Artificial intelligence for prediction of treatment outcomes in breast cancer: Systematic review of design, reporting standards, and bias. (July 2022)

• Record Type: Journal Article
• Authors: Corti, Chiara; Cobanaj, Marisa; Marian, Federica; Dee, Edward C.; Lloyd, Maxwell R.; Marcu, Sara; Dombrovschi, Andra; Biondetti, Giorgio P.; Batalini, Felipe; Celi, Leo A.; Curigliano, Giuseppe
• Is Part Of: Cancer treatment reviews. Volume 108(2022)
• Publication Date: 2022-07
• Subjects: Artificial intelligence -- Bias -- Decision support -- Breast cancer -- Outcome prediction; Cancer -- Periodicals; Cancer -- Treatment -- Periodicals; Neoplasms -- therapy -- Periodicals; Cancer -- Périodiques; Cancer -- Traitement -- Périodiques; Cancer -- Treatment; Electronic journals; Periodicals; 616.99406
• DOI: 10.1016/j.ctrv.2022.102410
• Languages: English
• ISSNs: 0305-7372

Abstract

Highlights: Pitfalls in applying population-based data to individual patients are well-known. (83/85) AI-based algorithms may improve personalized treatment approaches in breast cancer. (85/85) However, methodological limitations may limit clinical impact. (64/85) We highlight reporting gaps, limited external validation, poor code/data sharing. (83/85) We provide solutions to ensure a robust evidence base in this emerging field. (79/85) Abstract: Background: Artificial intelligence (AI) has the potential to personalize treatment strategies for patients with cancer. However, current methodological weaknesses could limit clinical impact. We identified common limitations and suggested potential solutions to facilitate translation of AI to breast cancer management. Methods: A systematic review was conducted in MEDLINE, Embase, SCOPUS, Google Scholar and PubMed Central in July 2021. Studies investigating the performance of AI to predict outcomes among patients undergoing treatment for breast cancer were included. Algorithm design and adherence to reporting standards were assessed following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement. Risk of bias was assessed by using the Prediction model Risk Of Bias Assessment Tool (PROBAST), and correspondence with authors to assess data and code availability. Results: Our search identified 1, 124 studies, of which 64 were included: 58 had a retrospective study design, with 6 studies with a prospective design. Access to datasets and code was severely limited (unavailable in 77% and 88% of studies, respectively). On request, data and code were made available in 28% and 18% of cases, respectively. Ethnicity was often under-reported (not reported in 52 of 64, 81%), as was model calibration (63/64, 99%). The risk of bias was high in 72% (46/64) of the studies, especially because of analysis bias. Conclusion: Development of AI algorithms should involve external and prospective validation, with improved code and data availability to enhance reliability and translation of this promising approach. Protocol registration number: PROSPERO - CRD42022292495.