Background: Radiomics has shown promise to non-invasively phenotype disease and address the limitations of extant biomarkers (e.g. PD for immune checkpoint inhibitors (ICI) in cancers, such as NSCLC. However, considerable barriers to the clinical adoption of these tools remain, such as their dependence on precise annotation of tumor extent by experienced clinical users. Here, we demonstrate a radiomic solution that requires only a single user mouse click within one or more target lesions on a baseline CT scan, to contour tumors in 3D and generate a patient-level radiomic prediction of response and outcome in ICI treated NSCLC patients. Methods: 1778 CT scans from 1261 patients were used to develop and validate an interactive, semi-automated tool for predicting ICI outcomes in NSCLC patients prior to therapy. A user click based deep learning contouring model was trained and validated on 1146 patients, then used to create annotations for radiomic analysis. A least absolute shrinkage and selection operator (LASSO) Cox proportional hazards model was utilized to select features associated with post-ICI overall survival (OS) and derive a radiomic risk score within a training cohort (n=74) that can separate patients into high and low risk groups. The model was tested on held out pre-treatment CTs of 41 ICI recipients from 2 institutions for association with OS, progression-free survival (PFS), and objective response (OR). Results: A total of 77 lesions were identified and segmented within the testing set. Average volume per lesion was 54.10 mL and per patient was 101.60 mL. OR was observed in 48.70% of patients. A threshold of -0.31 defining high and low radiomic risk groups was chosen based on optimal separation within the training set (HR=2.59 [95% 1.48~4.50], p=0.0009). Radiomic risk groups significantly stratified patients by OS (C-index=0.64, HR=3.03 [95% 1.15~8.02], p=0.03) and PFS (C-index=0.59, HR=3.20 [95% 1.13~9.10], p=0.03). Radiomic IO risk group was independently prognostic of clinical variables (Table 1) and further predicted ICI response with AUC=0.74 [95% 0.71-0.78]. Conclusions: From a single click in target lesions, our model was able to predict response and prognosis of ICI recipients from a baseline radiology scan. Additional multi-site validation and prospective evaluation will assess the value of the radiomics classifier as a decision support tool in the clinic.