Copenhagen, Denmark
Onsite/Online

ESTRO 2022

Session Item

Radiomics, modelling and statistical methods
7011
Poster (digital)
Physics
Methodological Quality of Machine Learning Quantitative Image Analysis Studies in Esophageal Cancer
Zhen Zhang, The Netherlands
PO-1782

Abstract

Methodological Quality of Machine Learning Quantitative Image Analysis Studies in Esophageal Cancer
Authors:

Zhen Zhang1, Leonard Wee2, Zhenwei Shi3, Andre Dekker2

1MAASTRO, Radiation oncology, Maastricht, The Netherlands; 2MAASTRO, Radiation Oncology, Maastricht, The Netherlands; 3Guangdong Provincial People's Hospital, Radiology, Guangdong, China

Show Affiliations
Purpose or Objective

Studies based on machine learning-based quantitative imaging techniques have gained much interest in cancer research. The aim of this review is to critically appraise the existing machine learning-based quantitative imaging analysis studies predicting outcomes of esophageal cancer after concurrent chemoradiotherapy in accordance with PRISMA guidelines.

Material and Methods

A systematic review was conducted in accordance with PRISMA guidelines. The citation search was performed via PubMed and Embase Ovid databases for literature published before April 2021. From each full-text article, study characteristics and model information were summarized. We proposed an appraisal matrix with 13 items to assess the methodological quality of each study based on recommended best-practices pertaining to quality.

Results

Out of 244 identified records, 37 studies met the inclusion criteria. Study endpoints included prognosis, treatment response, and toxicity after concurrent chemoradiotherapy with reported discrimination metrics in validation datasets between 0.6 and 0.9, but with wide variation in quality. A total of 30 studies published in the last five years were evaluated for methodological quality and we found 11 studies with at least 6 “Good” item ratings.

Table 1. Assessment of methodological quality of included studies.





Figure 1. Reported AUC/C-index of the included studies with number of good items were classified by Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD). Type 1a: Development only; Type 1b: Development and validation using resampling; Type 2a: Random split-sample development and validation; Type 2b: Nonrandom split-sample development and validation; Type 3: Development and validation using separate data; Type 4: Validation only.

Conclusion

A substantial number of studies lacked prospective registration, external validation, model calibration, and support for clinical use. To further improve the predictive power of machine learning-based models and translate into real clinical applications in cancer research, appropriate methodologies, prospective registration and multi-institution validation are recommended.