{"id":"W4318615266","doi":"10.1016/j.aca.2023.340868","title":"Deep learning-assisted ultra-accurate smartphone testing of paper-based colorimetric ELISA assays","year":2023,"lang":"en","type":"article","venue":"Analytica Chimica Acta","topic":"Biosensors and Analytical Detection","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"University of Liverpool","keywords":"Deep learning; Reliability (semiconductor); Artificial intelligence; Process (computing); Computer science; Feature (linguistics); Smartphone application; Microfluidics; Machine learning; Resource (disambiguation); Area under curve; Pattern recognition (psychology); Nanotechnology; Multimedia; Bioinformatics; Materials science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003502021,0.0009457736,0.0005980651,0.0005020483,0.0001527321,0.0005685336,0.001002741,0.0005693945,0.00239175],"category_scores_gemma":[0.001161764,0.0003087699,0.0002966263,0.0002953646,0.0001427582,0.000479605,0.0007697124,0.0007231275,0.001355413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003278636,"about_ca_system_score_gemma":0.0006151854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002634645,"about_ca_topic_score_gemma":0.008005054,"domain_scores_codex":[0.999655,0.00003603198,0.00001948577,0.0000939922,0.0001369796,0.00005848037],"domain_scores_gemma":[0.9994423,0.0001977746,0.00007629809,0.00004942815,0.0002004641,0.00003368182],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005361127,0.0004954559,0.008004699,0.0003466179,0.0001067753,0.0003380226,0.00007656782,0.05595762,0.1439334,0.0008203587,0.007271813,0.7821125],"study_design_scores_gemma":[0.00002067842,0.0001822114,0.002912113,0.00001702434,0.00002421126,0.0001531229,0.00002795584,0.9459884,0.04782125,0.0008003775,0.002032993,0.00001962592],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2395723,0.001498224,0.7385566,0.0005173216,0.0003456799,0.0001410785,0.001175895,0.01105127,0.007141531],"genre_scores_gemma":[0.8436919,0.0003881752,0.1466825,0.0003649904,0.00006423447,0.0001169071,0.0008100294,0.0001292992,0.007752014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002634645,"threshold_uncertainty_score":0.008001208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0229223250171122,"score_gpt":0.232172847892567,"score_spread":0.2092505228754548,"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."}}