A method for detecting intestinal preparation condition by mobile terminal and application thereof

Abstract

The application relates to the technical field of intestinal preparation detection, and discloses a kind of mobile terminal detection intestinal preparation condition judgment method, including guiding patient to carry out detection preparation work according to prompt;Patients upload stool photos to server;The uploaded stool image is identified and analyzed using a computer vision-based image processing system, which is divided into four stages and scored;According to the Boston score, a judgment report is generated, and the results are fed back to the patient, guiding the patient to take the next step;Also disclosed is the application of the above method in gastroenterology for remote medical services for patients who need to undergo gastrointestinal endoscopy. The mobile terminal detection intestinal preparation condition judgment method and application of the application not only simplify the intestinal preparation process of patients, improve the quality and efficiency of intestinal preparation, but also provide real-time and accurate feedback for doctors and patients, reduce unnecessary waste of medical resources, and improve the overall level of medical services.

Description

Technical Field

[0001] This invention relates to the field of intestinal preparedness detection technology, and in particular to a method and application for judging intestinal preparedness using a mobile device. Background Technology

[0002] Existing bowel preparation assessment technologies primarily rely on publicly available bowel preparation color charts. These charts typically consist of a substrate and a main body. The main body is positioned above the substrate, arranged in a fan-shaped structure with equal angles around the substrate's center line, forming a circular distribution above the substrate. Each color of the main body is uniformly distributed. A circular observation port is located in the center of the substrate. During use, the substrate is placed over a toilet or commode, and stool is observed separately through the central observation port, comparing its color to the main body of the color chart to determine the quality of bowel preparation. While this method avoids errors caused by visual observation and improves accuracy, it also has significant drawbacks. For example, it is relatively cumbersome, and for patients preparing bowel preparation at home, it is difficult to determine whether to continue taking laxatives, thus affecting the effectiveness of bowel preparation. Furthermore, traditional color chart methods lack intelligence and automation, failing to provide real-time feedback and guidance to patients, resulting in inconsistent bowel preparation quality and affecting the accuracy and efficiency of subsequent colonoscopies. Therefore, we propose a mobile-based method and application for assessing bowel preparation. Summary of the Invention

[0003] The main objective of this invention is to provide a method and application for judging intestinal preparation status via mobile device, which can effectively solve the problems in the background art.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for assessing bowel preparation status via a mobile device includes the following steps: S1: Guide the patient to complete the pre-test preparations according to the prompts; S2: The patient uploads a photo of their stool to the server; S3: Process and analyze the uploaded images; S4: Provide feedback to patients based on the analysis results.

[0005] Preferably, the preparatory work before detection in S1 specifically includes: S101: The patient took a laxative the night before the surgery as prescribed by the doctor; S102: After defecating, use your mobile phone to take a picture of the excreted feces.

[0006] Preferably, in step S3, the uploaded image is processed and analyzed, specifically including: S301: The mobile device or backend server receives the uploaded image of feces; S302: The artificial intelligence system identifies and analyzes the uploaded fecal images and divides them into four stages; S303: Score the fecal images at each stage.

[0007] Preferably, in S301, the mobile terminal includes, but is not limited to, devices such as smartphones and tablets, and the backend server is built using the TensorFlow architecture.

[0008] Preferably, in step S302, the artificial intelligence system is a computer vision-based image processing system, and the processing steps of the computer vision-based image processing system are as follows: S3021: Perform preprocessing operations such as cropping, scaling, brightness and contrast adjustment on the uploaded fecal photos; S3022: Use the SIFT feature extraction method to extract key features from fecal images; S3023: Use the random forest machine learning algorithm for classification.

[0009] Preferably, the computer vision-based image processing system uses the OpenCV computer vision library framework for image processing and feature extraction.

[0010] Preferably, in S303, the scoring standard is the Boston scoring standard, which specifically means: 0 points indicates poor bowel preparation, 1 point indicates poor bowel preparation, 2 points indicates good bowel preparation, and 3 points indicates very good bowel preparation.

[0011] Preferably, in step S4, the step of providing feedback to the patient is as follows: S401: The system generates a judgment report based on the Boston Scale score and sends the results back to the patient; S402: Based on the assessment report, guide the patient to take the next step.

[0012] Preferably, the specific criteria for guiding the patient to take the next step are as follows: if the score is 2 or 3, the system notifies the patient that bowel preparation is satisfactory and suggests that the patient go to the hospital for a colonoscopy; if the score is 0 or 1, the system notifies the patient that bowel preparation is unsatisfactory, prompts the patient to continue bowel preparation, and instructs the patient to take and upload new stool photos again until the score is satisfactory.

[0013] An application of a mobile terminal method for assessing bowel preparation status, used in gastroenterology for remote medical services for patients requiring gastroscopy and colonoscopy.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention involves taking photos of feces using a mobile device and uploading them to a server. An artificial intelligence system then identifies and analyzes the photos, generating a test report which is provided to the patient. This method not only allows patients to operate at home conveniently but also significantly reduces the number of times they need to visit the hospital, improving the convenience and efficiency of medical services.

[0015] 2. This invention employs advanced computer vision technology and machine learning algorithms to accurately identify and classify uploaded fecal images. The algorithm uses the OpenCV computer vision library for image preprocessing, including operations such as cropping, scaling, and brightness and contrast adjustment. Then, it extracts key features using the SIFT feature extraction method, and finally uses the random forest machine learning algorithm for classification. This multi-step image processing and analysis method ensures high-precision identification of fecal images and improves the accuracy of detection results.

[0016] 3. This invention uses the Boston Consulting Group (BCG) scoring system to evaluate stool images at each stage. The scoring criteria are as follows: 0 points indicate poor bowel preparation, 1 point indicates moderately poor bowel preparation, 2 points indicate moderately good bowel preparation, and 3 points indicate excellent bowel preparation. Based on the scoring results, the system automatically provides feedback to the patient regarding their condition and offers corresponding guidance. This automated scoring mechanism not only improves the objectivity and consistency of the assessment but also provides clear reference points for doctors and patients, contributing to improved quality and success rates of colonoscopy. Attached Figure Description

[0017] Figure 1 This is a flowchart of a method for judging intestinal preparation status using a mobile device according to the present invention. Detailed Implementation

[0018] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0019] like Figure 1 As shown, a method for assessing bowel preparation status using a mobile device includes the following steps: S1: Guide the patient to complete the pre-test preparations according to the prompts; The preparatory work before testing specifically includes: S101: The patient took a laxative the night before the surgery as prescribed by the doctor; S102: After defecating, use your mobile phone to take a picture of the excreted feces.

[0020] S2: The patient uploads a photo of their stool to the server; S3: Process and analyze the uploaded images; The processing and analysis of uploaded images specifically includes: S301: The mobile device or backend server receives the uploaded image of feces; Furthermore, the mobile terminals include, but are not limited to, smartphones, tablets, and other devices, and the backend servers are built using the TensorFlow architecture.

[0021] S302: The artificial intelligence system identifies and analyzes the uploaded fecal images and divides them into four stages; Furthermore, the artificial intelligence system is a computer vision-based image processing system, and the processing steps of the computer vision-based image processing system are as follows: S3021: Perform preprocessing operations such as cropping, scaling, brightness and contrast adjustment on the uploaded fecal photos; S3022: Use the SIFT feature extraction method to extract key features from fecal images; S3023: Use the random forest machine learning algorithm for classification.

[0022] Furthermore, the computer vision-based image processing system uses the OpenCV computer vision library framework for image processing and feature extraction.

[0023] S303: Score the fecal images at each stage.

[0024] The scoring criteria are based on the Boston Scale, which specifies that 0 points indicates poor bowel preparation, 1 point indicates relatively poor bowel preparation, 2 points indicates relatively good bowel preparation, and 3 points indicates very good bowel preparation.

[0025] S4: Provide feedback to patients based on the analysis results.

[0026] The steps for providing feedback to patients are as follows: S401: The system generates a judgment report based on the Boston Scale score and sends the results back to the patient; S402: Based on the assessment report, guide the patient to take the next step.

[0027] Furthermore, the specific criteria for guiding patients to take the next step are as follows: if the score is 2 or 3, the system will notify the patient that the bowel preparation is satisfactory and suggest that the patient go to the hospital for a colonoscopy; if the score is 0 or 1, the system will notify the patient that the bowel preparation is unsatisfactory, prompt the patient to continue bowel preparation, and instruct the patient to take and upload new stool photos again until the score is satisfactory.

[0028] An application of a mobile terminal method for assessing bowel preparation status, used in gastroenterology for remote medical services for patients requiring gastroscopy and colonoscopy.

[0029] This invention involves taking photos of feces using a mobile device and uploading them to a server. An artificial intelligence system then identifies and analyzes the photos, generating a report which is provided to the patient. This method is convenient for patients to operate at home and significantly reduces the number of trips to the hospital, improving the convenience and efficiency of medical services. Advanced computer vision technology and machine learning algorithms are employed to accurately identify and classify the uploaded fecal images. The algorithm uses the OpenCV computer vision library for image preprocessing, including cropping, scaling, and brightness and contrast adjustments. Key features are then extracted using the SIFT feature extraction method, and finally, a random forest machine learning algorithm is used for classification. This multi-step image processing and analysis method ensures high-precision identification of fecal images and improves the accuracy of the test results. The Boston Consulting Group (BCG) scoring system is used to score each stage of the fecal image, with a scoring scale of 0 for poor bowel preparation, 1 for moderately poor bowel preparation, 2 for moderately good bowel preparation, and 3 for excellent bowel preparation. Based on the scoring results, the system automatically provides feedback to the patient regarding their condition and offers corresponding guidance. This automated scoring mechanism not only improves the objectivity and consistency of the assessment but also provides clear reference points for doctors and patients, contributing to improved quality and success rates of colonoscopy.

[0030] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for judging bowel preparation status using a mobile terminal, characterized in that: Includes the following steps: S1: Guide the patient to complete the pre-test preparations according to the prompts; S2: The patient uploads a photo of their stool to the server; S3: Process and analyze the uploaded images; S4: Provide feedback to patients based on the analysis results.

2. The method for determining intestinal preparation status via mobile terminal according to claim 1, characterized in that: The preparatory work before detection in S1 specifically includes: S101: The patient took a laxative the night before the surgery as prescribed by the doctor; S102: After defecating, use your mobile phone to take a picture of the excreted feces.

3. The method for determining intestinal preparation status via mobile terminal according to claim 1, characterized in that: The uploaded image is processed and analyzed in step S3, specifically including: S301: The mobile device or backend server receives the uploaded image of feces; S302: The artificial intelligence system identifies and analyzes the uploaded fecal images and divides them into four stages; S303: Score the fecal images at each stage.

4. The method for determining intestinal preparation status via mobile terminal according to claim 3, characterized in that: In S301, the mobile terminal includes, but is not limited to, devices such as smartphones and tablets, and the backend server is built using the TensorFlow architecture.

5. The method for judging intestinal preparation status via mobile terminal according to claim 3, characterized in that: In step S302, the artificial intelligence system is a computer vision-based image processing system, and the processing steps of the computer vision-based image processing system are as follows: S3021: Perform preprocessing operations such as cropping, scaling, brightness and contrast adjustment on the uploaded fecal photos; S3022: Use the SIFT feature extraction method to extract key features from fecal images; S3023: Use the random forest machine learning algorithm for classification.

6. The method for determining intestinal preparation status via mobile terminal according to claim 5, characterized in that: The computer vision-based image processing system uses the OpenCV computer vision library framework for image processing and feature extraction.

7. The method for judging intestinal preparation status using a mobile terminal according to claim 3, characterized in that: In S303, the scoring standard is the Boston Scale, which is specifically defined as follows: 0 points indicates poor bowel preparation, 1 point indicates relatively poor bowel preparation, 2 points indicates relatively good bowel preparation, and 3 points indicates very good bowel preparation.

8. The method for determining bowel preparation status via mobile terminal according to claim 1, characterized in that: In S4, the step of providing feedback to the patient is as follows: S401: The system generates a judgment report based on the Boston Scale score and sends the results back to the patient; S402: Based on the assessment report, guide the patient to take the next step.

9. The method for determining intestinal preparation status via mobile terminal according to claim 8, characterized in that: The specific criteria for guiding patients to take the next step are as follows: if the score is 2 or 3, the system will notify the patient that the bowel preparation is satisfactory and suggest that the patient go to the hospital for a colonoscopy; if the score is 0 or 1, the system will notify the patient that the bowel preparation is unsatisfactory, prompt the patient to continue bowel preparation, and instruct the patient to take and upload new stool photos again until the score is satisfactory.

10. The application of the mobile terminal method for judging intestinal preparation status according to any one of claims 1-9, characterized in that: Telemedicine services for patients requiring gastroscopy or colonoscopy in the field of gastroenterology.

Images