CN114216851A - Acute pancreatitis assessment device based on surface enhanced Raman spectroscopy - Google Patents
Acute pancreatitis assessment device based on surface enhanced Raman spectroscopy Download PDFInfo
- Publication number
- CN114216851A CN114216851A CN202111430100.4A CN202111430100A CN114216851A CN 114216851 A CN114216851 A CN 114216851A CN 202111430100 A CN202111430100 A CN 202111430100A CN 114216851 A CN114216851 A CN 114216851A
- Authority
- CN
- China
- Prior art keywords
- acute pancreatitis
- sample
- machine learning
- learning model
- module
- 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.)
- Pending
Links
- 206010033645 Pancreatitis Diseases 0.000 title claims abstract description 76
- 206010033647 Pancreatitis acute Diseases 0.000 title claims abstract description 75
- 201000003229 acute pancreatitis Diseases 0.000 title claims abstract description 75
- 238000004416 surface enhanced Raman spectroscopy Methods 0.000 title claims abstract description 14
- 238000001514 detection method Methods 0.000 claims abstract description 40
- 238000010801 machine learning Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000001237 Raman spectrum Methods 0.000 claims abstract description 15
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 238000000479 surface-enhanced Raman spectrum Methods 0.000 claims abstract description 7
- 238000010790 dilution Methods 0.000 claims abstract description 4
- 239000012895 dilution Substances 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 15
- 210000002966 serum Anatomy 0.000 claims description 14
- 238000001228 spectrum Methods 0.000 claims description 14
- 210000004369 blood Anatomy 0.000 claims description 12
- 239000008280 blood Substances 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 10
- 239000000758 substrate Substances 0.000 claims description 9
- 238000012706 support-vector machine Methods 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 8
- 238000007865 diluting Methods 0.000 claims description 6
- 238000001035 drying Methods 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 6
- 239000003146 anticoagulant agent Substances 0.000 claims description 4
- 229940127219 anticoagulant drug Drugs 0.000 claims description 4
- 210000002381 plasma Anatomy 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 14
- 238000003745 diagnosis Methods 0.000 abstract description 8
- 230000034994 death Effects 0.000 abstract description 4
- 208000028399 Critical Illness Diseases 0.000 abstract description 3
- 208000016222 Pancreatic disease Diseases 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 29
- 238000004611 spectroscopical analysis Methods 0.000 description 18
- 238000001069 Raman spectroscopy Methods 0.000 description 12
- 208000024891 symptom Diseases 0.000 description 10
- 238000012549 training Methods 0.000 description 9
- 201000010099 disease Diseases 0.000 description 8
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 8
- 230000035945 sensitivity Effects 0.000 description 8
- 206010030113 Oedema Diseases 0.000 description 3
- 206010053159 Organ failure Diseases 0.000 description 3
- 230000001154 acute effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 239000002082 metal nanoparticle Substances 0.000 description 3
- 210000000496 pancreas Anatomy 0.000 description 3
- 230000002085 persistent effect Effects 0.000 description 3
- 238000004393 prognosis Methods 0.000 description 3
- 206010061218 Inflammation Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001684 chronic effect Effects 0.000 description 2
- 239000002131 composite material Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003574 free electron Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000004054 inflammatory process Effects 0.000 description 2
- 230000017074 necrotic cell death Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 210000005259 peripheral blood Anatomy 0.000 description 2
- 239000011886 peripheral blood Substances 0.000 description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 208000004998 Abdominal Pain Diseases 0.000 description 1
- 206010000097 Abdominal tenderness Diseases 0.000 description 1
- 239000004382 Amylase Substances 0.000 description 1
- 102000013142 Amylases Human genes 0.000 description 1
- 108010065511 Amylases Proteins 0.000 description 1
- 206010003445 Ascites Diseases 0.000 description 1
- 102000004625 Aspartate Aminotransferases Human genes 0.000 description 1
- 108010003415 Aspartate Aminotransferases Proteins 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 208000005443 Circulating Neoplastic Cells Diseases 0.000 description 1
- 208000003322 Coinfection Diseases 0.000 description 1
- 206010061818 Disease progression Diseases 0.000 description 1
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 102000003855 L-lactate dehydrogenase Human genes 0.000 description 1
- 108700023483 L-lactate dehydrogenases Proteins 0.000 description 1
- 102000004882 Lipase Human genes 0.000 description 1
- 108090001060 Lipase Proteins 0.000 description 1
- 239000004367 Lipase Substances 0.000 description 1
- 108700011259 MicroRNAs Proteins 0.000 description 1
- 208000034486 Multi-organ failure Diseases 0.000 description 1
- 208000010718 Multiple Organ Failure Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 206010051379 Systemic Inflammatory Response Syndrome Diseases 0.000 description 1
- PNNCWTXUWKENPE-UHFFFAOYSA-N [N].NC(N)=O Chemical compound [N].NC(N)=O PNNCWTXUWKENPE-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 208000038016 acute inflammation Diseases 0.000 description 1
- 230000006022 acute inflammation Effects 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 235000019418 amylase Nutrition 0.000 description 1
- 239000012491 analyte Substances 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- WQZGKKKJIJFFOK-VFUOTHLCSA-N beta-D-glucose Chemical compound OC[C@H]1O[C@@H](O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-VFUOTHLCSA-N 0.000 description 1
- 238000010876 biochemical test Methods 0.000 description 1
- 239000012472 biological sample Substances 0.000 description 1
- 238000004820 blood count Methods 0.000 description 1
- 210000001124 body fluid Anatomy 0.000 description 1
- 239000010839 body fluid Substances 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 239000011575 calcium Substances 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 231100001021 decreased hematocrit Toxicity 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 230000005750 disease progression Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 210000001808 exosome Anatomy 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 230000002008 hemorrhagic effect Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 210000000265 leukocyte Anatomy 0.000 description 1
- 235000019421 lipase Nutrition 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000002679 microRNA Substances 0.000 description 1
- 244000000010 microbial pathogen Species 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008383 multiple organ dysfunction Effects 0.000 description 1
- 208000029744 multiple organ dysfunction syndrome Diseases 0.000 description 1
- 239000002086 nanomaterial Substances 0.000 description 1
- 239000002105 nanoparticle Substances 0.000 description 1
- 230000001338 necrotic effect Effects 0.000 description 1
- 229910000510 noble metal Inorganic materials 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 210000004923 pancreatic tissue Anatomy 0.000 description 1
- 206010034674 peritonitis Diseases 0.000 description 1
- 230000002250 progressing effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000005204 segregation Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000002198 surface plasmon resonance spectroscopy Methods 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
- G01N21/658—Raman scattering enhancement Raman, e.g. surface plasmons
Landscapes
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The invention belongs to the field of pancreatic disease diagnosis and Raman spectrum detection, and particularly relates to an acute pancreatitis assessment device based on a surface-enhanced Raman spectrum technology. Acute pancreatitis evaluation device passes through pretreatment module to carry out preliminary treatment such as dilution to the sample, obtains the fingerprint atlas through SERS detection module to realize making an uproar, discernment and machine learning fall in data processing module, in time export the result through output module. The device can realize the rapid identification/evaluation of AP patients and the severity thereof within minutes. The AP advances rapidly, and the death rate of critically ill patients is high, so that the device can effectively solve the problems of complex operation, long time consumption and the like existing in the current AP diagnosis and critical degree assessment, has high accuracy, can help clinicians to quickly judge the conditions of patients, adopts targeted treatment measures, and has important clinical application value for reducing the AP severity and the death rate.
Description
Technical Field
The invention belongs to the field of pancreatic disease diagnosis and Raman spectrum detection, and particularly relates to an acute pancreatitis assessment device based on a surface-enhanced Raman spectrum technology.
Background
Acute Pancreatitis (AP) is an inflammatory reaction that causes pancreatic enzymes to be activated in pancreas and then causes self-digestion, edema, hemorrhage and even necrosis of pancreatic tissues, is characterized by rapid disease progression and high mortality of severe patients, and is a difficult problem to be solved urgently in the field of digestion and severe cases. Acute pancreatitis has large prognosis difference due to different critical degrees. In Mild patients, pancreatic edema is the main factor, the disease condition is self-limiting, the prognosis is good, and Mild Acute Pancreatitis (MAP); severe cases are marked by hemorrhagic and necrotic pancreas with multiple organ dysfunction, frequent secondary infection and high mortality, and Severe Acute Pancreatitis (SAP). SAP is typically acute, extremely aggressive, and rapidly progressive, with patients often progressing from relatively mild symptoms to systemic inflammatory response syndrome and multiple organ failure within a few days. Statistical data show that the death risk of SAP patients with persistent organ failure within 1-2 weeks of morbidity can reach 42% -46%. Therefore, timely judgment of the Acute Pancreatitis (AP) condition and severity, especially early identification of critically ill patients and the adoption of targeted therapeutic measures, is an important link for reducing the mortality of critically ill patients.
Currently, in AP diagnosis and treatment, clinicians diagnose AP and evaluate severity according to clinical manifestations of patients and combining laboratory and image examination results. The diagnosis of AP mainly includes: patient typical symptoms and physical manifestations (severe and persistent abdominal pain, abdominal tenderness, and signs of peritonitis), laboratory biochemical tests (elevated lipase, amylase), imaging characterization (pancreatic edema/necrosis, or effusion around the pancreas); and the evaluation of the criticality mainly depends on the traditional scoring system. However, the convenience and timeliness of these scoring systems are not ideal at present, and their application in clinical diagnosis and treatment fails to obtain satisfactory results, mainly because: (1) most scoring systems have more evaluation indexes and are complex to operate: for example, the common Ranson scoring system consists of 11 clinical and biochemical indices, including 2 clinical indices (age and fluid loss or segregation) and 9 laboratory indices (white blood cell count, blood glucose, lactate dehydrogenase, aspartate aminotransferase, serum calcium, decreased hematocrit, increased urea nitrogen, arterial oxygen partial pressure, alkali loss). The acute physiology and chronic health score (APACHE score) system consists of three parts, an age, an acute physiology score and a chronic health score. Although APACHE II is simplified on the basis of the original APACHE system, the APACHE II still comprises 12 evaluation indexes, and has the disadvantages of complex process and inconvenient use. (2) The timeliness is poor: the acquisition of laboratory test indexes and imaging results usually takes 1-2 days. However, since the evaluation indexes of the common criticality scoring system are more, it is difficult to collect a large number of laboratory indexes brought into the complete scoring system in a limited time in the early stage of clinical work. For example, 6 indexes in the Ranson system need to be treated for 48 hours before the evaluation can be completed. The state of illness and the severity of SAP can change rapidly in a short time, so that a clinician can look ahead to the trend of the state of illness, grasp the treatment opportunity in time and intervene accurately, and the method is very important for effective treatment of SAP. Therefore, the current evaluation system is difficult to meet the clinical requirements of SAP, and clinicians need to evaluate the severity of AP in time, make correct clinical decisions and treatment schemes, and save the lives of patients.
Aiming at the defects of the conventional clinical common evaluation system and detection mode in the aspects of convenience and timeliness, a detection means which is simpler and quicker to operate is urgently required to be found to evaluate the severity of AP in time so as to guide the clinical adoption of more effective treatment measures, improve the prognosis of SAP and reduce the death rate.
Raman Spectroscopy (Raman Spectroscopy) is a scattering spectrum that can be used to rapidly qualitatively and quantitatively analyze an analyte by generating a fingerprint spectrum by causing molecular bond vibrations through laser irradiation (fig. 1). The Raman fingerprint spectrum can be obtained within several seconds, and can detect substances by identifying fingerprint peaks of sample molecules. The scattering signal of ordinary raman is weak, and when some trace molecules are detected, the raman signal needs to be enhanced by using a surface enhanced raman scattering technology. Surface-enhanced Raman Spectroscopy (SERS) is based on a common Raman spectrum, and a noble metal (usually gold or silver) micro-nano structure or particle with a rough Surface is added, so that in an excitation region, the enhancement of an electromagnetic field on the Surface or near the Surface of a sample can enhance a Raman scattering signal of a sample molecule by millions of times compared with a common Raman scattering signal (fig. 2). Based on the advantages of high efficiency, simplicity, high precision and strong stability of the SERS detection technology, the application of the SERS detection technology in the field of biomedical detection has attracted wide attention of clinical medical staff and researchers in recent years, such as identification of circulating tumor cells, microRNA, exosomes, pathogenic microorganisms and the like by detecting body fluids of urine, blood or ascites and the like of patients. However, the technical details of SERS applied in different diseases vary greatly, and for example, different SERS detection methods and substrate materials are suitable for blood samples with different diseases, and different methods for early sample processing and subsequent data analysis of blood samples with different diseases are different.
As acute inflammation, AP is different from chronic diseases such as tumor, the inflammatory reaction of the organism is severe in the disease process, the disease progresses rapidly, and the organism and blood samples have certain particularity. At present, the SERS technology is not reported to be applied to acute pancreatitis diagnosis or critical severity assessment, and relevant technical details are not published.
Disclosure of Invention
The invention aims to solve the problems that: providing an acute pancreatitis assessment device based on a surface enhanced Raman spectroscopy technology; the assessment includes not only the identification of acute pancreatitis, but more importantly, the identification of severe acute pancreatitis.
The technical scheme of the invention is as follows:
an acute pancreatitis assessment device based on a surface enhanced Raman spectroscopy technology comprises a sample pretreatment module, an SERS detection module, a data processing module and a result output module;
the sample is any one of whole blood, blood plasma and blood serum added with anticoagulant;
the sample pretreatment module is used for diluting and drying a sample, so that the sample is easier to combine with a substrate, and the result is more stable;
the SERS detection module is used for detecting the surface enhanced Raman spectrum of the sample to obtain Raman spectrum fingerprint data;
the data processing module is internally provided with a data input port, a map preprocessing algorithm and a machine learning model;
the data input port is used for receiving data collected by the SERS detection module;
the spectrum preprocessing algorithm is a method for performing noise reduction processing on Raman spectrum fingerprint data;
the result output module outputs a data processing result in a mode of characters, images and/or sound.
Further, the machine learning model comprises a machine learning model for classifying the existence or nonexistence of acute pancreatitis and/or a machine learning model for classifying the mild acute pancreatitis and the severe acute pancreatitis.
Further, the sample pre-processing module dilutes the sample by a factor of 2-5; preferably, the sample is diluted by a factor of 2.
There are many ways for SERS to detect biological samples, some are to drip the sample on the surface of a substrate detection sheet for spectral detection, and some are to mix the sample with metal nanoparticles for spectral detection. The two methods have the advantages and the disadvantages, the detection effect is better by adopting the metal nano substrate sheet for the SERS detection of the AP blood sample, and the method for mixing the metal nano particles is easy to generate more miscellaneous peaks and is not beneficial to subsequent analysis.
Further, the denoising processing is to perform denoising processing on the data of the raman spectrum fingerprint by using a PCA and/or LDA multivariate statistical discriminant algorithm to obtain characteristic peak data.
Further, the machine learning model is a support vector machine model.
The blood serum without treatment is directly used as a sample for detection, the obtained fingerprint has poor effect, even the effective fingerprint can not be read, and severe symptoms and mild symptoms can not be effectively distinguished. The inventor finds that serum can be tightly combined with a substrate by diluting the serum by 2-5 times, and the detection result is more stable and effective.
The invention also provides the application of the surface-enhanced Raman spectrum detection device in manufacturing the acute pancreatitis assessment device, wherein the acute pancreatitis assessment is to assess whether the detected object has acute pancreatitis or not and/or distinguish light acute pancreatitis from severe acute pancreatitis.
Further, the device takes any one of whole blood, plasma or serum added with anticoagulant as a detection sample.
Preferably, the apparatus comprises a sample pre-treatment module for diluting and drying a sample;
preferably, a sample needs to be diluted, and the dilution multiple of the sample is 2-5 times; further preferably, the dilution factor is 2-fold.
Further, the surface-enhanced raman spectroscopy detection apparatus is set with the following parameters when in operation:
excitation light wavelength of 532nm, 633nm or 785nm, wavelength scanning range of 400-1800cm-1；
Preferably, the excitation light wavelength is 785 nm.
Further, an atlas preprocessing algorithm is built in the acute pancreatitis assessment device;
the spectrum preprocessing algorithm is a method for performing noise reduction processing on Raman spectrum fingerprint data;
preferably, the denoising processing is to perform denoising processing on the data of the raman spectrum fingerprint by using a PCA and/or LDA multivariate statistical discriminant algorithm to obtain characteristic peak data.
Further, the acute pancreatitis assessment device is internally provided with a machine learning model;
the machine learning model comprises a machine learning model for carrying out secondary classification on the existence of acute pancreatitis and/or the absence of acute pancreatitis and/or a machine learning model for carrying out secondary classification on the mild acute pancreatitis and the severe acute pancreatitis; preferably, the machine learning model is a support vector machine model.
The invention has the beneficial effects that:
1) the result can be rapidly obtained and the instant detection can be realized.
The invention can complete detection within several minutes to obtain the diagnosis of acute pancreatitis and the preliminary evaluation result of critical degree, and can realize instant detection; the current common method relates to a plurality of detection indexes, and some indexes need to wait for a long time to obtain a result. SAP is a typical emergency, the course and severity of the disease can change rapidly in a short time, and when the evaluation results of the conventional methods such as Ranson and APACHE II are waited, the problems of aggravation of the disease and untimely intervention of the patient can be caused.
The specific alignment is as follows:
TABLE 1 comparison of complexity and time consumption of detection methods
2) The operation is convenient.
The invention only needs to take blood and detect a single item, and non-professionals can master the blood through simple training; the existing method needs to detect a plurality of items (for example, Ranson and APACHE II scores relate to more than ten physiological, biochemical and health condition evaluation indexes), the detection workload is heavy and complex, and the requirement on the professional performance of personnel and equipment is high. The information and detection indexes required to be acquired by Ranson and APACHE II are as follows:
TABLE 2RANSON scoring table
TABLE 3 evaluation chart of APACHE II for critical patients
3) The accuracy is high.
In the area of patients with light and severe AP, the total sensitivity and specificity of the currently commonly used Ranson scoring system are 57% -85% and 68% -85% respectively, the sensitivity of APACHE II is 81%, and the specificity is 65.7%; the sensitivity of the invention is about 84.6%, the specificity is about 75.0%, and the sensitivity is higher than APACHE II and is equivalent to RNASON. As the sample size of machine learning increases, the sensitivity and specificity of the acute pancreatitis evaluation device of the present invention further improve.
Obviously, many modifications, substitutions, and variations are possible in light of the above teachings of the invention, without departing from the basic technical spirit of the invention, as defined by the following claims.
The present invention will be described in further detail with reference to the following examples. This should not be understood as limiting the scope of the above-described subject matter of the present invention to the following examples. All the technologies realized based on the above contents of the present invention belong to the scope of the present invention.
Drawings
FIG. 1: raman scattered light rationale. When laser light is irradiated onto a sample, incident light is scattered by the sample, and most of the scattered light has a component (rayleigh scattering) with the same frequency (wavelength) as the wavelength of the incident light, but a small amount of the scattered light changes the wavelength, which is raman scattering.
FIG. 2: the electromagnetic enhancement principle of SERS. When incident light acts on the metal nanoparticles, the photoelectric field induces free electrons in the particles to periodically oscillate under the action of electric power, and when the frequency of the incident light is the same as the oscillation frequency of the inherent free electrons in the particles, surface plasmon resonance occurs, so that the incident light field is enhanced.
FIG. 3: this device detects the SERS fingerprint spectrum who acquires.
FIG. 4: SERS fingerprint characteristic peaks of healthy control and AP patients;
FIG. 5: a scatter plot of healthy controls versus AP patient classifications; c, healthy controls, D, AP patients; when the straight line y is 0, the patient is judged as an AP patient, and when the straight line y is 0, the patient is judged as a healthy control.
FIG. 6: ROC curve for healthy control versus AP patient classification.
FIG. 7: MAP vs SAP patient classification scatter plot.
FIG. 8: ROC curve for MAP versus SAP patient classification.
Detailed Description
Example 1 use of the device of the invention to distinguish between normal healthy controls and AP patients
1. Method of producing a composite material
Peripheral blood was collected from 25 normal healthy controls and 50 AP patients and serum was isolated and frozen at-80 ℃. After all samples are completely collected, unfreezing on ice, dripping 20 mu L of diluted 2-fold (2-5-fold) serum into a prepared Raman detection substrate sheet (the detection substrate is prepared by the same method as CN 202010613921.0), and drying in an oven for 1 hour. Detecting in a iHR550 model Raman spectrum detector to obtain an SERS fingerprint spectrum.
Related parameters of SERS spectrum detection:
excitation light: 785nm wavelength; wavelength scanning range 400-1800cm-1And the laser power is 3.5 mW. To eliminate signal differences at different locations, each sample was tested 5 times at different locations, the signal was background removed and averaged.
And (3) carrying out noise reduction treatment on the fingerprint spectrum by combining a PCA multivariate statistical discriminant algorithm (figure 3), obtaining the spectrum average value of the healthy comparison and the AP patient, screening to obtain a characteristic peak (figure 4), randomly selecting half of data to carry out machine learning (training) by an SVM (support vector machine) algorithm, and predicting the other half of data by a model obtained by training.
2. Results
As shown in fig. 5, the training results are shown in the left ellipse, the prediction results are shown in the right ellipse, the healthy prediction is shown under the red dotted line (the curve shown by y ═ 0), and the pancreatitis is predicted on-line, which shows that the AP and the control are classified very accurately.
FIG. 6 shows the results of ROC analysis of AP predictions, showing an area under the curve (AUC) of about 0.915, a sensitivity of about 88.2%, specificity and accuracy of 100%, and an accuracy of about 92.3%.
The results of this experimental example demonstrate that: after the serum diluted by 2 times is detected by SERS, the PCA multivariate statistical discrimination algorithm is used for noise reduction treatment, and then the SVM vector machine algorithm is used for training whether the patients suffer from AP or not, so that an accurate AP diagnosis model can be obtained and used for distinguishing AP patients from healthy people.
Example 2 application of the device of the invention to distinguish the criticality of an AP
1. Method of producing a composite material
Peripheral blood was collected from 25 patients with Mild AP (MAP) and 25 patients with Severe AP (SAP), and serum was isolated and frozen at-80 ℃. And after all samples are completely collected, unfreezing on ice, dripping 20 mu L of diluted 2-fold (2-5-fold) serum on a prepared Raman detection substrate sheet, and drying in an oven for 1 hour. Detecting in a iHR550 model Raman spectrum detector to obtain an SERS fingerprint spectrum.
Relevant parameters of raman spectroscopy detection:
excitation light: 785nm wavelength; wavelength scanning range 400-1800cm-1And the laser power is 3.5 mW. To eliminate signal differences at different locations, each sample was tested 5 times at different locations, the signal was background removed and averaged.
And performing noise reduction treatment on the fingerprint spectrum by combining a PCA multivariate statistical discriminant algorithm to obtain the spectrum average values of MAP and SAP, screening to obtain characteristic peaks, randomly selecting half of data to perform machine learning (training) by using an SVM vector machine algorithm, and predicting the other half of data by using a model obtained by training.
Standard for MAP: there were no local or systemic complications, no organ failure, and recovery within 1-2 weeks.
Standard of SAP: with persistent organ failure (lasting more than 48 hours), one or more organs can be affected.
2. Results
As shown in fig. 7, the left ellipse represents the training result, the right ellipse represents the prediction result, mild symptoms (MAP) are shown above the red dotted line (curve y is 0), and severe Symptoms (SAP) are shown below the line.
FIG. 8 shows the results of ROC analysis of light and severe AP, showing an area under the curve (AUC) of about 0.885, a sensitivity of about 84.6%, a specificity of about 75.0%, an accuracy of about 91.6%, and an accuracy of about 82.3%. The sample size for machine learning is low, and the sensitivity, specificity, accuracy and precision can be expected to be further improved as the sample size for machine learning increases.
The results of this experimental example demonstrate that: after the serum diluted by 2 times is detected by SERS, the PCA multivariate statistical discrimination algorithm is used for noise reduction treatment, and then the SVM vector machine algorithm is used for distinguishing and training the AP light and severe symptoms, so that an accurate AP light and severe symptom evaluation model can be obtained and used for distinguishing AP light and severe patients.
In conclusion, the acute pancreatitis assessment device based on the surface-enhanced Raman spectroscopy can quickly and accurately diagnose whether acute pancreatitis is suffered or not, can effectively distinguish and assess the critical degree (mild symptoms and severe symptoms) of patients suffering from acute pancreatitis, and has a good application prospect.
Claims (10)
1. An acute pancreatitis assessment device based on a surface-enhanced Raman spectroscopy technology is characterized in that: the device comprises a sample preprocessing module, an SERS detection module, a data processing module and a result output module;
the sample is any one of whole blood, blood plasma or blood serum added with anticoagulant;
the sample pretreatment module is used for diluting and drying a sample, so that the sample is easier to combine with a substrate, and the result is more stable;
the SERS detection module is used for detecting the surface enhanced Raman spectrum of the sample to obtain Raman spectrum fingerprint data;
the data processing module is internally provided with a data input port, a map preprocessing algorithm and a machine learning model;
the data input port is used for receiving data collected by the SERS detection module;
the spectrum preprocessing algorithm is a method for performing noise reduction processing on Raman spectrum fingerprint data;
the result output module outputs a data processing result in a mode of characters, images and/or sound.
2. The apparatus of claim 1, wherein:
the machine learning model comprises a machine learning model for carrying out two classifications on the existence and non-existence of acute pancreatitis and/or a machine learning model for carrying out two classifications on the mild acute pancreatitis and severe acute pancreatitis.
3. The apparatus of claim 1, wherein: the sample pre-treatment module is used for diluting the sample by 2-5 times.
4. The apparatus of claim 1, wherein:
and the denoising treatment is to perform denoising treatment on the data of the Raman spectrum fingerprint by using a PCA and/or LDA multivariate statistical discrimination algorithm to obtain characteristic peak data.
5. The apparatus of claim 1, wherein: the machine learning model is a support vector machine model.
6. Use of a surface-enhanced raman spectroscopy detection device for the manufacture of an acute pancreatitis assessment device of any one of claims 1-5.
7. Use according to claim 6, characterized in that: the device takes any one of whole blood, blood plasma and blood serum added with anticoagulant as a detection sample;
the apparatus includes a sample pre-processing module for diluting and drying a sample;
the dilution multiple of the sample is 2-5 times.
8. Use according to claim 6 or 7, characterized in that: the parameters set when the surface-enhanced Raman spectrum detection device works are as follows:
excitation light wavelength of 532nm, 633nm or 785nm, wavelength scanning range of 400-1800cm-1。
9. Use according to claim 6, characterized in that: the acute pancreatitis assessment device is internally provided with an atlas pretreatment algorithm;
the spectrum preprocessing algorithm is a method for performing noise reduction processing on Raman spectrum fingerprint data;
and the denoising treatment is to perform denoising treatment on the data of the Raman spectrum fingerprint by using a PCA and/or LDA multivariate statistical discrimination algorithm to obtain characteristic peak data.
10. Use according to claim 6, characterized in that:
the acute pancreatitis assessment device is internally provided with a machine learning model;
the machine learning model comprises a machine learning model for carrying out secondary classification on the existence of acute pancreatitis and/or the absence of acute pancreatitis and/or a machine learning model for carrying out secondary classification on the mild acute pancreatitis and the severe acute pancreatitis; preferably, the machine learning model is a support vector machine model.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011368187 | 2020-11-27 | ||
| CN2020113681872 | 2020-11-27 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114216851A true CN114216851A (en) | 2022-03-22 |
Family
ID=80698740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111430100.4A Pending CN114216851A (en) | 2020-11-27 | 2021-11-29 | Acute pancreatitis assessment device based on surface enhanced Raman spectroscopy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114216851A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101438168A (en) * | 2006-03-24 | 2009-05-20 | 梅坦诺米克斯有限公司 | Means and method for predicting or diagnosing diabetes |
| CN104981695A (en) * | 2012-11-15 | 2015-10-14 | 中央兰开夏大学 | Methods of diagnosing proliferative disorders |
| WO2016022604A2 (en) * | 2014-08-05 | 2016-02-11 | Becton Dickinson And Company | Methods and compositions for analyzing glucose-6-phosphate dehydrogenase activity in blood samples |
| CN105628680A (en) * | 2016-03-23 | 2016-06-01 | 中国科学院上海技术物理研究所 | Blood identification method based on infrared Raman super-continuum diffuse comprehensive spectrum |
| CN106124476A (en) * | 2016-06-21 | 2016-11-16 | 中山大学 | Based on surface enhanced raman spectroscopy and the glucose sensing approach of bi-molecular probe |
| CN106770171A (en) * | 2016-12-29 | 2017-05-31 | 中国科学院城市环境研究所 | The preparation method of Raman spectrum base and sample |
| CN107586823A (en) * | 2017-10-10 | 2018-01-16 | 徐州医科大学 | The rapid identification method of Carbapenems drug susceptibility based on Raman spectroscopy |
| CN108090779A (en) * | 2016-11-21 | 2018-05-29 | 凌今 | The information-pushing method and equipment of a kind of scientific research merchandise sales platform |
| CN108780081A (en) * | 2015-08-10 | 2018-11-09 | Essenlix公司 | Step simplification, small sample, quickly, biology/chemical analysis device for easily using and method |
| CN109187485A (en) * | 2018-09-17 | 2019-01-11 | 东北大学 | A kind of keratitis pathogenic bacteria artificial intelligence detection method based on human eye tear |
| CN110320197A (en) * | 2018-03-31 | 2019-10-11 | 重庆大学 | Microminiature Raman blood specialized analyzer based on Raman spectrum analysis |
| CN110441438A (en) * | 2019-09-09 | 2019-11-12 | 大连医科大学附属第一医院 | A kind of Acute Pancreatitis in its severe degree prediction model and its detection method based on S100 protein family |
| WO2020081204A1 (en) * | 2018-10-18 | 2020-04-23 | Oklahoma Medical Research Foundation | Biomarkers for a systemic lupus erythematosus (sle) disease activity immune index that characterizes disease activity |
| CN111812078A (en) * | 2020-08-27 | 2020-10-23 | 上海交通大学医学院附属仁济医院 | Artificial intelligence assisted early diagnosis method for prostate tumor based on surface enhanced Raman spectroscopy |
-
2021
- 2021-11-29 CN CN202111430100.4A patent/CN114216851A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101438168A (en) * | 2006-03-24 | 2009-05-20 | 梅坦诺米克斯有限公司 | Means and method for predicting or diagnosing diabetes |
| CN104981695A (en) * | 2012-11-15 | 2015-10-14 | 中央兰开夏大学 | Methods of diagnosing proliferative disorders |
| WO2016022604A2 (en) * | 2014-08-05 | 2016-02-11 | Becton Dickinson And Company | Methods and compositions for analyzing glucose-6-phosphate dehydrogenase activity in blood samples |
| CN108780081A (en) * | 2015-08-10 | 2018-11-09 | Essenlix公司 | Step simplification, small sample, quickly, biology/chemical analysis device for easily using and method |
| CN105628680A (en) * | 2016-03-23 | 2016-06-01 | 中国科学院上海技术物理研究所 | Blood identification method based on infrared Raman super-continuum diffuse comprehensive spectrum |
| CN106124476A (en) * | 2016-06-21 | 2016-11-16 | 中山大学 | Based on surface enhanced raman spectroscopy and the glucose sensing approach of bi-molecular probe |
| CN108090779A (en) * | 2016-11-21 | 2018-05-29 | 凌今 | The information-pushing method and equipment of a kind of scientific research merchandise sales platform |
| CN106770171A (en) * | 2016-12-29 | 2017-05-31 | 中国科学院城市环境研究所 | The preparation method of Raman spectrum base and sample |
| CN107586823A (en) * | 2017-10-10 | 2018-01-16 | 徐州医科大学 | The rapid identification method of Carbapenems drug susceptibility based on Raman spectroscopy |
| CN110320197A (en) * | 2018-03-31 | 2019-10-11 | 重庆大学 | Microminiature Raman blood specialized analyzer based on Raman spectrum analysis |
| CN109187485A (en) * | 2018-09-17 | 2019-01-11 | 东北大学 | A kind of keratitis pathogenic bacteria artificial intelligence detection method based on human eye tear |
| WO2020081204A1 (en) * | 2018-10-18 | 2020-04-23 | Oklahoma Medical Research Foundation | Biomarkers for a systemic lupus erythematosus (sle) disease activity immune index that characterizes disease activity |
| CN110441438A (en) * | 2019-09-09 | 2019-11-12 | 大连医科大学附属第一医院 | A kind of Acute Pancreatitis in its severe degree prediction model and its detection method based on S100 protein family |
| CN111812078A (en) * | 2020-08-27 | 2020-10-23 | 上海交通大学医学院附属仁济医院 | Artificial intelligence assisted early diagnosis method for prostate tumor based on surface enhanced Raman spectroscopy |
Non-Patent Citations (2)
| Title |
|---|
| 邵丽婷: "基于表面增强拉曼光谱和多元统计分析的肝病血清快速检测技术研究" * |
| 郑向向: "基于信号处理方法的拉曼光谱疾病诊断算法研究" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sitnikova et al. | Breast cancer detection by ATR-FTIR spectroscopy of blood serum and multivariate data-analysis | |
| KR102291105B1 (en) | Method and System of Providing Cancer Diagnosis Information Using Artificial Intelligence-Based Liquid Biopsy by Exosomes | |
| Lovergne et al. | Investigating optimum sample preparation for infrared spectroscopic serum diagnostics | |
| Shao et al. | Deep convolutional neural networks combine Raman spectral signature of serum for prostate cancer bone metastases screening | |
| Mistek et al. | Phenotype profiling for forensic purposes: Nondestructive potentially on scene attenuated total reflection Fourier transform-infrared (ATR FT-IR) spectroscopy of bloodstains | |
| US10935495B2 (en) | Detection and analysis method for urine-modified nucleoside based on surface-enhanced resonance Raman spectroscopy | |
| González-Solís et al. | Type 2 diabetes detection based on serum sample Raman spectroscopy | |
| CN111812078A (en) | Artificial intelligence assisted early diagnosis method for prostate tumor based on surface enhanced Raman spectroscopy | |
| Cui et al. | Water as a probe for serum–based diagnosis by temperature–dependent near–infrared spectroscopy | |
| Ralbovsky et al. | Vibrational spectroscopy for detection of diabetes: A review | |
| Lin et al. | Discrimination of lung tumor and boundary tissues based on laser-induced breakdown spectroscopy and machine learning | |
| Liang et al. | Filter-membrane-based ultrafiltration coupled with surface-enhanced raman spectroscopy for potential differentiation of benign and malignant thyroid tumors from blood plasma | |
| JP2013533960A (en) | Diagnosis of cancer | |
| Güleken et al. | Diagnosis of opioid use disorder with high sensitivity and specificity by advanced computational analysis of Fourier transform infrared spectroscopy | |
| Bai et al. | Label-free detection of bladder cancer and kidney cancer plasma based on SERS and multivariate statistical algorithm | |
| Lü et al. | Label-free detection of echinococcosis and liver cirrhosis based on serum Raman spectroscopy combined with multivariate analysis | |
| Liang et al. | Rapid and non-invasive discrimination of acute leukemia bone marrow supernatants by Raman spectroscopy and multivariate statistical analysis | |
| Ehsan et al. | Surface-enhanced Raman spectroscopy of centrifuged blood serum samples of diabetic type II patients by using 50KDa filter devices | |
| Zniber et al. | Analysis of urine using electronic tongue towards non-invasive cancer diagnosis | |
| CN114216851A (en) | Acute pancreatitis assessment device based on surface enhanced Raman spectroscopy | |
| Richards et al. | Vibrational spectroscopy: a valuable screening and diagnostic tool for obstetric disorders? | |
| CN109243613A (en) | A kind of high renin hypertension model and its method for building up | |
| Duckworth et al. | Improving vibrational spectroscopy prospects in frontline clinical diagnosis: Fourier transform infrared on buccal mucosa cancer | |
| Wang et al. | Preliminary study on early detection technology of lung cancer based on surface-enhanced Raman spectroscopy | |
| Ou et al. | Based on serum Raman and fluorescence spectra to diagnose liver cancer |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220322 |