CN112116977B - Non-small cell lung cancer patient curative effect and prognosis prediction system - Google Patents
Non-small cell lung cancer patient curative effect and prognosis prediction system Download PDFInfo
- Publication number
- CN112116977B CN112116977B CN202010808966.3A CN202010808966A CN112116977B CN 112116977 B CN112116977 B CN 112116977B CN 202010808966 A CN202010808966 A CN 202010808966A CN 112116977 B CN112116977 B CN 112116977B
- Authority
- CN
- China
- Prior art keywords
- patient
- module
- lung cancer
- survival
- probability value
- 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
- 230000000694 effects Effects 0.000 title claims abstract description 31
- 208000002154 non-small cell lung carcinoma Diseases 0.000 title claims abstract description 26
- 208000029729 tumor suppressor gene on chromosome 11 Diseases 0.000 title claims abstract description 26
- 238000004393 prognosis Methods 0.000 title claims abstract description 19
- 230000004083 survival effect Effects 0.000 claims abstract description 29
- 102000003855 L-lactate dehydrogenase Human genes 0.000 claims abstract description 28
- 108700023483 L-lactate dehydrogenases Proteins 0.000 claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 230000000391 smoking effect Effects 0.000 claims abstract description 15
- 210000000440 neutrophil Anatomy 0.000 claims abstract description 13
- 210000004698 lymphocyte Anatomy 0.000 claims abstract description 10
- 210000002751 lymph Anatomy 0.000 claims abstract description 5
- 238000011282 treatment Methods 0.000 claims description 30
- 238000009169 immunotherapy Methods 0.000 claims description 18
- 238000002203 pretreatment Methods 0.000 claims description 11
- 210000000265 leukocyte Anatomy 0.000 claims description 5
- 108010010056 Terlipressin Proteins 0.000 claims description 4
- BENFXAYNYRLAIU-QSVFAHTRSA-N terlipressin Chemical compound NCCCC[C@@H](C(=O)NCC(N)=O)NC(=O)[C@@H]1CCCN1C(=O)[C@H]1NC(=O)[C@H](CC(N)=O)NC(=O)[C@H](CCC(N)=O)NC(=O)[C@H](CC=2C=CC=CC=2)NC(=O)[C@H](CC=2C=CC(O)=CC=2)NC(=O)[C@@H](NC(=O)CNC(=O)CNC(=O)CN)CSSC1 BENFXAYNYRLAIU-QSVFAHTRSA-N 0.000 claims description 4
- 229960003813 terlipressin Drugs 0.000 claims description 4
- 230000001225 therapeutic effect Effects 0.000 claims description 3
- 230000001575 pathological effect Effects 0.000 claims description 2
- 230000000750 progressive effect Effects 0.000 abstract description 2
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 9
- 201000005202 lung cancer Diseases 0.000 description 9
- 208000020816 lung neoplasm Diseases 0.000 description 9
- 230000001024 immunotherapeutic effect Effects 0.000 description 7
- 238000011088 calibration curve Methods 0.000 description 5
- 238000002512 chemotherapy Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- QOFFJEBXNKRSPX-ZDUSSCGKSA-N pemetrexed Chemical compound C1=N[C]2NC(N)=NC(=O)C2=C1CCC1=CC=C(C(=O)N[C@@H](CCC(O)=O)C(O)=O)C=C1 QOFFJEBXNKRSPX-ZDUSSCGKSA-N 0.000 description 4
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 102000008096 B7-H1 Antigen Human genes 0.000 description 3
- 108010074708 B7-H1 Antigen Proteins 0.000 description 3
- 208000032818 Microsatellite Instability Diseases 0.000 description 3
- ZDZOTLJHXYCWBA-VCVYQWHSSA-N N-debenzoyl-N-(tert-butoxycarbonyl)-10-deacetyltaxol Chemical compound O([C@H]1[C@H]2[C@@](C([C@H](O)C3=C(C)[C@@H](OC(=O)[C@H](O)[C@@H](NC(=O)OC(C)(C)C)C=4C=CC=CC=4)C[C@]1(O)C3(C)C)=O)(C)[C@@H](O)C[C@H]1OC[C@]12OC(=O)C)C(=O)C1=CC=CC=C1 ZDZOTLJHXYCWBA-VCVYQWHSSA-N 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 229960003668 docetaxel Drugs 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 206010028980 Neoplasm Diseases 0.000 description 2
- 238000009534 blood test Methods 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 230000000973 chemotherapeutic effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 229960003444 immunosuppressant agent Drugs 0.000 description 2
- 230000001861 immunosuppressant effect Effects 0.000 description 2
- 239000003018 immunosuppressive agent Substances 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 229960005079 pemetrexed Drugs 0.000 description 2
- 229910052697 platinum Inorganic materials 0.000 description 2
- 206010041823 squamous cell carcinoma Diseases 0.000 description 2
- 229940076838 Immune checkpoint inhibitor Drugs 0.000 description 1
- 102000037984 Inhibitory immune checkpoint proteins Human genes 0.000 description 1
- 108091008026 Inhibitory immune checkpoint proteins Proteins 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000090 biomarker Substances 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000000890 drug combination Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 239000012274 immune-checkpoint protein inhibitor Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- AHJRHEGDXFFMBM-UHFFFAOYSA-N palbociclib Chemical compound N1=C2N(C3CCCC3)C(=O)C(C(=O)C)=C(C)C2=CN=C1NC(N=C1)=CC=C1N1CCNCC1 AHJRHEGDXFFMBM-UHFFFAOYSA-N 0.000 description 1
- 229960004390 palbociclib Drugs 0.000 description 1
- 238000001959 radiotherapy Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000011519 second-line treatment Methods 0.000 description 1
- 238000009097 single-agent therapy Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000002626 targeted therapy Methods 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Epidemiology (AREA)
- Chemical & Material Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Pharmacology & Pharmacy (AREA)
- Toxicology (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention provides a non-small cell lung cancer patient curative effect and prognosis prediction system, which comprises three prediction models of patient curative effect, progression-free survival and total survival, wherein each model further comprises three modules of input, calculation and output. The input module transmits patient information to the calculation module, and the input module of the curative effect prediction model comprises smoking history and absolute lymphocyte count; the progression free survival prediction model includes age, sex, and lactate dehydrogenase; the overall survival prediction model included lactate dehydrogenase and derived neutrophil lymph ratios. The calculation module is internally provided with a corresponding alignment chart (nomogram) for calculating the effective probability of the sixth week of the patient, the non-progressive probability of the 6 th, 12 th and 18 th months and the survival probability. The output module is a web page version calculator and can output corresponding probability values. The invention has excellent prediction capability, better stability and efficiency, simple and quick prediction and very wide application prospect.
Description
Technical Field
The invention belongs to the field of medicines, and relates to a curative effect and prognosis prediction system for a non-small cell lung cancer patient.
Background
Lung cancer is the most common malignant tumor in China and even worldwide, the morbidity and the mortality of the lung cancer are the first malignant tumor, and in recent years, the morbidity and the mortality of the lung cancer are in an ascending trend, wherein non-small cell lung cancer (NSCLC) accounts for 80% -85% of the total lung cancer.
NSCLC is currently treated by surgery, radiotherapy and chemotherapy, targeted therapy, immunotherapy and the like. Among them, immunotherapy against immune checkpoint PD-1/PD-L1 is a revolution in recent years of advanced lung cancer treatment, so that the 5-year survival rate of advanced lung cancer is improved from less than 5% to 26%, and has become the first-line and second-line treatment option for advanced non-small cell lung cancer. Not all patients may benefit from immunotherapy.
Considering that the immune checkpoint inhibitor is expensive and has certain toxic and side effects, searching for a proper biomarker helps to screen out patients who can benefit from immunotherapy, plays the curative effect of the immunotherapy to the greatest extent, and has important significance for the accurate treatment of lung cancer.
The prior researches find that the PD-L1 expression, tumor mutation load (TMB), microsatellite instability (MSI) and other markers can predict the curative effect of immunotherapy, but the detection needs to be based on the acquisition of lung cancer tissue specimens, and the defects of difficult acquisition, repeated detection and the like exist, so that the method screens meaningful markers in clinical characteristics of patients and laboratory examination and establishes a corresponding prediction model, thereby being beneficial to simply, conveniently and rapidly predicting the curative effect and prognosis of immunotherapy of patients with non-small cell lung cancer.
Disclosure of Invention
The invention aims to provide a system for predicting the curative effect and prognosis of a non-small cell lung cancer patient, which comprises three prediction models for predicting the curative effect, progression-free survival and total survival.
Noun interpretation to which the invention relates:
PFS (progression-free survivinal): progression free survival;
OS (overall survival): total lifetime;
ALC (absolute lymphocyte count): absolute lymphocyte count;
LDH (lactate dehydrogenase): lactate dehydrogenase;
dNLR (derived neutrophil-to-lymphocyte ratio): the neutrophil lymph ratio was derived.
The invention provides a non-small cell lung cancer patient curative effect and prognosis prediction system, which mainly comprises three models, namely a curative effect prediction model, a progression-free survival (PFS) prediction model and a total survival (OS) prediction model. Each model comprises three modules, namely an input module, a calculation module and an output module. The method is realized by the following steps:
1. The input module in the input module of the curative effect prediction model is used for transmitting patient information to the calculation module, including smoking history and absolute lymphocyte count before treatment;
wherein absolute lymphocyte count is in units of 10 9/L;
The corresponding nomogram 1 is built in the computing module, and the specific steps are as follows:
The effective probability value y= (-1.93 e-07X 3+6.5238e-05×X2 + 0.000387789X + 0.052971747) X100) at the sixth week after patient treatment;
x = 38.93455X smoking history + 33.333333333X absolute lymphocyte count-6.666666667;
if the smoking history of the patient is "yes", the "smoking history" in the formula is taken as 1; otherwise, take 0.
The output module is a web page version calculator, and the value of the input variable in the web page can calculate and output a corresponding probability value Y.
2. The input module of the progression free survival prediction model is used for transmitting patient information to the calculation module, including age, gender and lactate dehydrogenase;
wherein, the lactate dehydrogenase is in U/L;
The corresponding nomogram 2 is built in the computing module, and the specific steps are as follows:
The probability value of no progress at 6 months after patient treatment, y= (1.37 e-06X 3-0.00023844×X2 -0.000129557X x+ 0.898134033) ×100%;
The probability value y= (2 502 e-06X 3-0.000318492×X2 -0.001023031X + 0.824736532) ×100% for no progress at 12 months after patient treatment;
the probability value of no progression at 18 months after patient treatment, y= (3.379 e-06X 3-0.000339952×X2 -0.003471356X x+ 0.76484454) ×100%;
x= 35.11728X sex+ 23.83088X age+ 0.076923077X lactate dehydrogenase;
if the sex of the patient is "female", the "sex" in the formula takes 1; otherwise, taking 0;
if the patient's age is > 65 years, then "age" in formula takes 1; otherwise, take 0.
The output module is a web page version calculator, and the value of the input variable in the web page can calculate and output a corresponding probability value Y.
An input module of the os prediction model for communicating patient information to the calculation module, including lactate dehydrogenase and pre-treatment derived neutrophil lymph ratios;
Wherein lactate dehydrogenase is in U/L, and derived neutrophil lymphorate = neutrophil absolute count/(leukocyte absolute count-neutrophil absolute count), absolute neutrophil count and absolute leukocyte count are in 10 9/L;
The corresponding nomogram is built in the computing module, and the computing module is specifically as follows:
The probability value of survival at 6 months after patient treatment, y= (3.255 e-06X 3-0.000762825×X2 + 0.040954221X + 0.259515127) ×100%;
Probability value y= (3.255 e-06X 3-0.000653776×X2 + 0.025135017X x+ 0.626258681) ×100% for survival 12 months after patient treatment;
probability value of survival at 18 months after treatment of the patient y= (5.944 e-06X 3 -0.000887041X 2+ 0.024720858X + 0.632409967) X100%;
x= 0.076923077X lactate dehydrogenase+ 6.631074059X derivatized neutrophil lymphorate-3.315537029;
The output module is a web page version calculator, and the value of the input variable in the web page can calculate and output a corresponding probability value Y.
The pathological type of the non-small cell lung cancer patient is non-small cell lung cancer (including squamous cell carcinoma and non-squamous cell carcinoma), the treatment effect refers to the treatment effect of immunotherapy, and the immunotherapy adopts NA Wu Liyou monoclonal antibody, palbociclizumab, terlipressin Li Shan antibody, carrilizumab, xindi Li Shan antibody and tirellizumab monoclonal antibody for treatment.
The input module in the system transmits patient information to the calculation module, and the input module of the curative effect prediction model comprises smoking history and absolute lymphocyte count; the progression free survival prediction model includes age, sex, and lactate dehydrogenase; the overall survival prediction model included lactate dehydrogenase and derived neutrophil lymph ratios. The calculation module is internally provided with a corresponding alignment chart (nomogram) for calculating the effective probability of the sixth week of the patient, the non-progressive probability of the 6 th, 12 th and 18 th months and the survival probability. The output module is a web page version calculator and can output corresponding probability values. Compared with PD-L1, TMB, MSI and other indexes, the patient information required by the prediction system has the advantages of simplicity and easiness in acquisition, and the built-in nomogram shows that the system has better C index and area under ROC curve, so that the system has excellent prediction capability. The invention has better stability and efficiency, can very simply and effectively predict the curative effect and prognosis of non-small cell lung cancer patients receiving immunotherapy, and has good application prospect.
Drawings
Fig. 1: nomogram for predicting patient efficacy and prognosis.
Fig. 2: the resulting nomogram ROC curve was plotted based on the immunotherapeutic group data.
Fig. 3: the resulting nomogram ROC curve was plotted based on the immunotherapeutic group data.
Fig. 4: the resulting nomogram ROC curve was plotted based on the immunotherapeutic group data.
Fig. 5: a calibration curve of nomogram 1 based on immunotherapeutic group data.
Fig. 6: a calibration curve of nomogram 2 based on immunotherapeutic group data.
Fig. 7: a calibration curve of nomogram based on immunotherapeutic group data.
Fig. 8: and a web page probability calculator.
The specific embodiment is as follows:
The invention is further described with reference to the drawings and examples.
Early preparation:
1. Basic information: age, sex (men's 0), smoking history (1, no 0),
2. Blood test information: blood test information is collected within one week before the patient begins treatment,
The main information obtained includes: LDH (U/L), ALC (10 9/L), ANC (10 9/L, WBC (10 9/L).
EXAMPLE 1 method of Using the prediction System of the efficacy and prognosis of immunotherapy for patients with non-Small cell lung cancer according to the invention
The user inputs the smoking history and ALC through the input module of the curative effect prediction model, the calculation module can substitute nomogram the information into nomogram to calculate, the effective probability of the sixth week after the treatment of the patient is obtained, and the effective probability is presented to the user through the output module.
The user inputs age, gender and LDH in the input module of the PFS prediction model, the calculation module can substitute nomogram the information into nomogram for calculation, the probability of progression-free survival of the 6 th, 12 th and 18 th months after treatment of the patient is obtained, and the probability is presented to the user through the output module.
The user inputs LDH and dNLR into the input module of the OS prediction model, the calculation module can substitute the information into nomogram to calculate, the probability of survival of the patient in 6 th, 12 th and 18 th months after treatment is obtained, and the probability is presented to the user through the output module.
The model of the invention is the key technical characteristics of a prediction system for the curative effect and prognosis of the non-small cell lung cancer patient to receive the immunotherapy, and the prediction effect is directly related; the predictive effect of the model of the present invention will be further described in the following by way of experimental examples.
Experimental example 2 verification of the effect of the inventive model
1. Inclusion criteria
The section is incorporated into 8 hospitals in Zhejiang province (a medical institute of Zhejiang affiliated Shao Yifu hospitals, a tumor hospital in Zhejiang province, a Xinhua hospital in Zhejiang province, a central hospital in Jinhua city, a central hospital in Huzhou city, a people's hospital in Lishui city, a Wen Lingshi first people's hospital and an affiliated hospital in Shaoxing national institute of Shaoxing) in 2010-2017.
The main inclusion criteria are as follows: (1) Receiving immunosuppressant monotherapy or chemotherapy alone; (2) clinical diagnosis of advanced lung cancer, including stages III B and IV.
The main exclusion criteria were as follows: (1) The score of the eastern tumor cooperative group (ECOG) in the United states is more than or equal to 3 points. The study was approved by the ethics committee of Shao Yifu hospitals affiliated with the university of Zhejiang university medical school.
2. Study object
The study included 327 patients with advanced non-small cell lung cancer.
203 Cases of the treatment with the immunosuppressant single drug are immunotherapy groups comprising nal Wu Liyou mab (43), pamil mab (50), carlizumab (31), terlipressin Li Shan mab (26), xindi Li Shan mab (31) and tirelimumab (22). All patients had a male to female ratio of 4.0:1.0 (162/41), and a median age of 66 years.
The remaining 124 received separate chemotherapy as a chemotherapy control group, including a platinum-based two-drug combination (68), pemetrexed (30) and docetaxel (26). Wherein the ratio of men and women of all patients is 2.6:1.0 (90/34), and the median age is 65 years.
Table 1 subject immunotherapeutic group treatment protocol distribution
Frequency number | Percentage by weight | |
Na Wu Liyou monoclonal antibodies | 43 | 21.18% |
Palbociclib monoclonal antibody | 50 | 24.63% |
Carrilizumab | 31 | 15.27% |
Terlipressin Li Shan antibody | 26 | 12.81% |
Xindi Li Shan antibody | 31 | 15.27% |
Tirelib bead monoclonal antibodies | 22 | 10.84% |
Totalizing | 203 | 100% |
Table 2 subject chemotherapeutic control treatment protocol distribution
Frequency number | Percentage by weight | |
Platinum-based combination of two drugs | 68 | 54.84% |
Pemetrexed | 30 | 24.19% |
Docetaxel (docetaxel) | 26 | 20.97% |
Totalizing | 124 | 100% |
3. Efficacy and survival analysis
The immunotherapy group 203 subjects were divided into 2 groups: group 1 was 92 training groups and group 2 was 111 verification groups.
In group 1, the multifactor Logistic regression model analysis suggested that the effective patients were accompanied by a history of smoking (or=3.388, p=0.027) and that pre-treatment ALC was higher (or=2.843, p=0.038) compared to the ineffective patients. Multifactorial Cox risk model analysis suggests that patients with progression are female (hr=4.165, p < 0.001), age > 65 years (hr=2.635, p=0.004), LDH higher before treatment (hr=1.003, p < 0.001) compared to non-progressed patients; pre-treatment LDH was higher in dead patients (hr=1.004, p < 0.001) and pre-treatment dNLR was higher (hr=1.434, p=0.035) compared to surviving patients.
However, in the chemotherapeutic control group, single factor Logistic regression model analysis suggests that there was no statistical difference in smoking history (p=0.688) and pre-treatment ALC (p=0.468) between the active and inactive patients; there were no statistical differences in gender (p=0.865), age (p=0.795) and pre-treatment LDH (p=0.809) between non-progressed and progressed patients; there was no statistical difference between pre-treatment LDH (p=0.572) and dNLR (p=0.336) between surviving and dead patients. The results show that the indexes can specifically predict the curative effect and prognosis of a non-small cell lung cancer patient receiving immune treatment.
4. Model creation and verification
4.1 Modeling
As shown in fig. 1a, based on two indicators of smoking history and pre-treatment ALC, nomogram is established to predict patient sixth week effective rate; as in fig. 1b, based on three indicators of gender, age and pre-treatment LDH, a nomogram 2 predicted progression-free probabilities for patients at 6, 12 and 18 months was established; as in fig. 1c, based on the two indices of pre-treatment LDH and dNLR, the survival probability of nomogram 3 predicted patients at months 6, 12 and 18 was established.
4.2 Model evaluation
As shown in FIG. 2a, the C index and ROC area under the curve of nomogram 1 are 0.706, 95% CI:0.601-0.796.
As shown in FIGS. 3a-C, nomogram has a C index of 0.728, 95% CI:0.653-0.803; the area under the ROC curve for predicting patient no-progression probability at month 6 is 0.782,95% CI:0.662-0.877; the area under the ROC curve for predicting patient's probability of no progress at 12 months is 0.702,95% CI:0.526-0.796; the area under the ROC curve that predicts the patient's probability of no progression at 18 months is 0.661,95% CI:0.511-0.880.
As shown in fig. 4a-C, nomogram has a C index of 0.741 95%CI:0.622-0.860; the area under the ROC curve that predicts the patient's probability of no progression at month 6 is 0.836,95% CI:0.650-0.946; area under ROC curve for predicting patient's probability of no progression at 12 months is 0.717,95% ci:0.531-0.808; the area under the ROC curve that predicts the patient's probability of no progression at 18 months is 0.691,95% CI:0.518-0.906.
In order to detect whether the predicted result of the model is consistent with the actual result, three nomogram calibration curves are respectively drawn in the group 1, as shown in fig. 5a, fig. 6a-c and fig. 7a-c, respectively, in which the application shows the fitting line of the predicted value corresponding to the actual value when the correction is not performed, and the Bias-corrected shows the fitting line after the correction Bias; ideal represents the most Ideal relationship between the predicted probability and the actual probability. The results show that the predicted results of the three models have better consistency with the actual results.
4.3 Model verification
111 Patients in group 2 were used to externally verify the efficacy of three nomogram.
In group 2, as shown in FIG. 2b, both the C index and the area under the ROC curve of nomogram 1 are 0.701, 95% CI:0.613-0.722.
As shown in FIGS. 3d-f, nomogram 2 has a C index of 0.701, 95% CI:0.638-0.764; the area under the ROC curve that predicts the patient's probability of no progression at month 6 is 0.767,95% CI:0.671-0.873; the area under the ROC curve for predicting patient's probability of no progression at 12 months is 0.680,95% CI:0.523-0.776; the area under the ROC curve that predicts the patient's probability of no progression at 18 months is 0.634,95% CI:0.506-0.856.
As shown in FIGS. 4d-f, nomogram has a C index of 0.709, 95% CI:0.612-0.806; the area under the ROC curve that predicts the patient's probability of no progression at month 6 is 0.818,95% CI:0.719-0.941; the area under the ROC curve that predicts the patient's probability of no progression at 12 months is 0.700,95% CI:0.571-0.841; the area under the ROC curve that predicts the patient's probability of no progression at 18 months is 0.667,95% CI:0.512-0.836.
Table 3 comparison of Performance of nomogram A in group 1 and group 2
Group of | AUC(95%CI) |
Group 1 | 0.706(0.601-0.796) |
Group 2 | 0.701.613-0.722) |
Table 4 comparison of potency of nomogram in groups 1 and 2
Table 5 comparison of Performance of nomogram in group 1 and group 2
In order to detect whether the predicted result of the model is consistent with the actual result, three nomogram calibration curves are respectively drawn in the group 2, as shown in fig. 5b, 6d-f and 7d-f, respectively, in which the application shows the fitting line of the predicted value corresponding to the actual value when the correction is not performed, and the Bias-corrected shows the fitting line after the correction Bias; ideal represents the most Ideal relationship between the predicted probability and the actual probability. The results show that the predicted results of the three models have better consistency with the actual results.
Web page version calculator: https:// summerxia. Shinyapps. Io/jameszhang/As shown in figure 8, a simple and convenient web page calculator for calculating curative effect and prognosis probability is manufactured based on three nomogram calculation formulas, and corresponding probability values can be automatically output after the numerical values of variables are input. Can help clinicians individually evaluate the probability of a particular therapeutic effect and prognosis before a non-small cell lung cancer patient receives immunotherapy.
Conclusion(s)
The prediction system for the curative effect and prognosis of the non-small cell lung cancer patient to receive the immunotherapy has good stability and efficiency, can be used for predicting the curative effect and prognosis of the non-small cell lung cancer patient to receive the immunotherapy very simply, conveniently and effectively, and has good application prospect.
It should be apparent that, in light of the foregoing, various modifications, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims. The foregoing is a further detailed description of the invention with reference to the following detailed description. It should not be understood that the scope of the above subject matter of the present invention is limited to the above examples only. All techniques implemented based on the above description of the invention are within the scope of the invention.
Claims (3)
1. A non-small cell lung cancer patient curative effect and prognosis prediction system mainly comprises a curative effect prediction model, a progression-free survival prediction model and a total survival prediction model, wherein each model is divided into an input module, a calculation module and an output module,
(1) The input module of the curative effect prediction model is used for transmitting patient information to the calculation module, including smoking history and absolute lymphocyte count before treatment;
wherein absolute lymphocyte count is in units of 10 9/L;
The corresponding nomogram 1 is built in the computing module, and the specific steps are as follows:
The probability value y1= (-1.93 e-07X 1 3+6.5238e-05×X12 + 0.000387789X 1+ 0.052971747) ×100) valid for the sixth week after patient treatment;
X1= 38.93455X smoking history + 33.333333333X absolute lymphocyte count-6.666666667;
if the smoking history of the patient is "yes", the "smoking history" in the formula is taken as 1; otherwise, 0 is taken out,
The output module is a web page version calculator, and the value of the input variable in the web page can calculate and output a corresponding probability value Y1;
(2) The input module of the progression free survival prediction model is used for transmitting patient information to the calculation module, including age, gender and lactate dehydrogenase;
wherein, the lactate dehydrogenase is in U/L;
The corresponding nomogram 2 is built in the computing module, and the specific steps are as follows:
The probability value of no progress at 6 months after patient treatment y2= (1.37 e-06×x2 3-0.00023844×X22 -0.000129557 ×x2+ 0.898134033) ×100%;
The probability value of no progress at 12 months after patient treatment y2= (2.502 e-06×x2 3-0.000318492×X22 -0.001023031 ×x2+ 0.824736532) ×100%;
The probability value of no progress at 18 months after patient treatment y2= (3.379 e-06×x2 3-0.000339952×X22 -0.003471356 ×x+ 0.76484454) ×100%;
x2= 35.11728 ×gender+ 23.83088 ×age+ 0.076923077 ×lactate dehydrogenase;
if the sex of the patient is "female", the "sex" in the formula takes 1; otherwise, taking 0;
if the patient's age is > 65 years, then "age" in formula takes 1; otherwise, 0 is taken out,
The output module is a web page version calculator, and the value of the input variable in the web page can calculate and output a corresponding probability value Y2;
(3) The input module of the total lifetime prediction model is used for transmitting patient information to the calculation module, including lactate dehydrogenase and pre-treatment derived neutrophil lymph ratio;
Wherein lactate dehydrogenase is in U/L, and derived neutrophil lymphorate = neutrophil absolute count/(leukocyte absolute count-neutrophil absolute count), absolute neutrophil count and absolute leukocyte count are in 10 9/L;
The corresponding nomogram is built in the computing module, and the computing module is specifically as follows:
probability value y3= (3.255 e-06×x 3-0.000762825×X32 +0.040954221 ×x3+ 0.259515127) ×100% for survival 6 months after patient treatment;
probability value y3= (3.255 e-06×x 3-0.000653776×X32 +0.025135017 ×x3+ 0.626258681) ×100% for survival 12 months after patient treatment;
Probability value y3= (5.944 e-06×x 3-0.000887041×X32 +0.024720858 ×x3+ 0.632409967) ×100% for survival 18 months after patient treatment;
x3= 0.076923077 ×lactate dehydrogenase+ 6.631074059 ×derivatized neutrophil lymphorate-3.315537029;
The output module is a web page version calculator, and the value of the input variable in the web page can calculate and output a corresponding probability value Y3.
2. The system for predicting the efficacy and prognosis of a patient with non-small cell lung cancer according to claim 1, wherein the pathological type of non-small cell lung cancer is non-small cell lung cancer.
3. The system for predicting the therapeutic effect and prognosis of a patient with non-small cell lung cancer according to claim 1, wherein the therapeutic effect is that of an immunotherapy selected from the group consisting of nal Wu Liyou mab, palbociclizumab, terlipressin Li Shan, carrilizumab, singedi Li Shan and tirelimumab.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010808966.3A CN112116977B (en) | 2020-08-12 | 2020-08-12 | Non-small cell lung cancer patient curative effect and prognosis prediction system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010808966.3A CN112116977B (en) | 2020-08-12 | 2020-08-12 | Non-small cell lung cancer patient curative effect and prognosis prediction system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112116977A CN112116977A (en) | 2020-12-22 |
CN112116977B true CN112116977B (en) | 2024-05-10 |
Family
ID=73804075
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010808966.3A Active CN112116977B (en) | 2020-08-12 | 2020-08-12 | Non-small cell lung cancer patient curative effect and prognosis prediction system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112116977B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112687394A (en) * | 2021-01-05 | 2021-04-20 | 四川大学华西医院 | Prognostic prediction model of metastatic castration resistant prostate cancer patient in abiraterone treatment and establishment method and application thereof |
CN115294129B (en) * | 2022-10-08 | 2023-02-07 | 北京肿瘤医院(北京大学肿瘤医院) | Tumor immunotherapy prognosis evaluation method and device, electronic device and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2516795A1 (en) * | 2003-02-27 | 2004-09-10 | Immunivest Corporation | Circulating tumor cells (ctc's): early assessment of time to progression,_survival and response to therapy in metastatic cancer patients |
CN109859801A (en) * | 2019-02-14 | 2019-06-07 | 辽宁省肿瘤医院 | A kind of model and method for building up containing seven genes as biomarker prediction lung squamous cancer prognosis |
WO2020081956A1 (en) * | 2018-10-18 | 2020-04-23 | Medimmune, Llc | Methods for determining treatment for cancer patients |
-
2020
- 2020-08-12 CN CN202010808966.3A patent/CN112116977B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2516795A1 (en) * | 2003-02-27 | 2004-09-10 | Immunivest Corporation | Circulating tumor cells (ctc's): early assessment of time to progression,_survival and response to therapy in metastatic cancer patients |
WO2020081956A1 (en) * | 2018-10-18 | 2020-04-23 | Medimmune, Llc | Methods for determining treatment for cancer patients |
CN109859801A (en) * | 2019-02-14 | 2019-06-07 | 辽宁省肿瘤医院 | A kind of model and method for building up containing seven genes as biomarker prediction lung squamous cancer prognosis |
Non-Patent Citations (4)
Title |
---|
LIPI评分与晚期胃癌患者免疫检查点抑制剂治疗疗效及预后的关系;侯柏村;刘婷婷;李涛;胡毅;;解放军医学院学报;20200527(第05期);全文 * |
中性-淋巴比和预后营养指数与非小细胞肺癌患者预后的相关性研究;高惜惜;尤青海;孙耕耘;;中华肺部疾病杂志(电子版);20160420(第02期);全文 * |
中性粒细胞淋巴细胞比值与小细胞肺癌预后关系的分析;王洪玲;李琳;王键玮;郭霞;韩晓庆;喻昌利;;河北医科大学学报;20180415(第04期);全文 * |
头颈部弥漫大B细胞淋巴瘤患者临床特征及预后模型分析研究;张艳;唐勇;姚一芸;邹丽芳;窦红菊;朱琦;;中国癌症杂志;20200630(第06期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112116977A (en) | 2020-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ward et al. | Estimating the total incidence of global childhood cancer: a simulation-based analysis | |
Hinks et al. | Innate and adaptive T cells in asthmatic patients: relationship to severity and disease mechanisms | |
CN112116977B (en) | Non-small cell lung cancer patient curative effect and prognosis prediction system | |
Diamond et al. | Dynamics of minimal residual disease in patients with multiple myeloma on continuous lenalidomide maintenance: a single-arm, single-centre, phase 2 trial | |
Leisenring et al. | An acute graft-versus-host disease activity index to predict survival after hematopoietic cell transplantation with myeloablative conditioning regimens | |
Alenzi et al. | The association of hyperglycemia and diabetes mellitus and the risk of chemotherapy-induced neutropenia among cancer patients: A systematic review with meta-analysis | |
CN108034708B (en) | System for determining individual effectiveness of tripterygium glycosides tablet in treating rheumatoid arthritis through expression quantity of multiple mRNA | |
CN112542247B (en) | Method and system for predicting complete remission probability of pathology after breast cancer neoadjuvant chemotherapy | |
CN112466464B (en) | Prognosis prediction model for primary metastatic prostate cancer patient, and establishment method and application method thereof | |
Yang et al. | Prognostic nomograms for primary high-grade glioma patients in adult: a retrospective study based on the SEER database | |
JP2023156317A (en) | cancer prognosis | |
Hui et al. | Association between health-related quality of life and progression-free survival in patients with advanced cancer: a secondary analysis of SWOG clinical trials | |
Chow et al. | Factors and trade-offs with rehabilitation effectiveness and efficiency in newly disabled older persons | |
Canavan et al. | A cohort study to determine factors associated with upstaging cutaneous squamous cell carcinoma during Mohs surgery | |
Stone et al. | The obesity paradox—what does it mean for lung cancer surgery? | |
Williams et al. | Cardiovascular outcomes of cancer patients in rural Australia | |
Karakioulaki et al. | Histopathological comparison of endobronchial biopsies from different pulmonary lobes of severe asthmatic patients | |
Jin et al. | Hodgkin lymphoma-associated hemophagocytic lymphohistiocytosis—a dangerous disease | |
Wang et al. | Clinical characteristics, treatment, and management of pembrolizumab induced hemophagocytic lymphohistiocytosis | |
Lin et al. | The predictive utility of cytokines, procalcitonin and C-reactive protein among febrile pediatric hematology and oncology patients with severe sepsis or septic shock | |
Xu et al. | Development and Validation of Nomograms for Predicting Pneumonia in Patients with COVID-19 and Lung Cancer | |
Elsayed | Outcomes After AKI: Are We Communicating Effectively?: FR-PO088 | |
İbrahim et al. | C-reactive protein Lymphocyte Ratio in the Diagnosis of Pulmonary Tuberculosis | |
Song et al. | A simple APACHE IV risk dynamic nomogram that incorporates early admitted lactate for the initial assessment of 28-day mortality in critically ill patients with acute myocardial infarction | |
Alden et al. | P33. 04 Programmed Death-Ligand 1 (PD-L1) Changes in Non-Small-Cell Lung Cancer (NSCLC): Clinical, Pathologic, and Genomic Correlates |
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 |