{"id":"W4392193191","doi":"10.1186/s13000-024-01464-7","title":"Challenges and barriers of using large language models (LLM) such as ChatGPT for diagnostic medicine with a focus on digital pathology – a recent scoping review","year":2024,"lang":"en","type":"article","venue":"Diagnostic Pathology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":257,"is_retracted":false,"has_abstract":true,"ca_institutions":"SKiN Health","funders":"","keywords":"Interpretability; Context (archaeology); Medicine; Health care; Autonomy; Political science; Artificial intelligence; Computer 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006482877,0.0002231308,0.000679478,0.000211002,0.00007162917,0.000009312433,0.00006895842,0.0001641363,0.00005500446],"category_scores_gemma":[0.01476596,0.0001677104,0.00005482911,0.0001899971,0.0002412752,0.0001086709,0.00003280252,0.0002120015,0.00001065859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006451624,"about_ca_system_score_gemma":0.0003773783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004909839,"about_ca_topic_score_gemma":0.00009002287,"domain_scores_codex":[0.9982255,0.0001079411,0.0005357232,0.0005305831,0.0001798371,0.0004204357],"domain_scores_gemma":[0.9928787,0.006271833,0.0001236645,0.0003141287,0.000194661,0.0002169964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0004922312,0.0005723334,0.003050158,0.03613511,0.000156821,0.005050593,0.04161917,0.00005368204,0.000474841,0.01947708,0.0004424233,0.8924755],"study_design_scores_gemma":[0.002780953,0.03311376,0.002830823,0.8183446,0.003426946,0.0146723,0.03623668,0.006414703,0.007756527,0.07059598,0.001850748,0.00197601],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.4473352,0.5270185,0.004338567,0.017152,0.000596336,0.002711333,0.00006570707,0.00008236594,0.0006999702],"genre_scores_gemma":[0.796646,0.2013047,0.0001777531,0.001239738,0.0002381924,0.0002913882,0.00005601597,0.00003563253,0.00001060657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8904995,"threshold_uncertainty_score":0.9935331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1529853727439693,"score_gpt":0.4414231193446899,"score_spread":0.2884377466007206,"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."}}