{"id":"W4390194888","doi":"10.1002/alz.079569","title":"Hyperspectral retinal imaging as a biomarker for Alzheimer’s disease","year":2023,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Optina Diagnostics (Canada)","funders":"","keywords":"Hyperspectral imaging; Retinal; Dementia; Retina; Biomarker; Medicine; Amyloid (mycology); Pathology; Artificial intelligence; Pattern recognition (psychology); Ophthalmology; Computer science; Neuroscience; Disease; Psychology; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003829429,0.0002626584,0.0003212823,0.0003024284,0.0002252964,0.00008283759,0.0001643686,0.00003621078,0.0004623516],"category_scores_gemma":[0.0001010627,0.000239165,0.0004464119,0.0005881383,0.0001275619,0.0001383216,0.00007688326,0.0001265437,0.0007067418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007281955,"about_ca_system_score_gemma":0.0001197868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001088943,"about_ca_topic_score_gemma":0.000001960675,"domain_scores_codex":[0.9980348,0.00004515511,0.0003474564,0.0005592502,0.0003866682,0.0006266333],"domain_scores_gemma":[0.998813,0.00007471674,0.0001003918,0.0004563807,0.00015557,0.0003999815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.002384824,0.0007084191,0.2188254,0.00007995389,0.06611763,0.00183584,0.0007141183,0.00001715186,0.03296974,0.0023674,0.3797306,0.2942489],"study_design_scores_gemma":[0.006574329,0.0004109844,0.2909068,0.0003656965,0.3820977,0.0002744373,0.001450132,0.0664289,0.02280551,0.003704834,0.2231565,0.001824213],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.3593344,0.4806382,0.002656903,0.1182639,0.002077931,0.003900958,0.0001981687,0.003181739,0.02974777],"genre_scores_gemma":[0.9948077,0.0001372557,0.002803049,0.001272399,0.0002811375,0.0001129552,0.0002912188,0.00006949892,0.0002247408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6354733,"threshold_uncertainty_score":0.9752864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04241413694170688,"score_gpt":0.3341995960906968,"score_spread":0.2917854591489899,"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."}}