Machine Learning-Based Nomogram for Predicting Endometrial Lesions after Tamoxifen Therapy in Breast Cancer Patients

doi:10.21203/rs.3.rs-4715381/v1

Download PDF

Article

Machine Learning-Based Nomogram for Predicting Endometrial Lesions after Tamoxifen Therapy in Breast Cancer Patients

https://doi.org/10.21203/rs.3.rs-4715381/v1

This work is licensed under a CC BY 4.0 License

You are reading this latest preprint version

Objective

Endometrial lesions is a frequent complication following breast cancer, and current diagnostic tools have limitations. This study aims to develop a machine learning-based nomogram graph prediction model for the early detection of endometrial lesions in patients. The model is intended to provide risk assessment and facilitate personalized treatment strategies for premenopausal breast cancer patients.

Method

A retrospective study was conducted on 224 patients who underwent diagnostic curettage post-tamoxifen (TAM) therapy between November 2012 and November 2023. These patients exhibited signs of endometrial abnormalities or symptoms such as colporrhagia. Clinical data were collected and analyzed using R software version 4.3.2 to identify factors influencing the occurrence of endometrial lesions and to evaluate their predictive values. Three machine learning methods were employed to develop a risk prediction model, and the performances of these models were compared. The best-performing model was selected to construct a nomogram of endometrial lesions. Internal validation was conducted using the bootstrap method, and the model’s accuracy and fit were assessed using the concordance index (C-index) and calibration curves.

Results

Independent risk factors for endometrial lesions included ultrasound characteristics, duration of TAM therapy, presence of colporrhagia, and endometrial thickness (P < 0.05). Among the machine learning methods compared, the LASSO regression integrated with a multifactorial logistic regression model demonstrated strong performance, with a concordance index (C-index) of 0.874 and effective calibration (mean absolute error of conformity: 0.014). This model achieved an accuracy of 0.853 and a precision of 0.917, with a training set AUC of 0.874 (95% CI: 0.794–0.831) and a test set AUC of 0.891 (95% CI: 0.777-1.000), closely matching the predicted risk to the actual observed risk.

Conclusion

The developed prediction model effectively assesses the likelihood of endometrial lesions in premenopausal breast cancer patients. This model offers a theoretical foundation for improving clinical predictions and devising tailored treatment strategies for this patient group.

breast cancer

tamoxifen

endometrial lesions

nomogram

prediction model

Breast cancer is one of the most prevalent cancers among women worldwide, as reported by the World Health Organization’s International Agency for Research on Cancer (IARC) in 2024, with approximately 310,000 new cases annually¹. In Asia, breast cancer shows a bimodal distribution, peaking first among women in their late 40s to early 50s, with 60% of these patients being premenopausal². With aggressive treatment, the five-year survival rate exceeds 90%, and the ten-year survival rate surpasses 85%. Approximately 75% of new breast cancer cases are hormone receptor-positive³. Endocrine therapy, primarily involving Tamoxifen (TAM), a selective estrogen receptor modulator, is often required for five years or more following surgical chemotherapy in premenopausal breast cancer patients⁴. Due to the local receptor imbalance in endometrial tissues, TAM exerts an estrogen-like effect on the endometrium, leading to endometrial proliferation and glandular hypertrophy. This frequently results in abnormal glandular hyperplasia or structural changes, causing pathologies such as endometrial hyperplasia, polyps, endometrial cancer, and sarcoma⁵.

Studies indicate that the incidence of endometrial thickening during endocrine therapy ranges from 5–30%, endometrial polyps from 26–60%, and endometrial cancer from approximately 0.8–8%⁶⁷. These rates are 2–7 times higher than those in the general population⁵. Additionally, Asian populations face a 2.87-fold increased risk of endometrial cancer compared to European and American groups, with about 20% of cases occurring in premenopausal women³. Several risk factors for breast cancer and endometrial carcinoma (EC) have been identified, making increased awareness essential for reducing disease burden. Obesity, hypertension, and diabetes are recognized risk factors for both EC and breast cancer. Colporrhagia often serves as an early symptom of endometrial cancer. Consequently, identifying risk factors for endometrial lesions in younger breast cancer patients is crucial for enhancing early detection, diagnosis, and intervention.

Currently, no screening method can accurately predict endometrial lesions; ultrasound remains the preferred screening tool and definitive diagnosis is achieved through endometrial biopsy. With the increased use of TAM and longer life expectancy among breast cancer survivors, the risk of endometrial lesions is rising. Repeated ultrasounds and endometrial biopsies, commonly employed to determine the continuation of endocrine therapy, are invasive and pose significant risks of complications. These procedures can adversely affect patients’ mental well-being and quality of life, potentially reducing their willingness to continue clinic visits and adhere to treatment regimens⁸. This may lead to the discontinuation of the medication or even tumor recurrence. Addressing the current research trends, the early prediction of endometrial lesions remains an urgent challenge to overcome.

Although many current clinical prediction models rely primarily on simple logistic regression, the advent of artificial intelligence and machine learning has improved prediction accuracy, particularly in medical oncology and surgery. Given the limited use of machine learning for predicting endometrial lesions in premenopausal breast cancer patients, this study aims to identify risk factors for endometrial lesions and develop machine learning models to forecast its likelihood. This approach seeks to enhance preoperative risk assessment and provide a more tailored and theoretically informed basis for endocrine therapy in these patients.

2.1 Dataset

This study retrospectively collected data from patients treated with tamoxifen (TAM) following breast cancer surgery who underwent diagnostic curettage at the gynecology department of Mianyang Central Hospital between 2012 and 2023. The ethical approval and participation consent followed the Helsinki Declaration guidelines. The inclusion criteria were: (1) premenopausal status at the time of breast cancer diagnosis; (2) before breast cancer, Vaginal ultrasound were normal; (3) postoperative treatment with TAM at a dosage of 20 mg/day; and (4) complete clinical case data and follow-up records. Exclusion criteria included: (1) patients with a history of other cancers; (2) patients with advanced or recurrent breast cancer at initial diagnosis; (3) serious underlying diseases affecting patient survival.

Patients meeting these criteria were included in the study cohort. Using a nested case-control design, patients who developed endometrial lesions were identified as the case group, while those who did not develop lesions served as the control group. Collected clinical data included age, age at breast cancer diagnosis, family history of cancer, metastasis, number of deliveries and pregnancies, weight, height, body mass index (BMI), age at menarche, breastfeeding history, endometrial thickness, presence of colporrhagia, duration of TAM therapy, previous use of sex hormones, smoking history, hypertension, diabetes mellitus, hyperlipidemia, history of fibroid tumors, endometriosis, benign breast lesions, previous endometrial lesions, ultrasound features, and endometrial biopsy results.

2.2 Development and validation of prediction model

This study followed the TRIPOD guidelines⁹. The data were initially cleaned and subjected to dimensionality reduction. The data were initially cleaned and subjected to dimensionality reduction. Univariate and multivariate analyses were performed to identify statistically significant factors between groups and to determine the optimal cut-off value for endometrial thickness. Three machine learning methods were employed to screen the data for high-risk factors: Least Absolute Shrinkage and Selection Operator(LASSO) regression combined with multifactor logistic regression, decision tree, and random forest.

The 224 patients were randomly divided into a training set (85%) and a test set (15%). The machine learning model was trained on the training set and validated on the test set. Model performance was assessed using the receiver operating characteristic (ROC) curve and accuracy metrics. The optimal model was selected and internally validated using the Bootstrap resampling method (1,000 iterations). The final model was presented as a nomogram graph nomogram, with the concordance index (C-index) and decision curve analysis (DCA) used to evaluate its clinical application value.

2.3 Statistical Methods.

Data analysis and graphing were performed using SPSS and R version 4.3.2 software. All data were statistically described: normally distributed measurements were expressed as mean ± standard deviation (Χ̅± s) and compared using the t-test; non-normally distributed measurements were expressed as median [P25, P75] and compared using the rank-sum test. Categorical variables were described as constituent ratios and compared using the chi-square test or Fisher's exact test. Statistical significance was set at p < 0.05.

3.1 Patient characteristics and endometrial biopsy results

A total of 224 premenopausal patients undergoing postoperative endocrine therapy for breast cancer were included in this study. Endometrial biopsies confirmed endometrial lesions in 98 cases, while the remaining 126 cases served as the control group, resulting in a prevalence rate of 43.75% (98/224). Detailed patient characteristics are presented in Table 1.

Table 1

Pathological characteristics of the endometrium [cases (%)]
physiology	control group(n = 126)	Lesion group(n = 98)
normal	126 (100)	0 (0)
Endometrial polyp	0 (0)	72 (73.5)
Endometrial hyperplasia without atypia	0 (0)	15 (15.3)
Endometrial polyp with EH	0 (0)	6 (6.1)
Atypical hyperplasia	0 (0)	2 (2)
Atypical polypoid adenomyoma	0 (0)	1 (1)
Endometrioid adenocarcinoma	0 (0)	2 (2)

In the lesion group, 39 cases (39.8%) had a medication duration of 2 years, 12 cases (12.2%) had a medication duration of 2–5 years, and 47 cases (48.0%) had a medication duration of more than 5 years. The mean endometrial thickness in the case group was 1.20 cm, while it was 0.76 cm in the control group, as shown in Table 2.

Table 2

Baseline characteristics of premenopausal breast cancer patients [cases (%)]
	control group	Lesion group	P-value
	126	98
age(year)	51.68 ± 5.30	50.97 ± 5.28	0.318
Age at diagnosis of breast cancer(year)	43.91 ± 4.39	43.15 ± 5.13	0.234
gravidity	2.73 ± 1.56	2.74 ± 1.59	0.945
parity	1.00[1.00,1.00]	1.00[1.00,2.00]	0.342
menophania(year)	13.00[12.25,14.00]	13.00[12.00,14.00]	0.679
weight(kg)	57.63 ± 6.76	56.85 ± 7.54	0.416
height(m)	1.57 ± 0.05	1.57 ± 0.05	0.589
Endometrial thickness(cm)	0.76 ± 0.37	1.20 ± 0.53	< 0.001
BMI(kg/m2)	23.39 ± 2.60	23.16 ± 2.78	0.533
Ultrasonic characteristics			< 0.001
Normal	92(73.0)	28(28.6)
Uneven echo	32(25.4)	31(31.6)
Uterine cavity occupation	2(1.6)	35(35.7)
Endometrium heterogeneity combined with uterine cavity occupation	0(0.0)	4(4.1)
duration of tamoxifen therapy			0.002
Within 2 years	70(55.6)	39(39.8)
2–5 years	24(19.0)	12(12.2)
More than 5 years	32(25.4)	47(48.0)
metastatic			0.061
yes	41(32.5)	20(20.4)
no	85(67.5)	78(80.6)
Family history of cancer			0.302
yes	18(14.3)	20(20.4)
no	108(85.7)	78(80.6)
breastfeeding			0.455
yes	121(96.0)	91(92.9)
no	5(4.0)	7(7.1)
diabetes			0.463
yes	4(3.2)	6(6.1)
no	122(96.8)	92(93.9)
hypertension			0.496
yes	12(9.5)	6(6.1)
no	114(90.5)	92(93.9)
smoking			1
yes	1(0.8)	1(1.0)
no	125(99.2)	97(99.0)
hyperlipemia			0.256
yes	16(12.7)	7(7.1)
no	110(87.3)	91(92.9)
colporrhagia			0.001
yes	30(23.8)	44(44.9)
no	96(76.2)	54(55.1)
hormoneuse			0.193
yes	7(5.6)	11(11.2)
no	119(94.4)	87(88.8)
leiomyoma			0.092
yes	44(34.9)	46(46.9)
no	82(65.1)	52(53.1)
endometriosis			0.826
yes	1(0.8)	2(2.0)
no	125(99.2)	96(98.0)
endometrialdisease			0.008
yes	3(2.4)	12(12.2)
no	123(97.6)	86(87.8)
benignlesion			1
yes	47(37.3)	36(36.7)
no	79(62.7)	62(63.3)
BMI group			0.843
underweight	1(0.8)	2(2.0)
Normal	89(70.6)	66(67.3)
overweight	32(25.4)	27(27.6)
obesity	4(3.2)	3(3.1)
Note: a. BMI refers to body mass index, calculation formula: BMI(kg/m2) = weight(kg)/(height×height(m2)), group: underweight < 18.5, normal:18.5–23.9, overweight:24-27.9, obesity:≥28; b. Data were expressed as (s) or n (%) or M (P25, P75), p < 0.05 statistically significant; nonnorm refers to data being non-normally distributed.

3.2 Correlation of clinical factors on endometrial lesions

The analysis revealed no statistically significant differences between the groups for age, age at diagnosis, presence of metastasis, hypertension, diabetes mellitus, history of endometriosis, benign breast lesions, age at menarche, number of pregnancies, number of deliveries, smoking, hyperlipidemia, history of breastfeeding, family history of cancer, pathological type of breast cancer, height, weight, BMI, hormone use, history of uterine fibroids, and previous benign breast lesions (P > 0.05). However, significant differences were found between the groups for ultrasound characteristics, duration of TAM therapy, presence of colporrhagia, previous endometrial lesions, and endometrial thickness (P < 0.05). The case group showed significantly higher rates of colporrhagia, greater endometrial thickness, and longer duration of TAM therapy compared to the control group.

The mean endometrial thickness was greater in the case group (1.20 ± 0.53 cm) compared to the control group (0.76 ± 0.37 cm, P < 0.001), and a higher proportion of colporrhagia symptoms was observed in the case group (44.9% vs. 23.8%, P < 0.001). The area under the ROC curves (AUC) for each factor was as follows: ultrasound characteristics (0.770), endometrial thickness (0.749), duration of TAM (0.608), colporrhagia (0.605), and history of leiomyoma (0.560). The ROC curve for endometrial thickness had the largest Youden index with a cut-off value of 0.438, a sensitivity of 71.4%, and a specificity of 72.4%, corresponding to an optimal ultrasonographic diagnostic threshold of 0.825 cm for abnormal endometrium. Detailed results are presented in Table 2 and illustrated in Figs. 1.

The heat map of correlation revealed many linear correlations between variables(Figs. 2). To minimize interference, clinical factors were included as predictors input machine learning model.

4.1 LASSO Regression with Logistic Regression Algorithm

In the LASSO regression to select the most predictive features. A 10-fold cross-validation was performed, resulting in the selection of four variables as independent predictors, with endometrial lesions occurrence as the dependent variable. A multifactorial binary logistic regression analysis showed that previous endometrial lesions was not statistically significant (P > 0.05). However, ultrasound characteristics, duration of TAM therapy, presence of colporrhagia symptoms, and endometrial thickness were identified as independent risk factors for endometrial lesions (P < 0.05). These factors were included in the multifactorial logistic regression model. The dataset was split into a training set (n = 190) and a validation set (n = 34) in an 8.5:1.5 ratio. After 1,000 Bootstrap self-samplings for internal validation, the results showed a C-index of 0.874, indicating excellent model discrimination. The model demonstrated an accuracy of 0.853, a precision of 0.917, with a training set AUC of 0.874 (95% CI: 0.794–0.831), and a test set AUC of 0.891 (95% CI: 0.777-1.000). Detailed results are shown in Figs. 3, 6a, and Table 3.

Table 3

Multifactorial Logistic Regression Analysis of Independent Risk Factors Based on Lasso Regression
	Coef	S.E.	Wald Z	Df	P-value	OR	95%CI
Constant	-3.851	0.637	-6.04	7	< 0.001	-	-
colporrhagia	1.385	0.422	3.28	7	0.001	3.996	1.746–9.145
Endometrial thickness	1.887	0.457	4.13	7	< 0.001	3.747	2.002–7.014
duration of tamoxifen therapy				7
2-5years: Within 2 years	0.35	0.56	0.63	-	0.532	1.419	0.474–4.253
More than 5 years: Within 2 years	0.946	0.432	2.19	-	0.029	2.575	1.104–6.006
Ultrasonic characteristics				7
Uneven echo	1.491	0.434	3.43	-	0.001	4.44	1.897–10.394
Uterine cavity occupation	3.349	0.802	4.17	-	< 0.001	28.475	5.908–137.250
Endometrium heterogeneity combined with uterine cavity occupation	7.192	21.794	0.33	-	0.741	1328.2	3.733E-16-4.726E + 21
Note: OR: ratio of ratios; CI: confidence interval.

4.2 Decision Tree Algorithm

A prediction model for endometrial lesions was constructed using a decision tree. The decision tree was built through recursive partitioning and pruned to avoid overfitting, with the cp value adjusted to 0.036 to improve the model's generalization ability. The average accuracy of the training set was 0.800, with an AUC of 0.888 (95% CI: 0.840–0.937). The average accuracy of the test set was 0.740 (95% CI: 0.533–0.947), with an AUC of 0.800 (95% CI: 0.640–0.960), demonstrating good prediction performance. Detailed result are illustrated in Figs. 4,6b.

4.3 Random Forest Algorithm

A prediction model for endometrial lesions was also constructed using a random forest approach. Five hundred trees were established, and as the number of trees increased, the out-of-bag (OOB) error rate decreased and eventually stabilized, indicating a relatively stable model. Factors were ranked in order of importance, with ultrasound characteristics, endometrial thickness, duration of TAM therapy, and colporrhagia symptoms being the most influential. The OOB error rate for the random forest training set was approximately 23.68%, with an average accuracy of 100% (95% CI: 0.981-1.000), and an AUC of 1.000 (95% CI: 1.000–1.000). The test set had an average accuracy of 0.735 (95% CI: 0.556–0.871), with an AUC of 0.784 (95% CI: 0.632–0.867), indicating good prediction performance. Detailed results are shown in Figs. 5, 6c.

A comparison of the accuracy and AUC of the models determined that the LASSO regression combined with multifactorial logistic regression (LR) was the optimal model (see Fig. 6, Table 4).

Table 4

Comparison of models
model	accuracy	AUC	sensitivity	specificity
LR	0.853	0.891	1.000	0.733
Decision tree	0.740	0.800	0.947	0.667
Random forest	0.735	0.784	0.632	0.867

Consequently, a nomogram graph model was constructed based on this combination for predicting the occurrence of endometrial lesions (see Figs. 7).For example, a female patient with more than five years of TAM therapy, colporrhagia, and an endometrial thickness of 1.6 cm would have corresponding scores of approximately 22.5, 17.5, and 60, respectively, for a total score of 100. This total score corresponds to an estimated probability of developing endometrial lesions of 80%. The application of the nomogram graph provides a clear and concise explanation of the model's individualized prediction for the patient.

The calibration curve suggests that the mean absolute error between predicted and actual values is 0.014, indicating that the predicted risk closely aligns with the actual risk. The Decision Curve Analysis (DCA) curve evaluates the predictive model and the concordance diagnostic test, calculating the clinical "net benefit" of the predictive model. The results show that using a column chart for predictions is valuable within a threshold probability range of 5–90% (see Figs. 8, 9).

In this study, we developed and evaluated three machine learning prediction models to accurately predict the risk of endometrial lesions in premenopausal breast cancer patients undergoing TAM therapy. The best predictive performance was achieved by LASSO regression combined with logistic regression, which demonstrated an accuracy of 0.853 and precision of 0.917 using four easily accessible patient features. This model had high diagnostic performance, with an AUC of 0.891 (95% CI: 0.777-1.000). The findings confirm that ultrasonographic features, duration of TAM administration, endometrial thickness, and colporrhagia symptoms are clear predictors of endometrial lesions.

A national retrospective study of 102 breast cancer patients treated with TAM postoperatively found that the duration of TAM use and symptoms of abnormal colporrhagia were significant risk factors for developing endometrial lesions, consistent with our study. Additionally, a large body of epidemiologic evidence suggests that TAM is associated with an increased risk of endometrial lesions, with the risk of developing endometrial carcinoma (EC) being 1.5–6.9 times higher in a dose- and time-dependent manner ¹⁰. The ATLAS study found that patients using TAM for 10 years had a higher cumulative risk of endometrial cancer compared to those using it for 5 years⁴. However, only 10% of the patients in the ATLAS study were premenopausal, which may limit the generalizability of these findings.

Our study showed that the duration of TAM was an independent risk factor for developing endometrial lesions, aligning with previous studies¹¹. However, the cumulative dose of the drug was not clarified. Choi et al. demonstrated that benign endometrial disease incidence was highest in subjects under 40 years of age treated with TAM, significantly increasing the risk of endometrial cancer¹². Similarly, Liu et al. found that the standardized incidence of endometrial cancer was elevated in breast cancer patients diagnosed after the age of 40¹³. Younger patients treated with TAM have a higher risk of subsequent endometrial cancer, particularly those aged 40-49¹⁴. Bergman’s study also indicated that endometrial cancers caused by TAM were more malignant and aggressive¹¹. Some studies have shown no correlation between TAM and endometrial lesions. For instance, Takashima¹⁵ found no significant association between shorter TAM therapy duration and endometrial lesions. Chiofalo and Chu also reported no correlation between TAM and endometrial cancer development ¹⁴¹⁶¹⁷.

In our study, ultrasound characteristics were the most important factor in predicting endometrial lesions, consistent with previous studies. Ultrasound is the preferred monitoring tool, and abnormal occupancy or heterogeneous endometrial echogenicity on ultrasound increases the likelihood of developing endometrial lesions and necessitating endometrial biopsy. Previous NSABP studies, which included mainly postmenopausal women, suggested no additional monitoring for asymptomatic women to avoid unnecessary invasive procedures. However, this may underestimate the risk in premenopausal patients ¹⁸¹⁹. Young breast cancer patients undergoing prolonged TAM therapy require more attention. Endometrial screening and evaluation should be performed before TAM treatment, with regular transvaginal ultrasound monitoring to detect and manage endometrial lesions early.

Endometrial thickness was also a significant factor in endometrial lesion occurrence, with the optimal diagnostic threshold being 0.825 cm, similar to previous findings by Zhouqi and Burkart ²²⁰. Since TAM stimulates endometrial gland hypertrophy, leading to pharmacological thickening, establishing a TAM-related endometrial thickness threshold in young breast cancer patients is challenging.

Colporrhagia was identified as an important risk factor. Patients with colporrhagia are more likely to develop endometrial lesions, and this symptom serves as a warning for early hospital visits, improving detection rates. However, Maria et al. found no difference in abnormal colporrhagia between the case group and patients with normal endometrium, highlighting the need for further research ²¹.

This study demonstrates that machine learning approaches can achieve high accuracy in predicting endometrial lesions. Most current clinical prediction models rely on linear relationships between variables, often resulting in poor predictive ability. Machine learning applications in medicine are becoming widespread, offering effective tools for clinical diagnosis and prediction. Our study visualized and predicted endometrial lesions incidence using machine learning, providing valuable insights for gynecologists evaluating premenopausal breast cancer patients during endocrine therapy. The LASSO regression combined with multifactorial logistic regression prevented overfitting, with validation results showing an average absolute error of 0.014 between predicted and actual values, suggesting clinical diagnostic significance for endometrial lesion prognosis.

However, this study has limitations. It was a single-center retrospective study with limited data collection and a small sample size, which could introduce selection and recall biases. More objective indicators and larger sample sizes are needed to clarify endometrial thickness criteria. The model also lacks external validation. Future studies should incorporate comprehensive factors and utilize joint neural network prediction models to provide a basis for individualized endocrine therapy treatment in premenopausal breast cancer patients.

In conclusion, our study identified ultrasound characteristics, TAM duration, colporrhagia, and endometrial thickness as independent risk factors for endometrial lesions in premenopausal breast cancer patients. We developed a predictive risk model using machine learning, with LASSO regression combined with multifactorial logistic regression showing the best performance. Regular monitoring of these factors can aid in early detection and reduction of endometrial lesions, providing a basis for evaluating endocrine therapy, endometrial monitoring during treatment, and individualized therapeutic strategies for breast cancer patients.

TAM Tamoxifen

EC endometrial carcinoma

IARC the World Health Organization’s International Agency for Research on Cancer

BMI body mass index

LASSO Least Absolute Shrinkage and Selection Operator

ROC curve Reiver Operating Characteristic Curve

C-index the Consistency index

DCA decision curve analysis

AUC Area Under Curve

OOB error out-of-bag error rate

Ethics approval and consent to participate

This study was approved by the Ethics Committee of Mianyang Central Hospital (No.

S20240332-01). Due to the retrospective nature of the study, IRB waived the need of obtaining informed consent.

Author contributions

All authors were involved in writing, all authors were involved in developing the methodology employed in the project, reviewing and editing the final draft.

Conflict of interest statement

None declared.

Funding information

No.

Data availability statement

All data are fully available without restriction. The datasets used and/or analysed during the current study available from the corresponding author on reasonable request.

Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA Cancer J Clin. 2024;74(1):12-49. doi:10.3322/caac.21820
ZHOU Qi, ZHANG Shiqian, WANG Xiaohong, et al. Guidelines for the management of endometriosis associated with adjuvant endocrine therapy for breast cancer (2021 edition)[J]. Chinese Journal of Practical Gynaology and Obstetrics, 2021, 37(8): 815-820. doi:10.19538/j.fk2021080108
Ghanavati M, Khorshidi Y, Shadnoush M, et al. Tamoxifen use and risk of endometrial cancer in breast cancer patients: A systematic review and dose-response meta-analysis. Cancer Rep (Hoboken). 2023;6(4):e1806. doi:10.1002/cnr2.1806
Christina Davies, Hongchao Pan, Richard Peto. 10 vs 5 years of adjuvant tamoxifen: exclusion of 1/402 centres in ATLAS. The Lancet. 2017;389(10082):1884. doi:10.1016/S0140-6736(17)31003-6
Emons G, Mustea A, Tempfer C. Tamoxifen and Endometrial Cancer: A Janus-Headed Drug. Cancers (Basel). 2020;12(9):2535. doi:10.3390/cancers12092535
Yan G, Li Y, Du Y, Ma X, Xie Y, Zeng X. Survival nomogram for endometrial cancer with lung metastasis: A SEER database analysis. Front Oncol. 2022;12:978140. doi:10.3389/fonc.2022.978140
TIAN Wenyan, ZHANG Huiying, XUE Fengxia. Interpretation of the Chinese expert consensus on the diagnosis and treatment of endometrial polyps (2022 edition)[J]. Journal of Obstetrics and Gynaology, 2023, 39(1): 29-33.
Park C, Heo JH, Mehta S, Han S, Spencer JC. Adherence to Adjuvant Endocrine Therapy and Survival Among Older Women with Early-Stage Hormone Receptor-Positive Breast Cancer. Clin Drug Investig. 2023;43(3):167-176. doi:10.1007/s40261-023-01247-w
Collins GS, Reitsma JB, Altman DG, Moons KGM. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ. 2015;350:g7594. doi:10.1136/bmj.g7594
Wijayabahu AT, Egan KM, Yaghjyan L. Uterine cancer in breast cancer survivors: a systematic review. Breast Cancer Res Treat. 2020;180(1):1-19. doi:10.1007/s10549-019-05516-1
Bergman L, Beelen ML, Gallee MP, Hollema H, Benraadt J, van Leeuwen FE. Risk and prognosis of endometrial cancer after tamoxifen for breast cancer. Comprehensive Cancer Centres’ ALERT Group. Assessment of Liver and Endometrial cancer Risk following Tamoxifen. Lancet. 2000;356(9233):881-887. doi:10.1016/s0140-6736(00)02677-5
Choi S, Lee YJ, Jeong JH, et al. Risk of Endometrial Cancer and Frequencies of Invasive Endometrial Procedures in Young Breast Cancer Survivors Treated With Tamoxifen: A Nationwide Study. Front Oncol. 2021;11:636378. doi:10.3389/fonc.2021.636378
Liu J, Jiang W, Mao K, et al. Elevated risks of subsequent endometrial cancer development among breast cancer survivors with different hormone receptor status: a SEER analysis. Breast Cancer Res Treat. 2015;150(2):439-445. doi:10.1007/s10549-015-3315-5
Chu SC, Hsieh CJ, Wang TF, Hong MK, Chu TY. Younger tamoxifen-treated breast cancer patients also had higher risk of endometrial cancer and the risk could be reduced by sequenced aromatase inhibitor use: A population-based study in Taiwan. Ci Ji Yi Xue Za Zhi. 2020;32(2):175-180. doi:10.4103/tcmj.tcmj_17_19
Matsuyama Y, Tominaga T, Nomura Y, et al. Second cancers after adjuvant tamoxifen therapy for breast cancer in Japan. Ann Oncol. 2000;11(12):1537-1543. doi:10.1093/oxfordjournals.annonc.a010406
Chiofalo B, Mazzon I, Di Angelo Antonio S, et al. Hysteroscopic Evaluation of Endometrial Changes in Breast Cancer Women with or without Hormone Therapies: Results from a Large Multicenter Cohort Study. J Minim Invasive Gynecol. 2020;27(4):832-839. doi:10.1016/j.jmig.2019.08.007
AlZaabi A, AlAmri H, ALAjmi G, et al. Endometrial Surveillance in Tamoxifen and Letrozole Treated Breast Cancer Patients. Cureus. 2021;13(11):e20030. doi:10.7759/cureus.20030
Fisher B, Costantino JP, Redmond CK, Fisher ER, Wickerham DL, Cronin WM. Endometrial cancer in tamoxifen-treated breast cancer patients: findings from the National Surgical Adjuvant Breast and Bowel Project (NSABP) B-14. J Natl Cancer Inst. 1994;86(7):527-537. doi:10.1093/jnci/86.7.527
Fisher B, Costantino JP, Wickerham DL, et al. Tamoxifen for prevention of breast cancer: report of the National Surgical Adjuvant Breast and Bowel Project P-1 Study. J Natl Cancer Inst. 1998;90(18):1371-1388. doi:10.1093/jnci/90.18.1371
Burkart C, Wight E, Pók J, et al. [Ultrasound endometrium follow-up during tamoxifen treatment: Really not reliable or useful after all?]. Ultraschall Med. 2001;22(3):136-142. doi:10.1055/s-2001-15243
Jeon J, Kim SE, Lee DY, Choi D. Factors associated with endometrial pathology during tamoxifen therapy in women with breast cancer: a retrospective analysis of 821 biopsies. Breast Cancer Res Treat. 2020;179(1):125-130. doi:10.1007/s10549-019-05448-w

No competing interests reported.

Download PDF

Reviews received at journal
12 Aug, 2024
Reviews received at journal
12 Aug, 2024
Reviewers agreed at journal
12 Aug, 2024
Reviewers agreed at journal
12 Aug, 2024
Reviewers invited by journal
12 Aug, 2024
Editor assigned by journal
12 Aug, 2024
Editor invited by journal
15 Jul, 2024
Submission checks completed at journal
13 Jul, 2024
First submitted to journal
10 Jul, 2024

You are reading this latest preprint version

Machine Learning-Based Nomogram for Predicting Endometrial Lesions after Tamoxifen Therapy in Breast Cancer Patients

Status:

Version 1

Abstract

Figures

1 Introduction

2 Methods

2.1 Dataset

2.2 Development and validation of prediction model

2.3 Statistical Methods.

3 Results

3.1 Patient characteristics and endometrial biopsy results

3.2 Correlation of clinical factors on endometrial lesions

4 Machine Learning

4.1 LASSO Regression with Logistic Regression Algorithm

4.2 Decision Tree Algorithm

4.3 Random Forest Algorithm

5 Model comparison and visualization

6 Discussion

Abbreviations

Declarations

References

Additional Declarations

Status:

Version 1