Abstract 1214P
Background
Accurate prediction of lung cancer recurrence risk is crucial for treatment decisions and follow-up, particularly for Stage I patients who are not eligible for (neo-)adjuvant therapy but approximately one-third still recur after surgical resection. We present a machine learning model that uses patient computed tomography (CT) images and clinical features to predict lung cancer recurrence.
Methods
A dataset of 968 clinical stage I-III lung cancer patients who underwent surgical resection was gathered from the US National Lung Screening Trial, the North Estonia Medical Centre, the Stanford University School of Medicine and Palo Alto Veterans Affairs Healthcare System. 313/968 had lung cancer recurrence, of which 221/776 were Stage 1. The pre-operative survival model was trained to predict the likelihood of recurrence at each time-point using radiomic features extracted from CT images and relevant clinical variables. An 8-fold cross-validation strategy was used and performance evaluated using the time-dependent Area-Under-the-ROC-Curve (AUC), disease-free survival (DFS), hazard ratio (HR) and log-rank test against clinical staging alone.
Results
The ML survival model was better able to stratify patients into high and low-risk (HR=2.7, p
Conclusions
The ML survival model outperforms clinical staging in patient risk-stratification and time-dependent lung cancer recurrence prediction. With further development, this algorithm could prove a valuable tool to aid the management of lung cancer patients.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Optellum.
Disclosure
A. Gasimova, B. Heames, N. Waterfield Price: Financial Interests, Institutional, Other, Employee: Optellum. G. Hodgkinson: Financial Interests, Institutional, Other, Employee: Medtronic. L. Freitag: Financial Interests, Institutional, Advisory Board: Optellum. All other authors have declared no conflicts of interest.
Resources from the same session
1111P - Genomic and transcriptomic analysis of Japanese melanoma reveals candidate biomarkers for immune checkpoint inhibitor responders
Presenter: Toshihiro Kimura
Session: Poster session 04
1112P - Immunotherapy after progression to double immunotherapy: Pembrolizumab and Lenvatinib versus conventional chemotherapy for patients with metastatic melanoma after failure of PD-1/CTLA-4 inhibition
Presenter: Dimitrios Ziogas
Session: Poster session 04
1113P - A machine learning model based on computed tomography radiomics to predict prognosis in subjects with stage IV melanoma
Presenter: Maria Teresa Maccallini
Session: Poster session 04
1114P - Deciphering unresectable in-transit metastasis in melanoma: Multi-modal and longitudinal insights
Presenter: Giuseppe Tarantino
Session: Poster session 04
1115P - Multiomics clustering of patients with cutaneous melanoma to reveal survival trends based on tumor immune evasion features
Presenter: Adeliya Leleytner
Session: Poster session 04
1116P - Application of the Scottish inflammatory prognostic score to the south-east Scotland cancer network real-world melanoma cohort
Presenter: Karim El-Shakankery
Session: Poster session 04
1117P - Intratumoral microbiota is associated with prognosis in Chinese patients with skin melanoma
Presenter: Hang Jiang
Session: Poster session 04
1118P - Immunological alterations during neoadjuvant BRAF/MEK inhibition in patients with prior unresectable regionally advanced melanoma: Translational analysis from the REDUCTOR trial
Presenter: Femke Burgers
Session: Poster session 04
1119P - Genomic and transcriptomic predictors of resistance to anti-PD1 monotherapy in patients with advanced melanoma
Presenter: Wenya Wang
Session: Poster session 04
1120P - Tumoral and peripheral immunophenotype of patients with stage II/III melanoma undergoing adjuvant immunotherapy following tumor resection
Presenter: Maria Ascierto
Session: Poster session 04