Multidimensional Machine Learning Personalized Prognostic Model in an Early Invasive Breast Cancer Population-Based Cohort in China: Algorithm Validation Study

Luo, Ting; Deng, Ling; Liu, Pei; Hu, Kejia; Lü, Donghao; Zheng, Dan; Luo, Chunying; Xie, Yuxin; Li, Jiayuan; He, Ping; Pu, Tianjie; Ye, Feng; Bu, Hong; Fu, Bo; Zheng, Hong

doi:10.2196/19069

Cited by 11 publications

(14 citation statements)

References 44 publications

(59 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models have been validated by external data set and are commonly used in the United States and Western Europe. However, several external validations that were made in Asian countries revealed a less-than-optimal predictive ability [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

The Application and Comparison of Machine Learning Models for the Prediction of Breast Cancer Prognosis: Retrospective Cohort Study

Xiao¹,

Mo²,

Wang³

et al. 2022

JMIR Med Inform

View full text Add to dashboard Cite

Background Over the recent years, machine learning methods have been increasingly explored in cancer prognosis because of the appearance of improved machine learning algorithms. These algorithms can use censored data for modeling, such as support vector machines for survival analysis and random survival forest (RSF). However, it is still debated whether traditional (Cox proportional hazard regression) or machine learning-based prognostic models have better predictive performance. Objective This study aimed to compare the performance of breast cancer prognostic prediction models based on machine learning and Cox regression. Methods This retrospective cohort study included all patients diagnosed with breast cancer and subsequently hospitalized in Fudan University Shanghai Cancer Center between January 1, 2008, and December 31, 2016. After all exclusions, a total of 22,176 cases with 21 features were eligible for model development. The data set was randomly split into a training set (15,523 cases, 70%) and a test set (6653 cases, 30%) for developing 4 models and predicting the overall survival of patients diagnosed with breast cancer. The discriminative ability of models was evaluated by the concordance index (C-index), the time-dependent area under the curve, and D-index; the calibration ability of models was evaluated by the Brier score. Results The RSF model revealed the best discriminative performance among the 4 models with 3-year, 5-year, and 10-year time-dependent area under the curve of 0.857, 0.838, and 0.781, a D-index of 7.643 (95% CI 6.542, 8.930) and a C-index of 0.827 (95% CI 0.809, 0.845). The statistical difference of the C-index was tested, and the RSF model significantly outperformed the Cox-EN (elastic net) model (C-index 0.816, 95% CI 0.796, 0.836; P=.01), the Cox model (C-index 0.814, 95% CI 0.794, 0.835; P=.003), and the support vector machine model (C-index 0.812, 95% CI 0.793, 0.832; P<.001). The 4 models’ 3-year, 5-year, and 10-year Brier scores were very close, ranging from 0.027 to 0.094 and less than 0.1, which meant all models had good calibration. In the context of feature importance, elastic net and RSF both indicated that TNM staging, neoadjuvant therapy, number of lymph node metastases, age, and tumor diameter were the top 5 important features for predicting the prognosis of breast cancer. A final online tool was developed to predict the overall survival of patients with breast cancer. Conclusions The RSF model slightly outperformed the other models on discriminative ability, revealing the potential of the RSF method as an effective approach to building prognostic prediction models in the context of survival analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

The Application and Comparison of Machine Learning Models for the Prediction of Breast Cancer Prognosis: Retrospective Cohort Study

Xiao¹,

Mo²,

Wang³

et al. 2022

JMIR Med Inform

View full text Add to dashboard Cite

show abstract

“…We enrolled patients with MBC who were admitted to West China Hospital from July 1, 2012 to October 30, 2020 and were registered in the Breast Cancer Information Management System (BCIMS). The BCIMS prospectively records patient clinical and pathological characteristics, medical history, diagnoses, laboratory results, treatments, and follow-up data ( 14 ).…”

Section: Methodsmentioning

confidence: 99%

A Retrospective Analysis of the Effect of Irinotecan-Based Regimens in Patients With Metastatic Breast Cancer Previously Treated With Anthracyclines and Taxanes

Suo

Zheng

et al. 2021

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

BackgroundAt present, patients with metastatic breast cancer (MBC) have few treatment options after receiving anthracyclines and taxanes. Studies have shown that irinotecan has modest systemic activity in some patients previously treated with anthracyclines and taxanes. This study aimed to evaluate the efficacy of irinotecan-based chemotherapy for breast cancer patients in a metastatic setting.MethodsWe retrospectively collected the clinical information and survival data of 51 patients with MBC who received irinotecan at West China Hospital of Sichuan University. The primary endpoints were the progression free survival (PFS) and overall survival (OS), and the secondary endpoint was the objective response rate (ORR). To minimize potential confounding factors, we matched 51 patients who received third-line chemotherapy without irinotecan through propensity score matching (PSM) based on age, hormone receptor (HR), and human epidermal growth factor receptor 2 (HER2), compared their OS and PFS rates to those treated with irinotecan.ResultsFrom July 2012 to October 2020, 51 patients were treated with an irinotecan-containing regimen. The median number of previous treatment lines was 4, and a median of two previous chemotherapy cycles (ranging from 1–14 cycles) were given in a salvage line setting. The ORR was 15.7%, and the disease control rate (DCR) was 37.3%. For the irinotecan group, the median PFS was 3.2 months (95% CI 2.7–3.7), while the median OS was 33.1 months (95% CI 27.9–38.3). Univariate analysis results suggested that irinotecan could improve PFS in patients with visceral metastasis (P=0.031), which was 0.7 months longer than patients without visceral metastasis (3.5 months vs. 2.8 months). Compared to the patients who received third-line non-irinotecan chemotherapy, the irinotecan group showed a longer trend of PFS without statistical significance (3.2 months vs 2.1 months, P = 0.052). Similarly, the OS of the irinotecan group was longer than the third-line survival without irinotecan, but it was not statistically significant (33.1 months vs 18.0 months, P = 0.072).ConclusionsFor MBC patients who were previously treated with anthracyclines and/or taxanes, an irinotecan-containing regimen achieved moderate objective response and showed a trend of survival benefit, which deserves further study.

show abstract

“…Patients pathologically diagnosed with breast cancer are prospectively registered in the Breast Cancer-specific Database System at West China Hospital, Sichuan University since 2008 ( 9 , 10 ). Medical records, diagnostic pathology reports, treatment records are recorded by oncologists.…”

Section: The Involvement Of Breast Cancer Patientsmentioning

confidence: 99%

Research on the Construction and Application of Breast Cancer-Specific Database System Based on Full Data Lifecycle

Yin

Wang

Jiang

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

Relying on the Biomedical Big Data Center of West China Hospital, this paper makes an in-depth research on the construction method and application of breast cancer-specific database system based on full data lifecycle, including the establishment of data standards, data fusion and governance, multi-modal knowledge graph, data security sharing and value application of breast cancer-specific database. The research was developed by establishing the breast cancer master data and metadata standards, then collecting, mapping and governing the structured and unstructured clinical data, and parsing and processing the electronic medical records with NLP natural language processing method or other applicable methods, as well as constructing the breast cancer-specific database system to support the application of data in clinical practices, scientific research, and teaching in hospitals, giving full play to the value of medical big data of the Biomedical Big Data Center of West China Hospital.

show abstract

Multidimensional Machine Learning Personalized Prognostic Model in an Early Invasive Breast Cancer Population-Based Cohort in China: Algorithm Validation Study

Cited by 11 publications

References 44 publications

The Application and Comparison of Machine Learning Models for the Prediction of Breast Cancer Prognosis: Retrospective Cohort Study

The Application and Comparison of Machine Learning Models for the Prediction of Breast Cancer Prognosis: Retrospective Cohort Study

A Retrospective Analysis of the Effect of Irinotecan-Based Regimens in Patients With Metastatic Breast Cancer Previously Treated With Anthracyclines and Taxanes

Research on the Construction and Application of Breast Cancer-Specific Database System Based on Full Data Lifecycle

Contact Info

Product

Resources

About