CN120148652B - Method and device for prognosis prediction of lung adenocarcinoma-derived meningioma, electronic device and storage medium - Google Patents
Method and device for prognosis prediction of lung adenocarcinoma-derived meningioma, electronic device and storage mediumInfo
- Publication number
- CN120148652B CN120148652B CN202510303665.8A CN202510303665A CN120148652B CN 120148652 B CN120148652 B CN 120148652B CN 202510303665 A CN202510303665 A CN 202510303665A CN 120148652 B CN120148652 B CN 120148652B
- Authority
- CN
- China
- Prior art keywords
- model
- tnf
- prognosis
- sample
- prediction
- 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
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B40/20—Supervised data analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Bioethics (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Epidemiology (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Biotechnology (AREA)
- General Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a prognosis prediction method, a device, electronic equipment and a storage medium for lung adenocarcinoma source meningiomycosis, belonging to the field of intelligent prediction methods; extracting the characteristics of the genetic information to obtain genetic characteristics and content data thereof, wherein the genetic characteristics are IL-6 and/or TNF-alpha; based on the content data of the genetic characteristics, classification prediction is carried out to obtain a classification result of whether the sample is a good prognosis or a bad prognosis sample.
Description
Technical Field
The invention belongs to the field of intelligent prediction methods, and particularly relates to a lung adenocarcinoma-derived meningioma prognosis prediction method, a device, electronic equipment and a storage medium.
Background
Lung adenocarcinoma-derived meningioma (MENINGEAL CARCINOMATOSIS, MC), which refers to metastasis of lung adenocarcinoma cells into the pia (spinal) membrane of the brain and spinal cord, exhibits diffuse or multifocal, localized distribution, and may or may not be accompanied by central nervous system metastases of metastatic tumor nodules in the brain and spinal cord parenchyma. Lung adenocarcinoma cells are invasive and can leave the primary tumor to enter the blood circulation or lymphatic system, migrate with blood flow or lymph fluid to the meninges, and grow, multiply and plant on the meninges. The transfer route comprises that the blood source is transferred to the choroidal blood vessel or the pia mater blood vessel to reach the subarachnoid space, is spread along the perinervous lymphatic vessel and the sheath in a retrograde way, is transferred to Batson's vein to reach the subarachnoid space, is expanded along the perivascular lymphatic vessel in a centrality way, and the like.
The lung adenocarcinoma-derived meningioma is a serious cancer complication, and the clinical manifestations thereof include symptoms of increased intracranial pressure (headache is persistent and progressive, nausea and vomiting are often in jet form, vision disorder such as blurred vision, double vision and the like, and symptoms of stimulation of meninges (which are positive in cervical rigidity, kernig and Brudzinski), symptoms of brain parenchyma (which can occur in consciousness disorder such as somnolence, coma, cognitive disorder such as hypomnesis, disorientation and the like), symptoms of cerebral nerve and spinal nerve damage (which can occur in double vision, eyeball movement disorder, facial numbness, hearing decline, dysphagia, hoarseness and the like, spinal nerve involvement with radicular pain, segmental sensory defects and the like).
Currently, methods commonly used for prognosis prediction of lung adenocarcinoma-derived meningioma include clinical factor assessment, imaging assessment, cerebrospinal fluid cytological examination assessment, and the like. The influence degree of each factor in clinical factor evaluation on prognosis is difficult to precisely quantify, subjective judgment of different doctors may be different, and the effects of some treatment means are also influenced by various other factors, such as tolerance, compliance and the like of patients on medicines. The tiny meninges metastasis can be difficult to accurately find by imaging examination, which leads to underestimation of the severity of the disease, and imaging examination can only provide morphological information of the tumor and can not reflect the biological characteristics and functional state of tumor cells. The cytological examination of cerebrospinal fluid has the possibility of false negative, and is influenced by factors such as sampling time, sampling amount and the like.
Although the methods commonly used for prognosis prediction of lung adenocarcinoma-derived meningioma can achieve a certain effect at present, the methods have low prediction accuracy for prognosis prediction of lung adenocarcinoma-derived meningioma, and are difficult to meet the requirements of clinical application.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a method, an apparatus, an electronic device, and a storage medium for prognosis prediction of lung adenocarcinoma-derived meningioma.
The invention adopts the following technical scheme to realize the aim of the invention:
in a first aspect, the invention provides a method for prognosis prediction of lung adenocarcinoma-derived meningioma based on IL-6 and/or TNF- α, the method comprising:
acquiring genetic information of a cerebrospinal fluid sample of a patient with lung adenocarcinoma derived from meningioma cancer;
Extracting the characteristics of the genetic information to obtain genetic characteristics and content data thereof, wherein the genetic characteristics are IL-6 and/or TNF-alpha;
And carrying out classification prediction based on the content data of the genetic characteristics to obtain a classification result of whether the sample is a good prognosis or a bad prognosis sample.
Further, the classification result is obtained based on a prediction model, and the construction method of the prediction model comprises the following steps:
acquiring content data of the genetic characteristics in a cerebrospinal fluid sample of a training set and clinical characteristics corresponding to the cerebrospinal fluid sample, wherein the clinical characteristics are good prognosis or bad prognosis, extracting the content data of the genetic characteristics in the training set, and inputting the content data into a machine learning model to construct a prediction model, so as to obtain a constructed prediction model and a threshold;
if the IL-6 content is higher than a threshold value and/or the TNF-alpha content is lower than a threshold value, obtaining a classification result that the sample is a good prognosis sample;
if the IL-6 content is below a threshold and/or the TNF-alpha content is above a threshold, a classification result is obtained in which the sample is a poor prognosis sample.
Further, the machine learning model is a Lasso regression model, a linear regression model, a logistic regression model, a Ridge regression model, a linear discriminant analysis model, a random forest model, a neighbor model, a decision tree model, a support vector machine model, a naive bayes model and/or a perceptron model.
Further, the content data of the genetic characteristics are obtained by any one or more of an enzyme-linked immunosorbent assay, an immunoblotting method, a real-time fluorescence quantitative PCR, a flow cytometry and a liquid chip technology.
In a second aspect, the invention provides a lung adenocarcinoma derived meningioma prognosis prediction system based on IL-6 and/or TNF- α, the system comprising:
the genetic information acquisition unit is used for acquiring genetic information of a cerebrospinal fluid sample of a patient with lung adenocarcinoma derived from meningioma cancer;
The genetic characteristic extracting unit is used for extracting the characteristics of the genetic information to obtain genetic characteristics and content data thereof, wherein the genetic characteristics are IL-6 and/or TNF-alpha;
The disease prognosis prediction unit is used for carrying out classification prediction based on the content data of the genetic characteristics to obtain a classification result of whether the sample is a good prognosis or a bad prognosis sample;
the classification result is obtained based on a prediction model, and the construction method of the prediction model comprises the following steps:
acquiring content data of the genetic characteristics in a cerebrospinal fluid sample of a training set and clinical characteristics corresponding to the cerebrospinal fluid sample, wherein the clinical characteristics are good prognosis or bad prognosis, extracting the content data of the genetic characteristics in the training set, and inputting the content data into a machine learning model to construct a prediction model, so as to obtain a constructed prediction model and a threshold;
if the IL-6 content is higher than a threshold value and/or the TNF-alpha content is lower than a threshold value, obtaining a classification result that the sample is a good prognosis sample;
if the IL-6 content is below a threshold and/or the TNF-alpha content is above a threshold, a classification result is obtained in which the sample is a poor prognosis sample.
Further, the machine learning model is a Lasso regression model, a linear regression model, a logistic regression model, a Ridge regression model, a linear discriminant analysis model, a random forest model, a neighbor model, a decision tree model, a support vector machine model, a naive bayes model and/or a perceptron model.
In a third aspect, the invention provides an apparatus or electronic device for prognosis prediction of lung adenocarcinoma derived meningioma cancer, the apparatus or electronic device comprising a memory and a processor;
the memory is used for storing program instructions;
the processor is used for calling program instructions, and when the program instructions are executed, the lung adenocarcinoma-derived meningioma prognosis prediction method based on IL-6 and/or TNF-alpha according to the first aspect of the invention is realized.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the IL-6 and/or TNF- α based lung adenocarcinoma derived meningococcal disease prognosis method according to the first aspect of the invention.
In a fifth aspect, the invention provides the use of an agent for detecting IL-6 and/or TNF- α levels in a cerebrospinal fluid sample in the preparation of a predictive product for a lung adenocarcinoma-derived meningioma.
Further, the reagent comprises a reagent for detecting the IL-6 and/or TNF-alpha expression level in a cerebrospinal fluid sample by one or more of enzyme-linked immunosorbent assay, immunoblotting, real-time fluorescent quantitative PCR, flow cytometry and liquid chip technology.
In some embodiments, the reagent includes a reagent that detects the level of IL-6 and/or TNF- α mRNA expression in a cerebrospinal fluid sample, and/or a reagent that detects the level of IL-6 and/or TNF- α encoded protein and/or polypeptide expression in a cerebrospinal fluid sample.
In some embodiments, the reagent that detects the level of IL-6 and/or TNF- α mRNA expression in a cerebrospinal fluid sample comprises a probe that specifically recognizes the IL-6 and/or TNF- α, and/or a primer that specifically amplifies the IL-6 and/or TNF- α.
In some embodiments, the agent that detects the expression level of the IL-6 and/or TNF- α encoded protein and/or polypeptide in a cerebrospinal fluid sample comprises an antibody, antibody fragment, and/or affinity protein that specifically binds to the IL-6 and/or TNF- α.
In a sixth aspect, the invention provides a product for prognosis prediction of lung adenocarcinoma derived meningioma, said product comprising an agent for detecting IL-6 and/or TNF- α levels in a cerebrospinal fluid sample as described above.
In some embodiments, the product comprises a detection kit, a detection chip, or a detection test strip.
In some embodiments, the detection kit further comprises instructions or labels for use, positive controls, negative controls, buffers, adjuvants or solvents, wherein the instructions or labels detail how to use the detection kit provided by the invention for detection of cerebrospinal fluid samples and the detection kit is used for prognosis prediction of a patient with a lung adenocarcinoma-derived meningioma.
In some embodiments, the test kit may further comprise a variety of different reagents suitable for use in practice (e.g., for different test methods), and is not limited to the reagents listed in the present invention, as long as reagents for prognosis prediction of lung adenocarcinoma-derived meningococcal disease based on detection of IL-6 and/or TNF- α in cerebrospinal fluid samples are included within the scope of the invention.
In some embodiments, the detection chip can be prepared by conventional preparation methods of a biochip known to those skilled in the art, including, but not limited to, using a solid support of a modified slide or a silicon wafer, the 5' end of the probe containing an amino-modified poly dT string, preparing an oligonucleotide probe into a solution, spotting it on the modified slide or the silicon wafer using a spotting instrument, arranging it into a predetermined sequence or array, and then fixing it by standing overnight.
In some embodiments, the primers included in the products of the invention may be prepared by chemical synthesis, appropriately designed by referring to known information using methods well known to those skilled in the art, and prepared by chemical synthesis. In some embodiments, the antibodies included in the products of the invention may use antibodies or fragments thereof of any structure, size, immunoglobulin class, origin, etc., so long as it binds to the target protein. Antibodies or fragments thereof contained in the products of the invention may be monoclonal or polyclonal. An antibody fragment refers to a portion of an antibody or a peptide containing a portion of an antibody that retains the binding activity of the antibody to an antigen. Antibody fragments may include F (ab ') 2, fab', fab, single chain Fv (scFv), disulfide bonded Fv (dsFv) or polymers thereof, dimerized V regions (diabodies), or CDR-containing peptides. Antibodies can be obtained by methods well known to those skilled in the art. For example, mammalian cell expression vectors retaining polypeptides of the whole or part of the target protein or polynucleotides encoding them are prepared as antigens. After immunization of an animal with an antigen, immune cells are obtained from the immunized animal and the cancer cells are fused to obtain hybridomas. Antibodies were then collected from the hybridoma cultures. Finally, monoclonal antibodies directed against IL-6 and/or TNF- α can be obtained by subjecting the obtained antibodies to antigen-specific purification using IL-6 and/or TNF- α or portions thereof used as antigen.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) The invention provides a brand-new lung adenocarcinoma source meningiomarcinoma prognosis prediction method based on IL-6 and/or TNF-alpha, which comprises the steps of obtaining genetic information of a lung adenocarcinoma source meningiomarcinoma patient cerebrospinal fluid sample, extracting characteristics of the genetic information to obtain genetic characteristics and content data thereof, wherein the genetic characteristics are IL-6 and/or TNF-alpha, and carrying out classification prediction based on the content data of the genetic characteristics to obtain a classification result of whether the sample is a good prognosis or a bad prognosis sample. The method provided by the invention can be used for early prediction of disease progress, guiding personalized treatment or monitoring treatment response and the like.
(2) The invention creatively discovers that the expression level of IL-6 and/or TNF-alpha in a cerebrospinal fluid sample of a patient with lung adenocarcinoma source meningioma and prognosis prediction of the patient with lung adenocarcinoma source meningioma have close correlation for the first time, and uses the expression level of IL-6 and/or TNF-alpha in the cerebrospinal fluid sample as genetic information for prognosis prediction of the patient with lung adenocarcinoma source meningioma, thereby not only having higher prediction precision, but also having higher prediction efficiency and meeting the requirements of clinical application. The invention provides a brand new thought and strategy for prognosis prediction of lung adenocarcinoma-derived meningioma, provides a more reliable basis for clinical treatment, can be used for helping clinicians to formulate more accurate treatment schemes, and has wide application prospect.
Drawings
FIG. 1 is a schematic flow chart of a lung adenocarcinoma derived meningioma prognosis prediction method based on IL-6 and/or TNF-alpha provided by the embodiment of the invention;
FIG. 2 is a schematic diagram of a lung adenocarcinoma derived meningioma prognosis system based on IL-6 and/or TNF- α according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a device or electronic equipment for prognosis prediction of lung adenocarcinoma-derived meningioma according to an embodiment of the present invention;
FIG. 4 is a graph of results of MC patients comparing CSF with serum IL-6, IL-1β, TNF- α levels;
FIG. 5 is a graph showing the results of significant increases in IL-6, IL-1β and TNF- α levels in MC-CSF over control CSF;
FIG. 6 is a graph of the results of MC and non-statistically significant IL-6, IL-1β and TNF- α levels in the serum of lung carcinoma group;
FIG. 7 shows graphs of the results of positive correlation of IL-6 with TNF- α in CSF and positive correlation of IL-1β with TNF- α in serum, wherein graph A shows TNF- α and graph B shows IL-1β;
FIG. 8 shows the results of TNF- α elevation associated with a worse OS and IL-6 elevation associated with a better OS, wherein A shows TNF- α and B shows IL-6.
Detailed Description
In order to enable those skilled in the art to better understand the present invention, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present invention with reference to the accompanying drawings.
In some of the flows described in the specification and claims of the present invention and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as S1, S2, etc., being merely used to distinguish between the various operations, the order of the operations itself not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel.
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments according to the invention without any creative effort, are within the protection scope of the invention.
FIG. 1 is a schematic flow chart of a lung adenocarcinoma derived meningioma prognosis prediction method based on IL-6 and/or TNF-alpha, which comprises the following steps:
s1, acquiring genetic information of a cerebrospinal fluid sample of a patient with lung adenocarcinoma derived from meningioma cancer;
in some embodiments, the patient refers to any animal, and also refers to human and non-human animals. The non-human animals include all vertebrates, for example, mammals such as non-human primates (particularly higher primates), sheep, dogs, rodents (such as mice or rats), guinea pigs, goats, pigs, cats, rabbits, cattle, and any domestic animals or pets, and non-mammals such as chickens, amphibians, reptiles, etc., in particular embodiments of the invention, the patient is a human.
In some embodiments, both IL-6 (interleukin-6) and TNF-alpha (tumor necrosis factor-alpha) are important cytokines that play a critical role in the immune response, inflammatory regulation, etc. of the body.
Wherein the IL-6 is a glycoprotein whose gene is located on chromosome 7 in humans. Mature IL-6 consists of 184 amino acids, contains 4 alpha-helical structures, and its spatial structure is critical for its binding to the receptor and its biological function.
Wherein, the TNF-alpha is a cytokine, the gene of which is located on human chromosome 6, and the encoded TNF-alpha protein consists of 233 amino acids. TNF- α can exist in the form of a trimer, a critical form for its biological activity.
S2, extracting characteristics of the genetic information to obtain genetic characteristics and content data thereof, wherein the genetic characteristics are IL-6 and/or TNF-alpha;
In some embodiments, the genetic profile content data is obtained using any one or more of the methods of enzyme-linked immunosorbent assay, immunoblotting, real-time fluorescent quantitative PCR, flow cytometry, liquid phase chip technology, but is not limited to the methods listed, as long as the methods that can be used to detect the genetic profile content data are applicable to the present invention.
In one embodiment, the enzyme-linked immunosorbent assay (ELISA) is to coat known IL-6 or TNF-alpha antibodies on a solid carrier by utilizing the specific binding of antigen and antibody, after a cerebrospinal fluid sample is added, IL-6 or TNF-alpha in the sample can be combined with the coated antibodies, then an enzyme-labeled secondary antibody is added to be combined with an antigen-antibody complex combined on the solid carrier, finally a substrate is added, the substrate is catalyzed by the enzyme to develop color, the absorbance value is measured by an enzyme-labeled instrument, and the concentration of IL-6 or TNF-alpha in the cerebrospinal fluid sample is calculated according to a standard curve.
In one embodiment, the immunoblotting (Western blot) is to perform polyacrylamide gel electrophoresis on the protein in the cerebrospinal fluid sample, separate the protein according to the molecular weight of the protein, transfer the separated protein onto a solid phase membrane, hybridize with a specific IL-6 or TNF-alpha antibody, detect the protein band bound with the antibody by a chemiluminescence or chromogenic method, and semi-quantitatively analyze the expression level of IL-6 or TNF-alpha in the cerebrospinal fluid sample according to the intensity of the band.
In one embodiment, the real-time fluorescent quantitative PCR (qPCR) uses total RNA in cerebrospinal fluid as a template, reverse transcription is carried out to form cDNA, then the cDNA is used as the template for PCR amplification, a fluorescent group is added into a PCR reaction system, the intensity of a fluorescent signal is in direct proportion to the amount of a PCR product, and the change of the fluorescent signal is monitored in real time, and the mRNA expression level of IL-6 or TNF-alpha is quantitatively analyzed by using a standard curve, so that the expression level of protein is indirectly reflected.
In one embodiment, the flow cytometry is incubating cells in a cerebrospinal fluid sample with a fluorescently labeled IL-6 or TNF-alpha antibody that specifically binds to IL-6 or TNF-alpha on the surface of or within the cells, and then detecting a fluorescent signal by a flow cytometer to analyze the expression level of IL-6 or TNF-alpha based on the intensity of the fluorescence and the number of cells.
In one embodiment, the liquid chip technology is to fix specific antibodies against IL-6, TNF-alpha and other cytokines on different microspheres respectively to form different detection microspheres, mix the detection microspheres with a cerebrospinal fluid sample, combine the cytokines in the sample with the corresponding antibodies, add a fluorescent-labeled secondary antibody, detect fluorescent signals on the microspheres by a liquid chip analyzer, and quantitatively analyze the cytokines.
S3, carrying out classification prediction based on the content data of the genetic characteristics to obtain a classification result of whether the sample is a good prognosis or a bad prognosis sample;
the classification result is obtained based on a prediction model, and the construction method of the prediction model comprises the following steps:
acquiring content data of the genetic characteristics in a cerebrospinal fluid sample of a training set and clinical characteristics corresponding to the cerebrospinal fluid sample, wherein the clinical characteristics are good prognosis or bad prognosis, extracting the content data of the genetic characteristics in the training set, and inputting the content data into a machine learning model to construct a prediction model, so as to obtain a constructed prediction model and a threshold;
if the IL-6 content is higher than a threshold value and/or the TNF-alpha content is lower than a threshold value, obtaining a classification result that the sample is a good prognosis sample;
if the IL-6 content is below a threshold and/or the TNF-alpha content is above a threshold, a classification result is obtained in which the sample is a poor prognosis sample.
In some embodiments, the machine learning model is a Lasso regression model, a linear regression model, a logistic regression model, a Ridge regression model, a linear discriminant analysis model, a random forest model, a neighbor model, a decision tree model, a support vector machine model, a naive bayes model, and/or a perceptron model.
In one embodiment, the threshold in the machine learning model refers to a threshold value used to convert model output to classification results. In binary classification problems, the model typically outputs a real value that represents the probability of belonging to a certain class. For example, the logistic regression model will output a probability value between 0 and 1, typically with a default threshold of 0.5, i.e., a probability of 0.5 or more is classified as positive and less than 0.5 is classified as negative.
In one embodiment, taking a Lasso regression model, a linear regression model, a logistic regression model, etc. as an example, these models are all based on statistical and mathematical principles, by learning and fitting a large amount of training data, a relationship between the input features (i.e., IL-6 and TNF- α content data) and the output results (good prognosis or poor prognosis) is found. Taking a logistic regression model as an example, by constructing a logistic function, the content data of IL-6 and TNF-alpha are mapped to a probability value between 0 and 1 to represent the probability that the sample belongs to good prognosis, and the judgment of whether the sample is good prognosis or bad prognosis is carried out by setting a threshold value. Other models, such as random forest models, are obtained by constructing a plurality of decision trees, and integrating the results of the decision trees to perform classification prediction and the like.
In one embodiment, the threshold may be determined by analyzing the training set data and training the model to find a suitable threshold to optimize the classification of the model on the training set when constructing the predictive model. This threshold is determined based on the degree of matching between the predicted outcome of the model and the actual clinical features (good or bad prognosis), and usually some evaluation criteria such as accuracy, recall, F1 value, etc. are used as optimization targets, and these evaluation criteria are optimized by adjusting the threshold.
In one embodiment, precision-Recall curves (Precision-Recall) may be used to select the best threshold, by which the impact of different thresholds on model performance can be intuitively seen. The point on the curve is chosen so that the accuracy and recall reach the optimal balance, which is the optimal threshold.
In one embodiment, the optimal threshold may be selected using an F1 score, which is a harmonic mean of accuracy and recall, by maximizing the F1 score.
In one embodiment, the optimal threshold may be selected using the ROC curve. The receiver operating characteristic curve (ROC) may also be used to select an optimal threshold, which may be determined by evaluating the performance of the model by calculating the area under the curve (AUC).
In one embodiment, the efficacy of the constructed prediction model may be further predicted, that is, a data set including the genetic characteristic content data corresponding to a patient with a lung adenocarcinoma derived meningioma with a good prognosis and a patient with a lung adenocarcinoma derived meningioma with a poor prognosis is taken as a verification set, and the efficacy of the constructed prediction model is further verified in the verification set.
In an embodiment, the threshold value is obtained in the prediction model, i.e. included in the prediction model, in the case of the determination of the above-mentioned construction method of the prediction model, i.e. the threshold value is also determined in the case of the determination of the prediction model. The classification result of whether the sample to be tested is a good prognosis sample or a bad prognosis sample can be predicted based on the determined threshold. The specific judgment result based on the prediction model is that if the content of IL-6 is higher than a threshold value and/or the content of TNF-alpha is lower than a threshold value, a classification result that the sample is a good prognosis sample is obtained, and if the content of IL-6 is lower than the threshold value and/or the content of TNF-alpha is higher than the threshold value, a classification result that the sample is a bad prognosis sample is obtained.
In some embodiments, the prognosis prediction result comprises a good prognosis or a poor prognosis, wherein the good prognosis comprises healing, alleviation or stabilization, and the poor prognosis comprises progression or death.
In some embodiments, the cure means that the disease can be completely cured by existing treatment means and the intended course of treatment, the patient's body is restored to a healthy state prior to the disease, no cancer cells or causative factors are present in the body, symptoms and signs completely disappear, and no recurrence occurs for a substantial period of time. For example, after some early malignant tumors are completely resected by surgery, no tumor recurrence is found after long-term follow-up, and the prognosis effect of cure can be considered to be achieved.
In some embodiments, the relief may be divided into a complete relief and a partial relief. Complete remission means that symptoms and signs of the disease completely disappear, and relevant examination indexes such as imaging examination, laboratory examination and the like are recovered to be normal, but the complete remission does not mean that cancer cells or pathogenic factors are completely absent in the body, but cannot be found by the current detection means. Partial remission refers to obvious remission of symptoms and signs of the disease, reduction of tumor volume or improvement of related abnormal indexes, but not complete recovery of the disease. For example, in tumor treatment, the reduction of tumor volume beyond a certain proportion after chemotherapy, and the obvious alleviation of symptoms are partial alleviation.
In some embodiments, stable means that the disease is in a relatively quiescent state, symptoms, signs are not significantly changed, the tumor is neither significantly increased nor decreased, and each examination index is maintained substantially at its original level. This may be due to the fact that the treatment effectively controls the progression of the disease, or that the natural course of the disease itself is in a relatively smooth stage.
In some embodiments, the progression indicates that the disease is continuously developing, symptoms and signs are continuously aggravated, tumor volume is increased, new lesions or metastases appear, and relevant examination indicators are made worse. This may be due to poor efficacy of the existing treatment regimen, inability to effectively inhibit disease progression, or resistance of the disease itself to treatment.
In some embodiments, the death is one of the worst prognosis, i.e., the patient eventually loses life due to the severity of the disease, ineffective treatment, or other uncontrollable factors.
In one embodiment, the invention contemplates comparison of IL-6, IL-1. Beta. And TNF-alpha levels in CSF and serum. The research shows that the PI3K/Akt signal pathway plays an important role in the processes of inflammatory reaction, cell activation, apoptosis and the like. It is widely recognized that the PI3K/Akt pathway is an upstream activator of the NF- κB signaling cascade, and that inflammatory cytokines may be involved in tumor regulation by activating the NF- κB pathway. Thus, the present study analyzed the levels of IL-6, IL-1. Beta. And TNF-. Alpha.in cerebrospinal fluid (cerebrospinal fluid, CSF) and serum from tumor and non-tumor patients. The study was performed to analyze 132 samples, 52 samples of CSF from a lung adenocarcinoma-derived meningioma patient (MC patient), 30 samples of serum, 25 samples of serum from a stage IV lung cancer patient, and 25 samples of CSF from a control group (non-neoplastic central nervous system disease). To analyze cytokine levels in lung adenocarcinoma and lung adenocarcinoma MC patients, we compared the differences in IL-6, IL-1β and TNF- α between the different groups (as shown in Table 1).
TABLE 1CSF and serum IL-6, IL-1 beta, TNF-alpha levels
The results showed that in the MC group, IL-6, TNF- α levels in CSF were significantly higher than in serum, and the differences were statistically significant (P <0.001, FIG. 4). However, the IL-1β levels were slightly higher than serum, but the differences were not statistically significant (p=0.07, fig. 4). IL-6, IL-1. Beta. And TNF-alpha. Levels were significantly elevated in the CSF of the MC group compared to the control group, the differences were statistically significant (P <0.0001, FIG. 5). The IL-6, IL-1. Beta. And TNF-. Alpha.levels in serum were not statistically significant in the MC and lung carcinoma groups (P >0.05, FIG. 6).
In one embodiment, the invention provides for the study of CSF in relation with serum IL-6, IL-1. Beta. And TNF-alpha. Specifically, further analysis of the correlation of the different cytokines (FIG. 7), we found that IL-6 in CSF correlated positively with TNF- α (r=0.38, P <0.001, FIG. 7A), whereas IL-6 correlated uncorrelated with IL-1β, IL-1β with TNF- α (P > 0.05). IL-1β was positively correlated with TNF- α in serum (r=0.0.95, P <0.0001, FIG. 7B), whereas IL-6 was uncorrelated with IL-1β, IL-6 with TNF- α (P > 0.05).
In one embodiment, the invention contemplates analysis of IL-6, IL-1. Beta. And TNF-alpha levels in CSF with respect to survival and survival. Specifically, we compared the relationship between cytokine levels in CSF of MC patients and KPS, ECOG PS scores, and found no correlation between IL-6, IL-1 β, TNF- α levels and KPS, ECOG PS scores (P > 0.05). It was demonstrated that different levels of cytokines were independent of survival scores. To clarify the relationship of IL-6, IL-1β, TNF- α levels and survival (Overall Survival, OS) (FIG. 8), we found that TNF- α (40.8 months vs 14.4 months, P=0.018, FIG. 8A), IL-6 (14.4 months vs not reached, P=0.034, FIG. 8B) were significantly correlated with survival of MC patients, IL-1β was not related to survival (61.5 months vs 14.4 months, P=0.058).
The results show that TNF-alpha and IL-1 beta are obviously related to prognosis of MC patients, TNF-alpha elevation is related to poor OS, IL-6 elevation is related to good OS, namely, the invention proves that TNF-alpha and/or IL-1 beta in cerebrospinal fluid samples can be used for effective and accurate prediction of prognosis of lung adenocarcinoma-derived meningioma patients through collecting clinical true samples and a large number of experimental verification. Based on the results of this initial study, the present invention developed a novel prognostic prediction method for lung adenocarcinoma-derived meningioma based on the content of IL-6 and/or TNF- α in cerebrospinal fluid samples of patients with lung adenocarcinoma-derived meningioma as described above.
FIG. 2 is a schematic diagram of a lung adenocarcinoma derived meningioma prognosis system based on IL-6 and/or TNF- α according to an embodiment of the present invention, specifically, the system includes:
the genetic information acquisition unit is used for acquiring genetic information of a cerebrospinal fluid sample of a patient with lung adenocarcinoma derived from meningioma cancer;
The genetic characteristic extracting unit is used for extracting the characteristics of the genetic information to obtain genetic characteristics and content data thereof, wherein the genetic characteristics are IL-6 and/or TNF-alpha;
The disease prognosis prediction unit is used for carrying out classification prediction based on the content data of the genetic characteristics to obtain a classification result of whether the sample is a good prognosis or a bad prognosis sample;
the classification result is obtained based on a prediction model, and the construction method of the prediction model comprises the following steps:
acquiring content data of the genetic characteristics in a cerebrospinal fluid sample of a training set and clinical characteristics corresponding to the cerebrospinal fluid sample, wherein the clinical characteristics are good prognosis or bad prognosis, extracting the content data of the genetic characteristics in the training set, and inputting the content data into a machine learning model to construct a prediction model, so as to obtain a constructed prediction model and a threshold;
if the IL-6 content is higher than a threshold value and/or the TNF-alpha content is lower than a threshold value, obtaining a classification result that the sample is a good prognosis sample;
if the IL-6 content is below a threshold and/or the TNF-alpha content is above a threshold, a classification result is obtained in which the sample is a poor prognosis sample.
In some embodiments, the machine learning model is a Lasso regression model, a linear regression model, a logistic regression model, a Ridge regression model, a linear discriminant analysis model, a random forest model, a neighbor model, a decision tree model, a support vector machine model, a naive bayes model, and/or a perceptron model.
In some embodiments, the content data of the genetic features is obtained using any one or more of an enzyme-linked immunosorbent assay, immunoblotting, real-time fluorescent quantitative PCR, flow cytometry, liquid phase chip technology.
FIG. 3 is a schematic diagram of an apparatus or electronic device for prognosis prediction of lung adenocarcinoma-derived meningioma according to an embodiment of the present invention, specifically, the apparatus or electronic device includes a memory and a processor;
the memory is used for storing program instructions;
The processor is configured to invoke the program instructions, which when executed, implement the IL-6 and/or TNF-alpha based lung adenocarcinoma derived meningioma prognosis prediction method as described above.
Embodiments of the present invention also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a lung adenocarcinoma-derived meningioma prognosis method based on IL-6 and/or TNF- α as described above.
The embodiment of the invention also provides application of the reagent for detecting the IL-6 and/or TNF-alpha level in the cerebrospinal fluid sample in preparing a lung adenocarcinoma-derived meningioma prognosis prediction product.
In some embodiments, the reagent comprises a reagent that detects the level of IL-6 and/or TNF- α expression in a cerebrospinal fluid sample using one or more of an enzyme-linked immunosorbent assay, immunoblotting, real-time fluorescent quantitative PCR, flow cytometry, liquid phase chip technology.
In one embodiment, the cerebrospinal fluid sample is derived from a subject in need thereof, preferably a lung adenocarcinoma-derived meningioma patient in need of disease prognosis prediction. The invention proves that TNF-alpha and IL-6 are obviously related to the survival time of a patient suffering from lung adenocarcinoma source meningioma through detailed experiments, wherein, the rise of TNF-alpha is related to poor OS and the rise of IL-6 is related to good OS.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program for instructing related hardware, and the program may be stored in a computer readable storage medium, where the storage medium may include a Read Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, etc.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in implementing the methods of the above embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, where the storage medium may be a read only memory, a magnetic disk or optical disk, etc.
While the foregoing describes a computer device provided by the present invention in detail, those skilled in the art will appreciate that the foregoing description is not meant to limit the invention thereto, as long as the scope of the invention is defined by the claims appended hereto.
Claims (9)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510303665.8A CN120148652B (en) | 2025-03-14 | 2025-03-14 | Method and device for prognosis prediction of lung adenocarcinoma-derived meningioma, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510303665.8A CN120148652B (en) | 2025-03-14 | 2025-03-14 | Method and device for prognosis prediction of lung adenocarcinoma-derived meningioma, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120148652A CN120148652A (en) | 2025-06-13 |
| CN120148652B true CN120148652B (en) | 2025-09-23 |
Family
ID=95958712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510303665.8A Active CN120148652B (en) | 2025-03-14 | 2025-03-14 | Method and device for prognosis prediction of lung adenocarcinoma-derived meningioma, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120148652B (en) |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE602007013405D1 (en) * | 2006-07-14 | 2011-05-05 | Us Government | METHOD FOR DETERMINING THE PROGNOSIS OF ADENOCARCINOMA |
| CN118191329A (en) * | 2022-12-14 | 2024-06-14 | 上海科技大学 | Biomarker array for assessing prognosis of spinal cord injury patient and construction method of risk early warning model |
| CN118345160A (en) * | 2023-01-13 | 2024-07-16 | 中国科学院上海药物研究所 | Lung adenocarcinoma prognosis marker and application thereof |
| WO2024184854A1 (en) * | 2023-03-07 | 2024-09-12 | Pomorski Uniwersytet Medyczny W Szczecinie | Methods, systems and assosiated computer program products for discriminating type of biological sample of an organism using epigenetic modification information |
| WO2024238813A2 (en) * | 2023-05-16 | 2024-11-21 | H. Lee Moffitt Cancer Center And Research Institute, Inc. | Methods of treating lemptomeningeal disease |
| CN116953259A (en) * | 2023-08-03 | 2023-10-27 | 遵义医科大学附属医院 | Application of cerebrospinal fluid cytokine as marker in diagnosis and treatment monitoring of tubercular meningitis |
| CN119480131A (en) * | 2024-10-28 | 2025-02-18 | 天津市环湖医院(天津市神经外科研究所、天津市脑系科中心医院) | Simulation model construction method, identification method and system for identifying lung cancer metastasis cells |
-
2025
- 2025-03-14 CN CN202510303665.8A patent/CN120148652B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| "脑膜癌病预测模型建立及肺腺癌来源脑膜癌病基因组学研究";白凯旋;《万方》;20250321;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120148652A (en) | 2025-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7370021B2 (en) | Medical applications of adaptive learning systems using gene expression data | |
| Crispín et al. | Expression of CD44 variant isoforms CD44v3 and CD44v6 is increased on T cells from patients with systemic lupus erythematosus and is correlated with disease activity | |
| KR101974135B1 (en) | Novel Marker for detection of bladder cancer and/or inflammatory conditions of the bladder | |
| AU2014224727B2 (en) | Methods and compositions for the diagnosis of Alzheimer's disease | |
| Shou et al. | Identification of blood biomarkers of rheumatoid arthritis by transcript profiling of peripheral blood mononuclear cells from the rat collagen-induced arthritis model | |
| US20130316921A1 (en) | Methods for diagnosis of kawasaki disease | |
| CN103080339A (en) | Biomarkers for diagnosis of stroke and its causes | |
| US20120178637A1 (en) | Biomarkers and methods for detecting alzheimer's disease | |
| CA3021036A1 (en) | Methods for assessment of multiple sclerosis activity | |
| CN107657149B (en) | System for predicting prognosis of liver cancer patient | |
| CN115678984B (en) | Marker for lupus nephritis curative effect evaluation and application | |
| CN114875149A (en) | Application of reagent for detecting biomarkers in preparation of product for predicting gastric cancer prognosis | |
| US20220214359A1 (en) | Elucidating a Proteomic Signature for the Detection of Intracerebral Aneurysms | |
| CN115948544B (en) | Use of CITED4 and/or METRN in differential diagnosis of the degree of disc degeneration | |
| KR20110014983A (en) | Cardiac Allograft Chronic Rejection Diagnosis | |
| Elamin et al. | A specific blood signature reveals higher levels of S100A12: a potential bladder cancer diagnostic biomarker along with urinary engrailed-2 protein detection | |
| CN120148652B (en) | Method and device for prognosis prediction of lung adenocarcinoma-derived meningioma, electronic device and storage medium | |
| Liu et al. | Innate immune cell profiling in peripheral blood mononuclear cells of patients with Moyamoya disease | |
| Da Silva Filho et al. | Disease trajectories in hospitalized COVID-19 patients are predicted by clinical and peripheral blood signatures representing distinct lung pathologies | |
| KR102138249B1 (en) | Biomarker for diagnosing breast cancer and use thereof | |
| JP7336517B2 (en) | Biomarkers for diagnosis and/or prediction of frailty | |
| CN119040462A (en) | Three-level lymphoid structure classification related novel marker and application thereof in liver cancer prognosis evaluation | |
| CN116445606A (en) | Application of serum molecular marker COMP in auxiliary diagnosis of depression | |
| CN116246710A (en) | Colorectal cancer prediction model based on cluster molecules and application | |
| CN115058512A (en) | Application of iron death related gene in identifying cerebral arterial thrombosis |
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 |