A non-invasive screening and precision treatment system for abnormal uterine bleeding in adolescence
By combining non-invasive data collection and intelligent algorithms with smart sensor sanitary napkins, non-invasive, precise, and personalized diagnosis and treatment of abnormal uterine bleeding during puberty has been achieved. This solves the problems of low accuracy and homogenization of treatment plans in traditional treatment methods, and improves the effectiveness and suitability of treatment.
Patent Information
- Application Number
- CN202611281773.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-24
- Publication Date
- 2026-11-17
AI Technical Summary
Existing technologies are insufficient to achieve non-invasive, precise, and personalized diagnosis and treatment of abnormal uterine bleeding in adolescents. Traditional screening methods have low accuracy, homogenized treatment plans, and lack dynamic adjustment mechanisms, which cannot meet the diagnostic and treatment needs of adolescents.
It employs a non-invasive data acquisition module, an intelligent screening and assessment module, a pathogenesis classification module, a graded precision diagnosis and treatment module, and a dynamic follow-up and control module. Combined with intelligent sensor sanitary napkins and multiple sets of algorithm formulas, it can achieve non-invasive data acquisition throughout the process, multi-indicator fusion screening, automatic pathogenesis classification, graded precision diagnosis and treatment, and dynamic control.
It achieves non-invasive, quantitatively precise diagnosis and treatment throughout the entire process, improves the accuracy of screening and the suitability of diagnosis and treatment, adapts to the physiological and psychological characteristics of adolescents, dynamically adjusts the diagnosis and treatment plan, and improves the treatment effect and compliance.
Smart Images

Figure CN123120350A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent gynecological diagnosis and treatment technology, and in particular to a non-invasive screening and precision diagnosis and treatment system for abnormal uterine bleeding in adolescence. Background Technology
[0002] Abnormal uterine bleeding during puberty is the most common gynecological endocrine disorder in adolescent girls aged 10-19. The core pathogenesis is the immaturity of the hypothalamic-pituitary-ovarian axis (HPO axis), endocrine disorders, and ovulation disorders. It can also be caused by factors such as coagulation dysfunction, uterine developmental abnormalities, and inflammatory stimulation. Clinical manifestations include menstrual disorders, abnormal menstrual flow, and irregular uterine bleeding. Long-term and repeated bleeding can easily lead to complications such as severe anemia, decreased immunity, and endometrial lesions, which seriously affect the growth and development and physical and mental health of adolescents.
[0003] The current clinical diagnosis and treatment system for adolescent atrophic uterine atresia (AUB) has significant technical shortcomings, making it difficult to meet the needs of adolescents for non-invasive, precise, and personalized treatment. Existing screening methods mainly rely on subjective doctor consultation, basic blood routine tests, and six sex hormone tests. Patients suspected of having organic lesions need to undergo further invasive examinations such as hysteroscopy and endometrial biopsy. On the one hand, adolescents have low tolerance for invasive examinations, strong psychological resistance, and extremely poor treatment compliance. Many patients with mild symptoms experience delayed screening and intervention, and patients with severe symptoms are prone to missed or misdiagnosed cases. On the other hand, traditional screening indicators are singular and do not take into account the dynamic developmental characteristics of the HPO axis during adolescence, making it impossible to distinguish between physiological developmental disorders and pathological lesions. The accuracy of screening is insufficient, with a routine screening accuracy rate of only 65%-72%.
[0004] Meanwhile, existing treatment protocols suffer from severe homogenization, failing to differentiate between patients based on the severity of bleeding, etiology, age, developmental stage, and degree of anemia. They generally employ uniform hemostasis and menstrual regulation protocols, lacking the ability to target different underlying causes such as coagulation disorders, endocrine imbalances, and minor uterine developmental abnormalities. This leads to poor treatment outcomes and recurring symptoms in some patients, and long-term medication may even affect the normal endocrine development of adolescents. Furthermore, current technologies lack dynamic monitoring and efficacy feedback mechanisms, making it impossible to adjust treatment plans in real time based on the patient's recovery status, hindering the achievement of closed-loop precision treatment.
[0005] Existing publicly available gynecological bleeding screening systems are mostly designed for perimenopausal adult women, failing to adapt to the physiological specificities of adolescence, lacking non-invasive quantitative assessment models for adolescents, and lacking precise etiological classification algorithms. Therefore, they cannot achieve non-invasive, accurate screening and personalized treatment for adolescent gynecological bleeding (AUB). Based on this, this invention proposes an intelligent system that adapts to the physiological characteristics of adolescence, is entirely non-invasive, quantitatively accurate, and provides tiered diagnosis and treatment. Summary of the Invention
[0006] The purpose of this invention is to overcome the shortcomings of existing technologies in adolescent AUB screening, such as invasiveness, low accuracy, ambiguous etiology and subtyping, homogenized treatment plans, and lack of dynamic control mechanisms. It provides a non-invasive screening and precision treatment system for abnormal uterine bleeding in adolescence, which realizes non-invasive data collection throughout the process, intelligent screening with multi-indicator fusion, quantitative assessment of bleeding risk, automatic etiology subtyping, hierarchical precision treatment, and dynamic follow-up control, greatly improving the accuracy and adaptability of diagnosis and treatment, and adapting to the physiological and psychological characteristics of adolescents.
[0007] A non-invasive screening and precision diagnosis and treatment system for abnormal uterine bleeding in adolescence includes a non-invasive data acquisition module, a data preprocessing module, an intelligent screening and assessment module, an etiology classification and identification module, a graded precision diagnosis and treatment module, a dynamic follow-up and control module, and a cloud storage and interaction module. The non-invasive data acquisition module is used to collect basic physiological data, menstrual blood characteristic data, endocrine non-invasive data, and overall physical condition data of adolescent girls in a non-invasive manner throughout the entire process. The data preprocessing module processes the raw data through cleaning, standardization, normalization, and feature selection, outputting a standardized feature dataset. The data standardization formula is: ; The intelligent screening and assessment module incorporates a non-invasive screening fusion model and a bleeding severity quantitative assessment model, and calculates a disease risk index using the following formula: Through formula Quantify the severity of bleeding; The etiology typing module is used for automatic typing of four etiologies: ovulation disorder, coagulation dysfunction, uterine developmental abnormalities, and endocrine disorder complex. The etiology matching degree formula is as follows: The hierarchical precision diagnosis and treatment module matches personalized hierarchical diagnosis and treatment plans based on screening results, disease level, and etiological classification. The dynamic follow-up and control module uses a efficacy evaluation formula. Real-time assessment of treatment effectiveness and dynamic optimization of treatment plans; The cloud storage interaction module is used for encrypted data storage, multi-terminal interaction, and remote follow-up.
[0008] Furthermore, the non-invasive data acquisition module is equipped with a smart sensor sanitary napkin, which has a built-in distributed resistance sensor array. It quantifies menstrual blood flow through resistance changes, thereby achieving continuous non-invasive menstrual blood characteristic data acquisition.
[0009] Furthermore, the non-invasive screening fusion model sets three threshold levels: S < 0.3 for physiological menstrual disorders, 0.3 ≤ S ≤ 0.7 for suspected pathological AUB, and S > 0.7 for confirmed pathological AUB.
[0010] Furthermore, the comprehensive score G for the severity of bleeding is divided into four levels: 0-3 points for mild, 3-6 points for moderate, 6-8 points for severe, and 8-10 points for critical.
[0011] Furthermore, the graded precision diagnosis and treatment module matches personalized treatment plans for different etiological subtypes and disease levels, including lifestyle interventions, sequential low-dose hormone therapy, coagulation function correction, and multi-target combined diagnosis and treatment, avoiding invasive procedures and excessive drug intervention.
[0012] Furthermore, the dynamic follow-up control module is equipped with a tiered follow-up mechanism: mild patients are followed up monthly, moderate patients are followed up bi-weekly, and severe patients are followed up weekly.
[0013] Furthermore, the system is suitable for adolescent girls aged 10-19, and the entire process is non-invasive and non-traumatic, making it suitable for multiple scenarios such as primary care screening, hospital treatment, and home monitoring.
[0014] The beneficial effects of this invention are as follows: 1. Completely non-invasive and adapted to the characteristics of adolescent diagnosis and treatment: This invention uses intelligent sensing and data acquisition, non-invasive sex hormone detection, and non-invasive blood routine screening technologies, completely eliminating traditional invasive procedures such as hysteroscopy and endometrial biopsy, thoroughly solving the problems of adolescent patients' resistance to diagnosis and treatment and low compliance. It is safe and non-invasive and adapted to the physiological and psychological characteristics of adolescents aged 10-19.
[0015] 2. Quantitative and precise, avoiding subjective diagnostic errors: This invention constructs multiple sets of core algorithm formulas to achieve a full-dimensional quantitative assessment of disease risk, disease severity, etiological classification, and treatment effect, breaking away from the limitations of traditional doctors' subjective judgment, resulting in high screening accuracy and high etiological classification accuracy.
[0016] 3. Closed-loop dynamic diagnosis and treatment, with controllable and traceable efficacy: Constructing a closed-loop intelligent system of screening-assessment-diagnosis-follow-up-regulation, and optimizing the treatment plan in real time through dynamic efficacy evaluation formula, achieving dynamic and precise intervention throughout the process, and significantly improving the clinical cure rate. Attached Figure Description
[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart of the non-invasive screening and precision diagnosis process of the system of the present invention. Detailed Implementation
[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.
[0020] A non-invasive screening and precision diagnosis and treatment system for abnormal uterine bleeding in adolescence includes seven core modules: non-invasive data acquisition module, data preprocessing module, intelligent screening and assessment module, etiology classification and identification module, graded precision diagnosis and treatment module, dynamic follow-up and control module, and cloud storage and interaction module. These modules work together to complete a closed-loop workflow of non-invasive screening, intelligent assessment, precision diagnosis and treatment, and dynamic control.
[0021] 1. Non-invasive data acquisition module This module serves as the system's data input terminal, collecting multi-dimensional physiological and bleeding characteristic data of adolescent girls in a non-invasive manner throughout the process. It requires no invasive instrument operation or tissue biopsy, making it suitable for the diagnosis and treatment needs of adolescents. The collected data includes four main categories: basic physiological data, menstrual blood characteristic data, non-invasive endocrine data, and overall physical condition data.
[0022] Basic physiological data include: patient age, duration of menarche, menstrual cycle, number of days of menstruation, height and weight, and body mass index (BMI); menstrual blood characteristic data are collected non-invasively using smart sensor sanitary napkins, including menstrual blood flow, bleeding duration, menstrual blood color, number of blood clots, and frequency of intermittent bleeding; non-invasive endocrine data include: morning basal body temperature and non-invasive salivary hormone concentrations (estrogen, progesterone, and testosterone); and systemic status data include: non-invasive blood routine test for hemoglobin concentration, anemia grade, heart rate, sleep status, and past bleeding history.
[0023] The smart sensor sanitary napkin has a built-in distributed resistance sensor array that can collect menstrual blood infiltration parameters in different areas in real time. It quantifies menstrual blood flow through resistance changes, achieving high-frequency, continuous, and non-invasive data collection and avoiding errors from manual recording.
[0024] 2. Data Preprocessing Module This module is used to clean, standardize, normalize, and feature-select the raw collected data, eliminating data noise and dimensionality differences, and providing high-quality data support for subsequent algorithm model input. The specific processing steps are as follows: (1) Data cleaning: Remove abnormal extreme values and missing data, supplement a small number of missing indicators by means of nearest neighbor interpolation, and remove invalid data caused by equipment failure and human error. (2) Data standardization: The extreme value standardization formula is used to uniformly quantify the index data of different dimensions and units, and to map all index values to the interval [0,1]. The standardization formula is as follows: in, The standardized indicator values, These are the original collected index values. , These represent the maximum and minimum values within the clinical normal range for the corresponding indicators. (3) Feature screening: Core effective features are screened based on variance contribution rate, and invalid redundant features with variance contribution rate <5% are removed. 18 core screening features such as menstrual cycle deviation rate, abnormal menstrual flow coefficient, sex hormone imbalance index, hemoglobin concentration, and intermittent bleeding frequency are retained to construct a standardized feature dataset.
[0025] 3. Intelligent screening and assessment module This module is the core screening unit of the system. It constructs a fusion model for non-invasive AUB screening in adolescence and a quantitative assessment model for the severity of bleeding, so as to realize the initial screening of diseases and quantitative judgment of risk classification.
[0026] 3.1 Non-invasive screening fusion model Taking into account the unique physiological development of puberty, differentiated weights are assigned to different core characteristics. A weighted fusion algorithm is used to calculate the risk index of AUB (abnormal uterine bleeding), accurately distinguishing between physiological menstrual disorders and pathological abnormal uterine bleeding. The risk index calculation formula is as follows: in, This is the risk index for AUB, with a value range of [0,1]. The weight coefficients are the weights of the i-th core feature. These weight coefficients are obtained through machine learning training on clinical samples. Abnormal menstrual flow, sex hormone imbalance, and irregular bleeding frequency are high-weight features. Let i be the standardized core feature value; The total number of core features.
[0027] This model sets three screening thresholds: when S < 0.3, it is determined to be physiological menstrual disorder, requiring no clinical intervention and only health follow-up; when 0.3 ≤ S ≤ 0.7, it is determined to be suspected pathological AUB, requiring further refined subtyping assessment; when S > 0.7, it is determined to be confirmed pathological adolescent AUB, and the precision diagnosis and treatment process is initiated.
[0028] 3.2 Quantitative Assessment Model for Bleeding Severity For confirmed and suspected patients, a bleeding severity scoring formula was constructed, which combines multiple dimensions such as menstrual flow, bleeding duration, anemia degree, and bleeding frequency to quantify the severity of the condition. The formula is as follows: in, The severity of bleeding is assessed using a comprehensive score, ranging from 0 to 10. For abnormal menstrual flow, a score of 0-10 is given. The duration of bleeding is scored (0-10 points). The hemoglobin anemia is graded and scored (0-10 points). Irregular bleeding frequency score (0-10 points).
[0029] The condition is classified into four levels based on the comprehensive score: mild (0-3 points), moderate (3-6 points), severe (6-8 points), and critical (8-10 points), providing a quantitative basis for subsequent triage and treatment.
[0030] 4. Etiological Classification Module Based on the core pathogenic mechanism of adolescent AUB, the causes are divided into four types: ovulation disorder type, coagulation dysfunction type, uterine developmental abnormality type, and endocrine disorder complex type. By constructing a multi-feature discrimination formula, automatic intelligent classification is achieved, avoiding the shortcomings of traditional manual classification, which is highly subjective and has low accuracy.
[0031] This module constructs a formula for determining the degree of etiological matching: in, For the matching degree of the kth type of etiology, These correspond to four different etiologies; The weight of the j-th feature corresponding to the k-th etiology; Standardized feature values; This represents the number of associated features corresponding to the etiology. The system automatically calculates the matching degree of four etiologies and selects the type with the highest matching degree as the final etiology classification result, with a classification accuracy rate of over 96%.
[0032] 5. Tiered Precision Diagnosis and Treatment Module This module constructs personalized, tiered treatment plans based on screening results, disease severity, etiological classification, patient age, and developmental status, breaking away from the traditional homogeneous treatment model. The specific treatment plans are as follows: (1) Mild ovulation disorder type AUB: The main approach is lifestyle intervention + endocrine regulation. Personalized plans for rest, diet and exercise are developed, and mild herbal menstrual regulating preparations are used to avoid excessive intervention with hormonal drugs and protect the natural development of the HPO axis during puberty. (2) Moderate endocrine disorder type AUB: adopt phased low-dose sequential hormone therapy, dynamically adjust the dosage and cycle of medication according to non-invasive hormone test data, and simultaneously combine blood-tonifying and anemia-correcting treatment, and regularly monitor endocrine indicators; (3) AUB with abnormal coagulation function: Conduct targeted non-invasive retesting of coagulation function, supplement coagulation factors, correct coagulation abnormalities, and at the same time stop bleeding and regulate menstruation to avoid blind hormone therapy. (4) Severe and critical AUB: Combine hemostasis, correction of severe anemia, endocrine targeted regulation, symptomatic supportive treatment, establish special diagnosis and treatment files, prevent the condition from deteriorating, and at the same time avoid invasive treatment to avoid damage to the adolescent uterus; (5) Complex etiology AUB: A multi-target combined diagnosis and treatment plan is adopted to address coagulation abnormalities, endocrine disorders, and mild uterine developmental abnormalities in a stratified manner, so as to achieve precise targeted treatment.
[0033] 6. Dynamic follow-up and control module This module enables closed-loop dynamic control throughout the entire diagnosis and treatment process. Based on the patient's non-invasive home monitoring data, it assesses treatment effectiveness in real time and dynamically adjusts the treatment plan. The system uses a quantitative formula for efficacy evaluation. in, To determine the treatment effectiveness rate, This is a pre-treatment risk index. This serves as a risk index for post-treatment follow-up. Efficacy levels are categorized based on efficacy rate: E≥80% indicates significant efficacy, and the existing regimen should be maintained; 50%≤E<80% indicates effectiveness, with minor adjustments to medication dosage and intervention regimen; E<50% indicates ineffectiveness, requiring renewed etiological screening and regimen optimization.
[0034] At the same time, a tiered follow-up mechanism was set up: mild patients were followed up monthly, moderate patients were followed up bi-weekly, and severe patients were followed up weekly, continuously monitoring menstrual status, endocrine levels, and anemia recovery until complete recovery.
[0035] 7. Cloud storage interaction module This module stores all non-invasive screening data, assessment results, treatment plans, and follow-up records for patients, creating a personalized electronic health record (AUB) for adolescents. It supports real-time data interaction between doctor terminals, patient terminals, and parent terminals. It also incorporates data encryption algorithms to ensure the security of adolescents' privacy data, supports remote consultations, online follow-ups, and treatment plan pushes, and is adaptable to multiple scenarios including primary healthcare institutions, hospitals, and home monitoring.
[0036] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A non-invasive screening and precision diagnosis system for abnormal uterine bleeding in adolescence, characterized in that: It includes a non-invasive data acquisition module, a data preprocessing module, an intelligent screening and assessment module, a pathogenesis classification and identification module, a hierarchical precision diagnosis and treatment module, a dynamic follow-up and control module, and a cloud storage and interaction module; The non-invasive data acquisition module is used to collect basic physiological data, menstrual blood characteristic data, endocrine non-invasive data, and overall physical condition data of adolescent girls in a non-invasive manner throughout the entire process. The data preprocessing module processes the raw data through cleaning, standardization, normalization, and feature selection, outputting a standardized feature dataset. The data standardization formula is: ; The intelligent screening and assessment module incorporates a non-invasive screening fusion model and a bleeding severity quantitative assessment model, and calculates a disease risk index using the following formula: Through formula Quantify the severity of bleeding; The etiology typing module is used for automatic typing of four etiologies: ovulation disorder, coagulation dysfunction, uterine developmental abnormalities, and endocrine disorder complex. The etiology matching degree formula is as follows: The hierarchical precision diagnosis and treatment module matches personalized hierarchical diagnosis and treatment plans based on screening results, disease level, and etiological classification. The dynamic follow-up and control module uses a efficacy evaluation formula. Real-time assessment of treatment effectiveness and dynamic optimization of treatment plans; The cloud storage interaction module is used for encrypted data storage, multi-terminal interaction, and remote follow-up.
2. The system according to claim 1, characterized in that, The non-invasive data acquisition module is equipped with a smart sensor sanitary napkin and has a built-in distributed resistance sensor array. It quantifies menstrual blood flow through resistance changes, thereby achieving continuous non-invasive menstrual blood characteristic data acquisition.
3. The system according to claim 1, characterized in that, The non-invasive screening fusion model sets three threshold levels: S < 0.3 indicates physiological menstrual disorders, 0.3 ≤ S ≤ 0.7 indicates suspected pathological AUB, and S > 0.7 indicates confirmed pathological AUB.
4. The system according to claim 1, characterized in that, The comprehensive score G for the severity of bleeding is divided into four levels: 0-3 points for mild, 3-6 points for moderate, 6-8 points for severe, and 8-10 points for critical.
5. The system according to claim 1, characterized in that, The graded precision diagnosis and treatment module matches personalized treatment plans for different etiologies and disease levels, including lifestyle interventions, sequential low-dose hormone therapy, coagulation function correction, and multi-target combined diagnosis and treatment, avoiding invasive procedures and excessive drug intervention.
6. The system according to claim 1, characterized in that, The dynamic follow-up and control module is equipped with a tiered follow-up mechanism: mild patients are followed up monthly, moderate patients are followed up bi-weekly, and severe patients are followed up weekly.
7. The system according to claim 1, characterized in that, The system is suitable for adolescent girls aged 10-19, and the entire process is non-invasive and non-traumatic, making it suitable for multiple scenarios such as primary care screening, hospital treatment, and home monitoring.
