Machine learning-enhanced normal tissue complication probability modeling for late sciatic nerve toxicity prediction
Yongqiang Li1,2,3, Ping Li4,2,3, Ruoxi Wang5
1Department of Medical Physics, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital, Shanghai 201321, People's Republic of China.
None:
Objective.To develop a machine learning-enhanced normal tissue complication probability (NTCP) model for predicting late sciatic nerve toxicity (LSNT) in sacrococcygeal chordoma (SC) and locally recurrent rectal cancer (LRRC) patients undergoing carbon-ion radiotherapy (CIRT).Methods.This dual-modeling study analyzed 106 CIRT-treated SC/LRRC patients. Notice that the unit of Gy is the relative biological effectiveness -weighted dose with local effect model version I in this study for the prescription of our CIRT treatments. The hybrid framework integrated the Lyman-Kutcher-Burman model with generalized machine learning. Radiation dosimetry (the equivalent uniform dose (EUD), the uniform dose over the sciatic nerve for a 50% complication probability [TD50], the parameter for the volume effect of the organ [n], the slop steepness of the dose response curve [m]) and biological parameters were analyzed through univariate/multivariate regression. Model performance was validated using the area under the receiver operating characteristic area under the curve, sensitivity, and specificity metrics.Results.16.9% (18/106) over all patients developed grade ⩾1 LSNT with no grade ⩾4 toxicity. Stratified outcome analysis across various subgroups revealed significant variations, especially that pathological subtype of re-irradiated rectal cancer exhibited manifested 15.6% G2 toxicity. We first successfully obtained coefficients for the NTCP models with univariate analysis by utilizing the correlation between significant variations of stratified outcome and TD50. We then establish an NTCP model by machine learning-enhanced multivariate analysis that allow identifying the critical dose-volume thresholds ofV62,V64, andD3ccto correlate dose-dependent progression of G1, G2, ad G3 toxicities, respectively.Significance.EUD > 61.1 Gy significantly elevates G1 LSNT risk. Our center recommends:V62⩽ 6.2%,V64⩽ 4.69%,D3cc⩽ 32.3 Gy to balance tumor control and neuroprotection in CIRT planning. The n/m parameters provide critical insights into individual radiation sensitivity gradients across toxicity grades with machine learning-enhanced NTCP modeling for LSNT prediction in CIRT.
