CN117747077A - Ophthalmic full-flow medical service system and method based on intelligent technology - Google Patents
Ophthalmic full-flow medical service system and method based on intelligent technology Download PDFInfo
- Publication number
- CN117747077A CN117747077A CN202410016032.4A CN202410016032A CN117747077A CN 117747077 A CN117747077 A CN 117747077A CN 202410016032 A CN202410016032 A CN 202410016032A CN 117747077 A CN117747077 A CN 117747077A
- Authority
- CN
- China
- Prior art keywords
- patient
- ophthalmic
- image
- treatment
- intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000005516 engineering process Methods 0.000 title claims abstract description 39
- 238000011282 treatment Methods 0.000 claims abstract description 104
- 201000010099 disease Diseases 0.000 claims abstract description 79
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 79
- 238000004458 analytical method Methods 0.000 claims abstract description 44
- 238000003745 diagnosis Methods 0.000 claims abstract description 35
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 34
- 238000010191 image analysis Methods 0.000 claims abstract description 25
- 230000004044 response Effects 0.000 claims abstract description 25
- 239000000463 material Substances 0.000 claims abstract description 13
- 230000000694 effects Effects 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000011269 treatment regimen Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 21
- 238000003064 k means clustering Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 13
- 238000011161 development Methods 0.000 claims description 12
- 230000018109 developmental process Effects 0.000 claims description 12
- 230000003902 lesion Effects 0.000 claims description 12
- 230000002068 genetic effect Effects 0.000 claims description 11
- 230000003993 interaction Effects 0.000 claims description 9
- 229940079593 drug Drugs 0.000 claims description 7
- 239000003814 drug Substances 0.000 claims description 7
- 238000010801 machine learning Methods 0.000 claims description 7
- 230000036541 health Effects 0.000 claims description 6
- 230000001575 pathological effect Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 208000030533 eye disease Diseases 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 5
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 210000004087 cornea Anatomy 0.000 claims description 4
- 230000003631 expected effect Effects 0.000 claims description 4
- 239000000090 biomarker Substances 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000003058 natural language processing Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000011160 research Methods 0.000 claims description 2
- 208000024891 symptom Diseases 0.000 abstract description 4
- 210000004204 blood vessel Anatomy 0.000 description 5
- 238000012937 correction Methods 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 208000010412 Glaucoma Diseases 0.000 description 1
- 206010038848 Retinal detachment Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000004836 empirical method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004264 retinal detachment Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention relates to the technical field of biomedical services, in particular to an ophthalmic full-flow medical service system and method based on an intelligent technology. Firstly, preprocessing professional ophthalmic image data of a patient, carrying out image recognition by utilizing an intelligent ophthalmic image analysis algorithm, and recognizing an image area matched with a known disease mode to obtain a recognition comparison result so as to form primary diagnosis; then, integrating and analyzing the primary diagnosis result and the patient data information, and exploring the disease mode, risk factors and treatment response trend to obtain a comprehensive analysis report; and finally, designing a treatment scheme of the patient based on the comprehensive analysis report, making educational materials, displaying the treatment scheme, collecting and analyzing feedback of the patient, and evaluating the effectiveness of the current treatment scheme according to the feedback and the treatment effect of the patient. Solves the technical problems of inaccurate analysis of the ophthalmic symptoms of the patient and lower personalized service level in the prior art.
Description
Technical Field
The invention relates to the technical field of biomedical services, in particular to an ophthalmic full-flow medical service system and method based on an intelligent technology.
Background
With the development of artificial intelligence technology, intelligent medical treatment is becoming an important development direction in the medical field. Particularly in the field of ophthalmic medical treatment, accurate diagnosis and treatment of eye diseases can be realized by utilizing technologies such as big data, machine learning and the like. However, at present, intelligent medical treatment still faces a plurality of challenges in terms of data processing efficiency, diagnosis accuracy and the like. The ophthalmic diseases have the characteristics of various types, complex symptoms and the like, and have extremely high requirements on the accuracy of diagnosis and treatment. In addition, with the advent of the aging society, the number of patients suffering from ophthalmic diseases has been continuously increased, and there has been an increasing demand for efficient and accurate medical services. Current ophthalmic medical systems rely heavily on the experience of doctors for diagnosis and treatment, which limits the efficiency and accuracy of diagnosis and treatment to some extent. Meanwhile, the lack of effective data integration and intelligent analysis means makes patient management and subsequent tracking of therapeutic effects difficult.
There are many methods for medical services, and the patent of our invention, "an intelligent processing method and system for medical services", has application number: "CN202310578627.4", publication date: 2023.06.23, mainly comprises: planning a hospital visit route of a target patient by acquiring visit service information of the target patient; marking a plurality of guideline connection devices and a plurality of correction connection devices; performing temporary connection and identity acquisition, and marking target connection equipment; when the target connection equipment is the guiding connection equipment, auxiliary live-action navigation is carried out; and when the target connection equipment is the correction connection equipment, performing auxiliary correction vibration. Can plan the route of seeing a doctor in the hospital, mark a plurality of guide connecting device and a plurality of correction connecting device, through the temporary connection with the mobile terminal of target patient, discern target patient's position, carry out live-action navigation and correct vibrations, make the customer can be accurate according to the route of seeing a doctor in the hospital reach the destination of seeing a doctor, more convenient, directly perceived than sign and manual guidance to make the patient see a doctor more convenient, high-efficient.
However, the above technology has at least the following technical problems: a technical problem of inaccurate analysis of the ophthalmic condition of the patient and a low personalized service level.
Disclosure of Invention
The invention provides an ophthalmic full-flow medical service system and method based on an intelligent technology, which solve the technical problems of inaccurate analysis of ophthalmic symptoms of patients and lower personalized service level in the prior art, and realize the technical effects of high-accuracy medical diagnosis and high-level personalized medical service.
The invention discloses an ophthalmic full-flow medical service system and method based on an intelligent technology, which concretely comprises the following technical scheme:
an ophthalmic full-flow medical service system based on an intelligent technology comprises the following parts:
the system comprises an intelligent image analysis module, a database, a big data processing and analysis module, a personalized treatment scheme generator, a patient interaction and education module and a remote medical consultation module;
the intelligent image analysis module is used for collecting professional ophthalmic images, wherein the professional ophthalmic images comprise fundus photos and cornea topographic maps of patients, analyzing the professional ophthalmic images by using an image recognition and deep learning algorithm, recognizing the characteristics of the ophthalmic lesions, obtaining image analysis results, comparing known pathological image data in a database based on the image analysis results, and providing preliminary diagnosis on diseases;
the database comprises known pathological image data information, patient data information and professional medical knowledge; the patient data information includes medical history, genetic information, lifestyle habits; the professional medical knowledge comprises ophthalmic research results, ophthalmic disease data and drug response data;
the big data processing and analyzing module processes and analyzes the image analysis result from the intelligent image analyzing module and the patient data information in the database, discovers the disease mode, risk factors and treatment reaction trend, and obtains a comprehensive analysis report on the basis of the preliminary diagnosis of the disease provided by the intelligent image analyzing module; the analysis-by-synthesis report contains personalized treatment advice and detailed assessment of patient condition;
the personalized treatment scheme generator designs a treatment scheme most suitable for a patient by utilizing an intelligent algorithm based on the comprehensive analysis report provided by the big data processing and analysis module; comprehensive treatment plans including medication, surgical plan, lifestyle adjustments;
the patient interaction and education module provides the patient with disease-related educational material, detailed explanation of the treatment regimen, and expected effects based on the treatment regimen from the personalized treatment regimen generator, while collecting questions, demands, and feedback raised by the patient for improving the treatment regimen;
the remote medical consultation module provides remote medical consultation services for the patient based on the health condition information of the patient and the output results of the personalized treatment scheme generator and the patient interaction and education module, and the remote medical consultation services comprise video conferences and online chatting.
An ophthalmic full-flow medical service method based on an intelligent technology comprises the following steps:
s1, preprocessing professional ophthalmic image data of a patient, carrying out image recognition by utilizing an intelligent ophthalmic image analysis algorithm, recognizing an image area matched with a known disease mode, obtaining a recognition comparison result, and forming preliminary diagnosis according to the recognition comparison result;
s2, integrating and analyzing the primary diagnosis result and the patient data information, and exploring a disease mode, risk factors and treatment response trend to obtain a comprehensive analysis report;
s3, designing a treatment scheme of the patient based on the comprehensive analysis report, making educational materials and displaying the treatment scheme based on the disease type and the treatment scheme of the patient, collecting and analyzing feedback of the patient, and evaluating the effectiveness of the current treatment scheme according to the feedback and the treatment effect of the patient.
Preferably, the S1 specifically includes:
preprocessing professional ophthalmic image data of a patient to obtain preprocessed professional ophthalmic image data; and performing image recognition on the preprocessed professional ophthalmic image data by using an intelligent ophthalmic image analysis algorithm.
Preferably, in the S1, the method further includes:
in the process of image recognition by utilizing an intelligent ophthalmologic image analysis algorithm, firstly, an intelligent edge sensor is designed to extract the preprocessed professional ophthalmologic image data; the intelligent edge sensor extracts edge characteristics of the image by introducing adaptive coefficients and enhancement functions; after the edge characteristics are acquired, a statistical method of a gray level co-occurrence matrix is used for carrying out texture analysis extraction; dividing the image into different areas by using a threshold segmentation method, matching the divided image with a known case, and identifying an image area matched with a known disease mode to obtain an identification comparison result; and finally, forming preliminary diagnosis according to the identification comparison result.
Preferably, in S2, the method specifically includes:
integrating the primary diagnosis result and the patient data information to obtain a comprehensive data set, cleaning the comprehensive data set, and processing the cleaned data by using a data conversion technology; features and biomarkers related to diagnosis and treatment of eye diseases are identified using data mining techniques to obtain a comprehensive feature set.
Preferably, in the S2, the method further includes:
based on the comprehensive feature set, the disease mode, risk factors and treatment response trend are discovered, and a comprehensive analysis report is obtained; for disease patterns, identifying different types of ophthalmic disease patterns using a K-means clustering algorithm; aiming at the risk factors, an association rule learning method is applied to find out potential risk factors of disease development, and the weight of each risk factor on the influence of the disease development is determined; and predicting the treatment response trend of the patient by using machine learning aiming at the treatment response trend to obtain the treatment response trend.
Preferably, in the S2, the method further includes:
the specific implementation process of identifying different types of ophthalmic disease patterns using a K-means clustering algorithm is as follows: firstly, calculating error square sums under different clusters by using an elbow rule, and determining a K value; further performing K-means clustering to obtain a clustering result, and performing feature mapping on features of the clustering result and the ophthalmic disease data features in the professional medical knowledge.
Preferably, in the S2, the method further includes:
in the process of identifying different types of ophthalmic disease patterns through a K-means clustering algorithm, a pattern enhancement data point distance formula is introduced to calculate the distance from each data point in the comprehensive feature set to each initial clustering center.
Preferably, the S3 specifically includes:
analyzing the comprehensive analysis report by using a natural language processing technology, calling patient data information in a database, analyzing personal preferences and demands of a patient by using a decision tree model, designing a treatment scheme by combining the health condition and preferences of the patient by using a random forest, and performing personalized adjustment by using a genetic algorithm; a treatment regimen is obtained that meets the individual needs of the patient.
The technical scheme of the invention has the beneficial effects that:
1. the invention can more accurately identify the key characteristics in the fundus image through the image processing technology and the intelligent algorithm, and the automatic analysis greatly improves the accuracy and the efficiency of diagnosis and reduces the requirement of relying on subjective judgment of doctors; the self-adaptive coefficient in the intelligent edge sensor can be automatically adjusted according to the local contrast of the image, so that the edge detection is more accurate; enhancement functions based on fundus specific structures can effectively emphasize blood vessels and lesion areas, helping to more accurately identify and analyze these key features.
2. The comprehensive understanding of the disease is provided by integrating the primary diagnosis result of the patient and detailed patient data information, such as medical record, genetic information, life habit and the like, and the comprehensive view is helpful for finding out the multidimensional characteristics and potential risk factors of the disease; different types of ophthalmic disease patterns can be more accurately identified by using a K-means clustering algorithm and a pattern enhancement distance formula; the potential risk factors of disease development are found out by applying an association rule learning method, and the risk factors are weighted by combining expert experience, so that the most critical risk factors can be identified; the treatment response trend of the patient is predicted by using a machine learning technology, so that a basis is provided for formulating a more effective treatment strategy.
3. The invention can effectively improve the understanding of patients on diseases and treatment schemes by formulating education materials easy to understand and presenting the information by using multimedia means such as videos and charts; the communication between doctors and patients is enhanced by means of detailed treatment scheme information, interactive question-answering links and the like provided by mobile application, and the satisfaction degree and treatment compliance of patients are improved; continuous evaluation and adjustment are carried out according to feedback and treatment effects of patients, so that the optimal state of a treatment scheme is always ensured, and rationality and safety of treatment adjustment are ensured through negotiation with a treatment team.
Drawings
FIG. 1 is a block diagram of an ophthalmic full-flow medical service system based on an intelligent technology according to an embodiment of the present invention;
fig. 2 is a flowchart of an ophthalmic full-flow medical service method based on an intelligent technology according to an embodiment of the present invention.
Detailed Description
In order to further illustrate the technical means and effects adopted by the present invention to achieve the preset purpose, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes the specific scheme of the full-flow medical ophthalmic service system and method based on the intelligent technology provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a block diagram of an ophthalmic full-flow medical service system based on intelligent technology according to an embodiment of the present invention is shown, where the system includes the following parts:
the system comprises an intelligent image analysis module, a database, a big data processing and analysis module, a personalized treatment scheme generator, a patient interaction and education module and a remote medical consultation module;
the intelligent image analysis module collects professional ophthalmic images, such as high-resolution fundus photos and cornea topographic maps of patients, analyzes the professional ophthalmic images by using an image recognition and deep learning algorithm, recognizes ophthalmic lesion features such as fundus abnormalities and cornea deformations, obtains image analysis results, compares known pathological image data in a database based on the image analysis results, and provides preliminary diagnosis on diseases;
the database comprises known pathological image data information, patient data information and professional medical knowledge; patient data information such as medical history, genetic information, lifestyle habits; professional medical knowledge such as ophthalmic study results, ophthalmic disease data, and drug response data;
the big data processing and analyzing module processes and analyzes the image analysis result from the intelligent image analyzing module and the patient data information in the database, deeply discovers the disease mode, the risk factors and the treatment response trend, and obtains a comprehensive analysis report on the basis of preliminary diagnosis of the intelligent image analyzing module on the disease; the analysis by synthesis report contains personalized treatment advice and detailed assessment of patient condition;
the personalized treatment scheme generator designs a treatment scheme most suitable for a patient by utilizing an intelligent algorithm based on the comprehensive analysis report provided by the big data processing and analysis module; treatment protocols include comprehensive treatment plans including medication, surgical protocols, lifestyle adjustments;
the patient interaction and education module provides the patient with disease-related educational material, detailed explanation and expected effect of the treatment regimen based on the treatment regimen in the personalized treatment regimen generator, and at the same time, collects questions, demands and feedback raised by the patient for improving the treatment regimen;
the remote medical consultation module provides remote medical consultation service for the patient based on the health condition information of the patient and the output results of the personalized treatment scheme generator and the patient interaction and education module; the remote medical consultation service comprises video conference and online chat, so that the patient can conveniently communicate with doctors at home.
Referring to fig. 2, a flowchart of an ophthalmic full-flow medical service method based on an intelligent technology according to an embodiment of the present invention is shown, the method includes the following steps:
s1, preprocessing professional ophthalmic image data of a patient, carrying out image recognition by utilizing an intelligent ophthalmic image analysis algorithm, recognizing an image area matched with a known disease mode, obtaining a recognition comparison result, and forming preliminary diagnosis according to the recognition comparison result;
firstly, preprocessing professional ophthalmic image data of a patient, wherein the preprocessing comprises cutting, rotating and scaling of the image so as to adapt to subsequent image analysis, denoising and contrast enhancement processing so as to improve the image quality and obtain the preprocessed professional ophthalmic image data of the patient;
the method comprises the steps of performing image recognition on professional ophthalmic image data of a preprocessed patient by utilizing an intelligent ophthalmic image analysis algorithm, and firstly designing an intelligent edge sensor to perform feature extraction on the professional ophthalmic image data of the preprocessed patient, wherein image features comprise edges, textures, sizes, shapes and colors; the characteristics of the image such as size, shape and color are extracted by adopting the prior art, and specific characteristics of edges and textures are as follows:
the intelligent edge sensor is designed for detecting and identifying micro blood vessels and lesion areas in fundus images, extracting edge characteristics of the images, and the intelligent edge sensor is expressed as follows:
wherein a is an adaptive coefficient used for performing approximate calculation on the intensity gradient of the image, and automatically adjusting according to the local contrast of the image so as to improve the accuracy of edge detection; s (a) is an enhancement function based on the specific structure of the fundus for highlighting certain specific features in the image, such as the fundus blood vessel or lesion area; alpha is an adjusting factor for adjusting the degree of influence of the enhancement function S (A) on the final result; a is an input image and is a matrix representation of professional ophthalmic image data of the pre-processed patient; g x 、G y Is the edge intensity in the horizontal and vertical directions of the image, i.e. the edge characteristics of the image;
adaptive coefficient a:
wherein, Q is local contrast, which represents the variation degree of pixel intensity in a small region in the image, and high contrast means that the brightness variation of the image is more remarkable, and the brightness variation is obtained by analyzing the local region of the image, in particular calculating the standard deviation of the pixel intensity in the local region; q (Q) 0 Is a contrast threshold value, is used for determining the contrast level at which to adjust the coefficient a, and is obtained according to an empirical method; k is an adjustment coefficient for controlling sensitivity, obtained empirically; e is the base of natural logarithms;
enhancement function S (a) based on fundus-specific structure:
S(A)＝w v ·V(A)+w d ·D(A)
wherein V (A) is a vessel emphasizing function for emphasizing a vessel structure in the image, based on gradient information of the image and a specific vessel detection algorithm; d (A) is a lesion region emphasizing function for highlighting a lesion region in the image, and is realized by local texture analysis and other characteristic recognition methods specific to fundus images; w (w) v And w d Is a weight factor for balancing the contributions of the vessel emphasis function and the lesion region emphasis function, depending on the particular applicationManually adjusting the scene;
after the edge characteristics are acquired, texture analysis and extraction are carried out on the fundus specific textures by using a statistical method of a gray level co-occurrence matrix, wherein one element P (i, j|d, theta) of the gray level co-occurrence matrix represents the transition probability from a gray level value i to a gray level value j in a distance d and a direction theta; thereby obtaining texture features;
dividing the image into different areas by using a threshold segmentation method, and distinguishing a critical lesion area from a normal tissue so as to facilitate identification;
according to the feature matching, image identification is realized, the segmented image is matched with the known case based on the correlation coefficient, an image area matched with the known disease mode is identified, and an identification comparison result is obtained;
finally, according to the identification comparison result, combining the clinical symptoms and medical history of the patient to form preliminary diagnosis;
the invention can more accurately identify the key characteristics in the fundus image through the image processing technology and the intelligent algorithm, and the automatic analysis greatly improves the accuracy and the efficiency of diagnosis and reduces the requirement of relying on subjective judgment of doctors; the self-adaptive coefficient in the intelligent edge sensor can be automatically adjusted according to the local contrast of the image, so that the edge detection is more accurate; enhancement functions based on fundus specific structures can effectively emphasize blood vessels and lesion areas, helping to more accurately identify and analyze these key features.
S2, integrating and analyzing the primary diagnosis result and the patient data information, and exploring a disease mode, risk factors and treatment response trend to obtain a comprehensive analysis report;
integrating the primary diagnosis result of the patient with patient data information, such as medical record, genetic information, life habit and past disease history, to obtain a comprehensive data set, and ensuring the consistency and the integrity of the data format so as to facilitate subsequent analysis;
cleaning the comprehensive data set, such as removing irrelevant data, processing missing values, standardizing data formats, and applying data conversion technology, such as normalization or standardization, to prepare data for subsequent analysis;
next, key features related to diagnosis and treatment of eye diseases are identified using data mining techniques, such as principal component analysis, automatic feature extraction, while biomarkers, such as specific genetic markers, sign indicators, which may be related to the development of eye diseases, are identified to obtain a comprehensive feature set;
further, based on the comprehensive feature set, a disease mode, risk factors and treatment response trend are discovered, and a comprehensive analysis report is obtained;
aiming at the disease mode, a K-means clustering algorithm is used for identifying different types of ophthalmic disease modes, and the specific implementation process is as follows: firstly, calculating the error square sum under different clusters by using an elbow rule, and observing the change of the error square sum to determine the optimal cluster number (K value); k-means clustering is further performed:
step one, initializing a clustering center; randomly selecting K data points from the comprehensive feature set as an initial clustering center;
second, assigning data points; calculating the distance between each data point in the comprehensive feature set and each initial cluster center, wherein the distance is calculated by using Euclidean distance, and each data point is distributed to the cluster center closest to the data point to form K clusters;
thirdly, updating a clustering center; for each cluster, calculating the average value of all points in the cluster, and setting the average value as a new cluster center;
fourth, iterating; repeating the steps of distributing data points and updating the clustering center until the clustering center is not changed any more or reaches the preset iteration times;
obtaining a clustering result through the process, and carrying out feature mapping on the features of the clustering result and the features of the known ophthalmic disease data in the professional medical knowledge, wherein if the clustered data points show the feature of retinal detachment, the features can be mapped to related diseases; further identifying potential disease patterns by statistically analyzing common characteristics of the data within the clusters, such as where a cluster may represent a particular type of glaucoma;
in the process of executing the identification of different types of ophthalmic disease modes by using a K-means clustering algorithm, the K-means clustering algorithm may not be capable of effectively distinguishing some subtle but important disease modes due to the high dimensionality and complexity of ophthalmic disease data, the invention optimizes the clustering index basis in the process of distributing data points, and introduces a mode enhancement data point distance formula to calculate the distance from each data point in the comprehensive feature set to each initial clustering center, wherein the specific formula is as follows:
wherein D (i, C j ) Is the data point i to the clustering center C j Taking into account the conventional euclidean distance and local density information around the data point; x is x ik Is the kth eigenvalue of data point i in the eigenvalue space; c jk Is the cluster center C j A kth feature value in the feature space; n is the total number of data points in the integrated feature set; x is x i ,x l Respectively representing the ith and the ith data point; ||x i -x l I is the euclidean distance of data points i and i in the feature space; n is the dimension of the feature space, i.e., the number of features per data point; the formula not only considers the basic distance between the data points, but also considers the local density around each point, so that the actual similarity between the data points is reflected more accurately, the formula has important value in processing high-dimensional and complex ophthalmic disease data, and the clustering accuracy and the disease pattern recognition effect can be improved;
aiming at the risk factors, an association rule learning method is applied to find out potential risk factors of disease development, and the weight of each risk factor on the influence of the disease development is determined according to an expert experience method so as to identify the most critical risk factors;
predicting the treatment response trend of the patient by machine learning aiming at the treatment response trend to obtain the treatment response trend;
the analysis results are integrated, a detailed comprehensive analysis report is compiled, and the disease mode, risk factors and treatment response trend are summarized;
the comprehensive understanding of the disease is provided by integrating the primary diagnosis result of the patient and detailed patient data information, such as medical record, genetic information, life habit and the like, and the comprehensive view is helpful for finding out the multidimensional characteristics and potential risk factors of the disease; the K-means clustering algorithm and the mode enhancement distance formula are used, so that different types of ophthalmic disease modes can be identified more accurately, and the method has important value for processing complex high-dimensional data; the potential risk factors of disease development are found out by applying an association rule learning method, and the risk factors are weighted by combining expert experience, so that the most critical risk factors can be identified; the treatment response trend of the patient is predicted by using a machine learning technology, so that a basis is provided for formulating a more effective treatment strategy.
S3, designing a treatment scheme of the patient based on the comprehensive analysis report, making educational materials and displaying the treatment scheme based on the disease type and the treatment scheme of the patient, collecting and analyzing feedback of the patient, and evaluating the effectiveness of the current treatment scheme according to the feedback and the treatment effect of the patient.
Firstly, analyzing a comprehensive analysis report by using a natural language processing technology to obtain key information in the report, calling patient data information in a database, analyzing personal preferences and demands of a patient by using a decision tree model, designing a treatment scheme by combining the health condition and preferences of the patient by using a random forest, and performing personalized adjustment by using a genetic algorithm to ensure that the treatment scheme is suitable for personal characteristics; obtaining a treatment scheme meeting the personalized requirements of patients;
formulating an easily understood educational material, such as disease background, treatment regimen and possible side effects, based on the type of disease and treatment regimen of the patient; the educational materials are more vivid and easy to understand by using a multimedia mode such as video, charts and information charts; personalized customization of the complexity and depth of the educational material according to the educational background and understanding capabilities of the patient;
by the mobile application showing the patient with detailed information of the treatment regimen, clearly interpreting the expected effect of the treatment regimen and the possible risks to the patient, managing the expected value of the patient; providing an interactive question-answering link, and allowing a patient to ask questions and obtain timely feedback;
collecting feedback of the patient by using an online questionnaire, a mobile application feedback function or a direct face-to-face interview, and analyzing the feedback content of the patient by using a text analysis method and an emotion analysis method to know the opinion and the requirement of the patient on a treatment scheme;
evaluating the effectiveness of the current treatment regimen based on the feedback and treatment effect of the patient; adjustments to the treatment regimen, e.g., altering the drug dosage, treatment method, or other aspects of the treatment plan, if desired; when the scheme is adjusted, negotiating with doctors and pharmacists of a treatment team to ensure the rationality and safety of treatment adjustment;
after any significant adjustments are made, the improved treatment regimen is ultimately reviewed by the medical team. And displaying the adjusted treatment regimen to the patient, ensuring that the patient understands and agrees to the regimen; continuously monitoring the response and progress of the patient during the treatment, and further adjusting the treatment regimen as necessary based on the monitoring results and the continuous feedback of the patient;
the above-mentioned processes are integrated to implement perfect ophthalmic full-flow medical service.
The invention can effectively improve the understanding of patients on diseases and treatment schemes by formulating education materials easy to understand and presenting the information by using multimedia means such as videos and charts; the communication between doctors and patients is enhanced by means of detailed treatment scheme information, interactive question-answering links and the like provided by mobile application, and the satisfaction degree and treatment compliance of patients are improved; continuous evaluation and adjustment are carried out according to feedback and treatment effects of patients, so that the optimal state of a treatment scheme is always ensured, and rationality and safety of treatment adjustment are ensured through negotiation with a treatment team.
In summary, the ophthalmic full-flow medical service system and method based on the intelligent technology are completed.
The embodiment of the invention can more accurately identify the key characteristics in the fundus image through an image processing technology and an intelligent algorithm, and the automatic analysis greatly improves the accuracy and the efficiency of diagnosis and reduces the requirement of relying on subjective judgment of doctors; the self-adaptive coefficient in the intelligent edge sensor can be automatically adjusted according to the local contrast of the image, so that the edge detection is more accurate; enhancement functions based on fundus specific structures can effectively emphasize blood vessels and lesion areas, helping to more accurately identify and analyze these key features. By integrating the primary diagnosis results of the patient with detailed patient data information, such as medical records, genetic information, lifestyle habits and the like, a comprehensive understanding of the disease is provided, and such comprehensive view is helpful to discover multi-dimensional features and potential risk factors of the disease; the K-means clustering algorithm and the mode enhancement distance formula are used, so that different types of ophthalmic disease modes can be identified more accurately, and the method has important value for processing complex high-dimensional data; the potential risk factors of disease development are found out by applying an association rule learning method, and the risk factors are weighted by combining expert experience, so that the most critical risk factors can be identified; the treatment response trend of the patient is predicted by using a machine learning technology, so that a basis is provided for formulating a more effective treatment strategy. Through formulating easy-to-understand educational materials and presenting the information by using multimedia means such as videos and charts, the understanding of patients on diseases and treatment schemes can be effectively improved; the communication between doctors and patients is enhanced by means of detailed treatment scheme information, interactive question-answering links and the like provided by mobile application, and the satisfaction degree and treatment compliance of patients are improved; continuous evaluation and adjustment are carried out according to feedback and treatment effects of patients, so that the optimal state of a treatment scheme is always ensured, and rationality and safety of treatment adjustment are ensured through negotiation with a treatment team.
The sequence of the embodiments of the invention is merely for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (9)
1. The ophthalmic full-flow medical service system based on the intelligent technology is characterized by comprising the following parts:
the system comprises an intelligent image analysis module, a database, a big data processing and analysis module, a personalized treatment scheme generator, a patient interaction and education module and a remote medical consultation module;
the intelligent image analysis module is used for collecting professional ophthalmic images, wherein the professional ophthalmic images comprise fundus photos and cornea topographic maps of patients, analyzing the professional ophthalmic images by using an image recognition and deep learning algorithm, recognizing the characteristics of the ophthalmic lesions, obtaining image analysis results, comparing known pathological image data in a database based on the image analysis results, and providing preliminary diagnosis on diseases;
the database comprises known pathological image data information, patient data information and professional medical knowledge; the patient data information includes medical history, genetic information, lifestyle habits; the professional medical knowledge comprises ophthalmic research results, ophthalmic disease data and drug response data;
the big data processing and analyzing module processes and analyzes the image analysis result from the intelligent image analyzing module and the patient data information in the database, discovers the disease mode, risk factors and treatment reaction trend, and obtains a comprehensive analysis report on the basis of the preliminary diagnosis of the disease provided by the intelligent image analyzing module; the analysis-by-synthesis report contains personalized treatment advice and detailed assessment of patient condition;
the personalized treatment scheme generator designs a treatment scheme most suitable for a patient by utilizing an intelligent algorithm based on the comprehensive analysis report provided by the big data processing and analysis module; comprehensive treatment plans including medication, surgical plan, lifestyle adjustments;
the patient interaction and education module provides the patient with disease-related educational material, detailed explanation of the treatment regimen, and expected effects based on the treatment regimen from the personalized treatment regimen generator, while collecting questions, demands, and feedback raised by the patient for improving the treatment regimen;
the remote medical consultation module provides remote medical consultation services for the patient based on the health condition information of the patient and the output results of the personalized treatment scheme generator and the patient interaction and education module, and the remote medical consultation services comprise video conferences and online chatting.
2. The full-flow medical service method based on the intelligent technology is applied to the full-flow medical service system based on the intelligent technology as claimed in claim 1, and is characterized by comprising the following steps:
s1, preprocessing professional ophthalmic image data of a patient, carrying out image recognition by utilizing an intelligent ophthalmic image analysis algorithm, recognizing an image area matched with a known disease mode, obtaining a recognition comparison result, and forming preliminary diagnosis according to the recognition comparison result;
s2, integrating and analyzing the primary diagnosis result and the patient data information, and exploring a disease mode, risk factors and treatment response trend to obtain a comprehensive analysis report;
s3, designing a treatment scheme of the patient based on the comprehensive analysis report, making educational materials and displaying the treatment scheme based on the disease type and the treatment scheme of the patient, collecting and analyzing feedback of the patient, and evaluating the effectiveness of the current treatment scheme according to the feedback and the treatment effect of the patient.
3. The full-flow medical service method for ophthalmic use based on the intelligent technology according to claim 2, wherein S1 specifically comprises:
preprocessing professional ophthalmic image data of a patient to obtain preprocessed professional ophthalmic image data; and performing image recognition on the preprocessed professional ophthalmic image data by using an intelligent ophthalmic image analysis algorithm.
4. The full-flow medical service ophthalmic method based on intelligent technology according to claim 3, wherein in S1, further comprising:
in the process of image recognition by utilizing an intelligent ophthalmologic image analysis algorithm, firstly, an intelligent edge sensor is designed to extract the preprocessed professional ophthalmologic image data; the intelligent edge sensor extracts edge characteristics of the image by introducing adaptive coefficients and enhancement functions; after the edge characteristics are acquired, a statistical method of a gray level co-occurrence matrix is used for carrying out texture analysis extraction; dividing the image into different areas by using a threshold segmentation method, matching the divided image with a known case, and identifying an image area matched with a known disease mode to obtain an identification comparison result; and finally, forming preliminary diagnosis according to the identification comparison result.
5. The full-flow medical service method for ophthalmic use based on the intelligent technology according to claim 2, wherein in S2, specifically includes:
integrating the primary diagnosis result and the patient data information to obtain a comprehensive data set, cleaning the comprehensive data set, and processing the cleaned data by using a data conversion technology; features and biomarkers related to diagnosis and treatment of eye diseases are identified using data mining techniques to obtain a comprehensive feature set.
6. The full-flow medical service ophthalmic method based on intelligent technology according to claim 5, further comprising, in S2:
based on the comprehensive feature set, the disease mode, risk factors and treatment response trend are discovered, and a comprehensive analysis report is obtained; for disease patterns, identifying different types of ophthalmic disease patterns using a K-means clustering algorithm; aiming at the risk factors, an association rule learning method is applied to find out potential risk factors of disease development, and the weight of each risk factor on the influence of the disease development is determined; and predicting the treatment response trend of the patient by using machine learning aiming at the treatment response trend to obtain the treatment response trend.
7. The full-flow medical service ophthalmic method based on intelligent technology according to claim 6, further comprising, in S2:
the specific implementation process of identifying different types of ophthalmic disease patterns using a K-means clustering algorithm is as follows: firstly, calculating error square sums under different clusters by using an elbow rule, and determining a K value; further performing K-means clustering to obtain a clustering result, and performing feature mapping on features of the clustering result and the ophthalmic disease data features in the professional medical knowledge.
8. The full-flow medical service ophthalmic method based on intelligent technology according to claim 7, further comprising, in S2:
in the process of identifying different types of ophthalmic disease patterns through a K-means clustering algorithm, a pattern enhancement data point distance formula is introduced to calculate the distance from each data point in the comprehensive feature set to each initial clustering center.
9. The full-flow medical service method for ophthalmic use based on the intelligent technology according to claim 2, wherein S3 specifically comprises:
analyzing the comprehensive analysis report by using a natural language processing technology, calling patient data information in a database, analyzing personal preferences and demands of a patient by using a decision tree model, designing a treatment scheme by combining the health condition and preferences of the patient by using a random forest, and performing personalized adjustment by using a genetic algorithm; a treatment regimen is obtained that meets the individual needs of the patient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410016032.4A CN117747077B (en) | 2024-01-04 | 2024-01-04 | Ophthalmic full-flow medical service system and method based on intelligent technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410016032.4A CN117747077B (en) | 2024-01-04 | 2024-01-04 | Ophthalmic full-flow medical service system and method based on intelligent technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117747077A true CN117747077A (en) | 2024-03-22 |
| CN117747077B CN117747077B (en) | 2024-07-16 |
Family
ID=90283307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410016032.4A Active CN117747077B (en) | 2024-01-04 | 2024-01-04 | Ophthalmic full-flow medical service system and method based on intelligent technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117747077B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101951523A (en) * | 2010-09-21 | 2011-01-19 | 北京工业大学 | Adaptive colour image processing method and system |
| CN111161196A (en) * | 2020-02-26 | 2020-05-15 | 上海电机学院 | Adaptive enhancement method for aerial image of power transmission line |
| CN111627555A (en) * | 2020-05-29 | 2020-09-04 | 东莞理工学院 | Intelligent inspection and diagnosis system based on deep learning |
| CN111656357A (en) * | 2018-04-17 | 2020-09-11 | 深圳华大生命科学研究院 | Artificial intelligence-based ophthalmic disease diagnosis modeling method, device and system |
| CN113962311A (en) * | 2021-10-27 | 2022-01-21 | 厦门大学 | Knowledge data and artificial intelligence driven ophthalmic multi-disease identification system |
| CN115862845A (en) * | 2022-12-21 | 2023-03-28 | 复旦大学附属中山医院 | Condition analysis system based on colorectal cancer CTC morphological typing |
| CN116563254A (en) * | 2023-05-12 | 2023-08-08 | 吉林大学 | Texture detection and matching method for printed patterns on surface of electronic component |
| US20230248998A1 (en) * | 2023-04-12 | 2023-08-10 | Buvaneswari Natarajan | System and method for predicting diseases in its early phase using artificial intelligence |
| CN117012364A (en) * | 2023-10-08 | 2023-11-07 | 吉林大学 | Medical health service cloud platform based on industrial Internet technology |
-
2024
- 2024-01-04 CN CN202410016032.4A patent/CN117747077B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101951523A (en) * | 2010-09-21 | 2011-01-19 | 北京工业大学 | Adaptive colour image processing method and system |
| CN111656357A (en) * | 2018-04-17 | 2020-09-11 | 深圳华大生命科学研究院 | Artificial intelligence-based ophthalmic disease diagnosis modeling method, device and system |
| CN111161196A (en) * | 2020-02-26 | 2020-05-15 | 上海电机学院 | Adaptive enhancement method for aerial image of power transmission line |
| CN111627555A (en) * | 2020-05-29 | 2020-09-04 | 东莞理工学院 | Intelligent inspection and diagnosis system based on deep learning |
| CN113962311A (en) * | 2021-10-27 | 2022-01-21 | 厦门大学 | Knowledge data and artificial intelligence driven ophthalmic multi-disease identification system |
| CN115862845A (en) * | 2022-12-21 | 2023-03-28 | 复旦大学附属中山医院 | Condition analysis system based on colorectal cancer CTC morphological typing |
| US20230248998A1 (en) * | 2023-04-12 | 2023-08-10 | Buvaneswari Natarajan | System and method for predicting diseases in its early phase using artificial intelligence |
| CN116563254A (en) * | 2023-05-12 | 2023-08-08 | 吉林大学 | Texture detection and matching method for printed patterns on surface of electronic component |
| CN117012364A (en) * | 2023-10-08 | 2023-11-07 | 吉林大学 | Medical health service cloud platform based on industrial Internet technology |
Non-Patent Citations (1)
| Title |
|---|
| 刘明坤;龙奕;尹忠科;王蕊;: "基于自适应方向窗的医学图像增强算法", 计算机工程与应用, no. 22, 1 August 2009 (2009-08-01) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117747077B (en) | 2024-07-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7428323B2 (en) | Method and system for automatic diagnosis of possible brain disease | |
| Gunes et al. | Assessing facial beauty through proportion analysis by image processing and supervised learning | |
| CN111292839B (en) | Image processing method, image processing device, computer equipment and storage medium | |
| US8391603B2 (en) | System and method for image segmentation | |
| CN111369576A (en) | Training method of image segmentation model, image segmentation method, device and equipment | |
| CN113724228A (en) | Tongue color and coating color identification method and device, computer equipment and storage medium | |
| CN113768461B (en) | Fundus image analysis method, fundus image analysis system and electronic equipment | |
| CN110338763A (en) | A kind of intelligence Chinese medicine examines the image processing method and device of survey | |
| CN115579104B (en) | Manual intelligent-based liver cancer whole course digital management method and system | |
| CN116664966B (en) | Infrared image processing system | |
| KR102162683B1 (en) | Reading aid using atypical skin disease image data | |
| Singh et al. | A novel hybrid robust architecture for automatic screening of glaucoma using fundus photos, built on feature selection and machine learning‐nature driven computing | |
| CN112233087A (en) | Artificial intelligence-based ophthalmic ultrasonic disease diagnosis method and system | |
| CN114820603B (en) | Intelligent health management method based on AI tongue diagnosis image processing and related device | |
| CN117237351B (en) | Ultrasonic image analysis method and related device | |
| CN115024725A (en) | Tumor treatment aid decision-making system integrating psychological state multi-parameter detection | |
| CN113946217B (en) | Intelligent auxiliary evaluation system for enteroscope operation skills | |
| Gaber et al. | Comprehensive assessment of facial paralysis based on facial animation units | |
| US20210335491A1 (en) | Predictive adaptive intelligent diagnostics and treatment | |
| CN117689891A (en) | Method for segmenting and classifying a target lumbar vertebral structure using a two-stage model | |
| CN115394406A (en) | Medical image artificial intelligence rapid diagnosis deployment method based on mobile terminal and mobile internet | |
| CN117747077B (en) | Ophthalmic full-flow medical service system and method based on intelligent technology | |
| CN117095835A (en) | Intelligent medical health consultation system | |
| CN115036034B (en) | Similar patient identification method and system based on patient characterization map | |
| CN112168141A (en) | Information processing method, device, equipment and storage medium for remote inquiry |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |