Skip to main content
Fig. 2 | BMC Cancer

Fig. 2

From: Effectiveness of CT radiomic features combined with clinical factors in predicting prognosis in patients with limited-stage small cell lung cancer

Fig. 2

Selection of radiomic features using the least absolute shrinkage and selection operator model. A LASSO coefficient profiles of the 9 features of OS. A coefficient profile plot was produced against the log(lamda) sequence. B Selection of tuning parameter lamda in the LASSO regression using tenfold cross-validation via minimun criteria. Selection for overall survival with λ = 2.0236 × 10–2 (C) LASSO coefficient profiles of the 10 features of PFS. D Selection for progression-free survival with λ = 1.6768 × 10.–2

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us