{"id":"W4406100364","doi":"10.2196/65001","title":"A Hybrid Deep Learning–Based Feature Selection Approach for Supporting Early Detection of Long-Term Behavioral Outcomes in Survivors of Cancer: Cross-Sectional Study","year":2025,"lang":"en","type":"article","venue":"JMIR Bioinformatics and Biotechnology","topic":"Cancer survivorship and care","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Term (time); Feature selection; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Computer science; Machine learning; Psychology; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002538359,0.000141331,0.0003924779,0.0005655511,0.0000718932,0.00001701535,0.00007213979,0.0003096627,0.000003274168],"category_scores_gemma":[0.00003737107,0.0001226883,0.00009639515,0.0004168437,0.0001177868,0.00006372335,0.00004112534,0.0003463379,7.647969e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008270144,"about_ca_system_score_gemma":0.00007556748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00129185,"about_ca_topic_score_gemma":0.00449706,"domain_scores_codex":[0.9989479,0.00001695614,0.0005263111,0.0001688971,0.0001424732,0.0001974737],"domain_scores_gemma":[0.9993492,0.00003312757,0.0003043884,0.0001275308,0.0001599624,0.00002579215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003317544,0.0003301649,0.9657027,0.0006871198,0.00005635202,8.544153e-7,0.000327336,0.00004469077,0.001880701,0.00001336845,7.322889e-7,0.03062424],"study_design_scores_gemma":[0.002036719,0.001465529,0.9550411,0.00004134226,0.0000668479,0.000007432873,0.0006887572,0.01147633,0.02905411,0.000008203667,0.00001190189,0.0001017256],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892948,0.00007216292,0.00918514,0.000060589,0.0001323383,0.001153388,0.00002546606,0.00005670823,0.00001943023],"genre_scores_gemma":[0.9991266,0.00001504011,0.0004991242,0.00001598036,0.00001034755,0.0002063616,0.00004022089,0.000008755404,0.0000775337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03052251,"threshold_uncertainty_score":0.5003085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01396898966182275,"score_gpt":0.3312783552135731,"score_spread":0.3173093655517504,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}