Prediction of checkpoint inhibitor immunotherapy efficacy for cancer using routine blood tests and clinical data Journal Article
| Authors: | Yoo, S. K.; Fitzgerald, C. W.; Cho, B. A.; Fitzgerald, B. G.; Han, C.; Koh, E. S.; Pandey, A.; Sfreddo, H.; Crowley, F.; Korostin, M. R.; Debnath, N.; Leyfman, Y.; Valero, C.; Lee, M.; Vos, J. L.; Lee, A. S.; Zhao, K.; Lam, S.; Olumuyide, E.; Kuo, F.; Wilson, E. A.; Hamon, P.; Hennequin, C.; Saffern, M.; Vuong, L.; Hakimi, A. A.; Brown, B.; Merad, M.; Gnjatic, S.; Bhardwaj, N.; Galsky, M. D.; Schadt, E. E.; Samstein, R. M.; Marron, T. U.; Gönen, M.; Morris, L. G. T.; Chowell, D. |
| Article Title: | Prediction of checkpoint inhibitor immunotherapy efficacy for cancer using routine blood tests and clinical data |
| Abstract: | Predicting whether a patient with cancer will benefit from immune checkpoint inhibitors (ICIs) without resorting to advanced genomic or immunologic assays is an important clinical need. To address this, we developed and evaluated SCORPIO, a machine learning system that utilizes routine blood tests (complete blood count and comprehensive metabolic profile) alongside clinical characteristics from 9,745 ICI-treated patients across 21 cancer types. SCORPIO was trained on data from 1,628 patients across 17 cancer types from Memorial Sloan Kettering Cancer Center. In two internal test sets comprising 2,511 patients across 19 cancer types, SCORPIO achieved median time-dependent area under the receiver operating characteristic curve (AUC(t)) values of 0.763 and 0.759 for predicting overall survival at 6, 12, 18, 24 and 30 months, outperforming tumor mutational burden (TMB), which showed median AUC(t) values of 0.503 and 0.543. Additionally, SCORPIO demonstrated superior predictive performance for predicting clinical benefit (tumor response or prolonged stability), with AUC values of 0.714 and 0.641, compared to TMB (AUC = 0.546 and 0.573). External validation was performed using 10 global phase 3 trials (4,447 patients across 6 cancer types) and a real-world cohort from the Mount Sinai Health System (1,159 patients across 18 cancer types). In these external cohorts, SCORPIO maintained robust performance in predicting ICI outcomes, surpassing programmed death-ligand 1 immunostaining. These findings underscore SCORPIO’s reliability and adaptability, highlighting its potential to predict patient outcomes with ICI therapy across diverse cancer types and healthcare settings. © The Author(s) 2025. |
| Keywords: | immunohistochemistry; adult; cancer chemotherapy; controlled study; treatment outcome; aged; middle aged; major clinical study; overall survival; clinical feature; bevacizumab; cisplatin; drug efficacy; liver cell carcinoma; systemic therapy; paclitaxel; cancer staging; neoplasm; neoplasms; protein blood level; carboplatin; cancer immunotherapy; melanoma; neutrophil count; etoposide; protein; cohort analysis; smoking; calcium; creatinine; hemoglobin; calcium blood level; creatinine blood level; hemoglobin blood level; urea nitrogen blood level; bladder cancer; renal cell carcinoma; alanine aminotransferase blood level; aspartate aminotransferase blood level; alanine aminotransferase; alkaline phosphatase; aspartate aminotransferase; bilirubin; prothrombin time; blood; immunology; body mass; clinical study; immunotherapy; head and neck cancer; glucose blood level; mean corpuscular volume; glucose; lactate dehydrogenase; alkaline phosphatase blood level; virus infection; blood cell count; leukocyte count; drug therapy; triacylglycerol lipase blood level; pemetrexed; bilirubin blood level; lactate dehydrogenase blood level; lymphocyte count; predictive value; roc curve; potassium; receiver operating characteristic; platelet count; triacylglycerol lipase; small cell lung cancer; hematocrit; carbon dioxide; blood examination; phosphorus; programmed death 1 ligand 1; magnesium; non small cell lung cancer; chloride; medical history; erythrocyte count; hematologic tests; enzyme blood level; calcium ion; clinical outcome; eosinophil count; phosphate blood level; international normalized ratio; procedures; vemurafenib; machine learning; glucose 6 phosphate dehydrogenase; support vector machine; first-line treatment; potassium blood level; immune checkpoint inhibitor; activated partial thromboplastin time; estimated glomerular filtration rate; magnesium blood level; humans; human; male; female; article; random forest; neutrophil lymphocyte ratio; feature selection; immune checkpoint inhibitors; cobimetinib; carbon dioxide blood level; atezolizumab; comprehensive metabolic panel; malignant neoplasm; ecog performance status; tumor mutational burden; mean corpuscular hemoglobin; blood cell ratio; monocyte count; bilirubin glucuronide; red blood cell distribution width; basophil count; mean corpuscular hemoglobin concentration; granulocyte count; anion gap; basophil to lymphocyte ratio; chloride blood level; eosinophil percentage; eosinophil to lymphocyte ratio; monocyte lymphocyte ratio |
| Journal Title: | Nature Medicine |
| Volume: | 31 |
| Issue: | 3 |
| ISSN: | 1078-8956 |
| Publisher: | Nature Publishing Group |
| Date Published: | 2025-03-01 |
| Start Page: | 869 |
| End Page: | 880 |
| Language: | English |
| DOI: | 10.1038/s41591-024-03398-5 |
| PUBMED: | 39762425 |
| PROVIDER: | scopus |
| PMCID: | PMC11922749 |
| DOI/URL: | |
| Notes: | Article -- MSK Cancer Center Support Grant (P30 CA008748) acknowledged in PubMed and PDF -- MSK corresponding author is Luc Morris -- Source: Scopus |
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
Related MSK Work