiments of the present disclosure. In an exemplary implementation, the present disclosure is directed to the exemplary method for performing and training AI-integrated childbirth assisting maneuvers500using the exemplary AI-integrated childbirth assisting and training system100. The exemplary method may comprise a) positioning a practitioner's or a trainee's hand correctly under a fetal head501during an actual or a simulated childbirth; b) passively capturing a mechanical energy502from the practitioner's or the trainee's ankle flexion, knee motion, or posterior leg muscle contractions via a passive force transmission assembly, wherein the assembly transfers the captured mechanical energy to a spring-based or a pneumatic actuator to amplify a hand grip force without an external motorized power source; c) applying the amplified hand grip force under a manual human control to provide a controlled assistance during the childbirth maneuvers503; d) monitoring, via a plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor, and transmitting data to a AI-driven advisory system and a built-in AR interface for real-time feedback and a guidance504; e) adjusting the hand orientation and the applied force based on the practitioner's or the trainee's expertise level and the AI-driven advisory system's recommendations505, while maintaining full human oversight to safely deliver the fetus from the birth canal or execute a training scenario; and f) recording the maneuver data for the AI training, real-time feedback, and structured educational assessment506, wherein all operational decisions remain under the direct authority of the supervising practitioner.Examples

[0062] EXAMPLE 1: Childbirth assisting by using an exemplary AI-integrated childbirth assisting and training system

[0063] InExample 1, Childbirth assisting by using an exemplary AI-integrated childbirth assisting and training system100was carried out, consistent with one or more exemplary embodiments of the present disclosure. In this example, a midwife utilized the exemplary AI-integrated childbirth assisting and training system100comprising the passive force transmission assembly101, the plurality of sensors102including force, pressure, and joint angle sensors, the AI-driven advisory system103, and the built-in augmented reality (AR) interface104to assist in the delivery of a fetus during the second stage of childbirth.

[0064] Prior to the procedure, the system was calibrated to the specific biometric parameters of the mother and fetus, including maternal pelvic dimensions, fetal estimated weight, and positioning data, which were input into the AI-driven advisory system103. The system also incorporated contextual metadata such as gestational age, childbirth progression metrics, and maternal vital signs, collected via the smart garment worn by the mother.

[0065] The midwife positioned her hand under the fetal head401, engaging the passive force transmission assembly101which amplified her grip force through the exoskeleton structure200configured with interconnected pulleys and levers. The assembly operated solely under manual human control without any external motorized power source, thereby preserving tactile feedback and ensuring precise force application. During the maneuver, the plurality of sensors continuously monitored the applied forces, pressures, and joint angles, wirelessly transmitting real-time data to the AI-driven advisory system103. The AI-driven advisory system103analyzed the data against historical optimal ranges and biomechanical models, providing the midwife with real-time feedback via the AR interface104. The AR interface104displayed visual guidance including fetal extraction vectors, force thresholds, and joint alignment, dynamically adapting to the midwife’s skill level and the complexity of the childbirth scenario. The midwife received haptic and auditory alerts from the feedback mechanism integrated within the system whenever the applied force approached or exceeded predetermined safety thresholds, allowing immediate adjustment of technique to prevent maternal or fetal injury.

[0066] The system also recorded all maneuver data for subsequent review and educational purposes406. This data was utilized by the embedded educational module105to simulate the childbirth scenario for training midwifery students and obstetric residents, enabling them to analyze the procedure and refine their skills under supervised conditions.

[0067] Throughout the procedure, the midwife retained full authority and discretion over all operational decisions, with the AI-driven advisory system103serving solely as a supportive tool. No autonomous machine control was engaged at any point, ensuring that the childbirth assisting maneuver was performed under complete human oversight. The successful delivery was achieved with optimized force application, reduced practitioner fatigue due to the passive force amplification, and enhanced procedural safety supported by the AI advisory and AR guidance systems.

[0068] EXAMPLE 2:Childbirth assistance training for midwifery studentsby using an exemplary AI-integrated childbirth assisting and training system

[0069] InExample 2, childbirth assistance training for midwifery students by using an exemplary AI-integrated childbirth assisting and training system was carried out, consistent with one or more exemplary embodiments of the present disclosure. In this example, a midwifery student was trained using the system’s embedded educational module105, which simulated a realistic childbirth scenario incorporating digitized biomechanical data and historical procedure analytics.

[0070] Session began with the student donning a glove300embedded with a plurality of sensors102including force, pressure, and joint angle sensors, wirelessly connected to the AI-driven advisory system. Furthermore, the passive force transmission assembly101, comprising an exoskeleton structure200with interconnected pulleys and levers, was worn on the student’s arm to amplify her hand grip force without any external motorized power source, thus preserving natural tactile feedback. The system was configured to provide real-time feedback and guidance through a built-in augmented reality (AR) interface104, which visually displayed fetal extraction vectors, applied force magnitudes, and joint positioning data.

[0071] Student was instructed to position her hand correctly under a simulated fetal head within an anatomically accurate virtual birth canal, as rendered by the AR interface104.

[0072] During the simulated childbirth maneuver, the AI-driven advisory system103continuously monitored the student’s applied forces and joint angles, comparing them with established optimal ranges derived from a machine learning model trained on historical childbirth data. The system issued real-time visual, auditory, and haptic alerts when the applied force approached or exceeded safe thresholds, prompting the student to adjust her technique accordingly.

[0073] The AR interface104dynamically adapted the training difficulty based on the student’s skill level, providing progressively complex scenarios including variations in fetal positioning, maternal pelvic dimensions, and labor progression metrics. The system also integrated data from a virtual smart garment worn by the simulated mother, which monitored uterine contractions and pelvic alignment to enhance the realism of the training environment.

[0074] All maneuvers performed by the student were digitally recorded, enabling subsequent review and structured educational assessment by a supervising midwife or a obstetrician. This data facilitated personalized feedback and refinement of the student’s skills, ensuring competency development under full human oversight without any autonomous machine control.

[0075] The childbirth training concluded with a debriefing session where the AI-generated performance metrics and biomechanical data were analyzed collaboratively, highlighting areas of strength and opportunities for improvement. The student expressed increased confidence in applying controlled force during fetal extraction, supported by the system’s integrated feedback and guidance mechanisms.

[0076] While particular aspects of the present subject matter described herein have been shown and described, it will be apparent to those skilled in the art that, based upon the teachings herein, changes and modifications may be made without departing from this subject matter described herein and its broader aspects and, therefore, the appended claims are to encompass within their scope all such changes and modifications as are within the true spirit and scope of this subject matter described herein. Furthermore, it is to be understood that the invention is solely defined by the appended claims. It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, as an aid to understanding, the following appended claims may contain usage of the introductory phrases “at least one” to introduce claim recitations. However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles “a” or “an” limits any particular claim containing such introduced claim recitation to inventions containing only one such recitation, even when the same claim includes the introductory phrases “at least one” and indefinite articles such as “a” or “an” (e.g., “a” and / or “an” should typically be interpreted to mean “at least one” or “one or more”); the same holds true for the use of definite articles used to introduce claim recitations. In addition, even if a specific number of an introduced claim recitation is explicitly recited, those skilled in the art will recognize that such recitation should typically be interpreted to mean at least the recited number (e.g., the bare recitation of “two recitations,” without other modifiers, typically means at least two recitations or two

[0077] It will be understood that the terms and expressions used herein have the ordinary meaning as is accorded to such terms and expressions with respect to their corresponding respective areas of inquiry and study except where specific meanings have otherwise been set forth herein. Relational terms such as first, second, and third and the like may be used solely to distinguish one entity or action from another without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms “comprises,” “comprising,” “include,” “including,” or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, apparatus, or device that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, apparatus, or device. An element proceeded by “a” or “an” does not, without further constraints, preclude the existence of additional identical elements in the process, method, article, or device that comprises the element. Moreover, “may” and other permissive terms are used herein for describing optional features of various embodiments. These terms likewise describe selectable or configurable features generally, unless the context dictates otherwise.

Claims

An Artificial intelligence (AI)-integrated childbirth assisting and training system, comprising:a) A passive force transmission assembly to amplify a hand grip force, wherein the assembly is configured to operate under manual human control without an external motorized power source, utilizing a user's natural mechanobiological forces to assist in fetal extraction from a birth canal;b) A plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor;c) An AI-driven advisory system configured to suggest real-time force modulation, feedback, and recommendations, including predictive alerts based on biomechanical patterns, detection of abnormal force applications, and identification of potential risks during fetal extraction; wherein the system continuously learns from aggregated and anonymized childbirth data to improve decision support accuracy over time, and concurrently contributes to the development of a centralized big data repository intended for future clinical research, practitioner education, and refinement of obstetric techniques; all while ensuring that operational decisions and actions remain under the direct authority and discretion of a midwife or a practitioner;d) A built-in augmented reality (AR) interface providing a visual guidance and biomechanical data during a childbirth maneuver;e) An embedded educational module for training midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees through a simulated childbirth scenario and analysis of historical procedure data; andf) A coordinated control architecture integrating components (a) through (e), configured to ensure fine-tuned biomechanical precision and safety during assisted delivery maneuvers, by dynamically modulating force application, monitoring tissue interaction parameters, and enabling practitioner-supervised, low-risk extraction of the fetus while minimizing mechanical trauma to neonatal structures;Wherein the system is configured to digitize and quantify the childbirth maneuver for practitioner review and educational purposes, operate under full human oversight with no autonomous machine control, and enable selective utilization of components (a), (b), (c), (d), (e), and (f) only when explicitly authorized by the midwife or the practitioner based on situational necessityThe AI-integrated childbirth assisting and training system of claim 1, wherein the passive force transmission assembly comprises an exoskeleton structure comprises a plurality of interconnected pulleys and levers configured to amplify the hand grip force, while preserving tactile feedback via a plurality of low-friction cables interlinking the pulleys and levers.The AI-integrated childbirth assisting and training system of claim 2, wherein the exoskeleton structure comprises a plurality of adjustable straps and a plurality of support elements configured to be securely fastened between a shoulder and an elbow region of a user, thereby minimizing obstruction and ensuring unrestricted movement during the childbirth maneuver.The AI-integrated childbirth assisting and training system of claim 2, wherein the exoskeleton structure comprises at least one lightweight, cost-effective composite material selected from materials including glass fiber-reinforced polypropylene, recycled carbon fiber-polyamide composites, cellulose-reinforced thermoplastic polyurethane and other polymers with comparable mechanical properties and medical-grade sterilizability, wherein said material provides an optimal balance of ergonomic flexibility, force transmission capability, and clinical durability while maintaining cost efficiency for disposable or reusable applications in obstetric settings.The AI-integrated childbirth assisting and training system of claim 1 and 2, wherein the exoskeleton structure comprises a plurality of actuators providing a controlled assistance for the childbirth maneuver, wherein the actuators are integrated into the exoskeleton structure and are configured to generate a controlled mechanical force to support and facilitate the childbirth maneuver.The AI-integrated childbirth assisting and training system of claim 1 and 2, wherein the exoskeleton structure comprises a lower limb-driven force augmentation system configured to capture a mechanical energy from a user’s lower limb muscles and transfer it to the exoskeleton to amplify the hand grip force during the childbirth maneuver.The AI-integrated childbirth assisting and training system of claim 1 and 6, wherein the lower limb-driven force augmentation system comprises a pneumatic actuator or a spring-based actuator configured to store the mechanical energy generated by an ankle dorsiflexion, a knee extension, or a posterior leg muscle contraction.The AI-integrated childbirth assisting and training system of claim 1, 6 and 7, wherein the lower limb-driven force augmentation system utilizes a force-controlled cable transmission system to transfer the stored mechanical energy to the exoskeleton.The AI-integrated childbirth assisting and training system of claim 1, wherein the plurality of sensors is integrated into a glove.The AI-integrated childbirth assisting and training system of claim 1, wherein the plurality of sensors wirelessly connected to the AI-driven advisory system, enabling real-time data transmission without obstructing the practitioner movement.The AI-integrated childbirth assisting and training system of claim 1, wherein the AI-driven advisory system monitors the applied force via the plurality of sensor, compares them with historical optimal ranges, and issues the practitioner alerts when a deviation occurs.The AI-integrated childbirth assisting and training system of claim 1, wherein the AI-driven advisory system is developed using a dataset that includes maternal biometric parameters (weight, pelvic dimensions, medical history), fetal biometric parameters (estimated weight, positioning), contextual metadata (ethnicity, gestational age, childbirth progression metrics), and additional data points (maternal oxygen saturation, uterine activity, fetal heart rate variability), which are analyzed to provide personalized guidance and optimize the childbirth maneuver.The AI-integrated childbirth assisting and training system of claim 1 and 12, wherein the AI-driven advisory system employs a machine learning model trained on historical childbirth maneuver data.The AI-integrated childbirth assisting and training system of claim 1, wherein the AR interface comprises an interactive AR display unit supporting a visual control, a voice control, a haptic input control, or a combination thereof, configured to dynamically render real-time biomechanical data including applied force, and joint angles while providing context-aware procedural guidance including fetal extraction vectors or overpressure alerts that auto-adapts to operator skill level and childbirth complexity wherein the AR interface synergizes with the plurality of sensors and the AI-driven advisory system to enable AR-simulated practice scenarios with live feedback, all outputs remaining under full supervisory control of the attending midwife or obstetrician.The AI-integrated childbirth assisting and training system of claim 1, wherein the AR interface is configured as an adaptive training module for midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees and comprises a virtual patient simulator dynamically responsive to applied forces and maneuvers, replicating biomechanical behaviors of maternal and fetal anatomy during childbirth.The AI-integrated childbirth assisting and training system of claim 1, further comprising a feedback mechanism selected from the group comprising a visual feedback mechanism, an auditory feedback mechanism, a haptic feedback mechanism, and a combination thereof, wherein said feedback mechanism is integrated with the passive force transmission assembly and configured to alert the practitioner when an applied force exceed a predetermined threshold.The AI-integrated childbirth assisting and training system of claim 1, further comprising a smart garment worn by the mother, embedded with a plurality of sensors to monitor uterine contractions and pelvic alignment, wirelessly transmitting data to the AI system for real-time correlation with the practitioner maneuvers, while at least one AR marker on the garment project maternal anatomical guidance onto the practitioner’s interface.An AI-integrated childbirth assisting and training device, comprising:a) A passive force transmission assembly to amplify a hand grip force, wherein the assembly configured to operate under a manual human control without an external motorized power source, utilizing a user's natural mechanobiological forces to assist in fetal extraction from the birth canal;b) A plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor;c) An AI-driven advisory system configured to suggest real-time force modulation, feedback, and recommendations, including predictive alerts based on biomechanical patterns, detection of abnormal force applications, and identification of potential risks during fetal extraction; wherein the system continuously learns from aggregated and anonymized childbirth data to improve decision support accuracy over time, and concurrently contributes to the development of a centralized big data repository intended for future clinical research, practitioner education, and refinement of obstetric techniques; all while ensuring that operational decisions and actions remain under the direct authority and discretion of a midwife or a practitioner;d) A built-in augmented reality (AR) interface providing a visual guidance and biomechanical data during a childbirth maneuvers;e) An embedded educational module for training midwifery students, obstetric residents, nurse practitioners, and other childbirth healthcare trainees through a simulated childbirth scenarios and analysis of historical procedure data; andf) A coordinated control architecture integrating components (a) through (e), configured to ensure fine-tuned biomechanical precision and safety during assisted delivery maneuvers, by dynamically modulating force application, monitoring tissue interaction parameters, and enabling practitioner-supervised, low-risk extraction of the fetus while minimizing mechanical trauma to neonatal structures.A method for performing and training AI-integrated childbirth assisting maneuvers using the AI-integrated childbirth assisting and training system, comprising:a) Positioning a practitioner's or a trainee's hand correctly under a fetal head during an actual or a simulated childbirth;b) Passively capturing a mechanical energy from the practitioner’s or the trainee’s ankle flexion, knee motion, or posterior leg muscle contractions via a passive force transmission assembly, wherein the assembly transfers the captured mechanical energy to a spring-based or a pneumatic actuator to amplify a hand grip force without an external motorized power source;c) Applying the amplified hand grip force under a manual human control to provide a controlled assistance during the childbirth maneuvers;d) Monitoring, via a plurality of sensors including at least one force sensor, at least one pressure sensor, at least one tactile sensor, at least one strain sensor, and at least one temperature sensor, and at least one joint angle sensor, and transmitting data to an AI-driven advisory system and a built-in AR interface for real-time feedback and a guidance;e) Adjusting the hand orientation and the applied force based on the practitioner's or the trainee's expertise level and the AI-driven advisory system's recommendations, while maintaining full human oversight to safely deliver the fetus from the birth canal or execute a training scenario;f) Recording the maneuver data for the AI training, real-time feedback, and structured educational assessment, wherein all operational decisions remain under the direct authority of the supervising practitioner

Images