Esther H Chung1, Chaitanya R Acharya2, Benjamin S Harris3, Kelly S Acharya3. 1. Division of Reproductive Endocrinology & Infertility, Department of Obstetrics and Gynecology, Duke University, 200 Trent Drive (Baker House 236), Durham, NC, 27710, USA. esther.h.chung@duke.edu. 2. Duke Center for Applied Therapeutics, Department of Surgery, Durham, NC, 27710, USA. 3. Division of Reproductive Endocrinology & Infertility, Department of Obstetrics and Gynecology, Duke University, 200 Trent Drive (Baker House 236), Durham, NC, 27710, USA.
Abstract
PURPOSE: To develop an innovative machine learning (ML) model that predicts personalized risk of primary ovarian insufficiency (POI) after chemotherapy for reproductive-aged women. Currently, individualized prediction of a patient's risk of POI is challenging. METHODS: Authors of published studies examining POI after gonadotoxic therapy were contacted, and six authors shared their de-identified data (N = 435). A composite outcome for POI was determined for each patient and validated by 3 authors. The primary dataset was partitioned into training and test sets; random forest binary classifiers were trained, and mean prediction scores were computed. Institutional data collected from a cross-sectional survey of cancer survivors (N = 117) was used as another independent validation set. RESULTS: Our model predicted individualized risk of POI with an accuracy of 88% (area under the ROC 0.87, 95% CI: 0.77-0.96; p < 0.001). Mean prediction scores for patients who developed POI and who did not were 0.60 and 0.38 (t-test p < 0.001), respectively. Highly weighted variables included age, chemotherapy dose, prior treatment, smoking, and baseline diminished ovarian reserve. CONCLUSION: We developed an ML-based model to estimate personalized risk of POI after chemotherapy. Our web-based calculator will be a user-friendly decision aid for individualizing risk prediction in oncofertility consultations.
PURPOSE: To develop an innovative machine learning (ML) model that predicts personalized risk of primary ovarian insufficiency (POI) after chemotherapy for reproductive-aged women. Currently, individualized prediction of a patient's risk of POI is challenging. METHODS: Authors of published studies examining POI after gonadotoxic therapy were contacted, and six authors shared their de-identified data (N = 435). A composite outcome for POI was determined for each patient and validated by 3 authors. The primary dataset was partitioned into training and test sets; random forest binary classifiers were trained, and mean prediction scores were computed. Institutional data collected from a cross-sectional survey of cancer survivors (N = 117) was used as another independent validation set. RESULTS: Our model predicted individualized risk of POI with an accuracy of 88% (area under the ROC 0.87, 95% CI: 0.77-0.96; p < 0.001). Mean prediction scores for patients who developed POI and who did not were 0.60 and 0.38 (t-test p < 0.001), respectively. Highly weighted variables included age, chemotherapy dose, prior treatment, smoking, and baseline diminished ovarian reserve. CONCLUSION: We developed an ML-based model to estimate personalized risk of POI after chemotherapy. Our web-based calculator will be a user-friendly decision aid for individualizing risk prediction in oncofertility consultations.
Authors: R Phelan; E Mann; C Napurski; T E DeFor; A Petryk; W P Miller; J E Wagner; M R Verneris; A R Smith Journal: Bone Marrow Transplant Date: 2016-06-06 Impact factor: 5.483
Authors: Halle C F Moore; Joseph M Unger; Kelly-Anne Phillips; Frances Boyle; Erika Hitre; David Porter; Prudence A Francis; Lori J Goldstein; Henry L Gomez; Carlos S Vallejos; Ann H Partridge; Shaker R Dakhil; Agustin A Garcia; Julie Gralow; Janine M Lombard; John F Forbes; Silvana Martino; William E Barlow; Carol J Fabian; Lori Minasian; Frank L Meyskens; Richard D Gelber; Gabriel N Hortobagyi; Kathy S Albain Journal: N Engl J Med Date: 2015-03-05 Impact factor: 91.245
Authors: Pamela N Munster; Amy P Moore; Roohi Ismail-Khan; Charles E Cox; Mensura Lacevic; Margaret Gross-King; Ping Xu; W Bradford Carter; Susan E Minton Journal: J Clin Oncol Date: 2012-01-09 Impact factor: 44.544
Authors: Barbara Pistilli; Chafika Mazouni; Anna Zingarello; Matthieu Faron; Mahasti Saghatchian; Michael Grynberg; Marc Spielmann; Paul Kerbrat; Henri Roché; Veronique Lorgis; Thomas Bachelot; Mario Campone; Christelle Levy; Anthony Gonçalves; Anne Lesur; Corinne Veyret; Laurence Vanlemmens; Jerome Lemonnier; Suzette Delaloge Journal: Clin Breast Cancer Date: 2018-08-23 Impact factor: 3.225
Authors: Daniel M Green; Vikki G Nolan; Pamela J Goodman; John A Whitton; DeoKumar Srivastava; Wendy M Leisenring; Joseph P Neglia; Charles A Sklar; Sue C Kaste; Melissa M Hudson; Lisa R Diller; Marilyn Stovall; Sarah S Donaldson; Leslie L Robison Journal: Pediatr Blood Cancer Date: 2013-08-12 Impact factor: 3.167