{"doi":"10.1001/jamanetworkopen.2023.3273","title":"Recalibration of a Deep Learning Model for Low-Dose Computed Tomographic Images to Inform Lung Cancer Screening Intervals","abstract":"Importance: Annual low-dose computed tomographic (LDCT) screening reduces lung cancer mortality, but harms could be reduced and cost-effectiveness improved by reusing the LDCT image in conjunction with deep learning or statistical models to identify low-risk individuals for biennial screening. Objective: To identify low-risk individuals in the National Lung Screening Trial (NLST) and estimate, had they been assigned a biennial screening, how many lung cancers would have been delayed 1 year in diagnosis. Design, Setting, and Participants: This diagnostic study included participants with a presumed nonmalignant lung nodule in the NLST between January 1, 2002, and December 31, 2004, with follow-up completed on December 31, 2009. Data were analyzed for this study from September 11, 2019, to March 15, 2022. Exposures: An externally validated deep learning algorithm that predicts malignancy in current lung nodules using LDCT images (Lung Cancer Prediction Convolutional Neural Network [LCP-CNN]; Optellum Ltd) was recalibrated to predict 1-year lung cancer detection by LDCT for presumed nonmalignant nodules. Individuals with presumed nonmalignant lung nodules were hypothetically assigned annual vs biennial screening based on the recalibrated LCP-CNN model, Lung Cancer Risk Assessment Tool (LCRAT + CT [a statistical model combining individual risk factors and LDCT image features]), and the American College of Radiology recommendations for lung nodules, version 1.1 (Lung-RADS). Main Outcomes and Measures: Primary outcomes included model prediction performance, the absolute risk of a 1-year delay in cancer diagnosis, and the proportion of people without lung cancer assigned a biennial screening interval vs the proportion of cancer diagnoses delayed. Results: The study included 10 831 LDCT images from patients with presumed nonmalignant lung nodules (58.7% men; mean [SD] age, 61.9 [5.0] years), of whom 195 were diagnosed with lung cancer from the subsequent screen. The recalibrated LCP-CNN had substantially higher area under the curve (0.87) than LCRAT + CT (0.79) or Lung-RADS (0.69) to predict 1-year lung cancer risk (P < .001). If 66% of screens with nodules were assigned to biennial screening, the absolute risk of a 1-year delay in cancer diagnosis would have been lower for recalibrated LCP-CNN (0.28%) than LCRAT + CT (0.60%; P = .001) or Lung-RADS (0.97%; P < .001). To delay only 10% of cancer diagnoses at 1 year, more people would have been safely assigned biennial screening under LCP-CNN than LCRAT + CT (66.4% vs 40.3%; P < .001). Conclusions and Relevance: In this diagnostic study evaluating models of lung cancer risk, a recalibrated deep learning algorithm was most predictive of 1-year lung cancer risk and had least risk of 1-year delay in cancer diagnosis among people assigned biennial screening. Deep learning algorithms could prioritize people for workup of suspicious nodules and decrease screening intensity for people with low-risk nodules, which may be vital for implementation in health care systems.","journal":"JAMA Network Open","year":2023,"id":329390,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":19,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9586,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1052079,"name":"Vivian Wang","orcid":"0000-0003-1700-0990","position":1,"is_corresponding":false},{"id":651212,"name":"David Baldwin","orcid":"0000-0001-8410-7160","position":2,"is_corresponding":false},{"id":218401,"name":"Paul F. Pinsky","orcid":"0000-0002-0350-3282","position":3,"is_corresponding":false},{"id":237721,"name":"Li C. Cheung","orcid":"0000-0003-1625-4331","position":4,"is_corresponding":false},{"id":285993,"name":"Philip E. Castle","orcid":"0000-0002-6408-5985","position":5,"is_corresponding":false},{"id":1052080,"name":"Martin Skarzynski","orcid":"0000-0003-0274-0160","position":6,"is_corresponding":false},{"id":630694,"name":"Hilary A. Robbins","orcid":"0000-0001-6041-6866","position":7,"is_corresponding":false},{"id":237731,"name":"Hormuzd A. Katki","orcid":"0000-0003-2002-0095","position":8,"is_corresponding":false},{"id":420942,"name":"Rebecca Landy","orcid":"0000-0003-4042-4820","position":0,"is_corresponding":true}],"reference_count":18,"raw_metadata":null,"created_at":"2026-07-19T01:09:01.509601Z","pmid":"36929398","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}