Human liver physiological age prediction method based on machine learning

Abstract

According to the human body liver physiological age prediction method based on machine learning, eight blood detection indexes closely related to the liver are collected in a targeted mode, computer model modeling is conducted on male and female data according to liver health data, and a computer model for male and female human body liver physiological age prediction is constructed; the method is used for evaluating the physiological ages of the livers of individuals with different genders. According to the human body liver physiological age prediction method based on machine learning, core data only uses blood data indexes related to the human body liver for modeling, the physiological age model of the human body liver is constructed, and the physiological age of the human body liver can be evaluated in a targeted mode; moreover, according to the human liver physiological age prediction method based on machine learning, modeling is carried out on the male and the female based on the data difference of the male and the female genders, so that the prediction result is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of machine learning, and in particular, to a method for predicting the physiological age of the human liver based on machine learning with good prediction effect. Background Art

[0002] The liver is the largest visceral organ in the human body, located in the upper right abdomen. Its main functions include metabolism, detoxification, storage, and immune regulation. The liver is responsible for decomposing nutrients in food, synthesizing proteins and bile, and storing vitamins, minerals, and glycogen. It can also filter blood, remove toxins and waste from the body, and plays an important role in drug metabolism. In addition, it plays a key role in regulating blood coagulation and supporting immune defense. Although the liver has a strong regenerative ability, long-term bad living habits or viral infections may lead to liver damage, developing into hepatitis, cirrhosis, or even liver cancer. Therefore, maintaining a healthy diet, moderate exercise, and avoiding excessive alcohol intake are crucial for liver health.

[0003] Indices such as albumin, total protein, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyl transferase (GGT), direct bilirubin, total bilirubin, and alkaline phosphatase (ALP) in physical examinations are closely related to liver health. ALT and AST are sensitive indicators of liver cell damage. When liver cells are damaged, these enzymes are released into the blood, leading to an increase in their levels, indicating that there may be inflammation or damage in the liver. Total protein and albumin reflect the synthetic function of the liver. When liver function is abnormal, these indices may decrease, indicating impaired synthetic function of the liver. Bilirubin is a metabolite after the breakdown of red blood cells, and the liver is responsible for excreting it from the body. An increase in bilirubin may cause jaundice, indicating impaired ability of the liver to process bilirubin. ALP and GGT are related to biliary problems, and an increase in them may indicate biliary problems.

[0004] Calendar age is the actual age calculated based on the date of birth, used to indicate the length of an individual's existence in time, which is simple, objective, and not affected by other factors. Physiological age, on the other hand, reflects the actual health status and functional level of the body, affected by multiple factors such as genes, lifestyle, environment, and diseases. The two may not be consistent. For example, a person with a healthy lifestyle may have a physiological age younger than their calendar age; conversely, an unhealthy lifestyle may lead to an advanced physiological age. Through health management and scientific lifestyle habits, the growth of physiological age can be delayed to a certain extent, improving the quality of life and prolonging lifespan.

[0005] The physiological age of the liver is a quantitative indicator for evaluating the degree of physiological aging of the liver based on its functional status and health indicators. It reflects the actual functional age of the liver and can be used to measure the health status and aging rate of the liver. Referring to the article published in "Nature Medicine" in 2023 by Tian, Y.E, etc., the physiological age of disease patients is significantly higher than that of non-disease individuals, and bad living habits (such as smoking, drinking, staying up late, etc.) are also associated with a higher physiological age.

[0006] Most of the existing physiological age assessment schemes use all physical examination indicators to construct machine learning models, without classifying relevant indicators into corresponding organs or systems. However, different organs or systems of an individual often have different physiological age indices. A single overall model is difficult to accurately reflect the physiological ages of different organs or systems of an individual, and some indicators vary greatly between men and women. A single model is difficult to reflect the physiological ages of different organs or systems of individuals of different genders.

[0007] Therefore, it is necessary to propose an improvement to overcome the defects of the existing technology. Summary of the Invention

[0008] The purpose of the present invention is to solve the problems in the existing technology and provide a machine learning-based human liver physiological age prediction method with good prediction effect.

[0009] The technical solution of the present invention is: A method for predicting the physiological age of the human liver based on machine learning, comprising the following steps: S1. Collecting human liver physical examination data: The human liver physical examination data includes the gender of the examinee, the calendar age, and the liver blood test data; the liver blood test data includes: albumin, total protein, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyl transferase, direct bilirubin, total bilirubin, alkaline phosphatase (ALP); S2. Dividing the health examination data into a male data set and a female data set according to gender; S3. Respectively dividing the male data set and the female data set into a training set and a test set according to a ratio; S4. Normalizing the data of the training set: Normalizing the data in the training sets of the male data set and the female data set respectively; S5. Modeling and performing model training: Modeling the data in the training sets of the male data set and the female data set respectively, and performing cross-validation hyperparameter optimization in a grid search manner; S6. Performing prediction and correction of the physiological age of the human liver: Performing age correction according to the regression to the mean effect, using the calendar age as the independent variable and the original age difference as the dependent variable for linear regression; Original age difference = slope * calendar age + intercept + residual; where the residual is the age difference after correction, that is, removing the part related to the calendar age from the original age difference, and the formula is: Corrected age difference = original age difference – (slope * original age difference + intercept); where the slope and intercept are calculated, and the specific calculation method is: respectively linearly fitting the original age difference and the calendar age in the training sets of the male data set and the female data set to obtain the slope and intercept in the male data set and the female data set.

[0010] As a preferred technical solution, after step S6, the following steps are further included: S7. Calculating the aging index: The aging index calculation formula is: Aging index = corrected age difference / calendar age.

[0011] As a preferred technical solution, in step S3, the ratio of the data volume of the training set to the test set is 2:1, 3:1, 4:1 or 5:1.

[0012] As a preferred technical solution, in step S4 when normalizing the data of the training set, the normalization method can be any one of Z-score standardization, maximum-minimum normalization, median normalization, and maximum absolute value normalization.

[0013] As a further preferred technical solution, in step S4 when normalizing the data of the training set, the normalization method is Z-score standardization, and the formula is z = (x - u) / σ, where x is the original value, u is the mean of the data set, σ is the standard deviation of the data set, and z is the normalized value.

[0014] As a preferred technical solution, in step S5, the following one or more regression machine learning models are used for modeling: SVR, LightGBM, CatBoost, Ridge, RandomForest, XGBoost, Huber, Lasso, ElasticNet.

[0015] As a further preferred technical solution, in step S5, SVR modeling is used for modeling; in step S5, the data in the training sets of the male dataset and the female dataset are respectively modeled, and the hyperparameter optimization is carried out by means of grid search and cross-validation, which specifically includes the following steps: S51. Create a model; S52. Define a parameter grid: the parameter grid includes a penalty coefficient, a kernel function, a kernel function coefficient, and a slack variable; S53. Perform hyperparameter tuning; S54. Obtain the best parameters and model.

[0016] As a further preferred technical solution, after step S54, the following steps are further included: S55. Perform evaluation and verification on the training set and / or the test set.

[0017] As another further preferred technical solution, the hyperparameter tuning in step S53 is specifically to use GridSearchCV for hyperparameter tuning.

[0018] A method for predicting the physiological age of the human liver based on machine learning according to the present invention collects 8 blood test indexes closely related to the liver, namely albumin, total protein, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyl transferase, direct bilirubin, total bilirubin, and alkaline phosphatase (ALP), and respectively performs computer model modeling on the male and female data around the liver health data, constructs a computer model for predicting the physiological age of the male and female human livers, and is used to evaluate the physiological age of the human liver of individuals of different genders. A method for predicting the physiological age of the human liver based on machine learning according to the present invention, because only the blood data indexes of albumin, total protein, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyl transferase, direct bilirubin, total bilirubin, and alkaline phosphatase (ALP) related to the human liver are used as the core data for modeling, constructs a physiological age model of the human liver, and can specifically evaluate the physiological age of the human liver; moreover, a method for predicting the physiological age of the human liver based on machine learning according to the present invention performs modeling for men and women respectively based on the data differences between men and women, making the prediction results more accurate. Description of the Drawings

[0019] Figure 1 It is a flowchart of the specific implementation manner of a method for predicting the physiological age of the human liver based on machine learning according to the present invention; Figure 2Prediction results of the male liver physiological age model in the test set of a method for predicting human liver physiological age based on machine learning in this embodiment; Figure 3 Prediction results of the female liver physiological age model in the test set of a method for predicting human liver physiological age based on machine learning in this embodiment; Figure 4 Male age difference after age prediction correction through step S6 in a method for predicting human liver physiological age based on machine learning in this embodiment; Figure 5 Female age difference after age prediction correction through step S6 in a method for predicting human liver physiological age based on machine learning in this embodiment. Specific implementation manners

[0020] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "said" used in the embodiments of the present invention and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. "Plural" generally includes at least two, but does not exclude the case of including at least one.

[0022] It should be understood that the term "and / or" used herein is only an associative relationship describing associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0023] Depending on the context, the words "if", "when" as used herein may be interpreted as "when...", "when...", "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (stated condition or event)" may be interpreted as "when determined", "in response to determining", "when detecting (stated condition or event)", or "in response to detecting (stated condition or event)".

[0024] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a commodity or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or elements inherent to such a commodity or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the commodity or system including the said element.

[0025] As Figure 1 shown is a specific implementation manner of a method for predicting the physiological age of the human liver based on machine learning according to the present invention. A method for predicting the physiological age of the human liver based on machine learning in this embodiment includes the following steps: S1. Collect human liver physical examination data: The human liver physical examination data includes the gender of the person being examined, the calendar age, and the liver blood test data; the liver blood test data includes: albumin, total protein, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyl transferase, direct bilirubin, total bilirubin, alkaline phosphatase (ALP); S2. Divide the physical examination data of the healthy people into a male data set and a female data set according to gender; S3. Divide the male data set and the female data set into a training set and a test set respectively according to a proportion; S4. Perform normalization processing on the data of the training set: Perform normalization processing on the data in the training sets of the male data set and the female data set respectively; S5. Model and perform model training: Model the data in the training sets of the male data set and the female data set respectively, and perform cross-validation hyperparameter optimization by means of grid search; S6. Perform correction on the prediction of the physiological age of the human liver: Perform age correction according to the regression to the mean effect, use the calendar age as the independent variable, and the original age difference as the dependent variable for linear regression; Original age difference = slope * calendar age + intercept + residual; wherein, the residual is the age difference after correction, that is, the part related to the calendar age is removed from the original age difference, and the formula is: Corrected age difference = original age difference – (slope * original age difference + intercept); wherein, the slope and the intercept are calculated, and the specific calculation method is: linearly fit the original age difference and the calendar age in the training sets of the male data set and the female data set respectively to obtain the slope and the intercept in the male data set and the female data set.

[0026] In this embodiment, after step S6, the following steps are further included: S7. Calculate the aging index: The formula for calculating the aging index is: Aging index = corrected age difference / calendar age.

[0027] Specifically, in a method for predicting the physiological age of the human liver based on machine learning in this implementation, 872 male individual samples were collected, with an age distribution range of 15 - 90 years old; 961 female individual samples were collected, with an age distribution range of 15 - 87 years old.

[0028] In step S3, the ratio of the data volume of the training set to the test set is 3:1. After division: among male individuals, the number of training set samples is 872, and the number of test set samples is 290; among female individuals, the number of training set samples is 721, and the number of test set samples is 240. It should be noted that in actual applications, the ratio of the training set to the test set can be 4:1, 3:1, 2:1, or 5:1 according to needs, which does not affect the implementation of the solution of the present invention.

[0029] In actual applications, in step S4 for normalizing the data of the training set, the normalization method can be any one of Z-score standardization, maximum-minimum normalization, median normalization, and maximum absolute value normalization. In a method for predicting the physiological age of the human liver based on machine learning in this embodiment, in step S4 for normalizing the data of the training set, the normalization method selects Z-score standardization, and the formula is z = (x - u) / σ, where x is the original value, u is the mean of the data set, σ is the standard deviation of the data set, and z is the normalized value.

[0030] In a method for predicting the physiological age of the human liver based on machine learning of the present invention, in specific applications, in step S5, the following one or more regression machine learning models can be used for modeling: SVR, LightGBM, CatBoost, Ridge, RandomForest, XGBoost, Huber, Lasso, ElasticNet. In a method for predicting the physiological age of the human liver based on machine learning in this embodiment, step S5 uses SVR to build a regression machine learning model. In a method for predicting the physiological age of the human liver based on machine learning in this embodiment, in step S5, the data in the training sets of the male data set and the female data set are respectively modeled, and hyperparameter optimization is performed by cross-validation in the way of grid search, which specifically includes the following steps: S51. Create a model; S52. Define the parameter grid: The parameter grid includes the penalty coefficient, kernel function, kernel function coefficient, and relaxation variable; S53. Perform hyperparameter tuning; S54. Obtain the optimal parameters and model.

[0031] A method for predicting the physiological age of the human liver based on machine learning, in practical applications, after step S54, the following steps are further included: S55. Evaluate and verify on the training set and / or test set. In the method for predicting the physiological age of the human liver based on machine learning in this embodiment, step S55 is to evaluate and verify on both the training set and the test set. Moreover, in this embodiment, the specific implementation of hyperparameter tuning in step S53 is to use GridSearchCV for hyperparameter tuning.

[0032] The specific implementation manner of step S5 of the method for predicting the physiological age of the human liver based on machine learning in this embodiment with male data, z-score standardization and homogenization, and SVR modeling in Python is as follows: Import the necessary Python packages: import numpy as np import pandas as pd from sklearn.model_selection import train_test_split, GridSearchCV from sklearn.pipeline import Pipeline from sklearn.preprocessing import StandardScaler from sklearn.svm import SVR from sklearn.metrics import mean_squared_error from scipy.stats import pearsonr # Read in the modeling data: data = pd.read_csv(“Cardiovascular modeling data.csv”, header =0, index_col = 0) # Obtain male data maledf = data[data[“gender”]==”male”] # Obtain the detection value matrix of 8 indicators (TP: total protein; ALB: albumin; DBIL: direct bilirubin; GGT: γ-glutamyl transpeptidase; AST: aspartate aminotransferase; ALT: alanine aminotransferase; ALP: alkaline phosphatase; TBIL: total bilirubin): X = maledf[['TP','ALB',"DBIL","GGT","AST","ALT","ALP", "TBIL"]] # Obtain age y = maledf["age"] # Split the training set and test set X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0) # Create a modeling Pipeline: pipeline = Pipeline( ("scaler", StandardScaler()), ("svm", SVR()) ) # Define the parameter grid: param_grid = { "svm__C": [0.1, 1, 10, 100], # Penalty coefficient "svm__kernel": ["linear", "rbf"], # Kernel function "svm__gamma": ["scale", "auto"], # Kernel function coefficient "svm__epsilon": [0.1, 0.2, 0.5], # Slack variable } # Use GridSearchCV for hyperparameter tuning: grid_search = GridSearchCV( estimator=pipeline, param_grid=param_grid, cv=5, scoring="neg_mean_squared_error", verbose=1 ) grid_search.fit(X_train, y_train) # Obtain the best parameters and model: best_params = grid_search.best_params_ best_model = grid_search.best_estimator_ # Evaluate on the training set y_train_pred = best_model.predict(X_train) train_mae = mean_squared_error(y_train, y_train_pred) train_r, train_p = pearsonr(y_train, y_train_pred) # Evaluate on the test set: y_test_pred = best_model.predict(X_test) test_mae = mean_squared_error(y_test, y_test_pred) test_r, test_p = pearsonr(y_test, y_test_pred) For a method for predicting the physiological age of the human liver based on machine learning in this embodiment, the slope and intercept in step S6 are calculated. The specific calculation method is as follows: linearly fit the original age difference and the calendar age in the training sets of the male dataset and the female dataset respectively to obtain the slope and intercept in the male dataset and the female dataset. In this embodiment, when the normalization method is z-score normalization and the SVR is used for modeling, by linearly fitting the original age difference and the calendar age in the training sets of the male dataset and the female dataset, the slope and intercept in the male dataset and the female dataset are as follows: the male slope is -0.8719, the male intercept is 47.50, the female slope is -0.7732, and the female intercept is 39.74.

[0033] A method for predicting the physiological age of the human liver based on machine learning in this embodiment has achieved good performance in practical applications. In the test set, as Figure 2 shown, the Pearson correlation coefficient between the physiological age predicted by the male cardiovascular physiological age model and the calendar age has reached 0.35. As Figure 3As shown, the correlation coefficient between the physiological age of women predicted by the female cardiovascular physiological age model and the calendar age reached 0.51, both showing relatively good modeling effects. However, both models showed the "regression to the mean effect" in statistics, that is, for young individuals, the predicted biological age was often higher than the calendar age; for older individuals, the predicted biological age was often lower than the calendar age. After age prediction correction in step S6, the age differences between men and women after correction are respectively as Figure 4 and Figure 5 shown. The MAE (Mean Absolute Error) of men after correction is 3.00, and the MAE of women after correction is 3.95, achieving very good results.

[0034] A method for predicting the physiological age of the human liver based on machine learning in this embodiment also defines and calculates the aging index through step S7. The aging index represents the number of years an individual ages each year and can evaluate the aging rate. If the aging index is greater than 1, it means that the individual's aging speed is higher than the normal speed and the aging speed is faster; if the aging index is less than 1, it represents that the individual's aging speed is slower than the normal speed and the aging speed is slower.

[0035] A method for predicting the physiological age of the human liver based on machine learning of the present invention collects 8 blood test indicators closely related to the liver, namely albumin, total protein, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyltransferase, direct bilirubin, total bilirubin, and alkaline phosphatase (ALP), in a targeted manner. Computer models are built for male and female data respectively around the liver health data to construct computer models for predicting the physiological age of the human liver of men and women, so as to evaluate the physiological age of the human liver of individuals of different genders. A method for predicting the physiological age of the human liver based on machine learning of the present invention, because only the blood data indicators of albumin, total protein, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyltransferase, direct bilirubin, total bilirubin, and alkaline phosphatase (ALP) related to the human liver are used as the core data for modeling to construct the physiological age model of the human liver, can evaluate the physiological age of the human liver in a targeted manner; moreover, a method for predicting the physiological age of the human liver based on machine learning of the present invention builds models for men and women respectively based on the data differences between men and women, making the prediction results more accurate.

[0036] The above is only a preferred embodiment of the present invention and is not used to limit the scope of implementation of the present invention. That is, all equivalent changes and modifications made according to the content of the patent application scope of the present invention shall fall within the technical scope of the present invention.

Claims

1. A method for predicting the physiological age of the human liver based on machine learning, characterized in that: It includes the following steps: S1. Collect human liver physical examination data: The human liver physical examination data includes the gender of the examinee, calendar age, and liver blood test data; The liver blood test data includes: albumin, total protein, alanine aminotransferase (ALT), aspartate aminotransferase (AST), γ-glutamyl transferase, direct bilirubin, total bilirubin, alkaline phosphatase (ALP); S2. Divide the health examination data into a male data set and a female data set according to gender; S3. Divide the male data set and the female data set into a training set and a test set according to a ratio respectively; S4. Perform normalization processing on the data in the training set: Perform normalization processing on the data in the training sets of the male data set and the female data set respectively; S5. Build a model and perform model training: Build models for the data in the training sets of the male data set and the female data set respectively, and perform cross-validation hyperparameter optimization by means of grid search; S6. Perform prediction and correction of human liver physiological age: Perform age correction according to the regression to the mean effect, use the calendar age as the independent variable, and the original age difference as the dependent variable for linear regression; Original age difference = slope * calendar age + intercept + residual; Among them, the residual is the age difference after correction, that is, the part related to the calendar age is removed from the original age difference, and the formula is: Corrected age difference = original age difference – (slope * original age difference + intercept); Among them, the slope and intercept are calculated. The specific calculation method is: Perform linear fitting of the original age difference and the calendar age in the training sets of the male data set and the female data set respectively to obtain the slope and intercept in the male data set and the female data set.

2. The method for predicting the physiological age of the human liver based on machine learning according to claim 1, characterized in that: After step S6, the following steps are further included: S7. Calculate the aging index: The formula for calculating the aging index is: Aging index = corrected age difference / calendar age.

3. A method for predicting the physiological age of the human liver based on machine learning according to claim 1, characterized in that: In step S3, the ratio of the data volume of the training set to the test set is 2:1, 3:1, 4:1 or 5:

1.

4. A method for predicting the physiological age of the human liver based on machine learning according to claim 1, characterized in that: In step S4, when performing normalization processing on the data in the training set, the normalization method can be any one of Z-score standardization, maximum-minimum normalization, median normalization, and maximum absolute value normalization.

5. The method for predicting the physiological age of the human liver based on machine learning according to claim 4, characterized in that: In step S4, when performing normalization processing on the data in the training set, the normalization method is Z-score standardization, and the formula is z = (x - u) / σ, where x is the original value, u is the mean of the data set, σ is the standard deviation of the data set, and z is the normalized value.

6. The method for predicting the physiological age of the human liver based on machine learning according to claim 1, characterized in that: In step S5, the following one or more regression machine learning models are used for modeling: SVR, LightGBM, CatBoost, Ridge, RandomForest, XGBoost, Huber, Lasso, ElasticNet.

7. A method for predicting the physiological age of the human liver based on machine learning according to claim 6, characterized in that: In step S5, SVR modeling is used; in step S5, models are built for the data in the training sets of the male data set and the female data set respectively, and cross-validation hyperparameter optimization is performed by means of grid search, which specifically includes the following steps: S51. Create a model; S52. Define a parameter grid: The parameter grid includes a penalty coefficient, a kernel function, a kernel function coefficient, and a slack variable; S53. Perform hyperparameter tuning; S54. Obtain the optimal parameters and model.

8. A method for predicting the physiological age of the human liver based on machine learning according to claim 7, characterized in that: After step S54, the following steps are further included: S55. Conduct evaluation and verification on the training set and / or test set.

9. A method for predicting the physiological age of the human liver based on machine learning according to claim 7, characterized in that: Specifically, step S53 for hyperparameter tuning is to use GridSearchCV for hyperparameter tuning.

Images