CN109998488B - Identification model of Crohn's disease and intestinal ulcer type lymphoma and construction method - Google Patents
Identification model of Crohn's disease and intestinal ulcer type lymphoma and construction method Download PDFInfo
- Publication number
- CN109998488B CN109998488B CN201910296400.4A CN201910296400A CN109998488B CN 109998488 B CN109998488 B CN 109998488B CN 201910296400 A CN201910296400 A CN 201910296400A CN 109998488 B CN109998488 B CN 109998488B
- Authority
- CN
- China
- Prior art keywords
- score
- intestinal
- grid
- disease
- crohn
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/42—Detecting, measuring or recording for evaluating the gastrointestinal, the endocrine or the exocrine systems
- A61B5/4216—Diagnosing or evaluating gastrointestinal ulcers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/42—Detecting, measuring or recording for evaluating the gastrointestinal, the endocrine or the exocrine systems
- A61B5/4222—Evaluating particular parts, e.g. particular organs
- A61B5/4255—Intestines, colon or appendix
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Endocrinology (AREA)
- Gastroenterology & Hepatology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
Aiming at the problem that Crohn's disease and intestinal ulcer lymphoma are difficult to identify clinically, the invention provides an identification model, which is designed after carrying out statistical analysis on a plurality of indexes in clinical manifestations, endoscopic features and imaging features, so as to obtain the indexes according to the clinical manifestations, including intestinal hemorrhage and extraintestinal manifestations; the indexes of the characteristics under the endoscope are segmental lesion and paving stone characteristics; dividing 7 indexes of the iconography characteristics into hierarchical reinforcement, medium-heavy reinforcement, mesenteric peripheral blood vessel increase and the like, and finally summing, wherein the total score is larger than or equal to 3 minutes and is Crohn's disease, and the total score is smaller than 3 minutes and is intestinal ulcer type lymphoma; the Crohn's disease and the intestinal ulcer lymphoma can be rapidly and accurately distinguished through the model, and the corresponding identification instrument is invented, so that the identification is simpler and more intuitive.
Description
Technical Field
The invention belongs to the technical field of disease distinguishing and identifying models, particularly relates to a model for distinguishing Crohn's disease and intestinal ulcer type lymphoma and a model construction method, and aims to conveniently distinguish the Crohn's disease and the intestinal ulcer type lymphoma.
Background
Crohn's disease is an inflammatory disease of the intestinal tract of unknown origin that can occur in any part of the gastrointestinal tract, but occurs well in the terminal ileum and right colon. Both this disease and ulcerative colitis are collectively referred to as inflammatory bowel disease. The clinical manifestations of the disease are abdominal pain, diarrhea, intestinal obstruction, accompanied with the extra-intestinal manifestations of fever, malnutrition, etc. Intestinal ulcer lymphoma is a malignant tumor of the digestive system, and the clinical common clinical manifestations are fever, abdominal pain, diarrhea, and weight loss.
The differential diagnosis of Crohn's disease and ulcerative lymphoma is a clinical problem, and has many similarities, but the treatment schemes of the Crohn's disease and ulcerative lymphoma are different, and the prognosis is also different, so that the accurate diagnosis is helpful for the selection of therapeutic drugs and the improvement of the prognosis of patients. Both of them can be used as the diagnostic gold standard, but the clinical positive rate of typical pathological manifestations is low, so many patients still cannot be diagnosed with crohn's disease or intestinal ulcer lymphoma. Thus, a more ready differentiation of the identification of Crohn's disease from ulcerated intestinal lymphoma would provide a great reference to the treatment of patients.
At present, the examination of the Crohn's disease and the intestinal ulcer type lymphoma mainly comprises several aspects such as clinical characteristics, laboratory examination, endoscopy and imaging characteristics, and the examination of each aspect has a plurality of indexes, and the distinguishing and identification of the included indexes becomes the most key technical problem to be solved, and the technical problem to be solved is how to assign a value to determine a model after selecting a specific index.
The invention provides a model for identifying Crohn's disease and intestinal ulcer lymphoma and a model construction method, aiming at the problems that effective and appropriate indexes cannot be selected for identifying the Crohn's disease and the intestinal ulcer lymphoma in the prior art and how each index is effectively assigned.
Disclosure of Invention
In order to solve the problems that effective and appropriate indexes cannot be selected for identifying the Crohn's disease and the intestinal ulcer type lymphoma and how each index is effectively assigned, the invention provides an identification model and a model construction method for the Crohn's disease and the intestinal ulcer type lymphoma.
A differential model of Crohn's disease and intestinal ulcer type lymphoma, it includes clinical manifestation, the score of corresponding index and score sum of corresponding index of at least 2 aspects of characteristic and visualization characteristic under the endoscope; it is characterized in that when the total score is greater than or equal to a set score, the diagnosis is Crohn's disease, and when the total score is less than the set score, the diagnosis is intestinal ulcer lymphoma.
Further, the indicators of clinical manifestations include intestinal bleeding, extra-intestinal manifestations; the indexes of the characteristics under the endoscope are segmental lesion and paving stone characteristics; the imaging characteristics are indicated by stratification enhancement, moderate-to-severe enhancement and mesenteric peripheral vascularity.
Furthermore, there was an intestinal bleeding score of-2, no intestinal bleeding score of 0; the score of the appearance of the intestines is 2, and the score of the appearance of the intestines is 0; the score of 1 is the segmental lesion, and the score of 0 is the non-segmental lesion; the pavement stone characterization score is 2, the pavement stone characterization score is 0 when the pavement stone characterization score is not available, the layered reinforcement score is 1 when the pavement stone characterization score is available, and the layered reinforcement score is 0 when the pavement stone characterization score is not available; score 1 for moderate and severe reinforcement and score 0 for no moderate and severe reinforcement; there was a score of 1 for mesenteric peripheral vascularity and 0 for mesenteric peripheral vascularity.
Further, when the total score is not less than 3 minutes, the patient is Crohn's disease, and when the total score is less than 3 minutes, the patient is intestinal ulcer type lymphoma.
A method for constructing an identification model of Crohn's disease and intestinal ulcer type lymphoma,
1) collecting sufficient patients with confirmed crohn's disease and ulcerated intestinal lymphoma;
2) collecting endoscopic features and imaging features according to clinical manifestations of patients, and counting data;
3) performing single-factor analysis on each index of the endoscopic features and the imaging features according to clinical performance, and selecting potential prediction scoring indexes through the single-factor analysis; selecting an index with P <0.05 as a potential prediction score index;
4) determining independent prediction indexes through multi-factor analysis; bringing the indexes with the P less than 0.05 into binary logistic regression line multi-factor analysis; establishing and evaluating a scoring model, wherein the established logistic regression equation is as follows: logit (p) -4.9437-2.3876X1+2.0993X2+1.7663X3+2.5769X4+1.6304X5+1.8204X6+1.2979X7(X1 stands for intestinal bleeding, X2 for extra-intestinal performance, X3 for segmental lesions, X4 for paving stones, X5 for stratified fortification, X6 for moderate-heavy fortification, and X7 for mesenteric perimesenteric vascularity) score was established depending on regression coefficients. And according to the result of the multi-factor analysis, taking the index of the minimum regression coefficient as 1 point, dividing the regression coefficients of other variables by the minimum regression coefficient, and rounding the result to obtain the score of each variable.
The invention also discloses a device for identifying the Crohn disease and the intestinal ulcer type lymphoma, which comprises a rectangular structure, wherein the upper part of the rectangular structure is a table partition structure, and the device is characterized in that the upper part of the table partition comprises an index grid and a score grid; a "no score" lattice; the front grid at the bottom is a specific index name grid, and the grids at the back of the same line are obtained; the result is the corresponding division whether each index is yes or not; the lowest row is a total counting row, and the total score is counted; the specific index grids are respectively as follows: the "intestinal hemorrhage" grid, the "extra-intestinal manifestation" grid, the "segmental lesion" grid, the "features of paving stones" grid, the "stratified reinforcement" grid, the "moderate and severe reinforcement" grid, and the "mesenteric peripheral vascularity" grid.
Further, a classification column is arranged in front of the specific index grid; the "intestinal hemorrhage" and "intestinal exterior manifestations" are classified as "clinical manifestations" in front of the grid; the front of the grid of segmental lesion and pavement stone sign is classified as
"under endoscope feature" pane; the "layered reinforcement" lattice, "moderate and severe reinforcement" lattice, and "mesenteric peripheral vascularity" lattice front are classified as "imaging characteristics" lattice.
Further, the "-2" case and the "0" case are arranged behind the 1) "intestinal hemorrhage" case; scores for the presence of intestinal bleeding and no intestinal bleeding, respectively.
2) The back of the extra-intestinal manifestation is the 2 and 0 lattices; the score for the presence of an intestinal appearance and the score for the absence of an intestinal appearance, respectively.
3) The back of the compartment of segmental lesion is a compartment of 1 and a compartment of 0; scores for the presence of segmental lesions and scores for non-segmental lesions, respectively.
4) The back of the paving stone sign grid is a grid of 2 and a grid of 0; the score for the presence of paving stones and the score for the absence of paving stones, respectively.
5) The '1' lattice and the '0' lattice are arranged behind the 'layered reinforcement' lattice; the score for the presence of a stratified boost and the score for the absence of a stratified boost, respectively.
6) The rear part of the medium-heavy strengthening lattice is a 1 lattice and a 0 lattice; scores for the presence of moderate to severe reinforcement and scores for the absence of moderate to severe reinforcement, respectively.
7) The back of the mesenteric peripheral vasculogenesis lattice is a 1 lattice and a 0 lattice; scores for the presence of mesenteric peripheral vascularity and no mesenteric peripheral vascularity, respectively.
Furthermore, the rectangular structure is a rectangular plate, the rectangular plate is a sliding surface rectangular plate, and a pen-wiping structure and a wiping structure are arranged beside the rectangular plate; the rectangular plate is provided with corresponding erasable pens and wiping structure placing structures; when in use, the erasable pen marks the characteristics and then collects and calculates scores, so that the Crohn disease and the intestinal ulcer type lymphoma can be quickly distinguished.
Further, the placing structure is a placing groove arranged on the edge of the upper surface of the rectangular plate.
Further, the standing groove is set as a rotatable standing groove, and the standing groove is rotated through the rotating shaft.
Further, the placing groove is arranged on the right side, and the rotating shaft is arranged above the right side; the arrangement can ensure that the placing groove rotates to the top when the instrument is used, and the marking of a doctor is not influenced.
Further, a magnetic structure is arranged on the lower side in front of the placing groove, the magnetic structure which corresponds to the magnetic structure on the placing groove and is mutually attracted and fixed is arranged at the corresponding position of the rectangular structure, the magnetic structures are arranged on the positions of the rectangular structure before and after the placing groove rotates, and the magnetic structure can effectively maintain the position of the placing groove in various states.
Or, a cavity is arranged in the rectangular structure; a switch with a lamp is arranged below the grid; the switch with the lamp is connected with a direct current power supply in the cavity with the rectangular structure. The lamp is turned on when the corresponding scoring grid is pressed down or touched to be provided with the lamp switch, so that the marking effect is achieved, the scoring condition is counted by the user through the opened lamp, and the scoring marking mode is more convenient.
Furthermore, a main switch is arranged on the rectangular structure to control the whole instrument.
Further, a control structure is provided, each switch being connected to the control structure, the control structure controlling that two scoring switches within a single row cannot be turned on simultaneously.
Furthermore, the control structure is also connected with a computing unit, and the computing unit is also connected with a display structure. The control structure is connected with the computing unit, the computing unit collects corresponding values of the switches with the lamps under the cells, the corresponding values are computed, and computed results are transmitted to the display structure to be displayed; by displaying the score through the display structure, a conclusion can be drawn quickly.
Compared with the model and the scoring method in the prior art, the model constructed by the method has higher prediction accuracy and stronger operability.
Drawings
FIG. 1 is a graph of different model multivariate analysis ROC curves, model _1 is a model ROC curve containing only clinical performance indicators; model _2 is a model ROC curve containing clinical performance indicators and endoscopic indicators; model _3 is a model ROC curve that includes clinical performance indices, endoscopic indices, and imaging indices.
FIG. 2 is a ROC curve for a ten-fold verification method for a model including clinical performance indicators, endoscopic indicators, and imaging indicators;
FIG. 3 is an overall structural view of a placement structure of embodiment 2 of the present invention on the upper side;
FIG. 4 is a schematic side view of the overall structure of a placement structure according to example 2 of the present invention;
FIG. 5 is a schematic bottom view of the placement structure of the present invention;
FIG. 6 is a longitudinal cross-sectional structural view of the placement structure and the shaft portion of the present invention;
FIG. 7 is a schematic view of the overall structure of embodiment 3 of the present invention;
FIG. 8 is a perspective view of a cavity without a back cover in accordance with embodiment 3 of the present invention;
FIG. 9 is a schematic non-perspective structural view of a cavity portion without a back cover in embodiment 3 of the present invention;
FIG. 10 is a schematic view of the inner side of the back cover part in accordance with embodiment 3 of the present invention;
FIG. 11 is a schematic view of a structure with a back cover portion and a bottom view according to embodiment 3 of the present invention;
in the figure, 1, a rectangular structure 1; 2. "index" pane 2; 3. "is score" pane 3; 4. no score lattice 4; 5. a total row 5; 61. the case of intestinal hemorrhage; 62. the "extra-intestinal manifestation" compartment; 63. "segmental lesion" compartment; 64. a 'paving stone sign' grid; 65. a layering strengthening grid; 66. a medium-heavy strengthening grid; 67. "mesenteric peripheral vascularity" compartment; 71. "clinical manifestations" pane 71; 72. "under endoscope feature" pane 72; 73. "imaging characteristics" pane 73; 81. an erasable pen 81; 82. a wiping structure 82; 83. a placement structure 83; 84. a rotating shaft 84; 85. a magnetic structure 85; 91. a cavity 91; 92. a switch with a lamp; 93. a DC power supply 93; 94. a master switch 94; 95. a control structure 95; 96. a calculation unit 96; 97. a display structure 97; 98. and (7) backing a cover.
Detailed Description
Example 1 method for constructing differential model of Crohn's disease and intestinal ulcer type lymphoma
First, patients with crohn's disease and intestinal ulcer lymphoma were admitted to a 30-day beijing cooperative hospital, a sixth subsidiary hospital of zhongshan university, a first subsidiary hospital of zhongshan university, a beijing hospital, a shore-off hospital, a shanghai renji hospital, a tenth national hospital of shanghai city, a subsidiary hospital of medical university of anhui, a wuhan cooperative hospital, and multi-center continuous diagnosis and treatment in 2004, 1/2018, and clinical, endoscopic and imaging data of the patients were collected at the same time, wherein 91 cases of crohn's disease and 50 cases of intestinal ulcer lymphoma were collected.
1. Diagnostic criteria:
the diagnosis of crohn's disease is based on ECC0 guidelines and the consensus opinion of diagnosis and treatment of inflammatory bowel disease 2012 in our country: on the basis of the exclusion of other diseases, the following points can be followed: (1) patients with typical clinical manifestations of diarrhea, abdominal pain, weight loss, perianal lesion and the like can be clinically diagnosed; (2) simultaneously has the characteristics (segmental, longitudinal ulcer, cobblestone-like appearance and the like) of a colonoscope or a enteroscope (lesion is limited in small intestine) and the characteristics (CTE or MRE, unconditional person adopts small intestine barium contrast agent contrast) of imaging (intestine wall thickening, target sign, wood comb sign and the like), and can be clinically diagnosed; (3) if the biopsy is added, the characteristic change of the Crohn's disease is suggested, and the intestinal tuberculosis can be eliminated, so that the clinical diagnosis can be made; (4) if the operation excision specimen (including excision of the intestinal segment and lymph nodes near the lesion) exists, the pathological diagnosis can be made according to the standard; (5) the initial diagnosis case without pathological diagnosis is followed for more than 6-12 months, and the clinical confirmed diagnosis can be made according to the response to treatment and the disease change judgment of the patient, which accords with the natural course of Crohn's disease; the patients who were included were confirmed clinically and pathologically.
The diagnosis of the intestinal ulcer type lymph mainly depends on pathology, and combines endoscopic ulcerative lesions and Dawson standards (except that systemic lymphoma affects intestinal tracts), and the specific Dawson standards are as follows: there is no superficial lymph node enlargement, normal peripheral blood leukocyte count and classification, no mediastinal lymph node enlargement on the chest piece, no mesenteric lymph node enlargement around the affected intestinal segment during diagnosis, and no evidence of liver and spleen involvement.
2. Inclusion and exclusion criteria
Inclusion criteria were: 1) clinically and pathologically confirmed patients with Crohn's disease, pathologically confirmed patients with primary intestinal ulcer type lymphoma. 2) Meanwhile, the utility model has complete clinical, endoscopic and imaging data. The clinical data includes clinical presentation, original image of enhanced abdominopelvic CT/CTE, original image of endoscope lesion site and report. Exclusion criteria: 1) imaging, endoscopic raw pictures and reporters are missing. 2) The clinical symptoms are not complete. 3) Patients after surgery or treatment (patients with pre-surgery/pre-treatment data can be enrolled). 4) Those who have not been diagnosed clearly.
Retrospectively analyzing clinical data of patients with Crohn's disease and intestinal ulcer lymphoma, and analyzing clinical manifestations, endoscopic characteristics and imaging characteristics of the patients by using SAS9.3 software, wherein the specific contents are as follows:
1) the clinical manifestations are as follows: the analyzed indicators include fever, abdominal pain, diarrhea, nausea, vomiting, hematochezia, perianal lesions, weight loss, extra-intestinal manifestations (oral vulvar ulcer, skin lesions, joint lesions, etc.), and complications (intestinal stenosis, intestinal fistula, intestinal perforation, etc.).
2) Endoscopic data: including lesion sites, lesion distribution, ulcer shape, number and size, ileocecal valve affected condition, ulcer peripheral mucosa condition, etc.
3) Imaging data: including the longest segment of the lesion, thickness, lesion distribution, reinforcement characteristics, mucosal and serosal surface conditions, perimesenteric vascular and fat density conditions, intestinal fistulas, and the like.
For the continuous variable identified by the Crohn's disease and the intestinal ulcer lymphoma, the mean value is expressed by a standard deviation; for categorical variables, a percentage is used. The classification variables are compared by adopting a chi-square test or a Fisher accurate test, and the continuity variables are compared by adopting a t test.
3. Selection of potential predictive scoring index by one-factor analysis
3.1 clinical manifestations of Crohn's disease and primary peptic lymphoma patients were analyzed in comparison to the clinical manifestations including fever, nausea, vomiting, abdominal pain, diarrhea, hematochezia, anorexia, weight loss, perianal lesions, complications (abdominal mass, abdominal abscess, intestinal fistula, intestinal perforation, intestinal bleeding), canker sores, vulvar ulcers and other extra-intestinal manifestations (e.g. skin lesions, ocular lesions, joint lesions, MDS, thromboembolic diseases).
TABLE 1 comparative analysis of clinical manifestations in patients with intestinal ulcerated lymphoma and Crohn's disease
Chi-square test or Fisher's exact test
3.2 endoscopic characteristics including lesion distribution, lesion location, ulcer morphology, ulcer number, ulcer diameter, and ileocecal characteristics under contrast analysis of endoscopic characteristics of patients with Crohn's disease and intestinal ulcer lymphoma
Valve involvement, deformation of the ileocaecal region, patency of the ileocaecal region, mucosal conditions around lesions (inflammatory polyps, mucosal bridges), signs of paving stones, stiffness of the intestinal canal, deformation of the intestinal canal, bleeding.
TABLE 2 comparative analysis of endoscopic characteristics of intestinal ulcerated lymphoma and Crohn's disease
Chi-square test or Fisher's exact test
3.3 comparative analysis of the imaging characteristics of patients with Crohn's disease and intestinal ulcerated lymphoma
The analyzed indicators include the longest segment of the lesion, thickness, lesion distribution, reinforcement characteristics, mucosal and serosal surface conditions, perimesenteric blood vessel and fat density conditions, intestinal fistula, etc.
TABLE 3 comparative analysis of the imaging characteristics of intestinal ulcerated lymphoma and Crohn's disease
4. Multi-factor analysis determination of independent predictors
The index with P <0.05 was included in the binary logistic regression line multifactorial analysis. The results show that 7 indexes, such as intestinal hemorrhage, extraintestinal manifestation, segmental lesions, paving stone signs, stratified strengthening, moderate-severe strengthening and mesenteric peripheral vascularity, have significant statistical difference between the Crohn's disease and the intestinal white plug, and the like in the table 4.
TABLE 4 Multi-factor analysis results
5. Comparison of different models
The single-factor and logistic regression multi-factor analysis is carried out by aiming at clinical indexes, the finally included indexes are intestinal bleeding and parenteral performance, and the area under the ROC curve for identifying the Crohn's disease and the intestinal ulcerative lymphoma according to the two indexes is 0.7260. Single-factor and logistic regression multi-factor analysis is carried out aiming at clinical and endoscopic indexes, the finally included indexes are intestinal bleeding, parenteral performance, segmental lesion and paving stone, and the area under the ROC curve of the Crohn's disease and the intestinal ulcerative lymphoma is identified to be 0.8629 according to the two indexes. The single-factor and logistic regression multi-factor analysis is carried out on clinical + endoscopic + imaging indexes, the finally included indexes are intestinal bleeding, parenteral performance, segmental lesion, paving stone, layered reinforcement, moderate-severe reinforcement and mesenteric peripheral angiogenisis, and the area under the ROC curve of the Crohn's disease and the intestinal ulcer lymphoma is identified to be 0.9468 (figure 1) according to the two indexes. Therefore, the discrimination capability of the Crohn's disease and the intestinal ulcer type lymphoma can be obviously improved by increasing endoscopic and imaging indexes.
6. Scoring model establishment and evaluation
The score is established depending on the regression coefficient, and according to the result of the multifactor analysis, referring to table 4, the index of the regression coefficient with the smallest absolute value is taken as 1 score, the regression coefficients of other variables are divided by the smallest regression coefficient, and the result is rounded to obtain the score of each variable.
Based on the logistic regression model, the final differential diagnosis scoring model for the intestinal ulcer type lymphoma and Crohn's disease was established (Table 5)
The corresponding formula of the logistic regression equation is logit (P) -4.9437-2.3876X1+2.0993X2+1.7663X3+2.5769X4+1.6304X5+1.8204X6+1.2979X7(X1 represents intestinal bleeding, X2 represents parenteral performance, X3 represents segmental lesion, X4 represents paving stone, X5 represents layered reinforcement, X6 is medium-heavy reinforcement, and X7 is mesenteric peripheral blood vessel increase).
TABLE 5 scoring System for Crohn's disease and intestinal ulcerated lymphoma
7. Model validation
And verifying the results by using a ten-fold verification method, dividing the data set into 10 parts, taking 9 parts as training data and 1 part as test data in turn, and verifying. The area under the obtained ten-fold verified ROC curve is 0.9008, which indicates that the model has good capacity of distinguishing CD and intestinal ulcer type lymphoma.
Example 2 apparatus for discriminating Crohn's disease from intestinal ulcer lymphoma
The invention also discloses a device for identifying the Crohn's disease and the intestinal ulcer type lymphoma, which comprises a rectangular structure 1, wherein the upper part of the rectangular structure 1 is a table partition structure, the upper part of the table partition comprises an index grid 2 and a score grid 3; no score lattice 4; the forefront grid at the lower part is a specific index name grid, and a grid is obtained behind the same line; the result is the corresponding division whether each index is yes or not; the lowest row is a total counting row 5, and the total score is counted; the specific index grids are respectively as follows: the "intestinal hemorrhage" grid, the "extra-intestinal manifestation" grid, the "segmental lesion" grid, the "features of paving stones" grid, the "stratified reinforcement" grid, the "moderate and severe reinforcement" grid, and the "mesenteric peripheral vascularity" grid.
A classification column is arranged in front of the specific index grid; the "intestinal bleeding" compartment and the "extra-intestinal manifestation" compartment are classified as the "clinical manifestation" compartment 71; the section lesion grid and the paving stone characteristic grid are classified into an under-endoscope characteristic grid 72 in front of the section lesion grid and the paving stone characteristic grid; the "layered reinforcement" compartment, "moderate-severe reinforcement" compartment, and "mesenteric peripheral vascularity" compartment are classified as the "imaging characteristics" compartment 73.
1) The back of the 'intestinal hemorrhage' case is a case of '-2' and a case of '0'; scores for the presence of intestinal bleeding and no intestinal bleeding, respectively.
2) The back of the extra-intestinal manifestation is the 2 and 0 lattices; the score for the presence of an intestinal appearance and the score for the absence of an intestinal appearance, respectively.
3) The back of the compartment of segmental lesion is a compartment of 1 and a compartment of 0; scores for the presence of segmental lesions and scores for non-segmental lesions, respectively.
4) The back of the paving stone sign grid is a grid of 2 and a grid of 0; the score for the presence of a paving stone feature and the score for the absence of a paving stone feature, respectively.
5) The '1' lattice and the '0' lattice are arranged behind the 'layered reinforcement' lattice; there is a score for a layered reinforcement present and a score for no layered reinforcement, respectively.
6) The rear part of the medium-heavy strengthening lattice is a 1 lattice and a 0 lattice; scores for the presence of moderate to severe reinforcement and scores for the absence of moderate to severe reinforcement, respectively.
7) The back of the mesenteric peripheral vasculogenesis lattice is a 1 lattice and a 0 lattice; scores for the presence of mesenteric peripheral vascularity and no mesenteric peripheral vascularity, respectively.
The rectangular structure 1 is a rectangular plate, the rectangular plate is a smooth rectangular plate, and a pen 81 and a wiping structure 82 are arranged beside the rectangular plate; the rectangular plate is provided with corresponding erasable pen 81 and wiping structure 82 placing structure 83; when in use, the erasable pen 81 marks the characteristics and then collects and calculates scores, so that the Crohn disease and the intestinal ulcer lymphoma can be quickly distinguished.
The placing structure 83 is a placing groove provided at an edge of an upper surface of the rectangular plate.
The placing groove is provided as a rotatable placing groove, and the placing groove is rotated by the rotating shaft 84.
The placement groove is provided on the right side, and the rotation shaft 84 is provided above the right side; the arrangement can ensure that the placing groove rotates to the top when the instrument is used, and the marking of a doctor is not influenced.
A magnetic structure 85 is arranged on the lower side in front of the placing groove, the magnetic structure 85 which corresponds to the magnetic structure 85 on the placing groove and realizes mutual attraction and fixation is arranged at the corresponding position of the rectangular structure 1, the magnetic structures 85 are arranged on the positions of the rectangular structure 1 before and after the placing groove rotates, and the arrangement can effectively maintain the position fixation of the placing groove in various states.
EXAMPLE 3 an apparatus for discriminating Crohn's disease from intestinal ulcer lymphoma
The invention also discloses a device for identifying the Crohn disease and the intestinal ulcer type lymphoma, which comprises a rectangular structure 1, wherein the upper part of the rectangular structure 1 is a table partition structure, the upper part of the table partition comprises an index grid 2 and a score grid 3; no score lattice 4; the front grid at the bottom is a specific index name grid, and the grids at the back of the same line are obtained; the result is the corresponding division whether each index is yes or not; the lowest row is a total counting row 5, and the total score is counted; the specific index grids are respectively as follows: the "intestinal hemorrhage" grid, the "extra-intestinal manifestation" grid, the "segmental lesion" grid, the "features of paving stones" grid, the "stratified reinforcement" grid, the "moderate and severe reinforcement" grid, and the "mesenteric peripheral vascularity" grid.
A classification column is arranged in front of the specific index grid; the "intestinal bleeding" compartment and the "extra-intestinal manifestation" compartment are classified as the "clinical manifestation" compartment 71; the section lesion grid and the paving stone characteristic grid are classified into an under-endoscope characteristic grid 72 in front of the section lesion grid and the paving stone characteristic grid; the "layered reinforcement" compartment, "moderate-severe reinforcement" compartment, and "mesenteric peripheral vascularity" compartment are classified as the "imaging characteristics" compartment 73.
1) The back of the 'intestinal hemorrhage' case is a case of '-2' and a case of '0'; scores for the presence of intestinal bleeding and no intestinal bleeding, respectively.
2) The back of the extra-intestinal manifestation is the 2 and 0 lattices; the score for the presence of an intestinal appearance and the score for the absence of an intestinal appearance, respectively.
3) The back of the compartment of segmental lesion is a compartment of 1 and a compartment of 0; scores for the presence of segmental lesions and scores for non-segmental lesions, respectively.
4) The back of the paving stone sign grid is a grid of 2 and a grid of 0; the score for the presence of paving stones and the score for the absence of paving stones, respectively.
5) The '1' lattice and the '0' lattice are arranged behind the 'layered reinforcement' lattice; the score for the presence of a stratified boost and the score for the absence of a stratified boost, respectively.
6) The rear part of the medium-heavy strengthening lattice is a 1 lattice and a 0 lattice; scores for the presence of moderate to severe reinforcement and scores for the absence of moderate to severe reinforcement, respectively.
7) The back of the mesenteric peripheral vasculogenesis lattice is a 1 lattice and a 0 lattice; there is a score for perimesenteric vascularisation and a score for no perimesenteric vascularisation, respectively.
A cavity 91 is arranged in the rectangular structure 1; a switch 92 with a lamp is arranged below the grid; the lighted switch 92 is connected to a dc power supply 93 within the cavity 91 of the rectangular structure 1. The light is turned on when the corresponding scoring grid is pressed or touched to form the light-carrying switch 92, so that the marking effect is achieved, the scoring condition is counted by the user through the turned-on light, and the scoring marking mode is more convenient.
The rectangular structure 1 is provided with a main switch 94 for controlling the whole instrument.
A control structure 95 is provided, each switch being connected to the control structure 95, the control structure 95 controlling that two scoring switches within a single row cannot be turned on simultaneously.
The control structure 95 is further connected to a computing unit 96, and the computing unit 96 is further connected to a display structure 97. By connecting the control structure 95 with the calculating unit 96, the calculating unit 96 collects the corresponding scores of the under-cell lighted switches 92, calculates, and transmits the calculated results to the display structure 97 for display; by displaying the score through display structure 97, a conclusion can be reached quickly. A back cover 98 is provided behind the cavity, and the control structure 95 and dc power supply are provided on the back cover.
The above description of the embodiments is only for the understanding of the present invention. It should be noted that modifications could be made to the invention without departing from the principle of the invention, which would also fall within the scope of the claims of the invention.
Claims (3)
1. A device for distinguishing Crohn's disease and intestinal ulcer type lymphoma, which comprises a rectangular structure, wherein the upper part of the rectangular structure is a table partition structure, and is characterized in that the upper part of the table partition comprises an index grid and a score grid; a "no score" lattice; the front grid at the bottom is a specific index name grid, and the grids at the back of the same line are obtained; the result is the corresponding division whether each index is yes or not; the lowest row is a total counting row, and the total score is counted; the specific index grids are respectively as follows: the case of intestinal hemorrhage, the case of extra-intestinal manifestation, the case of segmental lesion, the case of paving stone sign, the case of stratified strengthening, the case of moderate and severe strengthening and the case of mesenteric peripheral vascularity; a classification column is arranged in front of the specific index grid; the "intestinal bleeding" case and the "extra-intestinal manifestation" case are classified as the "clinical manifestation" case in front of the "intestinal bleeding" case; the section lesion grids and the paving stone feature grids are classified into feature grids under the endoscope in front of the section lesion grids and the paving stone feature grids; the front of the layering strengthening grid, the moderate and severe strengthening grid and the mesenteric peripheral vascularity grid is classified as an imaging characteristic grid; the index score is: with intestinal bleeding score-2, no intestinal bleeding score 0; the score of the appearance of the intestines is 2, and the score of the appearance of the intestines is 0; the score of 1 is the segmental lesion, and the score of 0 is the non-segmental lesion; the score of the paving stone is 2, the score of the non-paving stone is 0, the score of the layering strengthening is 1, and the score of the non-layering strengthening is 0; score 1 for moderate and severe reinforcement and score 0 for no moderate and severe reinforcement; there was a score of 1 for mesenteric peripheral vascularity and 0 for no mesenteric peripheral vascularity; the corresponding formula for the operation of the instrument is as follows: logit (p) -4.9437-2.3876X1+2.0993X2+1.7663X3+2.5769X4+1.6304X5+1.8204X6+1.2979X 7; wherein X1 represents intestinal bleeding, X2 represents extra-intestinal manifestations, X3 represents segmental lesions, X4 represents paving stones, X5 represents stratified fortification, and X6 represents moderate-heavy fortification; x7 represents mesenteric perivascular hyperplasia; the establishment of the score for each index depends on the regression coefficients; according to the result of the multi-factor analysis, taking the index of the regression coefficient with the minimum absolute value as 1 point, dividing the regression coefficients of other variables by the minimum regression coefficient, and rounding the result to obtain the score of each index; logit (p) is the final total score, which is crohn's disease when the total score is ≧ 3 minutes, and intestinal ulcer type lymphoma when the total score is less than 3 minutes.
2. The device for differentiating between crohn's disease and ulcerated intestinal lymphoma according to claim 1, wherein 1) "intestinal bleeding" compartment is followed by "-2" compartment and "0" compartment; score for the presence of intestinal bleeding and score for the absence of intestinal bleeding, respectively; 2) the back of the extra-intestinal manifestation is the 2 and 0 lattices; scores for the presence of an intestinal appearance and scores for the absence of an intestinal appearance, respectively; 3) the back of the compartment of segmental lesion is a compartment of 1 and a compartment of 0; score for the presence of segmental lesions and score for the absence of segmental lesions, respectively; 4) the back of the paving stone sign grid is a grid of 2 and a grid of 0; respectively the score of the presence of paving stones and the score of the absence of paving stones; 5) the '1' lattice and the '0' lattice are arranged behind the 'layered reinforcement' lattice; scores for the presence of stratified augmentation and scores for the absence of stratified augmentation, respectively; 6) the rear part of the medium-heavy strengthening lattice is a 1 lattice and a 0 lattice; scores for the presence of moderate to severe reinforcement and scores for the absence of moderate to severe reinforcement, respectively; 7) the back of the mesenteric peripheral vasculogenesis lattice is a 1 lattice and a 0 lattice; scores for the presence of mesenteric peripheral vascularity and no mesenteric peripheral vascularity, respectively.
3. The apparatus for differentiating between Crohn's disease and intestinal ulcerated lymphoma according to claim 2, wherein the rectangular structure is a rectangular plate, the rectangular plate is a sliding-surface rectangular plate, and a pen and a wiping structure are arranged beside the rectangular plate; the rectangular plate is provided with a corresponding erasable pen and wiping structure placing structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910296400.4A CN109998488B (en) | 2019-04-13 | 2019-04-13 | Identification model of Crohn's disease and intestinal ulcer type lymphoma and construction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910296400.4A CN109998488B (en) | 2019-04-13 | 2019-04-13 | Identification model of Crohn's disease and intestinal ulcer type lymphoma and construction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109998488A CN109998488A (en) | 2019-07-12 |
| CN109998488B true CN109998488B (en) | 2022-08-02 |
Family
ID=67171601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910296400.4A Active CN109998488B (en) | 2019-04-13 | 2019-04-13 | Identification model of Crohn's disease and intestinal ulcer type lymphoma and construction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109998488B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020143951A (en) * | 2019-03-05 | 2020-09-10 | 国立大学法人 東京大学 | Method for differentiation between chronic enteritis and gastrointestinal lymphoma, differentiation marker and kit |
| CN116631510B (en) * | 2022-10-28 | 2024-01-12 | 中国人民解放军军事科学院军事医学研究院 | Device for differential diagnosis of Crohn's disease and ulcerative colitis |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040073120A1 (en) * | 2002-04-05 | 2004-04-15 | Massachusetts Institute Of Technology | Systems and methods for spectroscopy of biological tissue |
| KR20110027851A (en) * | 2002-07-19 | 2011-03-16 | 애보트 바이오테크놀로지 리미티드 | TREATMENT OF TNFα RELATED DISORDERS |
| SE0402025D0 (en) * | 2004-08-13 | 2004-08-13 | Active Biotech Ab | Treatment of hyperproliferative disease with superantigens in combination with another anticancer agent |
| EP2252707A2 (en) * | 2008-03-14 | 2010-11-24 | Exagen Diagnostics, Inc. | Biomarkers for inflammatory bowel disease and irritable bowel syndrome |
| KR101632369B1 (en) * | 2010-06-10 | 2016-06-21 | 인두스 바이오텍 프라이빗 리미티드 | A method for preparation of highly pure asiaticoside composition from centella asiatica and a method of use thereof |
| US9535068B2 (en) * | 2010-11-12 | 2017-01-03 | William Marsh Rice University | Oral cancer point of care diagnostics |
| SG194710A1 (en) * | 2011-05-10 | 2013-12-30 | Nestec Sa | Methods of disease activity profiling for personalized therapy management |
| RU2018124339A (en) * | 2015-12-09 | 2020-01-09 | Рамот Ат Тель-Авив Юниверсити Лтд. | METHOD AND SYSTEM FOR SENSOR DETECTION BY MEANS OF MODIFIED NANOSTRUCTURE |
| FR3049104B1 (en) * | 2016-03-15 | 2020-02-21 | Universite De Nantes | METHOD FOR DIAGNOSING CHRONIC INFLAMMATORY BOWEL DISEASES |
| CN207640381U (en) * | 2017-03-06 | 2018-07-24 | 中国医学科学院北京协和医院 | Chronic auto-immune disease is disabled Index Assessment instrument |
| CN207912677U (en) * | 2017-05-16 | 2018-09-28 | 中国医学科学院北京协和医院 | Various dimensions information data acquisition analysis system |
| CN109615633A (en) * | 2018-11-28 | 2019-04-12 | 武汉大学人民医院（湖北省人民医院） | Crohn disease assistant diagnosis system and method under a kind of colonoscopy based on deep learning |
-
2019
- 2019-04-13 CN CN201910296400.4A patent/CN109998488B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109998488A (en) | 2019-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chung et al. | Efficacy of computed virtual chromoendoscopy on colorectal cancer screening: a prospective, randomized, back-to-back trial of Fuji Intelligent Color Enhancement versus conventional colonoscopy to compare adenoma miss rates | |
| Zhao et al. | Screening for gastric cancer with magnetically controlled capsule gastroscopy in asymptomatic individuals | |
| Hanson et al. | Anatomic factors predictive of incomplete colonoscopy based on findings at CT colonography | |
| CN113164025B (en) | Medical support system, medical support apparatus, and medical support method | |
| CN109998488B (en) | Identification model of Crohn's disease and intestinal ulcer type lymphoma and construction method | |
| Levin et al. | Quality in the technical performance of screening flexible sigmoidoscopy: recommendations of an international multi-society task group | |
| Geboes et al. | The value of colonoscopy in the diagnosis of Crohn’s disease | |
| Rondonotti et al. | Utility of 3-dimensional image reconstruction in the diagnosis of small-bowel masses in capsule endoscopy (with video) | |
| Schroy et al. | Video endoscopy by nurse practitioners: a model for colorectal cancer screening | |
| Rodrigues et al. | Validation of SPICE, a method to differenciate small bowel submucosal lesions from innocent bulges on capsule endoscopy | |
| Shaheen et al. | Progression of Barrett’s esophagus, crypt dysplasia, and low-grade dysplasia diagnosed by wide-area transepithelial sampling with 3-dimensional computer-assisted analysis: a retrospective analysis | |
| Ruiqing et al. | A novel radiomics model integrating luminal and mesenteric features to predict mucosal activity and surgery risk in Crohn's disease patients: a multicenter study | |
| Štimac et al. | What’s new in diagnosing diverticular disease | |
| Waldmann et al. | How can screening colonoscopy be optimized? | |
| Muthukudage et al. | Color based stool region detection in colonoscopy videos for quality measurements | |
| Park et al. | Risk of advanced colorectal neoplasm by the proposed combined United States and United Kingdom risk stratification guidelines | |
| van Heijningen et al. | Developing a score chart to improve risk stratification of patients with colorectal adenoma | |
| Rex | Update on colonoscopic imaging and projections for the future | |
| Yang et al. | Differential diagnosis of Crohn’s disease and ulcerative primary intestinal lymphoma: a scoring model based on a multicenter study | |
| Neri et al. | How to read and report CTC | |
| Lachter et al. | Novel artificial intelligence–enabled deep learning system to enhance adenoma detection: a prospective randomized controlled study | |
| Park et al. | Multiple small, rectal neuroendocrine tumors with numerous micronests. | |
| Sharma et al. | Accuracy of visual prediction of pathology of colorectal polyps: how accurate are we? | |
| CN109994214A (en) | The identification model and model building method of Crohn disease and the white plug of intestines | |
| Kabra et al. | A Brief Study on Artificial Intelligence in Cancer Research, Diagnosis and Therapy |
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 |