Jaundice risk index evaluation method and apparatus, computer device and storage medium

Abstract

Disclosed in the present application are a jaundice risk index evaluation method and apparatus, a computer device and a storage medium. The method comprises: determining a skin area to be measured; successively measuring said skin area by means of a measurement instrument, so as to obtain a plurality of successive pieces of real transcutaneous bilirubin (TcB) information of said skin area; according to the plurality of successive pieces of real transcutaneous bilirubin (TcB) information of said skin area, determining successive transcutaneous bilirubin absolute value change information TcB(t); and, on the basis of the successive transcutaneous bilirubin absolute value change information TcB(t), determining a jaundice risk index by means of a risk index prediction model. By determining the plurality of successive pieces of real transcutaneous bilirubin (TcB) information of the skin area to be measured by means of successive measurements, then determining the successive transcutaneous bilirubin absolute value change information TcB(t) on this basis, and estimating the progression of jaundice on the basis of the successive transcutaneous bilirubin absolute value change information TcB(t), the present application can measure the concentration of subcutaneous bilirubin accurately, and provides a prediction function for the progression trend of jaundice.

Description

Jaundice risk index assessment method, device, computer equipment and storage medium Technical Field

[0001] The present application relates to the technical field of jaundice detection, and in particular to a method, apparatus, computer equipment and storage medium for evaluating a jaundice risk index. Background Art

[0002] Jaundice is a sign of excessive bilirubin levels in the body. Clinically, it manifests as the sclera, mucous membranes, skin and other tissues being stained yellow. Excessive bilirubin levels are the cause of jaundice, which often occurs in newborns, which is also the group focused on in this application.

[0003] Neonatal jaundice is a yellowing of the skin or other organs caused by the accumulation of bilirubin in the body. Jaundice is very common in newborns, affecting approximately 60% of full-term infants and 80% of premature infants. It accounts for approximately 49% of neonatal hospitalizations and is one of the most common clinical problems in newborns. While vaginally delivered newborns are generally discharged around three days after birth, peak bilirubin levels in Asian newborns typically occur between five and seven days after birth. Rapidly increasing or excessively high bilirubin levels in newborns can cause brain damage and lead to serious neurological sequelae, such as intellectual disability and hearing impairment. In severe cases, it can even lead to death, placing significant strain on society and families. Therefore, timely, effective, safe, and cost-effective assessment and prediction of neonatal jaundice are crucial to prevent the complications of high bilirubin levels.

[0004] The Need and Significance of Age-Based Bilirubin Curves: The American Academy of Pediatrics (AAP) developed its first guidelines for the intervention of neonatal jaundice in 1994, which advocated using age-based bilirubin values ​​to guide clinical intervention for neonatal jaundice. However, with the advancement of clinical research and practice, this approach of using age-based bilirubin values ​​to guide treatment is no longer suitable for current diagnosis and treatment. In 2004, the AAP, based on evidence-based medicine and summarizing experience, developed new guidelines, proposing the use of age-based bilirubin curves in place of age-based bilirubin values ​​to guide clinical diagnosis and intervention. They exemplified this: a total bilirubin value of 8 mg / dL at 24.1 hours would be in the high-risk range, requiring evaluation and close follow-up; whereas a value at 47.9 hours, corresponding to the same bilirubin value, would be in the low-risk range, requiring no follow-up. Both values ​​represent daily total bilirubin values ​​on the second day of life, but require different approaches. Age-based bilirubin values ​​cannot accurately and timely guide clinical diagnosis and treatment. Domestic pediatric experts have also conducted relevant research: In 2010, Ding Guofang noted that approximately 44% of pediatricians surveyed believed that intervention based on bilirubin values ​​at birth was optimal. Bhutani et al. first developed an hourly total bilirubin percentile curve in 1999. Doctors from various regions of my country have collaborated to develop a chart for hourly bilirubin percentiles in newborns, as shown in Figure X. In 2014, the Neonatology Group of the Chinese Medical Association's Pediatrics Branch developed the "Expert Consensus on the Diagnosis and Treatment of Severe Neonatal Jaundice (2014)," which explicitly uses the hourly total bilirubin curve as a key reference for neonatal jaundice monitoring.

[0005] Although both the American Academy of Pediatrics and the Chinese Medical Association have proposed the use of hourly total bilirubin curves as an important reference for monitoring neonatal jaundice, there is a lack of effective tools to obtain accurate hourly jaundice curves. Currently, in clinical practice, a transcutaneous jaundice meter is used to measure 2-4 times daily to generate hourly total bilirubin curves. However, due to the limited number of sampling points per day, the resulting hourly bilirubin curves are extremely rough.

[0006] Existing technical solutions can be classified according to the measurement method into serum bilirubin determination (invasive) and transcutaneous bilirubin determination (non-invasive).

[0007] The invasive method involves drawing blood and testing the bilirubin content in vitro. Serum total bilirubin test: Draw arterial or venous blood, centrifuge it, and measure the supernatant using a biochemical analyzer.

[0008] The non-invasive method uses optical detection to detect bilirubin. A specific wavelength of light is injected into the skin. This wavelength of light is then absorbed by bilirubin in the human body, reducing the outflow light signal detected outside the body. The higher the bilirubin concentration, the smaller the detected signal. This allows for quantitative analysis of the bilirubin concentration in the body.

[0009] Existing technical methods are widely used in existing measurement equipment, and all of them claim to have very high measurement accuracy. However, after the applicant's measurements, it was found that the existing measurement technology has inherent deficiencies in measurement precision and accuracy. During the measurement process, it will be affected by various environmental factors (ambient temperature, equipment temperature, system preheating) and human factors (human movement, body surface temperature). However, the existing instruments and equipment themselves have not been specially optimized to address the above issues. Experienced doctors and nurses still need to use their accumulated knowledge and experience to correct the experimental results. This makes it still difficult to provide bilirubin concentration measurement services for newborns.

[0010] Moreover, skin color affects measurement accuracy. In essence, factors other than the instrument bring systematic errors to optical measurement. Instantaneous error: at the moment the sensor works, the ambient light information will be superimposed on the measured information, thus generating instantaneous error; long-term error: the human skin color itself will also absorb specific light signals, which varies with individual skin color; the skin will change with the change of a person's mental state, thereby affecting the optical properties of the skin.

[0011] Application Contents

[0012] Based on this, it is necessary to propose a jaundice risk index evaluation method, device, computer equipment and storage medium to address the above problems.

[0013] Based on this, it is necessary to propose a jaundice risk index evaluation method, device, computer equipment and storage medium to address the above problems.

[0014] A method for evaluating a jaundice risk index, comprising:

[0015] Determine the skin area to be examined;

[0016] Continuously pass the detection instrument to the skin area to be detected to obtain the real bilirubin concentration information TcB of several consecutive skin areas to be detected;

[0017] Determining continuous bilirubin absolute value change information TcB(t) based on the actual bilirubin concentration information TcB of the plurality of continuous skin areas to be detected;

[0018] The continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model.

[0019] In the above scheme, the continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model, specifically including: the first-order derivative of the continuous bilirubin absolute value change information (TcB(t) As the first jaundice risk coefficient W1, the first derivative of the real-time continuous bilirubin absolute value change information (TcB(t) As the second jaundice risk coefficient W2, the second derivative of the continuous bilirubin absolute value change information (TcB(t) As the third jaundice risk coefficient W3, the first jaundice risk coefficient W1, the second jaundice risk coefficient W2, the third jaundice risk coefficient W3 and other factors are fitted through a risk index prediction model to determine a jaundice risk index JRI.

[0020] In the above scheme, the first jaundice risk coefficient W1, the second jaundice risk coefficient W2, the third jaundice risk coefficient W3 and other factors are fitted by the risk index prediction model to determine the jaundice risk index JRI, specifically including: according to JRI=β0+β1W1+....+β p-1 +e determines the jaundice risk index JRI, where β=(β0,β1,…,β p-1 ) is the unknown parameter vector, W1,…,W p-1 are explanatory variables, namely, jaundice risk coefficients W1, W2, W3 and other influencing factors, and e is the random error.

[0021] In the above solution, the step of continuously passing the detection instrument through the skin area to be detected to obtain the true bilirubin concentration information TcB of a plurality of consecutive skin areas to be detected specifically includes:

[0022] The detection instrument is continuously used to perform preliminary measurement of subcutaneous bilirubin on the skin area to be detected to obtain a plurality of preliminary measurement results, wherein the preliminary measurement results include bilirubin concentration BCM affected by skin color information and skin color information;

[0023] Determine dynamic skin color information DSC of the skin area to be detected;

[0024] Determine static skin color information SSC of the skin area to be detected;

[0025] The bilirubin concentration BCM affected by the skin color information is corrected according to the dynamic skin color information DSC and the static skin color information SSC of the skin area to be detected to determine the true bilirubin concentration information TcB.

[0026] In the above scheme, the dynamic skin color information DSC of the skin area to be detected is determined specifically by: the white light source generated by the detection instrument generates light to illuminate the skin area to be detected, collects a wide-bandwidth optical measurement signal, and then determines the dynamic skin color information DSC of the skin area to be detected by analyzing the wide-bandwidth optical measurement signal.

[0027] In the above solution, determining the static skin color information SSC of the skin area to be detected specifically includes:

[0028] Obtaining a comparison image of the skin area to be detected and a color chart of known color;

[0029] The static skin color information SSC of the skin area to be detected is extracted from the control image through an image processing algorithm.

[0030] In the above scheme, the bilirubin concentration BCM affected by the skin color information is corrected according to the dynamic skin color information DSC and the static skin color information SSC of the skin area to be detected to determine the true bilirubin concentration information TcB, specifically including: according to the formula Determine the true bilirubin concentration information TcB; where the function F(SSC,DSC) is used to calculate the difference or ratio between the two color temperature information DSC and SSC; V(T,H) is the relationship between the light signal intensity and the ambient temperature T and ambient humidity H; a, b, c, d, and e are coefficients.

[0031] A device for evaluating a jaundice risk index, comprising: a unit for determining an area to be measured, a measuring unit, and a unit for determining a risk index;

[0032] The to-be-detected area determination unit is configured to determine the skin area to be detected;

[0033] The measuring unit is configured to obtain the true bilirubin concentration information TcB of a plurality of consecutive skin areas to be detected by the detection instrument; and is further configured to determine the continuous bilirubin absolute value change information TcB(t) based on the true bilirubin concentration information TcB of the plurality of consecutive skin areas to be detected;

[0034] The risk index determination unit is used to determine the jaundice risk index through a risk index prediction model based on the continuous bilirubin absolute value change information TcB(t).

[0035] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0036] Determine the skin area to be examined;

[0037] Continuously pass the detection instrument to the skin area to be detected to obtain the real bilirubin concentration information TcB of several consecutive skin areas to be detected;

[0038] Determining continuous bilirubin absolute value change information TcB(t) based on the actual bilirubin concentration information TcB of the plurality of continuous skin areas to be detected;

[0039] The continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model.

[0040] A computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0041] Determine the skin area to be examined;

[0042] Continuously pass the detection instrument to the skin area to be detected to obtain the real bilirubin concentration information TcB of several consecutive skin areas to be detected;

[0043] Determining continuous bilirubin absolute value change information TcB(t) based on the actual bilirubin concentration information TcB of the plurality of continuous skin areas to be detected;

[0044] The continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model.

[0045] Implementing the embodiments of this application will have the following beneficial effects:

[0046] The present application determines the actual bilirubin concentration information TcB of several consecutive skin areas to be tested through continuous detection, and then determines the continuous bilirubin absolute value change information TcB(t) based on it. The continuous bilirubin absolute value change information TcB(t) is used to predict the development of jaundice. It can accurately measure the concentration of subcutaneous bilirubin and provide a prediction function for the development trend of jaundice. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0048] in:

[0049] FIG1 is a flow chart of a method for evaluating a jaundice risk index according to one embodiment;

[0050] FIG2 is a flow chart of step 102 in a method for evaluating a jaundice risk index according to one embodiment;

[0051] FIG3 is a schematic diagram of a colorimetric card used in a method for evaluating jaundice risk index according to one embodiment;

[0052] FIG4 is a structural block diagram of a device for evaluating jaundice risk index in one embodiment. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] As shown in FIG1 , in one embodiment, a method for evaluating a jaundice risk index is provided. The method for evaluating a jaundice risk index specifically comprises the following steps:

[0055] Step 101: Determine the skin area to be detected;

[0056] Step 102: determining continuous bilirubin absolute value change information TcB(t) based on the actual bilirubin concentration information TcB of the plurality of continuous skin areas to be detected;

[0057] Specifically, the continuous bilirubin absolute value change information TcB(t) adopts the derivative with respect to time, such as the first-order derivative, the second-order derivative, the third-order derivative, etc.

[0058] For example, the first derivative of the continuous bilirubin absolute value change information (TcB(t) The second derivative of the continuous bilirubin absolute value change information (TcB(t)

[0059] Step 103: The continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model.

[0060] Specifically, the Jaundice Risk Index (JRI) indicates the possibility that a newborn may experience high jaundice symptoms; the JRI index is a percentage ranging from 0% to 100%. The higher the value, the higher the concentration of bilirubin in the newborn's body, and the more medical intervention is needed.

[0061] The other factors include at least one of the following: ① serum bilirubin value or transcutaneous bilirubin value in the high-risk range before discharge; ② jaundice within 24 hours after birth; ③ blood type incompatibility with positive direct antiglobulin test, other hemolytic diseases (such as G-6-PD deficiency), etc.; ④ gestational age of 35 to 36 weeks; ⑤ newborns whose siblings have received phototherapy; ⑥ cephalohematoma or obvious bruising; ⑦ exclusive breastfeeding or significant weight loss; ⑧ Asian ethnicity; ⑨ serum bilirubin value or transcutaneous bilirubin value in the medium-to-high-risk range before discharge; ⑩ jaundice before discharge; Gestational age 37–38 weeks; Siblings have a history of jaundice; His mother has diabetes; Maternal age ≥25 years; boy.

[0062] The first derivative of the continuous bilirubin absolute value change information (TcB(t) As the first jaundice risk coefficient W1, the first derivative of the real-time continuous bilirubin absolute value change information (TcB(t) As the second jaundice risk coefficient W2, the second derivative of the continuous bilirubin absolute value change information (TcB(t) As the third jaundice risk coefficient W3, the first jaundice risk coefficient W1, the second jaundice risk coefficient W2, the third jaundice risk coefficient W3 and other factors are fitted through a risk index prediction model to determine a jaundice risk index JRI.

[0063] According to JRI=β0+β1W1+….+β p-1 +e determines the jaundice risk index JRI, where β=(β0,β1,…,β p-1 ) is the unknown parameter vector, W1,…,W p-1 are explanatory variables, namely, jaundice risk coefficients W1, W2, W3 and other influencing factors, and e is the random error.

[0064] Furthermore, the first jaundice risk coefficient W1: combining the prior probability and the new true bilirubin concentration information TcB, the posterior probability is calculated using the Bayesian method, and the posterior probability is expressed as the first jaundice risk coefficient W1.

[0065] Second jaundice risk coefficient W2: Combining the prior probability and the first-order derivative of the new continuous bilirubin absolute value change information (TcB(t), the posterior probability is calculated using the Bayesian method, and the posterior probability is expressed as the second jaundice risk coefficient W2.

[0066] The third jaundice risk coefficient W3: The posterior probability is calculated by combining the prior probability and the second-order derivative of the new continuous bilirubin absolute value change information (Tc(t)) using the Bayesian method. The posterior probability is expressed as the third jaundice risk coefficient W3.

[0067] The Bayesian method is used to calculate the posterior probability, specifically including

[0068] A priori probability: The initial probability that a newborn has significant hyperbilirubinemia in the absence of any transcutaneous bilirubin (TcB) measurement; the prior probability can be determined based on epidemiological data, clinical experience, or literature data.

[0069] Likelihood ratio: The positive likelihood ratio (LR+) and negative likelihood ratio (LR-) of TcB were calculated. The likelihood ratio reflects the predictive performance of TcB; specifically, a positive likelihood ratio (LR+) indicates that a high TcB increases the likelihood of having significant hyperbilirubinemia, while a negative likelihood ratio (LR-) indicates that a low TcB decreases the likelihood of having significant hyperbilirubinemia.

[0070] Application of Bayes' theorem: Once the prior probability (usually based on the basic incidence of the disease) and the likelihood ratio (the predictive performance of TcB) are obtained, Bayes' theorem can be used to calculate the new posterior probability, that is, the probability that the newborn has significant hyperbilirubinemia taking into account TcB, which can be expressed as a risk coefficient for jaundice.

[0071] The calculation formula is as follows:

[0072] Posterior probability = prior probability * positive likelihood ratio / (prior probability * positive likelihood ratio + (1-prior probability) * negative likelihood ratio).

[0073] The present application determines the actual bilirubin concentration information TcB of several consecutive skin areas to be tested through continuous detection, and then determines the continuous bilirubin absolute value change information TcB(t) based on it. The continuous bilirubin absolute value change information TcB(t) is used to predict the development of jaundice. It can accurately measure the concentration of subcutaneous bilirubin and provide a prediction function for the development trend of jaundice.

[0074] Since skin color has a great influence on all wearable optical detection (such as blood oximeters), jaundice detectors are no exception. Dark skin color is due to the high content of hemoglobin and melanin in the skin, especially melanin. These two substances also have strong absorption of light within the visible light range.

[0075] The jaundice detector detects the loss of light in the human body and infers the concentration of the substance to be tested. If the light absorbed by melanin and hemoglobin cannot be excluded, it will cause a large deviation in the test results, affecting the accuracy of the test results and reducing the versatility of the medical equipment.

[0076] In some embodiments, as shown in FIG2 , determining the continuous bilirubin absolute value change information TcB(t) based on the actual bilirubin concentration information TcB of the plurality of continuous skin areas to be detected is achieved by the following steps:

[0077] Step 1021: The detection instrument is continuously used to perform preliminary measurement of subcutaneous bilirubin on the skin area to be detected, and a plurality of preliminary measurement results are obtained, wherein the preliminary measurement results include bilirubin concentration BCM affected by skin color information and skin color information;

[0078] Specifically, the detection instrument generates light from a blue light source and a green light source and irradiates the skin area to be detected, collects the bilirubin absorption signal of the light, and then determines the bilirubin concentration BCM affected by skin color information by analyzing the bilirubin absorption signal of the light.

[0079] The wavelength of the blue light source is 440-480 nm and the wavelength of the green light source is 485-580 nm.

[0080] Step 1022: Determine dynamic skin color information DSC of the skin area to be detected;

[0081] Specifically, the white light source generated by the detection instrument generates light that is irradiated onto the skin area to be detected, collects a wide-bandwidth optical measurement signal, and then determines the dynamic skin color information DSC of the skin area to be detected by analyzing the wide-bandwidth optical measurement signal.

[0082] Furthermore, the detection instrument generates a broadband light source in the range of 300-1000nm to irradiate the skin area to be detected, and the continuous irradiation time is within 0-2s, and a wide-bandwidth optical measurement signal is collected. The dynamic skin color information DSC of the skin area to be detected is then determined by analyzing the wide-bandwidth optical measurement signal.

[0083] Continuous white light measurement can instantly correct skin color and eliminate the impact of changes in external ambient light on the test results.

[0084] The spectrum range of the white light source may cover the entire visible light spectrum or a portion of the visible light spectrum.

[0085] Step 1023: Determine static skin color information SSC of the skin area to be detected;

[0086] Specifically, a control image of the skin area to be detected and a colorimetric card of known color is obtained, and static skin color information SSC of the skin area to be detected is extracted from the control image using an image processing algorithm;

[0087] The static skin color information SSC of the skin area to be detected is determined by the white balance correction principle.

[0088] As shown in FIG3 , there is a circular hole in the middle of the colorimetric card, and the area of ​​the hole is equivalent to the area of ​​the skin area to be detected; in addition, the colorimetric card also includes a known color pattern.

[0089] For example, black pattern and white pattern are known standard colors, the RGB value of white pattern is (0,0,0), and the RGB value of black pattern is (255,255,255). The reference interval for skin color assessment and the correction standard for white balance are given by black pattern and white pattern to prevent the influence of changes in ambient light on color detection, so that accurate skin color information can be given.

[0090] The center of the card has a known pattern cutout, which can be a square, rectangle, circle, oval, or other known specific shapes. The cutout ensures that when the colorimetric card is placed on the skin, the tested area can be displayed in the photo along with the black and white patterns of the colorimetric card.

[0091] Because the specific pattern has a unique identification mark, it is convenient for automatic recognition and also helps to accurately locate the position of the skin.

[0092] Step 1024: Correct the bilirubin concentration BCM affected by the skin color information according to the dynamic skin color information DSC and the static skin color information SSC of the skin area to be detected, and determine the true bilirubin concentration information TcB.

[0093] Specifically, skin color significantly impacts all wearable optical detection systems (such as pulse oximeters), including jaundice detectors. Dark skin color is due to higher levels of hemoglobin and melanin in the skin. These two substances also have distinct absorption spectra within the visible light range.

[0094] Secondly, the jaundice detector detects the loss of light in the human body and infers the concentration of the substance being detected; if the absorption spectra corresponding to melanin and hemoglobin cannot be excluded, it will affect the accuracy of the test results, thereby reducing the versatility of the medical equipment.

[0095] This application systematically corrects the error caused by skin color, according to the formula Determine the true bilirubin concentration information TcB;

[0096] The function F(SSC,DSC) is used to calculate the difference or ratio between the two color temperature information, SSC and DSC; V(T,H) is the relationship between the change of light signal intensity with ambient temperature T and ambient humidity H; a, b, c, d, and e are coefficients.

[0097] This application corrects the bilirubin concentration information through the dynamic skin color information DSC and static skin color information SSC of the skin area to be detected, providing an accurate data basis for subsequent jaundice prediction.

[0098] As shown in FIG3 , in one embodiment, a device for evaluating a jaundice risk index is provided, the device comprising: a unit for determining an area to be measured, a measuring unit, and a risk index determining unit;

[0099] The to-be-detected area determination unit is configured to determine the skin area to be detected;

[0100] The measuring unit is configured to obtain the true bilirubin concentration information TcB of a plurality of consecutive skin areas to be detected by the detection instrument; and is further configured to determine the continuous bilirubin absolute value change information TcB(t) based on the true bilirubin concentration information TcB of the plurality of consecutive skin areas to be detected;

[0101] The risk index determination unit is used to determine the jaundice risk index through a risk index prediction model based on the continuous bilirubin absolute value change information TcB(t).

[0102] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0103] Step 101: Determine the skin area to be detected;

[0104] Step 102: determining continuous bilirubin absolute value change information TcB(t) based on the actual bilirubin concentration information TcB of the plurality of continuous skin areas to be detected;

[0105] Step 103: The continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model.

[0106] Furthermore, when the computer program is executed by the processor, the processor further performs the following steps:

[0107] Step 1021: The detection instrument is continuously used to perform preliminary measurement of subcutaneous bilirubin on the skin area to be detected, and a plurality of preliminary measurement results are obtained, wherein the preliminary measurement results include bilirubin concentration BCM affected by skin color information and skin color information;

[0108] Step 1022: Determine dynamic skin color information DSC of the skin area to be detected;

[0109] Step 1023: Determine static skin color information SSC of the skin area to be detected;

[0110] Step 1024: Correct the bilirubin concentration BCM affected by the skin color information according to the dynamic skin color information DSC and the static skin color information SSC of the skin area to be detected, and determine the true bilirubin concentration information TcB.

[0111] In one embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the processor performs the following steps:

[0112] Step 101: Determine the skin area to be detected;

[0113] Step 102: determining continuous bilirubin absolute value change information TcB(t) based on the actual bilirubin concentration information TcB of the plurality of continuous skin areas to be detected;

[0114] Step 103: The continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model.

[0115] Furthermore, when the computer program is executed by the processor, the processor further performs the following steps:

[0116] Step 1021: The detection instrument is continuously used to perform preliminary measurement of subcutaneous bilirubin on the skin area to be detected, and a plurality of preliminary measurement results are obtained, wherein the preliminary measurement results include bilirubin concentration BCM affected by skin color information and skin color information;

[0117] Step 1022: Determine dynamic skin color information DSC of the skin area to be detected;

[0118] Step 1023: Determine static skin color information SSC of the skin area to be detected;

[0119] Step 1024: Correct the bilirubin concentration BCM affected by the skin color information according to the dynamic skin color information DSC and the static skin color information SSC of the skin area to be detected, and determine the true bilirubin concentration information TcB.

[0120] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0121] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0122] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for evaluating jaundice risk index, characterized in that: The method comprises: Determine the skin area to be examined; Continuously pass the detection instrument to the skin area to be detected to obtain the real bilirubin concentration information TcB of several consecutive skin areas to be detected; Determine continuous bilirubin absolute value change information TcB(t) according to the actual bilirubin concentration information TcB of the plurality of continuous skin areas to be detected; The continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model.

2. The method for evaluating jaundice risk index according to claim 1, characterized in that: The continuous bilirubin absolute value change information TcB(t) is used to determine the jaundice risk index through a risk index prediction model, specifically including: the first-order derivative of the continuous bilirubin absolute value change information (TcB(t) As the first jaundice risk coefficient W1, the first-order derivative of the real-time continuous bilirubin absolute value change information (TcB(t) As the second jaundice risk coefficient W2, the second derivative of the continuous bilirubin absolute value change information (TcB(t) As the third jaundice risk coefficient W3, the first jaundice risk coefficient W1, the second jaundice risk coefficient W2, the third jaundice risk coefficient W3 and other factors are fitted through a risk index prediction model to determine a jaundice risk index JRI.

3. The method for evaluating jaundice risk index according to claim 2, characterized in that: The first jaundice risk coefficient W1, the second jaundice risk coefficient W2, the third jaundice risk coefficient W3 and other factors are fitted through the risk index prediction model to determine the jaundice risk index JRI, specifically including: according to JRI=β0+β1W1+….+β p-1 +e determines the jaundice risk index JRI, where β= (β0,β1,…,β p-1 ) is the unknown parameter vector, W1,…,W p-1 are the explanatory variables, namely, jaundice risk coefficients W1, W2, W3 and other influencing factors, and e is the random error.

4. The method for evaluating jaundice risk index according to any one of claims 1 to 3, characterized in that: The method of continuously passing the detection instrument through the skin area to be detected to obtain the real bilirubin concentration information TcB of a plurality of consecutive skin areas to be detected specifically includes: The detection instrument is continuously used to perform preliminary measurement of subcutaneous bilirubin on the skin area to be detected to obtain a number of preliminary measurement results, wherein the preliminary measurement results include bilirubin concentration BCM affected by skin color information and skin color information; Determine dynamic skin color information DSC of the skin area to be detected; Determine static skin color information SSC of the skin area to be detected; The bilirubin concentration BCM affected by the skin color information is corrected according to the dynamic skin color information DSC and the static skin color information SSC of the skin area to be detected, so as to determine the real bilirubin concentration information TcB.

5. The method for evaluating jaundice risk index according to claim 4, characterized in that: The method of determining the dynamic skin color information DSC of the skin area to be detected specifically includes: the white light source generated by the detection instrument generates light to irradiate the skin area to be detected, collects a wide-bandwidth optical measurement signal, and then determines the dynamic skin color information DSC of the skin area to be detected by analyzing the wide-bandwidth optical measurement signal.

6. The method for evaluating jaundice risk index according to claim 5, characterized in that: The step of determining the static skin color information SSC of the skin area to be detected specifically includes: Obtaining a comparison image of a skin area to be detected and a colorimetric card of known color; The static image of the skin area to be detected is obtained by extracting it from the control image through an image processing algorithm. Skin color information SSC.

7. The method for evaluating jaundice risk index according to claim 6, characterized in that: The method of correcting the bilirubin concentration BCM affected by the skin color information according to the dynamic skin color information DSC and the static skin color information SSC of the skin area to be detected to determine the true bilirubin concentration information TcB specifically includes: according to the formula Determine the true bilirubin concentration information TcB; wherein, the function F(SSC,DSC) is used to calculate the difference or ratio between the two color temperature information of DSC and SSC; V(T,H) is the relationship between the intensity of the light signal and the ambient temperature T and the ambient humidity H; a, b, c, d, e are coefficients.

8. A device for evaluating jaundice risk index, characterized in that: The device comprises: a unit for determining an area to be measured, a measuring unit, and a unit for determining a risk index; The to-be-detected area determination unit is used to determine the skin area to be detected; The measuring unit is used to continuously obtain the real bilirubin concentration information TcB of a plurality of continuous skin areas to be detected through the detection instrument; and is also used to determine the continuous bilirubin absolute value change information TcB(t) according to the real bilirubin concentration information TcB of the plurality of continuous skin areas to be detected; The risk index determination unit is used to determine the jaundice risk index through the risk index prediction model based on the continuous bilirubin absolute value change information TcB(t).

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 7.

Images