INFLUENCE 3.0 模型：对局部复发和对侧乳腺癌的最新预测，现在也适用于接受新辅助系统治疗的患者。

IF 5.7 2区医学 Q1 OBSTETRICS & GYNECOLOGY

Breast Pub Date : 2024-10-28 DOI:10.1016/j.breast.2024.103829

M.C. Van Maaren , T.A. Hueting , D.J.P. van Uden , M. van Hezewijk , L. de Munck , M.A.M. Mureau , P.A. Seegers , Q.J.M. Voorham , M.K. Schmidt , G.S. Sonke , C.G.M. Groothuis-Oudshoorn , S. Siesling , NABOR project group

{"title":"INFLUENCE 3.0 模型：对局部复发和对侧乳腺癌的最新预测，现在也适用于接受新辅助系统治疗的患者。","authors":"M.C. Van Maaren , T.A. Hueting , D.J.P. van Uden , M. van Hezewijk , L. de Munck , M.A.M. Mureau , P.A. Seegers , Q.J.M. Voorham , M.K. Schmidt , G.S. Sonke , C.G.M. Groothuis-Oudshoorn , S. Siesling , NABOR project group","doi":"10.1016/j.breast.2024.103829","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Individual risk prediction of 5-year locoregional recurrence (LRR) and contralateral breast cancer (CBC) supports decisions regarding personalised surveillance. The previously developed INFLUENCE tool was rebuild, including a recent population and patients who received neoadjuvant systemic therapy (NST).</div></div><div><h3>Methods</h3><div>Women, surgically treated for nonmetastatic breast cancer, diagnosed between 2012 and 2016, were selected from the Netherlands Cancer Registry. Cox regression with restricted cubic splines was compared to Random Survival Forest (RSF) to predict five-year LRR and CBC risks. Separate models were developed for NST patients. Discrimination and calibration were assessed by 100x bootstrap resampling.</div></div><div><h3>Results</h3><div>In the non-NST and NST group, 49,631 and 10,154 patients were included, respectively. Age, mode of detection, histology, sublocalisation, grade, pT, pN, hormonal receptor status ± endocrine treatment, HER2 status ± targeted treatment, surgery ± immediate reconstruction ± radiation therapy, and chemotherapy were significant predictors for LRR and/or CBC in non-NST patients. For NST patients this was similar, but excluding (y)pT and (y)pN status, and including presence of ductal carcinoma in situ, axillary lymph node dissection and pathologic complete response.</div><div>For non-NST patients, the Cox and RSF models were integrated in the online tool with 5-year AUCs of 0.77 (95%CI:0.77–0.77) and 0.68 (95%CI:0.67–0.68)] for LRR and CBC prediction, respectively. For NST patients, the RSF model performed best (AUCs 0.77 (95%CI:0.76–0.78) and 0.73 (95%CI:0.69–0.76) for LRR and CBC, respectively). Regarding calibration, observed-predicted differences were all <1 %.</div></div><div><h3>Conclusion</h3><div>This INFLUENCE 3.0 models showed moderate performance in LRR and CBC prediction. The models have been made available as online tool to enable clinical decision support regarding personalised follow-up.</div></div>","PeriodicalId":9093,"journal":{"name":"Breast","volume":"79 ","pages":"Article 103829"},"PeriodicalIF":5.7000,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The INFLUENCE 3.0 model: Updated predictions of locoregional recurrence and contralateral breast cancer, now also suitable for patients treated with neoadjuvant systemic therapy\",\"authors\":\"M.C. Van Maaren , T.A. Hueting , D.J.P. van Uden , M. van Hezewijk , L. de Munck , M.A.M. Mureau , P.A. Seegers , Q.J.M. Voorham , M.K. Schmidt , G.S. Sonke , C.G.M. Groothuis-Oudshoorn , S. Siesling , NABOR project group\",\"doi\":\"10.1016/j.breast.2024.103829\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Individual risk prediction of 5-year locoregional recurrence (LRR) and contralateral breast cancer (CBC) supports decisions regarding personalised surveillance. The previously developed INFLUENCE tool was rebuild, including a recent population and patients who received neoadjuvant systemic therapy (NST).</div></div><div><h3>Methods</h3><div>Women, surgically treated for nonmetastatic breast cancer, diagnosed between 2012 and 2016, were selected from the Netherlands Cancer Registry. Cox regression with restricted cubic splines was compared to Random Survival Forest (RSF) to predict five-year LRR and CBC risks. Separate models were developed for NST patients. Discrimination and calibration were assessed by 100x bootstrap resampling.</div></div><div><h3>Results</h3><div>In the non-NST and NST group, 49,631 and 10,154 patients were included, respectively. Age, mode of detection, histology, sublocalisation, grade, pT, pN, hormonal receptor status ± endocrine treatment, HER2 status ± targeted treatment, surgery ± immediate reconstruction ± radiation therapy, and chemotherapy were significant predictors for LRR and/or CBC in non-NST patients. For NST patients this was similar, but excluding (y)pT and (y)pN status, and including presence of ductal carcinoma in situ, axillary lymph node dissection and pathologic complete response.</div><div>For non-NST patients, the Cox and RSF models were integrated in the online tool with 5-year AUCs of 0.77 (95%CI:0.77–0.77) and 0.68 (95%CI:0.67–0.68)] for LRR and CBC prediction, respectively. For NST patients, the RSF model performed best (AUCs 0.77 (95%CI:0.76–0.78) and 0.73 (95%CI:0.69–0.76) for LRR and CBC, respectively). Regarding calibration, observed-predicted differences were all <1 %.</div></div><div><h3>Conclusion</h3><div>This INFLUENCE 3.0 models showed moderate performance in LRR and CBC prediction. The models have been made available as online tool to enable clinical decision support regarding personalised follow-up.</div></div>\",\"PeriodicalId\":9093,\"journal\":{\"name\":\"Breast\",\"volume\":\"79 \",\"pages\":\"Article 103829\"},\"PeriodicalIF\":5.7000,\"publicationDate\":\"2024-10-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Breast\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0960977624001607\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"OBSTETRICS & GYNECOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Breast","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0960977624001607","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OBSTETRICS & GYNECOLOGY","Score":null,"Total":0}

引用次数: 0

摘要

背景：5年局部复发（LRR）和对侧乳腺癌（CBC）的个体风险预测有助于做出个性化监测的决策。对之前开发的 INFLUENCE 工具进行了重建，包括近期人群和接受新辅助系统治疗（NST）的患者：方法：从荷兰癌症登记处选取了2012年至2016年期间确诊为非转移性乳腺癌并接受过手术治疗的女性患者。在预测五年 LRR 和 CBC 风险时，将使用受限立方样条的 Cox 回归与随机生存森林 (RSF) 进行了比较。为 NST 患者开发了单独的模型。通过 100 倍引导重采样评估了辨别度和校准度：在非 NST 组和 NST 组中，分别纳入了 49,631 名和 10,154 名患者。在非 NST 患者中，年龄、检测方式、组织学、亚定位、分级、pT、pN、激素受体状态（内分泌治疗）、HER2 状态（靶向治疗）、手术（即刻重建）、放疗和化疗是 LRR 和/或 CBC 的重要预测因素。对于 NST 患者，情况类似，但不包括 (y)pT 和 (y)pN 状态，还包括是否存在导管原位癌、腋窝淋巴结清扫和病理完全反应。对于非 NST 患者，在线工具中整合了 Cox 和 RSF 模型，对 LRR 和 CBC 预测的 5 年 AUC 分别为 0.77（95%CI:0.77-0.77）和 0.68（95%CI:0.67-0.68）]。对于 NST 患者，RSF 模型表现最佳（LRR 和 CBC 的 AUC 分别为 0.77（95%CI:0.76-0.78）和 0.73（95%CI:0.69-0.76））。在校准方面，观测值与预测值之间的差异均为结论：INFLUENCE 3.0 模型在 LRR 和 CBC 预测方面表现中规中矩。该模型已作为在线工具提供，以便为个性化随访提供临床决策支持。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

The INFLUENCE 3.0 model: Updated predictions of locoregional recurrence and contralateral breast cancer, now also suitable for patients treated with neoadjuvant systemic therapy

Background

Individual risk prediction of 5-year locoregional recurrence (LRR) and contralateral breast cancer (CBC) supports decisions regarding personalised surveillance. The previously developed INFLUENCE tool was rebuild, including a recent population and patients who received neoadjuvant systemic therapy (NST).

Methods

Women, surgically treated for nonmetastatic breast cancer, diagnosed between 2012 and 2016, were selected from the Netherlands Cancer Registry. Cox regression with restricted cubic splines was compared to Random Survival Forest (RSF) to predict five-year LRR and CBC risks. Separate models were developed for NST patients. Discrimination and calibration were assessed by 100x bootstrap resampling.

Results

In the non-NST and NST group, 49,631 and 10,154 patients were included, respectively. Age, mode of detection, histology, sublocalisation, grade, pT, pN, hormonal receptor status ± endocrine treatment, HER2 status ± targeted treatment, surgery ± immediate reconstruction ± radiation therapy, and chemotherapy were significant predictors for LRR and/or CBC in non-NST patients. For NST patients this was similar, but excluding (y)pT and (y)pN status, and including presence of ductal carcinoma in situ, axillary lymph node dissection and pathologic complete response.

For non-NST patients, the Cox and RSF models were integrated in the online tool with 5-year AUCs of 0.77 (95%CI:0.77–0.77) and 0.68 (95%CI:0.67–0.68)] for LRR and CBC prediction, respectively. For NST patients, the RSF model performed best (AUCs 0.77 (95%CI:0.76–0.78) and 0.73 (95%CI:0.69–0.76) for LRR and CBC, respectively). Regarding calibration, observed-predicted differences were all <1 %.

Conclusion

This INFLUENCE 3.0 models showed moderate performance in LRR and CBC prediction. The models have been made available as online tool to enable clinical decision support regarding personalised follow-up.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Breast 医学-妇产科学

CiteScore

8.70

自引率

2.60%

发文量

165

审稿时长

59 days

期刊介绍： The Breast is an international, multidisciplinary journal for researchers and clinicians, which focuses on translational and clinical research for the advancement of breast cancer prevention, diagnosis and treatment of all stages.