Esophageal squamous cell carcinoma absolute risk prediction method, equipment and medium

Abstract

The invention belongs to the field of intelligent medical treatment, and particularly relates to an esophageal squamous cell carcinoma absolute risk prediction method, equipment and a medium. The method comprises the following steps: acquiring a score of whether a to-be-detected person prefers hard food, a score of high-temperature food preference and other clinical characteristics, wherein the other clinical characteristics comprise age; calculating an unhealthy dietary habit score based on the hard food preference score and the high-temperature food preference score; and inputting the unhealthy dietary habit score and the other clinical features into an esophageal squamous cell carcinoma absolute risk prediction model to obtain the absolute risk of the to-be-detected person suffering from esophageal squamous cell carcinoma. The unhealthy dietary habit score is calculated based on the hard food preference score and the high-temperature food preference score, and it is determined that the unhealthy dietary habit score is an effective predictive factor of the absolute risk of esophageal squamous cell carcinoma.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medicine, and more particularly, to a method, device, medium and program product for predicting the absolute risk of esophageal squamous cell carcinoma. Background Art

[0002] Esophageal cancer (EC) currently ranks seventh in the global incidence rate and sixth in the mortality rate. EC is divided into two histological subtypes: squamous cell carcinoma (ESCC) and adenocarcinoma (EAC). EAC is the main subtype of EC in Western countries. In contrast, ESCC is the main subtype of EC in East Asia to Central Asia, along the East African Rift Valley, and South Africa, accounting for more than 85% of the confirmed cases. The prevalence of ESCC varies significantly in different geographical regions, with the very high-risk regions being nearly 20 times higher than the low-risk regions. Endoscopic screening for patients can reduce the mortality rate of esophageal squamous cell carcinoma, which highlights the importance of early diagnosis and treatment, and is an effective method for the prevention and control of esophageal squamous cell carcinoma. Although a series of organized ESCC screening programs have been implemented in high-risk regions, the actual and economic inefficiency of universal endoscopic screening requires a more precise method based on individualized risk assessment using a risk prediction model.

[0003] We have developed a series of models to identify common esophageal squamous cell carcinoma cases, focusing on current diagnosis. These models can help make immediate decisions regarding endoscopic screening. However, for esophageal squamous cell carcinoma, like most cancers with a long-term, multi-stage natural history, regular screening may be more effective than one-time screening. For regular screening strategies, long-term risk assessment is crucial, especially for individuals with a higher future risk of disease. Absolute risk models can be used for comprehensive, continuous, and dynamic risk assessment, informing individuals of their long-term or even lifetime risks, in order to participate in repeated self-assessment and regular screening.

[0004] Several absolute risk prediction models for esophageal squamous cell carcinoma (ESCC) have been reported so far. Most of them were developed based on European populations, and only one was developed based on a Chinese community cohort - "Electronic Health Record-Based Absolute Risk Prediction Model for Esophageal Cancer in the Chinese Population: Model Development and External Validation" (DOI: 10.2196 / 43725). However, this model has significant limitations. First, it ignores the huge differences in disease burden across different regions, which will lead to large errors in the estimation of individualized EC risk. Second, the main predictor (the factor with the highest weight / contribution) of this model is "whether living in a high-risk area", which will inevitably lead to poor prediction performance when the model stratifies risks in high-incidence or low-incidence areas, greatly weakening its applicability in the real world. Summary of the Invention

[0005] In view of the above problems, the present invention provides an adaptive absolute risk prediction model that incorporates age-specific incidence rates and is based on up to 10 years of follow-up data from a large-scale community screening trial conducted in high-risk areas for ESCC. This model can accurately estimate individualized absolute risks and also adapt to regional disease burdens. We recommend it as a tool for dynamic risk assessment and precise periodic screening for ESCC.

[0006] This application (in the first aspect) discloses a method for predicting the absolute risk of esophageal squamous cell carcinoma, the method comprising:

[0007] Obtaining the scores of whether the person to be tested prefers hard food, the preference score for high-temperature food, and other clinical characteristics, where the other clinical characteristics include age;

[0008] Calculating an unhealthy eating habit score based on the scores of whether the person to be tested prefers hard food and the preference score for high-temperature food;

[0009] Inputting the unhealthy eating habit score and the other clinical characteristics into an absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the person to be tested having esophageal squamous cell carcinoma, where the absolute risk prediction model for esophageal squamous cell carcinoma is an absolute risk prediction model constructed based on the unhealthy eating habit score and other clinical characteristics of a training set.

[0010] Further, the unhealthy diet score is classified based on the sum of the scores of whether the person to be tested prefers hard food and the preference score for high-temperature food. If the sum of the scores of whether the person to be tested prefers hard food and the preference score for high-temperature food is 0 or 1, the unhealthy diet score is 0; otherwise, it is 1.

[0011] Optionally, the score for preference for hard food is represented as: if the subject's preference for hard food is "occasionally", the score is 0; if it is "frequently", the score is 1. The score for preference for high-temperature food is represented as: if the subject's preference for high-temperature food is "occasionally", the score is 0; if it is "frequently", the score is 1.

[0012] Optionally, when the frequency of preference for hard food and high-temperature food is less than or equal to once a week, the situation is "occasionally".

[0013] Furthermore, the other clinical features further include: gender, whether the diet is regular; the unhealthy eating habit score and the other clinical features are input into the absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the subject suffering from esophageal squamous cell carcinoma, where the absolute risk prediction model for esophageal squamous cell carcinoma is an absolute risk prediction model constructed based on the unhealthy eating habit score and the other clinical features of the training set.

[0014] Furthermore, the other clinical features further include: BMI, family history of esophageal cancer; the unhealthy eating habit score and the other clinical features are input into the absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the subject suffering from esophageal squamous cell carcinoma, where the absolute risk prediction model for esophageal squamous cell carcinoma is an absolute risk prediction model constructed based on the unhealthy eating habit score and the other clinical features of the training set;

[0015] Optionally, whether the diet is regular is classified as "yes" or "no";

[0016] Optionally, the BMI is divided into two categories based on a division threshold;

[0017] Optionally, the family history of esophageal cancer is divided into three categories based on the number of cases of esophageal squamous cell carcinoma among direct blood relatives within three generations, namely the number of cases equal to 0, the number of cases equal to 1, and the number of cases greater than 1.

[0018] Furthermore, the absolute risk prediction model outputs the absolute risk of the subject suffering from esophageal squamous cell carcinoma at different times, and the different times include one or more of the following: six months later, one year later, three years later, five years later, after a certain time;

[0019] Optionally, the unhealthy eating habit score, the other clinical features, and the prediction period are input into the absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the subject suffering from esophageal squamous cell carcinoma at the prediction period.

[0020] Furthermore, the method for constructing an absolute risk prediction model based on the unhealthy eating habit score and other clinical features of the training set includes:

[0021] Step 1: Obtain the unhealthy eating habit scores, the other clinical characteristics, the overall incidence rate, the incidence rate at a specific age, the population attributable risk, and the all-cause mortality at a specific age excluding esophageal squamous cell carcinoma of the training set;

[0022] Step 2: Fit a relative risk based on the unhealthy eating habit scores, the other clinical characteristics, and the overall incidence rate;

[0023] Step 3: Calculate a baseline hazard rate based on the incidence rate at a specific age and the population attributable risk;

[0024] Step 3: Obtain an absolute risk prediction model based on the baseline hazard rate, the relative risk, and the competing risk of death;

[0025] Optionally, the baseline hazard rate is expressed as:

[0026] h 1 (t) = h 0 (t){1 - PAR(t) %}

[0027] where h 1 (t) represents the baseline hazard rate; h 0 (t) represents the incidence rate at a specific age of esophageal cancer; PAR(t) represents the population attributable risk;

[0028] Optionally, the absolute risk prediction model is expressed as:

[0029]

[0030] where AR i (a, a + τ) represents the absolute risk of an esophageal squamous cell carcinoma occurring in a subject in the i-th risk group with an age interval of [a, a + τ]; h 1 (t) represents the baseline hazard rate, h 2 (t) represents the all-cause mortality at a specific age excluding esophageal squamous cell carcinoma; r i represents the relative risk of the i-th risk group; S i (t - 1) represents the survival risk of age t - 1 in the i-th risk group; S i (0) = 1.

[0031] Furthermore, the steps for obtaining the absolute risk of an esophageal squamous cell carcinoma in a subject to be tested by inputting the unhealthy eating habit scores and the other clinical characteristics into the esophageal squamous cell carcinoma absolute risk prediction model are as follows:

[0032] Step 1: Determine an applicable esophageal squamous cell carcinoma absolute risk prediction model based on the unhealthy eating habit scores and the other clinical characteristics;

[0033] Step 2: Determine the baseline risk and all-cause mortality corresponding to the age of the subject to be tested based on the age of the subject to be tested, and determine the risk group to which the subject to be tested belongs, the relative risk of the risk group to which the subject belongs, and the survival risk of the subject at age t-1 in the risk group to which the subject belongs based on the unhealthy eating habit score and the other clinical characteristics of the subject to be tested;

[0034] Step 3: Calculate the absolute risk based on the baseline risk, all-cause mortality, the risk group to which the subject belongs, the relative risk of the risk group to which the subject belongs, and the survival risk of the subject at age t-1 in the risk group to which the subject belongs corresponding to the age of the subject to be tested, where τ is six months later, one year later, three years later, five years later, and ten years later respectively.

[0035] The second aspect of the present application discloses a prediction system for the absolute risk of esophageal squamous cell carcinoma, including:

[0036] An acquisition module 201: configured to acquire the score of whether the subject to be tested prefers hard food, the score of preference for high-temperature food, and other clinical characteristics, where the other clinical characteristics include age;

[0037] A feature extraction module 202: configured to calculate an unhealthy eating habit score based on the score of whether the subject to be tested prefers hard food and the score of preference for high-temperature food;

[0038] A prediction module 203: configured to input the unhealthy eating habit score and the other clinical characteristics into an absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the subject to be tested suffering from esophageal squamous cell carcinoma, and the absolute risk prediction model for esophageal squamous cell carcinoma is an absolute risk prediction model constructed based on the unhealthy eating habit score and other clinical characteristics of the training set.

[0039] The third aspect of the present application discloses a computer device, the device includes: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the above method.

[0040] The fourth aspect of the present application discloses a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the above method.

[0041] The fifth aspect of the present application discloses a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the steps of the above method.

[0042] The present application has the following beneficial effects:

[0043] (1) In the present application, an unhealthy eating habit score is calculated based on the score of whether the subject to be tested prefers hard food and the score of preference for high-temperature food, and it is determined that the unhealthy eating habit score is an effective predictor of the absolute risk of esophageal squamous cell carcinoma;

[0044] (2) We modified h 0 (t) to obtain various baseline hazards h 1 (t), calculate the absolute risk of a specific region based on the local disease burden, and be able to adapt to the risk burden of different risk regions. The generalization of the absolute prediction model constructed in this application is relatively strong. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 It is a schematic flowchart of the method provided in the first aspect of the embodiment of the present invention;

[0047] Figure 2 It is a schematic diagram of the program product provided in the second aspect of the embodiment of the present invention;

[0048] Figure 3 It is a schematic diagram of the computer device provided in the embodiment of the present invention;

[0049] Figure 4 It is a schematic diagram of the architecture of the exemplary computing device provided in the embodiment of the present invention;

[0050] Figure 5 It is a schematic diagram of the storage medium provided in the embodiment of the present invention;

[0051] Figure 6 It is an ROC graph of an absolute risk prediction model provided in the embodiment of the present invention in different groups;

[0052] Figure 7 It is a comparison graph of the absolute risks in different regions (a) and a comparison graph of the covered populations with different absolute risks (b) provided in the embodiment of the present invention;

[0053] Figure 8 It is the AUC value of different risk factors provided in the embodiment of the present invention;

[0054] Figure 9 It is a 5-year (a) and a 10-year risk prediction model calibration graph for the calibration evaluation of the control arm model provided in the embodiment of the present invention;

[0055] Figure 10 It is a schematic diagram of the online prediction of an absolute risk prediction method provided in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0057] In some processes described in the specification, claims and above-mentioned accompanying drawings of the present invention, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as S101, S102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0058] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present invention.

[0059] Figure 1 It is a schematic flow chart of a method for predicting the absolute risk of esophageal squamous cell carcinoma provided by an embodiment of the present invention. Specifically, the method includes the following steps:

[0060] S101: Obtain the score of whether the subject prefers hard food, the score of preference for high-temperature food, and other clinical characteristics, where the other clinical characteristics include age;

[0061] S102: Calculate an unhealthy eating habit score based on the score of whether the subject prefers hard food and the score of preference for high-temperature food;

[0062] S103: Input the unhealthy eating habit score and the other clinical characteristics into an absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the subject suffering from esophageal squamous cell carcinoma. The absolute risk prediction model for esophageal squamous cell carcinoma is an absolute risk prediction model constructed based on the unhealthy eating habit score and other clinical characteristics of the training set.

[0063] This application is formed based on the following basic research.

[0064] Overview of basic research is as follows:

[0065] I. Materials and Methods

[0066] 1.1 Subjects

[0067] The subjects of our study were participants in the ESECC trial launched in rural Huaxian County, Henan Province, China in January 2012. The design of this trial has been reported in detail previously (see the article "Efficacy of endoscopic screening for esophageal cancer in China (ESECC)"). Briefly, 668 villages were randomly assigned to the screening group or the control group at a ratio of 1:1 using group randomization according to their population size. A total of 17,151 subjects were recruited in the screening group and 16,797 subjects in the control group in the ESECC trial. In the screening group, all subjects were invited to undergo endoscopic screening, among whom 1,544 withdrew before the trial and 303 failed to complete the test. Another 5 participants in the screening group and 33 participants in the control group did not complete the questionnaire survey. Therefore, the number of participants who completed all examination and investigation phases in the screening group and the control group was 15,299 and 16,764 respectively.

[0068] Esophageal malignant tumor cases were diagnosed by endoscopy combined with Lugol's iodine staining, biopsy, and pathological examination. Lugol's iodine staining has been proven to have a sensitivity of 96% and a specificity of 63% in population-based screening. In this study, we further excluded subjects with missing values of body mass index (BMI), resulting in 15,191 subjects in the screening group and 16,692 subjects in the control group.

[0069] 1.2 Data collection and follow-up

[0070] Trained interviewers conducted computer-assisted, personalized questionnaire-based surveys on each participant at baseline to collect information on demographic characteristics and potential risk factors for ESCC, such as lifestyle, eating habits, and family history of ESCC. A comprehensive physical examination was also performed, including measurements of height, weight, and blood pressure.

[0071] The outcome events in this study were defined as severe esophageal dysplasia, carcinoma in situ, and squamous cell carcinoma (collectively referred to as SDA), which were detected during endoscopic screening and follow-up from January 2012 to August 2022. Events occurring during the follow-up period were determined based on two data sources, one being annual door-to-door interviews (i.e., active follow-up), and the other being the New Rural Cooperative Medical Scheme reimbursement data (i.e., passive follow-up), with a population coverage rate of nearly 100% in this area. The performance of the follow-up framework has been comprehensively evaluated previously.

[0072] II. Statistical analysis

[0073] We estimated the absolute risk of individual esophageal squamous cell carcinoma in three steps: 1) constructing a relative risk prediction model; 2) calculating the region-specific age baseline hazard rate, and 3) calculating the individual absolute risk and adjusting for competing death risks.

[0074] Step 1: Construct a relative risk prediction model

[0075] Candidate predictors were selected based on the results of relevant studies, and candidate variables were determined by considering the applicability of each predictive variable in different populations.

[0076] Candidate variables included demographic characteristics, dietary habits, lifestyle variables, and family history of ESCC. A two-stage selection method was used to determine the final set of variables to be included in the relative risk prediction model.

[0077] First, univariate logistic regression was used to evaluate the candidate variables. Subsequently, variables with odds ratio (OR) > 1.3 and P-value < 0.5 or P-value < 0.05 were included in the multivariate logistic regression model. Age and gender were deterministically added to the model as prior confounders. The final relative risk prediction model was determined using backward selection based on the Akaike information criterion (AIC). The area under the receiver operating characteristic curve (AUC) calculated using the bootstrap method was used to evaluate the performance of the relative risk model. AUC values were generated for all included ESECC trial participants, screening groups, and control groups, respectively.

[0078] Step 2: Calculate the age-specific baseline hazard rate

[0079] Baseline hazard 1 (t) represents the potential risk of an event, without considering any risk factors, and is calculated based on age-specific incidence and population attributable risk (PAR). The variable t refers to age. The age-specific incidence of esophageal cancer h 0 (t) data were sourced from the reimbursement data of the New Rural Cooperative Medical Scheme in Huaxian County. PAR is the proportion of the incidence of ESCC in the population due to exposure to a series of known risk factors presented in the selected final relative risk model. Therefore, based on the relative risk model constructed in the previous step, there were l risk groups. Here, l represents the total number of combinations of risk factors, which is equal to the product of the number of categories of each risk factor. For example, if there are k risk factors, and each risk factor has n i categories (where i = 1, 2…, k), then there is:

[0080] Define r i as the relative risk of the i-th risk group compared to the baseline group (the baseline group represents the group in which no risk factors occur), where r 1 = 1 represents the baseline group, x iis the number of cases in the i-th group, and x is the total number of cases in the entire cohort.

[0081] Assume that the proportion of subjects of age t belonging to the i-th risk group is P i (t), and the incidence rate h 0 (t) can be expressed as:

[0082]

[0083] Then, assume that s i (t) represents the proportion of cases of age t in the i-th risk group, and the calculation formula is:

[0084] s i (t) = P i (t)h 1 (t)r i / h 0 (t)

[0085] According to this formula, the baseline hazard 1 (t) is as follows:

[0086]

[0087] Step 3: Calculate the individualized absolute risk and adjust for competing risks of death

[0088] The absolute risk is calculated based on the following information:

[0089] 1) Relative risk (r i ): Calculated using a relative risk prediction model;

[0090] 2) Baseline hazard h 1 (t)

[0091] 3) Cause-specific all-cause mortality h 2 (t) excluding esophageal squamous cell carcinoma.

[0092] The all-cause mortality is estimated based on the death registration data of Huaxian County, and we assume that h 2 (t) is the same for all subjects.

[0093] For subjects in the age range [a, a + τ] in the i-th risk group, the absolute risk (AR) of developing ESCC is defined as:

[0094]

[0095] The above equation predicts the probability that an event of interest will occur in a given time interval [a, a+τ] for a subject, provided that the subject does not die before age a. In our study, we considered age at discrete one-year intervals. Therefore, we replaced the integral with an appropriate sum to reflect the discrete nature of the age variable.

[0096] For subjects in the age interval [a, a+τ] in the i-th risk group after correction, the absolute risk (AR) of developing ESCC is defined as:

[0097] Cumhaz(a) i = h 1 (a)r i + h 2 (a)

[0098] S i (a) = S i (a - 1)exp{-Cumhaz(a) i}

[0099]

[0100] Calibration analysis was performed by stratifying the predicted AR into five quantiles, and the mean predicted risk was calculated and compared with the observed risk in each group. A calibration plot was used to visually inspect the calibration curve, and a Hosmer-Lemeshow test was used for statistical testing.

[0101] The uncertainty of our model mainly comes from β (the coefficient of the relative risk model), h 1 (t) and h 2 (t). Since h 1 (t) and h 2 (t) are from a large amount of population data and are considered relatively stable, we focused on the uncertainty generated by the estimation of β. The parametric bootstrap method was used to evaluate the uncertainty of the model (details are described in the supplementary materials).

[0102] The performance of the ESCC absolute risk model in the extremely high, high, and low risk regions. The estimation of the absolute risk involves not only the relative risk but also the regional incidence level. Given the significant geographical heterogeneity in the incidence of ESCC, adapting to the incidence rates specific to the region is crucial for the application of our model. In our study, we modified h 0 (t) to obtain various baseline hazards h 1 (t), and calculated the absolute risk for a specific region based on the local disease burden (local incidence / prevalence of esophageal cancer).

[0103] Here, we provide examples of applying the absolute risk model in areas with extremely high risk (Linzhou, Henan), high risk (Huaxian, Henan), and low risk (Beijing) of ESCC. The age-standardized incidence rates (ASRs) in Linzhou, Huaxian, and Beijing were 72.46 / 100,000 (2008 - 2013)

[27] , 30.03 / 100,000 (2014 - 2018)

[23] , and 3.78 / 100,000 (2017)

[28] , respectively. We calculated the individual absolute risks, assuming that the age distributions in the three regions were comparable and that the ratio of age-specific incidence rates was the same as the ratio of ASRs, i.e.,

[0104]

[0105] Then, using their average 5-year cumulative risk as an indicator, we calculated the proportion of the population that needed to be screened in different regions under a series of varying cumulative incidence cut-off values. All analyses were performed using R software (version 4.4.3, RRID: SCR_001905), and all significant tests used two-sided tests with a P-value of 0.05.

[0106] Ethical approval and consent to participate: This study was conducted in accordance with the Declaration of Helsinki and was approved by the Institutional Review Board of Peking University Cancer Hospital [2011KT27]. All participants provided written informed consent. Data availability The data generated in this study can be found in the article and its supplementary data files. The datasets used and / or analyzed during the current study are available from the corresponding author upon reasonable request.

[0107] III. Results

[0108] 3.1 Characteristics of study participants

[0109] A total of 31,883 subjects from the ESECC trial were included in this study. Among them, 151 subjects were diagnosed with SDA cases during baseline endoscopic screening and follow-up, and 144 EC cases were diagnosed during the follow-up period until August 12, 2022. The baseline distributions of the candidate predictors are shown in Table 1. Compared with the non-case group (n = 31,588), individuals in the case group (n = 295) were older, mainly male, more likely to have a lower BMI (≤22 kg / m2), a family history of esophageal cancer, irregular diet, and a preference for high-temperature and hard foods.

[0110] Table 1. Demographic and behavioral characteristics of 31,883 participants in the rural esophageal cancer endoscopic screening (ESECC) trial in Huaxian, China, from 2012 to 2022

[0111]

[0112] aOccasionally: ≤ once a week; Frequency: > once a week;

[0113] Number of esophageal squamous cell carcinoma cases among immediate family members and relatives within three generations;

[0114] c P-value comes from Pearson chi-square test.

[0115] 3.2 Structure and performance of the relative risk model

[0116] As shown in Table 2, the final relative risk model consists of six risk factors:

[0117] Advanced age (OR adjusted : 2.00, 95% CI: 1.81 - 2.24),

[0118] Male (OR adjusted : 1.56, 95% CI: 1.09 - 2.22),

[0119] Irregular dietary pattern (OR adjusted : 1.40, 95% CI: 1.09 - 1.79),

[0120] Preference for hot or hard foods (OR adjusted : 1.48, 95% CI: 1.13 - 1.94),

[0121] BMI < 22 kg / m 2 (OR adjusted : 1.48, 95% CI: 1.13 - 1.94),

[0122] Family history of esophageal cancer (one case of esophageal cancer in three generations of blood relatives) (OR adjusted : 1.77, 95% CI: 1.25 - 2.51;

[0124] > 1 case of ESCC in three generations of blood relatives (OR adjusted : 3.60, 95% CI: 2.07 - 6.27).

[0125] Table 2: Crude and adjusted odds ratios of ESCC risk predictors in the ESECC trial in Huaxian, China, 2012 - 2022

[0126]

[0127] Abbreviations: No., number; CI, confidence interval.

[0128] a The unhealthy diet habit score is the sum of two variables: "preference for hard foods" and "preference for high-temperature foods".

[0129] b Number of esophageal squamous cell carcinoma cases among immediate blood relatives within three generations.

[0130] In the ESECC trial, the AUC of the model was 0.753 (95% CI: 0.749 - 0.757)( Figure 6 -a). Specifically, the AUC of the model in the screening group was 0.759 (95% CI: 0.732 - 0.786)( Figure 6 -b), and in the control group it was 0.749 (95% CI: 0.705 - 0.794)( Figure 6 -c). Subgroup analysis indicated that the AUC within the predictors was relatively robust( Figure 9 ).

[0131] 3.3 Individualized absolute risk assessment

[0132] Based on the relative risks of the predictors, age-specific incidence rates, baseline hazards, and all-cause mortality excluding esophageal cancer, we calculated the individualized 1-year to 10-year absolute risks of esophageal cancer. Among all participants in the ESECC trial, the mean 3-year, 5-year, and 10-year absolute risks of developing ESCC were 0.28%, 0.53%, and 1.30%, respectively. There were 48 combinations of risk factors within each age group. As Figure 7 shown, area under the curve (AUC) analysis showed the predictive performance of risk factors including sex, diet pattern, eating habits, family history, and BMI. The model was well calibrated for the predicted 5-year absolute risk in the control arm (p = 0.460), while the 10-year prediction tended to overestimate the actual risk in the ESECC control arm trial (p < 0.001).

[0133] Given the large geographical differences in disease burden, we calculated the absolute risk adjustment range of ASR from 1 to 80 / 100,000.

[0134] Based on the above estimates, we developed a user-friendly online tool (https: / / pkugenetics.shinyapps.io / escc_risk_prediction / ) that can assess an individual's absolute risk of esophageal squamous cell carcinoma in different regions.

[0135] First, the user is required to manually fill in the regional ASR or select from a list of residential areas (including Asian and African countries) with known ASR in the database. Then, the tool will prompt the user to enter information about the selected predictors, including age, sex, height, weight, eating habits, and EC family history. After submitting this data, the tool will calculate and present a personalized risk profile showing the predicted probabilities of the user developing ESCC in 3, 5, and 10 years( Figure 10 ).

[0136] 3.4 Application of the absolute risk model in regions with different ESCC burdens

[0137] We selected three typical regions with different burdens of esophageal squamous cell carcinoma in China, namely Linzhou (formerly Lin County, an extremely high-risk area), Huaxian (a high-risk area), and Beijing (a low-risk area) to verify the performance of our model. We calculated the adjusted 1-year to 10-year absolute risks of the subjects in these three regions respectively and found that the average cumulative risk of the subjects in Linzhou was significantly higher than that in Huaxian and Beijing ( Figure 7 -a). Taking the 10-year cumulative risk as an example, the average absolute risks in Linzhou were 3.21%, 2.4, and 18.9 times those in Huaxian (1.30%) and Beijing (0.17%) respectively.

[0138] Then, taking the average 5-year cumulative risk as an index, we calculated the population proportions at different critical values.

[0139] Table 3: Risk stratification effectiveness of 5-year cumulative risks in Beijing, Huaxian, and Linzhou calculated based on the absolute risk prediction model

[0140]

[0141] a The population coverage rate refers to the proportion of individuals whose predicted 5-year cumulative risk exceeds the critical value.

[0142] Obviously, the population coverage rates exceeding a specific absolute risk level vary greatly among different regions. For example, when considering

[0143] the 5-year absolute risk threshold of 1%, in regions with extremely high incidence such as Linzhou, more than 50% of the population exceeds

[0144] the specified risk level ( Figure 7 -b and Table 3), so screening is required. In contrast, people living in Beijing

[0145] (low-incidence area) do not exceed this threshold. In high-incidence areas such as Huaxian, the proportion of subjects exceeding this risk threshold is about 17%.

[0146] Discussion

[0147] Advanced esophageal squamous cell carcinoma has a poor prognosis, and early diagnosis and treatment are required to improve the prognosis. One of the key

[0148] methods for early diagnosis is screening, but for a large populous country like China, popularizing endoscopic screening is difficult in practice and economically

[0149] feasible.

[0150] These are all inefficient. Therefore, precision strategies based on individual risk prediction and stratification provide practical solutions. In addition, for chronic diseases such as esophageal squamous cell carcinoma with a long latency period from the emergence of tumor cells to the onset of symptoms, the long-term absolute risk of developing the disease in the future may become a more robust

[0151] indicator. There is a risk of widespread lesions. In addition, accurate prediction of absolute risk must take into account the significant geographical heterogeneity of the ESCC burden. Based on a large-scale community screening trial with up to 10 years of follow-up, this study constructed an absolute risk prediction model for individualized assessment of the long-term risk of ESCC adapted to the regional disease burden, using the regional incidence rate as a parameter. We first developed a relative risk prediction model that incorporated six individual-level risk factors: older age, male gender, irregular dietary patterns, preference for hot or hard foods, BMI < 22 kg / m2, and a family history of esophageal cancer. The selection of these factors was based on their contribution to improving the predictive performance of the model and was generally consistent with the factors identified in previous studies [24, 29 - 31], supporting their relevance in the risk prediction model.

[0152] It is worth noting that smoking has been proven to be a recognized risk factor in Western countries and the United States. However, in the screening settings of high-risk regions, especially in the Taihang Mountain area, smoking has not been conclusively proven to be a risk factor for ESCC, not only in the ESECC trial but also in community surveys conducted in Linxian County. First, the increase in the risk of esophageal squamous cell carcinoma seems to be more closely related to the duration of smoking, and the current smoking status may not be sufficient to reflect the cumulative effect of long-term smoking. Second, differences in tobacco processing between cigarettes and pipes may also affect cancer risk. Cigarettes with lower tar content. Finally, the low smoking rate among rural women in China (nearly half of esophageal squamous cell carcinoma cases) further reduces the overall impact of smoking as an important risk factor in these regions.

[0153] Our model showed good calibration, with the 5-year prediction closely matching the observed risk, while the 10-year prediction tended to overestimate the actual risk. However, we believe that this difference may be partly attributed to the selection of participants during the recruitment phase of the ESECC trial, which recruited approximately 20% of eligible subjects in the target villages [8]. Compared with the general population, they were generally healthier, more health-conscious, and had fewer risky behaviors. Therefore, the long-term incidence of ESCC in the control group of the ESECC trial was lower.

[0154] The risk factors evaluated in our study were based on a systematic literature review and the results of previous large-scale population studies conducted in high-risk areas for esophageal squamous cell carcinoma. This supports the potential robustness and cross-population applicability of the model risk factor framework. However, there may be other risk factors in populations with different ethnic distributions and genetic backgrounds, and adding these factors to specific populations would help improve the predictive ability. In addition, although there were differences in the distribution of risk factors and the determination of outcomes between the screening group and the control group, the model showed equally satisfactory predictive accuracy in both groups, indicating that the model is a robust case for risk prediction in screening tests and subsequent identification.

[0155] To date, five ESCC absolute risk models have been published, three of which are based on Nordic and UK cohorts. For the remaining models developed in China, only one model was constructed based on a community cohort, but it has significant limitations. First, the model was not developed in a cohort specifically designed for ESCC, so it failed to systematically collect information on potential predictive factors related to the occurrence of ESCC, such as preference for hard foods, eating speed, etc. Second, the model estimated the risk with the same baseline hazard for absolute values. This "one-size-fits-all" approach largely ignored the huge regional differences in the disease burden of esophageal cancer. In this study, we illustrated the significant differences in absolute risks in three regions with different incidences of esophageal squamous cell carcinoma ( Figure 7 -a), thus highlighting the inaccuracy of the previously reported absolute risk prediction model, which did not consider the regional heterogeneity of the disease burden. Third, the model incorporated individuals from high-incidence and low-incidence areas in model development and generated a "high-risk area or not" variable, resulting in a relatively high AUC. However, when the model was applied to high-incidence or low-incidence areas, including this binary variable diluted the large geographical differences observed in real-world practice.

[0156] Our model further reflects the disease burden in different regions by integrating flexible incidence parameters. Our model further incorporates the incidence rates of each region, allowing the tested individuals to select their region of residence, and calculating the absolute risk of the tested individuals based on the region of residence. Therefore, it is a more accurate and flexible tool for evaluating the long-term absolute risk of ESCC. This enhances its applicability across geographical regions globally, enabling the formulation of more targeted and effective prevention and control strategies. For example, if we define individuals with a 5-year risk greater than 1% as high-risk populations, our model shows that half of the people in Linzhou are considered high-risk populations, while the proportions in Huaxian and Beijing are approximately 17% and 0% respectively.

[0157] Our online tool helps to actively evaluate the absolute risk of an individual developing esophageal squamous cell carcinoma, covering regions with different incidence rates, not only in China but also in other Asian and African countries where esophageal cancer is the main subtype of esophageal cancer. In addition, for public health policymakers, the model can identify high-risk populations based on a balance of local disease burden and medical resources, guiding precision screening policies in high-incidence and low-incidence areas.

[0158] Conclusion: In summary, we developed a reliable model that can predict the individualized absolute risk of ESCC. The model performs well and can be adjusted to reflect the regional burden of the disease globally. The model can help identify high-risk populations and enable them to proactively undergo regular endoscopic screening. In addition, our model can also assist healthcare professionals in planning long-term care and monitoring programs for screened individuals, thus ensuring continuous lifelong health management and monitoring.

[0159] Figure 3 It is a schematic diagram of a computer device provided by an embodiment of the present invention, as Figure 3 shown, the device 2000 may include: one or more processors 2010, and one or more memories 2020; wherein, computer-readable code is stored in the memory, and when the computer-readable code is run by the one or more processors, the method described above can be executed.

[0160] The processor in this embodiment may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, operations and logic block diagrams disclosed in the embodiments of the present disclosure. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc., which may be of the X86 architecture or the ARM architecture.

[0161] Generally speaking, the various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that can be executed by a controller, a microprocessor or other computing devices. When the aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flowcharts or using some other graphical representation, it will be understood that the blocks, devices, systems, technologies or methods described herein may be implemented as non-limiting examples in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0162] For example, the method or apparatus according to an embodiment of the present disclosure can also be implemented by means of Figure 4 the architecture of the computing device 3000 shown. As Figure 4 shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. Storage devices in the computing device 3000, such as the ROM 3030 or the hard disk 3070, can store various data or files used for the processing and / or communication of the method provided by the present disclosure and program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 the architecture shown is only exemplary, and when implementing different devices, one or more components shown in the Figure 4 computing device may be omitted according to actual needs.

[0163] An embodiment of the present invention also provides a computer-readable storage medium. As Figure 5 shown, it is a schematic diagram of the storage medium 4000 provided by an embodiment of the present invention. A computer-readable instruction 4010 is stored on the computer storage medium 4020. When the computer-readable instruction 4010 runs on a processor, it can execute the method according to an embodiment of the present disclosure described with reference to the above drawings. The computer-readable storage medium in the embodiments of the present disclosure may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memories of the methods described herein are intended to include, but are not limited to, these and any other suitable types of memories. It should be noted that the memories of the methods described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0164] An embodiment of the present disclosure also provides a computer program product or a computer program, which, when executed by a processor, implements the steps of the above method. AsFigure 2 As shown, the computer program product or computer program includes:

[0165] An acquisition module 201: configured to acquire the score of whether the person to be tested prefers hard food, the score of preference for high-temperature food, and other clinical features of the person to be tested, where the other clinical features include age;

[0166] A feature extraction module 202: configured to calculate an unhealthy eating habit score based on the score of whether the person to be tested prefers hard food and the score of preference for high-temperature food;

[0167] A prediction module 203: configured to input the unhealthy eating habit score and the other clinical features into an absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the person to be tested having esophageal squamous cell carcinoma, where the absolute risk prediction model for esophageal squamous cell carcinoma is an absolute risk prediction model constructed based on the unhealthy eating habit score and other clinical features of a training set.

[0168] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0169] Generally speaking, the various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that can be executed by a controller, a microprocessor, or other computing devices. When aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, devices, systems, technologies, or methods described herein may be implemented as non-limiting examples in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof.

[0170] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0171] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0172] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0173] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0174] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art should understand that various modifications and combinations can be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A method for predicting the absolute risk of esophageal squamous cell carcinoma, characterized in that: The method comprises: Obtaining the subject's preference score for hard food, high-temperature food preference score, and other clinical characteristics, wherein the other clinical characteristics include age; The unhealthy eating habits score was calculated based on the preference for hard food and the preference for high-temperature food. The unhealthy eating habits score and the other clinical characteristics are input into the absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the subject suffering from esophageal squamous cell carcinoma. The absolute risk prediction model for esophageal squamous cell carcinoma is an absolute risk prediction model constructed based on the unhealthy eating habits score and other clinical characteristics of the training set.

2. The method for predicting the absolute risk of esophageal squamous cell carcinoma according to claim 1, characterized in that: The unhealthy diet score is obtained based on the sum of the preference score for hard food and the preference score for hot food. If the sum of the preference score for hard food and the preference score for hot food is 0 or 1, the unhealthy diet score is 0, otherwise it is 1. Optionally, the score of preference for hard food is expressed as follows: if the subject prefers hard food "occasionally", the score is 0; if the subject prefers hard food "often", the score is 1; The high-temperature food preference score is expressed as follows: if the subject's high-temperature food preference is "occasionally" the score is 0, if it is "often" the score is 1; Optionally, if the preference for hard food and high temperature food is less than or equal to once a week, the situation is "occasionally".

3. The method for predicting the absolute risk of esophageal squamous cell carcinoma according to claim 1, characterized in that: The other clinical characteristics also include: gender, whether the diet is regular; the unhealthy eating habit score and the other clinical characteristics are input into the absolute risk prediction model of esophageal squamous cell carcinoma to obtain the absolute risk of the subject suffering from esophageal squamous cell carcinoma, wherein the absolute risk prediction model of esophageal squamous cell carcinoma is an absolute risk prediction model constructed based on the unhealthy eating habit score of the training set and the other clinical characteristics.

4. The method for predicting the absolute risk of esophageal squamous cell carcinoma according to claim 1, characterized in that: The other clinical characteristics also include: BMI, family history of esophageal cancer; the unhealthy eating habits score and the other clinical characteristics are input into the esophageal squamous cell carcinoma absolute risk prediction model to obtain the absolute risk of the subject suffering from esophageal squamous cell carcinoma, wherein the esophageal squamous cell carcinoma absolute risk prediction model is an absolute risk prediction model constructed based on the unhealthy eating habits score of the training set and the other clinical characteristics; Optionally, whether the diet is regular is classified as "yes" or "no"; Optionally, the BMI is divided into two categories based on a division threshold; Optionally, the family history of esophageal cancer is divided into three categories based on the number of cases of esophageal squamous cell carcinoma in direct blood relatives within 3 generations, namely, the number of cases is equal to 0, the number of cases is equal to 1, and the number of cases is greater than 1.

5. The method for predicting the absolute risk of esophageal squamous cell carcinoma according to claim 1, characterized in that: The absolute risk prediction model outputs the absolute risk of the subject suffering from esophageal squamous cell carcinoma at different times, and the different times include one or more of the following: six months later, one year later, three years later, five years later, and time later; Optionally, the unhealthy eating habits score, the other clinical characteristics, and the predicted years are input into an absolute risk prediction model for esophageal squamous cell carcinoma to obtain the absolute risk of the subject developing esophageal squamous cell carcinoma in the predicted years.

6. The method for predicting the absolute risk of esophageal squamous cell carcinoma according to claim 1, characterized in that: Methods for constructing absolute risk prediction models based on unhealthy eating habits scores and other clinical characteristics of the training set include: Step 1: Obtain the unhealthy eating habits score and other clinical characteristics, overall incidence, age-specific incidence, population-attributable risk, and age-specific all-cause mortality excluding esophageal squamous cell carcinoma of the training set; Step 2: derive the relative risk based on the unhealthy eating habits score and the other clinical characteristics and overall incidence rate. Step 3: derive the baseline hazard rate based on the age-specific incidence rate and population attributable risk. Step 3: Obtain the absolute risk prediction model based on the baseline hazard rate, relative risk, and competing risk of death; Optionally, the baseline hazard rate is expressed as: h1(t)=h0(t){1-PAR(t)%} Where h1(t) represents the baseline hazard rate; h0(t) represents the age-specific incidence of esophageal cancer; PAR(t) represents the population attributable risk; Optionally, the absolute risk prediction model is expressed as: Among them, AR i (a, a+τ) represents the absolute risk of esophageal squamous cell carcinoma in the age range [a, a+τ] in the i-th risk group; h1(t) represents the baseline hazard rate, h2(t) represents the age-specific all-cause mortality rate excluding esophageal squamous cell carcinoma; r i represents the relative risk of the ith risk group; S i (t-1) represents the survival risk of the person at age t-1 in the i-th risk group; S i (0)=1.

7. The method for predicting the absolute risk of esophageal squamous cell carcinoma according to claim 6, characterized in that: The steps of inputting the unhealthy eating habits score and the other clinical characteristics into the esophageal squamous cell carcinoma absolute risk prediction model to obtain the absolute risk of the subject suffering from esophageal squamous cell carcinoma are as follows: Step 1: determining an applicable absolute risk prediction model for esophageal squamous cell carcinoma based on the unhealthy eating habit score and the other clinical characteristics; Step 2: Determine the baseline risk and all-cause mortality rate corresponding to the age of the subject based on the age of the subject, and determine the risk group to which the subject belongs, the relative risk of the risk group, and the survival risk of the subject at age t-1 in the risk group based on the unhealthy eating habit score and other clinical characteristics of the subject; Step 3: Calculate the absolute risk based on the baseline risk corresponding to the age of the subject, the all-cause mortality rate, the risk group to which he belongs, the relative risk of the risk group, and the survival risk of the risk group at age t-1, where τ is six months, one year, three years, five years, and ten years later, respectively.

8. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images