Life auxiliary system for deafness and hearing loss patients

Abstract

The invention relates to a life assistance system for deaf and hearing loss patients, which comprises a data acquisition module, a preprocessing module, a feature extraction module, a model training module, a classification rating module, a prediction module, a user interaction module, a feedback optimization module, a report generation module, a remote cooperation module and a life assistance execution module, by integrating the advantages of the prior art and combining the innovative application of the artificial cochlea, more comprehensive, efficient and personalized life auxiliary service is provided for hearing disorder patients such as auditory sclerosis, and the diagnosis accuracy, the treatment effect and the life quality of the patients are improved.

Description

Technical Field

[0001] The present invention relates to the field of assistance for patients with deafness or hearing loss, and in particular to a life assistance system for patients with deafness or hearing loss. Background Art

[0002] Otosclerosis, a disease characterized by pathological changes in the ear, has a core pathological mechanism involving primary localized bone resorption in the bony labyrinth, which is replaced by new, spongy bone rich in blood vessels and cells. This process leads to bone sclerosis and fixation, which in turn causes conductive or mixed hearing loss. Currently, the diagnosis of otosclerosis relies primarily on auxiliary methods such as pure tone audiometry, CT scanning, and electronic otoscopy. However, each of these methods has limitations. For example, pure tone audiometry is susceptible to patient subjective influence, the positive rate of CT scans varies widely across different literature, and the detection rate of electronic otoscopy is relatively low.

[0003] Wideband acoustic immittance testing, as a non-invasive, objective hearing assessment method, provides an effective and sensitive means for detecting middle and external ear pathology by comprehensively analyzing multiple parameters, including tympanograms, acoustic reflex elicitation rate, sound energy absorption rate, and static compliance. Combining the patient's clinical presentation with broadband acoustic immittance testing results, physicians can more accurately diagnose otosclerosis and develop appropriate treatment plans. Furthermore, with technological advancements, broadband acoustic immittance testing has shown great potential in assisting the daily lives of patients with deafness and hearing loss.

[0004] Although broadband acoustic immittance testing has performed well in the diagnosis of otosclerosis, existing diagnostic systems still face several challenges. First, pure tone audiometry and broadband acoustic immittance testing are typically performed as two separate testing procedures, increasing testing time and inconvenience for patients. Second, existing life-assistance systems for patients with deafness and hearing loss often focus on the use of hearing-assistive devices (such as hearing aids and cochlear implants) and lack comprehensive management and prediction capabilities for specific diseases such as otosclerosis. In particular, when it comes to predicting symptom progression, existing systems often rely on physicians' empirical judgment and lack objective data support and scientific prediction models. Therefore, we propose a life-assistance system for patients with deafness and hearing loss. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiencies of the prior art, meet practical needs, and provide a life-assistance system for patients with deafness and hearing loss, so as to solve the problem that pure tone audiometry and broadband acoustic immittance testing are usually performed as two independent testing processes, which increases the testing time and inconvenience for patients. Secondly, the existing life-assistance systems for patients with deafness and hearing loss often focus on the use of hearing-assistance devices (such as hearing aids and cochlear implants), but lack the comprehensive management and prediction capabilities for specific diseases such as otosclerosis. In particular, in terms of symptom development prediction, the existing systems often rely on the experience and judgment of doctors, lacking objective data support and scientific prediction models.

[0006] In order to achieve the purpose of the present invention, the technical solution adopted by the present invention is as follows: a life-assistance system for patients with deafness and hearing loss is designed, including a data acquisition module, a preprocessing module, a feature extraction module, a model training module, a classification and rating module, a prediction module, a user interaction module, a feedback optimization module, a report generation module, a remote collaboration module and a life-assistance execution module;

[0007] The data acquisition module is used to collect the patient's middle ear acoustic immittance data and hearing threshold data through a broadband acoustic immittance test device and a pure tone audiometer;

[0008] The pre-processing module is used to perform standardization processing and outlier correction on the collected acoustic immittance data and hearing test data;

[0009] The feature extraction module is used to extract the resonance frequency, the peak characteristics of the acoustic energy absorption rate and the ear canal volume parameters from the acoustic immittance data;

[0010] The model training module is used to construct an otosclerosis staging classification model and a symptom development prediction model based on a machine learning algorithm;

[0011] The classification and rating module is used to stage and grade the patient's hearing loss according to the model output results;

[0012] The prediction module is used to predict the development trend of the patient's hearing symptoms by combining time series analysis of historical data;

[0013] The user interaction module is used to visually display test results, classification ratings and prediction charts to patients and doctors;

[0014] The feedback optimization module is used to collect clinical feedback data and iteratively optimize model parameters;

[0015] The report generation module is used to automatically generate a standardized medical report containing diagnostic recommendations;

[0016] The remote collaboration module is used to support encrypted transmission of patient data and model sharing among multiple medical institutions;

[0017] The life-assistance execution module includes a bone conduction cochlear implant with an integrated broadband acoustic immittance probe. While improving the patient's hearing, the cochlear implant regularly performs broadband acoustic immittance tests through the probe and transmits the test data in real time to a hospital terminal for remote monitoring by doctors.

[0018] Preferably, the broadband acoustic immittance test equipment in the data acquisition module covers a frequency range of 226 to 8000 Hz, and synchronously records the first peak sound energy absorption rate, the second peak sound energy absorption rate and the middle ear resonance frequency.

[0019] Preferably, the pre-processing module includes a noise filtering unit and a data alignment unit, which are used to eliminate environmental noise interference and align the acoustic immittance data with the hearing threshold in the frequency dimension.

[0020] Preferably, the feature extraction module uses correlation analysis and variance analysis to screen features that are significantly correlated with the otosclerosis stage, and preferentially retains parameters associated with the first peak sound energy absorption rate and the degree of hearing loss.

[0021] Preferably, the machine learning algorithms in the model training module include support vector machines, random forests and deep neural networks, and a cross-validation method is used to optimize model hyperparameters.

[0022] Preferably, the bone conduction cochlear implant of the life-assistance execution module supports multi-band acoustic energy emission function, and the probe has a built-in micro sensor for collecting acoustic immittance data in the patient's daily environment and synchronizing the data to the system cloud through a wireless communication module.

[0023] Preferably, the microsensor supports adaptive noise suppression function, can separate effective acoustic immittance signals in complex environments, and automatically calibrate the probe pressure to adapt to changes in the external auditory canal morphology.

[0024] Preferably, the time series analysis of the prediction module adopts an ARIMA model or an LSTM network, and the prediction results are displayed through a heat map to show the change trend of the hearing threshold at different time nodes.

[0025] Preferably, the report generation module generates a dynamic hearing health report based on the patient's daily test data, and pushes personalized rehabilitation training suggestions and medication reminders through the user interaction module.

[0026] Preferably, the remote collaboration module also includes a doctor monitoring interface for displaying the patient's acoustic immittance data, hearing threshold change curve and prediction trend chart at different periods in real time, and supports the generation of alarms by marking abnormal data.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention effectively combines broadband acoustic immittance testing with hearing testing. A pure tone audiometer is used to play pure tone stimuli corresponding to the broadband acoustic immittance test frequency, and the intensity and frequency are adjusted until the patient perceives it. The hearing threshold is then recorded. Since broadband acoustic immittance testing already covers a relatively wide frequency range (226-8000 Hz), these frequencies can be used directly for hearing testing without the need to set additional test frequencies. A comprehensive hearing test is performed by simulating the frequency sounds used in the broadband acoustic immittance test, thereby simplifying the testing process and improving testing efficiency. Furthermore, the system utilizes a machine learning algorithm to construct an otosclerosis staging and classification model and a symptom development prediction model, enabling automatic staging of the patient's hearing loss and accurate prediction of symptom development trends. This not only provides doctors with a more objective and accurate basis for diagnosis, but also provides patients with personalized lifestyle advice and treatment plans.

[0029] 2. This invention integrates a broadband acoustic immittance probe with a bone conduction cochlear implant, achieving the dual functions of hearing assistance and disease monitoring. While improving the patient's hearing, the cochlear implant regularly performs broadband acoustic immittance testing through the probe and transmits the test data in real time to the hospital terminal for remote monitoring by doctors. This not only facilitates the patient's daily life, but also provides doctors with continuous monitoring data, helping to adjust treatment plans in a timely manner. The probe's built-in microsensor supports adaptive noise suppression, can isolate effective acoustic immittance signals in complex environments, and automatically calibrates the probe pressure to adapt to changes in the external auditory canal morphology, further improving the accuracy and stability of the test.

[0030] 3. The present invention uses a remote collaboration module to view the patient's acoustic immittance data, hearing threshold change curve and prediction trend chart in real time, so as to detect abnormal situations in time and provide intervention.

[0031] In summary, the life-assistance system for patients with deafness and hearing loss of the present invention integrates the advantages of existing technologies and combines the innovative application of cochlear implants to provide more comprehensive, efficient and personalized life-assistance services for patients with hearing impairments such as otosclerosis, thereby improving the patients' diagnostic accuracy, treatment effects and quality of life. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the system of the present invention;

[0033] Figure 2 This is a schematic diagram of the life-assistance execution module of the present invention;

[0034] Figure 3 Schematic diagram of the pre-processing module of the present invention;

[0035] Figure 4 Schematic diagram of the remote collaboration module of the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0037] A life-assisting system for deaf and hearing-impaired patients, see Figures 1 to 4 , including data acquisition module, preprocessing module, feature extraction module, model training module, classification and rating module, prediction module, user interaction module, feedback optimization module, report generation module, remote collaboration module and life assistance execution module;

[0038] The data acquisition module is used to collect the patient's middle ear immittance data and hearing threshold data through a broadband immittance test device and a pure tone audiometer;

[0039] The pre-processing module is used to standardize the collected acoustic immittance data and hearing test data and correct outliers;

[0040] The feature extraction module is used to extract the resonance frequency, the peak characteristics of the acoustic energy absorption rate and the ear canal volume parameters from the acoustic immittance data;

[0041] The model training module is used to build an otosclerosis staging classification model and a symptom development prediction model based on machine learning algorithms;

[0042] The classification and rating module is used to stage and grade the patient's hearing loss according to the model output results;

[0043] The prediction module is used to predict the development trend of patients' hearing symptoms by combining time series analysis of historical data;

[0044] The user interaction module is used to visually display test results, classification ratings, and prediction charts to patients and doctors;

[0045] The feedback optimization module is used to collect clinical feedback data and iteratively optimize model parameters;

[0046] The report generation module is used to automatically generate standardized medical reports containing diagnostic recommendations;

[0047] The remote collaboration module is used to support encrypted transmission of patient data and model sharing among multiple medical institutions;

[0048] The life-assistance execution module includes a bone conduction cochlear implant with an integrated broadband acoustic immittance probe. While improving the patient's hearing, the cochlear implant regularly performs broadband acoustic immittance tests through the probe and transmits the test data in real time to the hospital terminal for remote monitoring by doctors.

[0049] Specifically, the broadband acoustic immittance test equipment in the data acquisition module covers a frequency range of 226 to 8000 Hz, and simultaneously records the first peak sound energy absorption rate, the second peak sound energy absorption rate and the middle ear resonance frequency.

[0050] More specifically, the preprocessing module includes a noise filtering unit and a data alignment unit, which are used to eliminate environmental noise interference and align the acoustic immittance data with the hearing threshold in the frequency dimension.

[0051] Furthermore, the feature extraction module uses correlation analysis and variance analysis to screen features that are significantly correlated with the stage of otosclerosis, and prioritizes the parameters associated with the first peak sound energy absorption rate and the degree of hearing loss.

[0052] Furthermore, the machine learning algorithms in the model training module include support vector machines, random forests, and deep neural networks, and cross-validation methods are used to optimize model hyperparameters.

[0053] It is worth noting that the bone conduction cochlear implant of the life-assistance execution module supports multi-band sound energy emission function. The probe has a built-in micro sensor for collecting acoustic immittance data in the patient's daily environment and synchronizing the data to the system cloud through the wireless communication module.

[0054] It is worth noting that the microsensor supports adaptive noise suppression function, which can separate effective acoustic immittance signals in complex environments and automatically calibrate the probe pressure to adapt to changes in the external auditory canal morphology.

[0055] It is worth mentioning that the time series analysis of the prediction module adopts the ARIMA model or LSTM network, and the prediction results show the change trend of hearing thresholds at different time nodes through heat maps.

[0056] It is worth noting that the report generation module generates dynamic hearing health reports based on the patient's daily test data, and pushes personalized rehabilitation training suggestions and medication reminders through the user interaction module.

[0057] It is worth emphasizing that the remote collaboration module also includes a doctor monitoring interface, which is used to display the patient's acoustic immittance data, hearing threshold change curve and predicted trend chart at different periods in real time, and supports the generation of alarms by marking abnormal data.

[0058] Example 1

[0059] Comprehensive testing and prediction for patients with mild hearing loss

[0060] Background: Patient A, a 35-year-old male, was diagnosed with early otosclerosis and mild hearing loss (PTA = 28 dB).

[0061] method:

[0062] 1. Data collection: Broadband acoustic immittance testing (226-8000 Hz) showed a first-peak acoustic energy absorption rate of 78.5% (frequency = 1200 Hz), ear canal volume = 1.1 ml, and resonance frequency = 850 Hz.

[0063] 2. Model prediction: The LSTM time series model analyzes historical data (6 months) and predicts that the hearing threshold change will be +3dB in the next 3 months.

[0064] Results: The system automatically generated a mild classification report, recommended quarterly review, and pushed personalized ear protection recommendations (such as avoiding noise exposure) through the user interaction module.

[0065] Conclusion: The system integrates testing and prediction functions to provide early warning of potential hearing loss and assist in early intervention.

[0066] Example 2

[0067] Real-time monitoring and adjustment for patients with moderate hearing loss

[0068] Background: Patient B, female, 48 years old, moderate hearing loss (PTA = 42dB), wears a bone conduction cochlear implant

[0069] method:

[0070] 1. Life-assistance execution module: The cochlear implant automatically performs acoustic immittance testing every week, the probe pressure is adaptively calibrated (error <±5daPa), and the data is uploaded in real time.

[0071] 2. Remote collaboration: The doctor finds through the monitoring interface that the first peak sound energy absorption rate has dropped to 72% (frequency = 1450 Hz), triggering an alarm.

[0072] Results: The doctor remotely adjusted the cochlear implant sound energy parameters (increasing high-frequency compensation by 5dB), and the patient's hearing threshold improved to 38dB.

[0073] Conclusion: The combination of real-time monitoring and remote intervention can improve the treatment effect.

[0074] Example 3

[0075] Group management of patients with severe hearing loss

[0076] Background: A hospital conducted centralized management of 20 patients with severe otosclerosis (PTA ≥ 65dB).

[0077] method:

[0078] 1. Classification and rating module: automatically classifies patients into four severe levels (L1-L4), where the average ABG of patients in level L3 is 52dB.

[0079] 2. Report generation module: Dynamic reports show that 50% of patients have an annual hearing threshold increase of >8dB, and surgical intervention is recommended.

[0080] Results: Eight patients who needed surgery were selected systematically, and their average ABG decreased to 25dB after surgery.

[0081] Conclusion: Group grading and dynamic reporting optimize the allocation of medical resources and improve the success rate of surgery.

[0082] Example 4

[0083] Noise suppression testing in complex environments

[0084] Background: Patient C, a 60-year-old male, often works in a noisy environment (factory) and has moderate to severe hearing loss (PTA=58dB).

[0085] method:

[0086] 1. Micro sensor: Adaptive noise suppression function reduces ambient noise (85dB) to 20dB, effectively extracting acoustic immittance signals.

[0087] 2. Feature extraction: First peak sound energy absorption rate = 68% (frequency = 1600 Hz), which is less than 3% different from the quiet environment test.

[0088] Results: The system accurately identified the trend of hearing deterioration (PTA=63dB after 6 months) and recommended replacement with a high-power cochlear implant.

[0089] Conclusion: Noise suppression technology ensures data reliability in complex environments and avoids misdiagnosis.

[0090] Example 5

[0091] Broadband acoustic immittance and pure tone audiometry complement each other as subjective and objective methods for staging otosclerosis

[0092] 1. Data of broadband acoustic immittance at each stage according to hearing loss classification

[0093] Statistical analysis of broadband acoustic immittance testing data from 136 patients after staging is available (Table 1). The mean formant frequency increased with increasing hearing loss severity, but the correlation between formant frequency and stage was weak (p = 0.273) and not statistically significant. The maximum values ​​for ear canal volume, 226 Hz / 1000 Hz compliance, and mean peak pressure (1000 Hz 0 daPa / 226 Hz 0 daPa) were all found in the moderate hearing loss group, but the correlation between each data point and stage was weak (Table 2) and not statistically significant.

[0094] Table 1. Data of broadband acoustic immittance in different stages of hearing loss classification

[0095]

[0096]

[0097] (Continued)

[0098]

[0099] Table 2 Significance of various data of broadband acoustic immittance in different stages of hearing loss classification

[0100]

[0101] 2. According to the preoperative pure tone audiometry ABG classification, the broadband acoustic immittance data of each phase

[0102] Statistical analysis of the various data from the broadband acoustic immittance test after staging of 136 patients was available (Table 3). The maximum resonance peak frequency appeared in the M group, and its value did not change in a single pattern with the increase of ABG value. The maximum mean pressure values ​​of 1000Hz0daPa / 226Hz0daPa appeared in the L group, and were significantly different from those of the S and M groups. The maximum 226Hz / 1000Hz acoustic compliance value appeared in the S group, and showed an overall downward trend with the increase of ABG value. The maximum mean peak pressure value appeared in the L group, and its value showed a single increasing trend with the increase of ABG value. The above 7 types of data had a low correlation with the staging (Table 4) and were not statistically significant.

[0103] Table 3 Data of broadband acoustic immittance in each phase according to preoperative pure tone audiometry ABG classification

[0104]

[0105] (Continued)

[0106]

[0107] Table 4 Significance of broadband acoustic immittance data in each stage according to preoperative pure tone audiometry ABG classification

[0108]

[0109] 3. Data on broadband acoustic immittance and sound energy absorption rate by stage of hearing loss classification

[0110] Analysis of broadband acoustic immittance sound energy absorption rate data for 136 patients after staging (Table 5) revealed that, with the exception of the frequency corresponding to the first peak sound energy absorption rate, which showed an increasing trend with increasing hearing loss, the remaining data did not show a single change with increasing hearing loss. The maximum sound energy absorption rate occurred in the mild-to-moderate hearing loss group, the maximum second peak sound energy absorption rate occurred in the severe hearing loss group, and the maximum first and second peak sound energy absorption rates occurred in the moderate hearing loss group. The correlation between various data and staging is shown in the figure (Table 6). The first peak sound energy absorption rate was correlated with the degree of hearing loss (p = 0.039 < 0.05, which was statistically significant). The remaining data were not statistically significant.

[0111] Table 5 Data on broadband acoustic immittance and sound energy absorption rate in different stages of hearing loss classification

[0112]

[0113] (Continued)

[0114]

[0115] Table 6 Significance of data related to broadband acoustic immittance and sound energy absorption rate in different stages of hearing loss classification

[0116]

[0117] 4. Data related to broadband acoustic impedance and sound energy absorption rate at each stage according to preoperative pure tone audiometry ABG classification

[0118] Analysis of broadband acoustic immittance sound energy absorption rate data for 136 patients after staging revealed that the maximum sound energy absorption rate and the first peak sound energy absorption rate were highest in Group M, the first peak frequency and the second peak sound energy absorption rate were highest in Group L, and the second peak frequency and the difference between the two peak sound energy absorption rates were highest in Group S. The correlation between these data and staging is shown in the figure (Table 8). The significance of the data in all six groups was low and not statistically significant.

[0119] Table 7 Data on broadband acoustic immittance and sound energy absorption rate at each stage according to preoperative pure tone audiometry ABG classification

[0120]

[0121] (Continued)

[0122]

[0123] Table 8 Significance of relevant data of broadband acoustic impedance and sound energy absorption rate at each stage according to preoperative pure tone audiometry ABG classification

[0124]

[0125] Comparative Example 1

[0126] Traditional step-by-step testing process

[0127] Background: Pure tone audiometry and acoustic immittance testing were performed independently without data integration.

[0128] Methods: Fifty patients were given two tests, each taking an average of 45 minutes.

[0129] result:

[0130] The test efficiency is low and patient compliance is poor (30% do not complete the retest).

[0131] Doctors need to manually compare data, and the misdiagnosis rate is as high as 18%.

[0132] Conclusion: The step-by-step process is inefficient and error-prone and cannot support accurate staging.

[0133] Comparative Example 2

[0134] Existing systems without predictive capabilities

[0135] Background: A hospital uses traditional hearing aids and regular outpatient follow-up without a prediction model.

[0136] Methods: 100 patients were followed up for one year, and the progression of the disease was judged based on the doctors' experience.

[0137] result:

[0138] 40% of patients fail to adjust their treatment plans in a timely manner, resulting in accelerated hearing loss (annual increase >10dB).

[0139] Emergency surgery rates increased by 25% and medical costs rose by 30%.

[0140] Conclusion: The lack of a predictive model leads to passive treatment and prevents early intervention.

[0141] By comparing the embodiments with the comparative examples, the system of the present invention shows advantages in efficiency, accuracy and patient management.

[0142] In addition, the components designed in the present invention are all universal standard parts or components known to those skilled in the art. Their structures and principles can be known to those skilled in the art through technical manuals or conventional experimental methods. They can be fully implemented by those skilled in the art. Needless to say, the content protected by the present invention does not involve improvements to internal structures and methods.

[0143] The embodiments disclosed in the present invention are preferred embodiments, but are not limited to them. Ordinary technicians in this field can easily understand the spirit of the present invention based on the above embodiments and make different extensions and changes. As long as they do not deviate from the spirit of the present invention, they are all within the scope of protection of the present invention.

Claims

1. A life-assistance system for patients with deafness and hearing loss, characterized in that: It includes data acquisition module, preprocessing module, feature extraction module, model training module, classification and rating module, prediction module, user interaction module, feedback optimization module, report generation module, remote collaboration module and life assistance execution module; The data acquisition module is used to collect the patient's middle ear acoustic immittance data and hearing threshold data through a broadband acoustic immittance test device and a pure tone audiometer; The pre-processing module is used to perform standardization processing and outlier correction on the collected acoustic immittance data and hearing test data; The feature extraction module is used to extract the resonance frequency, the peak characteristics of the acoustic energy absorption rate and the ear canal volume parameters from the acoustic immittance data; The model training module is used to construct an otosclerosis staging classification model and a symptom development prediction model based on a machine learning algorithm; The classification and rating module is used to stage and grade the patient's hearing loss according to the model output results; The prediction module is used to predict the development trend of the patient's hearing symptoms by combining time series analysis of historical data; The user interaction module is used to visually display test results, classification ratings and prediction charts to patients and doctors; The feedback optimization module is used to collect clinical feedback data and iteratively optimize model parameters; The report generation module is used to automatically generate a standardized medical report containing diagnostic recommendations; The remote collaboration module is used to support encrypted transmission of patient data and model sharing among multiple medical institutions; The life-assistance execution module includes a bone conduction cochlear implant with an integrated broadband acoustic immittance probe. While improving the patient's hearing, the cochlear implant regularly performs broadband acoustic immittance tests through the probe and transmits the test data in real time to a hospital terminal for remote monitoring by doctors.

2. The life-assisting system for deaf and hearing-impaired patients according to claim 1, characterized in that: The broadband acoustic immittance test equipment in the data acquisition module covers a frequency range of 226 to 8000 Hz, and simultaneously records the first peak sound energy absorption rate, the second peak sound energy absorption rate and the middle ear resonance frequency.

3. The life-assisting system for deaf and hearing-impaired patients according to claim 1, characterized in that: The preprocessing module includes a noise filtering unit and a data alignment unit, which are used to eliminate environmental noise interference and align the acoustic immittance data with the hearing threshold in the frequency dimension.

4. The life-assisting system for deaf and hearing-impaired patients according to claim 1, characterized in that: The feature extraction module uses correlation analysis and variance analysis to screen features that are significantly correlated with the stages of otosclerosis, and prioritizes retaining parameters associated with the first peak sound energy absorption rate and the degree of hearing loss.

5. The life-assisting system for deaf and hearing-impaired patients according to claim 1, characterized in that: The machine learning algorithms in the model training module include support vector machines, random forests, and deep neural networks, and a cross-validation method is used to optimize model hyperparameters.

6. The life-assisting system for deaf and hearing-impaired patients according to claim 1, characterized in that: The bone conduction cochlear implant of the life-assistance execution module supports multi-band sound energy emission function. The probe has a built-in micro sensor for collecting acoustic immittance data in the patient's daily environment and synchronizing the data to the system cloud through a wireless communication module.

7. The life-assisting system for deaf and hearing-impaired patients according to claim 6, characterized in that: The microsensor supports adaptive noise suppression function, can separate effective acoustic immittance signals in complex environments, and automatically calibrate the probe pressure to adapt to changes in the external auditory canal morphology.

8. The life-assisting system for deaf and hearing-impaired patients according to claim 1, characterized in that: The time series analysis of the prediction module adopts ARIMA model or LSTM network, and the prediction results are displayed through heat map to show the change trend of hearing threshold at different time nodes.

9. The life-assisting system for deaf and hearing-impaired patients according to claim 1, characterized in that: The report generation module generates a dynamic hearing health report based on the patient's daily test data, and pushes personalized rehabilitation training suggestions and medication reminders through the user interaction module.

10. The life-assisting system for deaf and hearing-impaired patients according to claim 1, characterized in that: The remote collaboration module also includes a doctor monitoring interface for displaying the patient's acoustic immittance data, hearing threshold change curve and prediction trend chart at different periods in real time, and supports marking abnormal data to generate alarms.

Images