Abstract 1312
Background
Predictive online calculators are used by clinicians as decision aids in early breast cancer (EBC). While use statistics for these calculators have not been published, as of 2017 NHS Predict was being accessed more than 20,000 times a month. These predictive tools have not had accuracy & benefit of use prospectively confirmed in EBC, yet use of calculators has been encouraged in EBC guidelines. It is important to understand the populations informing model development & validation, to understand how data bias may impact predictions in under-represented subpopulations. This work sought to elucidate the risk of bias in model development & validation for 3 online EBC calculators (NHS Predict, Adjuvant! & Cancermath), in an effort to highlight sub-populations where calculated risk & therefore treatment benefit estimates may be less reliable.
Methods
A literature search was conducted in PubMed, search terms were “predict*” “adjuvant” “breast” & “algorithm”. Results were screened for relevance to the three predictive tools under scrutiny & additional references were extracted from relevant papers. Using a modified CHARMS checklist, the relevant sections of the development & validation papers were extracted.
Results
6 development & 24 validation papers were reviewed as summarised in the TableTable:
264P
Predict | Adjuvant | Cancermath | |
---|---|---|---|
Development population size & date range | 5694 1977-2008 | 37,968 1977-2007 | 499,724 1977-2007 |
Aged <35 in development population | 2% (111) | 0 | >0.5% |
Aged >65 in development population | 32% (1781) | 0 | >17% |
Tumour size >5cm in development population | 5% (287) | 0 | 0 |
Number of validation studies | 10 | 13 | 3 |
% retrospective | 100 | 100 | 100 |
Total number of patients in validation studies | 19,864 | 19,618 | 11,203 |
Age >65 in validations | 35% (7134) | 42% (8313) | 40% (4519) |
Age <35 in validations | 16% (3235) | 8% (1518) | 9% (1007) |
Tumour size >5cm in validations | 5% (287) | 5% (1015) | 6% (634) |
Universal exclusions | Multi-focal, inflammatory, male | Multi-focal, inflammatory, male | Multi-focal, inflammatory, male |
Neoadjuvant chemotherapy not an exclusion | 1 study (121 patients) | 0 | 0 |
Overall conclusions of validation authors | Earlier versions under-predicted mortality in women <35 Poor performance in tumours >5cm. | Poor performance in general in: <35 and >65 More advanced disease Malay ethnicity Overly optimistic survival predictions across subgroups in UK population. | Poor performance in < 35 Systematically under-predicted mortality, especially for ER-negative tumours. |
Conclusions
All 3 predictive tools have under-represented groups in their development cohorts, specifically those under 35 & over 65 years old, as well as larger tumours. Validation studies consistently demonstrate worse performance in these groups. However, due to inconsistent methodology in validation studies, quantitating the summary performance within & across tools is difficult. These predictive tools should be used with caution in under-represented populations. More work is required to look at clinical utility of tools as well as their statistical performance.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
4732 - Progesterone Receptor Isoform Ratio Dictates Antiprogestins/Progestins Effects on Metastatic Breast Cancer Models
Presenter: Maria Abascal
Session: Poster Display session 2
Resources:
Abstract
5737 - PAM50 and CGH-array genomic characterization of HER2-Equivocal Breast Cancers defined by the 2018 ASCO/CAP recommendations.
Presenter: Carine Ngo
Session: Poster Display session 2
Resources:
Abstract
1096 - OncotypeDX® predictive nomogram for recurrence score output: a machine learning system based on quantitative immunochemistry analysis - ADAPTED01
Presenter: Fabio Marazzi
Session: Poster Display session 2
Resources:
Abstract
5426 - Geriatric parameters predict both disease-related and patient-reported outcomes in older patients with breast cancer
Presenter: Willeke van der Plas-Krijgsman
Session: Poster Display session 2
Resources:
Abstract
5865 - Patients with a 21-gene assay in South East London differ from the TAILORx trial population
Presenter: Charalampos Gousis
Session: Poster Display session 2
Resources:
Abstract
2445 - Oncologic outcome of invasive lobular carcinoma: Is it different from that of invasive ductal carcinoma?
Presenter: Hee Jun Choi
Session: Poster Display session 2
Resources:
Abstract
2476 - Pathologic response and survival efficacy in patients with initial nodal involvement after neoadjuvant chemotherapy in early breast cancer
Presenter: SERAFIN MORALES Murillo
Session: Poster Display session 2
Resources:
Abstract
3761 - Chemotherapy-induced amenorrhea: prognostic impact on premenopausal Egyptian patients with breast cancer
Presenter: Khaled Abdel Karim
Session: Poster Display session 2
Resources:
Abstract
4687 - Predicting the presence of breast cancer using circulating small RNA in the serum
Presenter: Yumiko Koi
Session: Poster Display session 2
Resources:
Abstract
5612 - Evaluation of germ line mutational status among women with triple-negative breast cancer in Russia
Presenter: Elena Shagimardanova
Session: Poster Display session 2
Resources:
Abstract