Ji-Yeon Kim1, Eunjoo Jeon2, Soonhwan Kwon2, Hyungsik Jung2, Sunghoon Joo2, Youngmin Park2, Se Kyung Lee3, Jeong Eon Lee3, Seok Jin Nam3, Eun Yoon Cho4, Yeon Hee Park1, Jin Seok Ahn1, Young-Hyuck Im5. 1. Division of Hematology-Oncology, Department of Internal Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea. 2. Digital Health Business Team, Samsung SDS, Seoul, 05510, South Korea. 3. Department of Surgery, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea. 4. Department of Pathology, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea. 5. Division of Hematology-Oncology, Department of Internal Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, South Korea. imyh00@skku.edu.
Abstract
BACKGROUND: The aim of this study was to develop a machine learning (ML) based model to accurately predict pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) using pretreatment clinical and pathological characteristics of electronic medical record (EMR) data in breast cancer (BC). METHODS: The EMR data from patients diagnosed with early and locally advanced BC and who received NAC followed by curative surgery were reviewed. A total of 16 clinical and pathological characteristics was selected to develop ML model. We practiced six ML models using default settings for multivariate analysis with extracted variables. RESULTS: In total, 2065 patients were included in this analysis. Overall, 30.6% (n = 632) of patients achieved pCR. Among six ML models, the LightGBM had the highest area under the curve (AUC) for pCR prediction. After hyper-parameter tuning with Bayesian optimization, AUC was 0.810. Performance of pCR prediction models in different histology-based subtypes was compared. The AUC was highest in HR+HER2- subgroup and lowest in HR-/HER2- subgroup (HR+/HER2- 0.841, HR+/HER2+ 0.716, HR-/HER2 0.753, HR-/HER2- 0.653). CONCLUSIONS: A ML based pCR prediction model using pre-treatment clinical and pathological characteristics provided useful information to predict pCR during NAC. This prediction model would help to determine treatment strategy in patients with BC planned NAC.
BACKGROUND: The aim of this study was to develop a machine learning (ML) based model to accurately predict pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) using pretreatment clinical and pathological characteristics of electronic medical record (EMR) data in breast cancer (BC). METHODS: The EMR data from patients diagnosed with early and locally advanced BC and who received NAC followed by curative surgery were reviewed. A total of 16 clinical and pathological characteristics was selected to develop ML model. We practiced six ML models using default settings for multivariate analysis with extracted variables. RESULTS: In total, 2065 patients were included in this analysis. Overall, 30.6% (n = 632) of patients achieved pCR. Among six ML models, the LightGBM had the highest area under the curve (AUC) for pCR prediction. After hyper-parameter tuning with Bayesian optimization, AUC was 0.810. Performance of pCR prediction models in different histology-based subtypes was compared. The AUC was highest in HR+HER2- subgroup and lowest in HR-/HER2- subgroup (HR+/HER2- 0.841, HR+/HER2+ 0.716, HR-/HER2 0.753, HR-/HER2- 0.653). CONCLUSIONS: A ML based pCR prediction model using pre-treatment clinical and pathological characteristics provided useful information to predict pCR during NAC. This prediction model would help to determine treatment strategy in patients with BC planned NAC.
Entities:
Keywords:
Breast cancer; Machine learning; Neoadjuvant chemotherapy; Pathologic complete response
Authors: A Bottini; A Berruti; M Tampellini; B Morrica; A Brunelli; E Gnocchi; M P Brizzi; S Aguggini; E Fara; P Alquati; L Dogliotti Journal: Tumour Biol Date: 1997
Authors: Patricia Cortazar; Lijun Zhang; Michael Untch; Keyur Mehta; Joseph P Costantino; Norman Wolmark; Hervé Bonnefoi; David Cameron; Luca Gianni; Pinuccia Valagussa; Sandra M Swain; Tatiana Prowell; Sibylle Loibl; D Lawrence Wickerham; Jan Bogaerts; Jose Baselga; Charles Perou; Gideon Blumenthal; Jens Blohmer; Eleftherios P Mamounas; Jonas Bergh; Vladimir Semiglazov; Robert Justice; Holger Eidtmann; Soonmyung Paik; Martine Piccart; Rajeshwari Sridhara; Peter A Fasching; Leen Slaets; Shenghui Tang; Bernd Gerber; Charles E Geyer; Richard Pazdur; Nina Ditsch; Priya Rastogi; Wolfgang Eiermann; Gunter von Minckwitz Journal: Lancet Date: 2014-02-14 Impact factor: 79.321
Authors: A Schneeweiss; S Chia; T Hickish; V Harvey; A Eniu; R Hegg; C Tausch; J H Seo; Y-F Tsai; J Ratnayake; V McNally; G Ross; J Cortés Journal: Ann Oncol Date: 2013-05-22 Impact factor: 32.976
Authors: W Fraser Symmans; Florentia Peintinger; Christos Hatzis; Radhika Rajan; Henry Kuerer; Vicente Valero; Lina Assad; Anna Poniecka; Bryan Hennessy; Marjorie Green; Aman U Buzdar; S Eva Singletary; Gabriel N Hortobagyi; Lajos Pusztai Journal: J Clin Oncol Date: 2007-09-04 Impact factor: 44.544
Authors: S M Swain; M S Ewer; G Viale; S Delaloge; J-M Ferrero; M Verrill; R Colomer; C Vieira; T L Werner; H Douthwaite; D Bradley; M Waldron-Lynch; A Kiermaier; J Eng-Wong; C Dang Journal: Ann Oncol Date: 2018-03-01 Impact factor: 32.976