Searchable abstracts of presentations at key conferences in endocrinology
Endocrine Abstracts (2024) 99 EP14 | DOI: 10.1530/endoabs.99.EP14

ECE2024 Eposter Presentations Endocrine-Related Cancer (90 abstracts)

Machine Learning-based Online Survival Prediction Tool for Adrenocortical Carcinoma

Emre Sedar Saygili 1 , Yasir S Elhassan 2 , Alessandro Prete 2 , Juliane Lippert 3 , Barbara Altieri 4 & Cristina L Ronchi 2


1Division of Endocrinology and Metabolism, Department of Internal Medicine, Faculty of Medicine, Canakkale Onsekiz Mart University, Çanakkale, Turkey; 2Institute of Metabolism and Systems Research, University of Birmingham, United Kingdom; 3Institute of Human Genetics, University of Wuerzburg, Germany; 4Division of Endocrinology and Diabetes, University Hospital of Wuerzburg, Germany


Background: Adrenocortical carcinoma (ACC) is a rare endocrine cancer. We aimed to develop machine learning (ML) models for predicting clinical outcomes of patients with ACC and deploy them as a web-based decision support tool.

Methods: The S-GRAS dataset1 was used as a training cohort (n=942), while the COMBI dataset2 and new patients were used as a validation cohort (n=220). We used S-GRAS parameters previously described1 for ML models. The PyCaret 3.1.0 ML library in Python was used to create models. The F1 score is calculated as the harmonic mean of sensitivity and precision. We compared sixteen ML models and chose the best by F1 score. Clinical outcomes were defined as 5-year overall mortality (OM), 1-year disease progression (DP), and 3-year DP, respectively.

Results: The study has 579, 968, and 858 patients’ data for clinical outcomes, respectively. The study’s 5-year OM, 1-year DP, and 3-year DP rates were 55.1%, 39.7%, and 67.6%, respectively (training+validation cohorts). Quadratic Discriminant Analysis (QDA), Light Gradient Boosting Machine (LGBM), and AdaBoost Classifier (ABC) were the best models for predicting clinical outcomes. The F1 scores of the best ML models for the training cohort were 0.79 for OM, 0.63 for 1-year DP, and 0.83 for 3-year DP; while for the validation cohort were 0.72, 0.60, and 0.83, respectively. Sensitivity and specificity for 5-year OM were 77% and 77% in the training cohort and 65%, and 81% in the validation cohort, respectively. Streamlit in Python is used for deploying the models as a website (https://acc-survival.streamlit.app).

Table 1. Performance of the best ML models
OutcomesBest modelCohortAccuracyAUCSensitivityPrecisionF1Specificity
OMQDATraining0.770.850.770.800.790.77
Validation0.730.790.650.800.720.81
1-year DP LGBM Training0.740.780.570.700.630.84
Validation0.680.740.530.710.600.81
3-year DP ABCTraining0.760.790.880.830.830.50
Validation0.770.870.790.830.830.71

Conclusion: We could demonstrate that S-GRAS parameters can predict OM and disease progression with an AUC range of 0.74-0.87. To the best of our knowledge, this is the first ML-based online survival tool for ACC. This app instantly gives the probability of outcomes for patients with ACC based on S-GRAS parameters after resection. Medical professionals could use it in clinical practice to drive personalised management decisions.

References: 1. Elhassan YS, et al. Eur J Endocrinol.2021;1861:25-36.

2. Lippert J, et al. Eur J Endocrinol. 2023;189(2):262-270.

Volume 99

26th European Congress of Endocrinology

Stockholm, Sweden
11 May 2024 - 14 May 2024

European Society of Endocrinology 

Browse other volumes

Article tools

My recent searches

No recent searches.