{
  "id": "AIBD-0275",
  "title": "Google deep-learning DR screening in Thailand's national program: 7,651 patients, specialist-level accuracy",
  "summary": "At nine primary-care sites (Dec 2018-Mar 2020) Google's deep-learning system graded fundus photos in real time, 94.7% accuracy for vision-threatening DR, 2,412 referrals; a fifth of images rejected.",
  "date_observed": "2022-03-07",
  "date_basis": "unassessed",
  "date_precision": "unassessed",
  "benefit_status": null,
  "source_collection": null,
  "source_entry": null,
  "account": "Ruamviboonsuk et al. (Lancet Digital Health, 7 March 2022) report a prospective interventional cohort study funded by Google and Rajavithi Hospital with Google Health co-authors. It deployed a deep-learning system at nine primary-care sites of Thailand's national diabetic retinopathy screening program between 12 December 2018 and 29 March 2020. Of 7,940 patients screened, 7,651 were analyzed and 2,412 (31.5%) were referred for retinopathy, macular edema, ungradable images or low acuity. For vision-threatening retinopathy the system's accuracy was 94.7%, sensitivity 91.4% and specificity 95.4%. The retina-specialist over-readers scored 93.5%, 84.8% and 95.5%. MIT Technology Review (27 April 2020) reported Google's own field study of the deployment in 11 clinics. Over a fifth of images were rejected, nurses were frustrated by rejections and slow internet, and when it worked the system sped screening. The Nation Thailand (10 February 2025) reported Google and Perceptra planning AI screening for about 1 million people in Thailand over a decade. It cited over 600,000 patients screened with the model globally. The paper's abstract is among the sources.",
  "category": "benefit created",
  "unexpected": false,
  "purpose": "Real-time automated grading of fundus photographs for diabetic retinopathy in a national screening program",
  "system": "Google Health deep-learning diabetic retinopathy screening system",
  "model_version": "ARDA",
  "developer": "Google (Google Health)",
  "deployer": "Thailand national diabetic retinopathy screening program (Ministry of Public Health guidelines) with Rajavithi Hospital, Bangkok",
  "location": "Thailand (nine primary-care sites)",
  "domain": "Health; ophthalmology",
  "segment": "People with diabetes due for retinopathy screening",
  "benefit_type": "Improved Physical Health",
  "taxonomy_note": null,
  "registry_ids": {},
  "ratings": [
    {
      "group": "personal",
      "depth": 2,
      "reason": "7,651 patients received real-time grading with specialist-level accuracy and 2,412 were referred."
    },
    {
      "group": "organizational",
      "depth": 1,
      "reason": "Real-time results in primary care; field reporting notes speed gains when the system worked and rejections and connectivity problems when it did not."
    },
    {
      "group": "societal",
      "depth": null,
      "reason": "No population-level vision outcome reported."
    }
  ],
  "ai_role": {
    "status": "assessed",
    "statement": "The deep-learning grades and referral recommendations were delivered in real time with specialist over-reading as a safety net. Accuracy figures come from the vendor-funded, vendor co-authored prospective study. An independent news account of Google's field study records substantial image rejection and nurse frustration."
  },
  "evidence": [
    {
      "kind": "peer-reviewed study",
      "citation": "Ruamviboonsuk P, Tiwari R, Sayres R, et al. Lancet Digit Health 4(4):e235-e244 (2022)",
      "title": "Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study",
      "url": "https://doi.org/10.1016/s2589-7500(22)00017-6",
      "date": "2022-03-07",
      "written_by": "makers",
      "quote": "A deep-learning system can deliver real-time diabetic retinopathy detection capability similar to retina specialists in community-based screening settings."
    },
    {
      "kind": "news report",
      "citation": "Heaven WD. MIT Technology Review, 27 Apr 2020",
      "title": "Google's medical AI was super accurate in a lab. Real life was a different story.",
      "url": "https://www.technologyreview.com/2020/04/27/1000658/google-medical-ai-accurate-lab-real-life-clinic-covid-diabetes-retina-disease/",
      "date": "2020-04-27",
      "written_by": "independent",
      "quote": "Nurses felt frustrated, especially when they believed the rejected scans showed no signs of disease and the follow-up appointments were unnecessary."
    },
    {
      "kind": "news report",
      "citation": "The Nation Thailand, 10 Feb 2025",
      "title": "Google, Perceptra offer AI-powered diabetic retinopathy screening",
      "url": "https://www.nationthailand.com/business/tech/40046121",
      "date": "2025-02-10",
      "written_by": "independent",
      "quote": "From initial research to the first patient screening in Thailand, we are committed to translating the potential of AI into meaningful change."
    },
    {
      "kind": "other",
      "citation": "Nature Medicine 32:3525-3527 (23 Sep 2026). Comment by Google and partner-site authors on scaling deep-learning diabetic retinopathy screening across India, Thailand and Australia.",
      "title": "Nature Medicine comment on scaling a deep learning diabetic retinopathy tool across India, Thailand and Australia",
      "url": "https://www.nature.com/articles/s41591-026-04643-9",
      "date": "2026-09-23",
      "written_by": "makers",
      "quote": null
    },
    {
      "kind": "other",
      "citation": "AI Weekly (6 Oct 2026). Google ARDA eye AI tops a million patients in three countries.",
      "title": "Google ARDA eye AI tops a million patients in three countries",
      "url": "https://aiweekly.co/alerts/google-arda-eye-ai-tops-a-million-patients-in-three-countries",
      "date": "2026-10-06",
      "written_by": "independent",
      "quote": null
    }
  ],
  "replication": {
    "produced_by": [
      "Fundus photography at primary-care sites",
      "Real-time deep-learning grading with referral recommendations",
      "Retina-specialist over-reading as a safety mechanism"
    ],
    "must_hold": [
      "Image quality sufficient for grading (a fifth of images were rejected in the 2020 field study)",
      "Reliable connectivity",
      "Referral pathways able to absorb referrals"
    ],
    "echoes": [
      {
        "date": "2025-02-10",
        "setting": "Google-Perceptra program to screen about 1 million people in Thailand over a decade (announcement)",
        "model_version": null,
        "outcome": "unknown",
        "source": "https://www.nationthailand.com/business/tech/40046121"
      },
      {
        "date": "2022-10-15",
        "setting": "Same Thai community-based national screening program, 4,852 participants and eight non-mydriatic camera types: the deep-learning algorithm showed better sensitivity, specificity and kappa than human graders (Srinivasan et al., Life)",
        "model_version": null,
        "outcome": "recurred",
        "source": "https://doi.org/10.3390/life12101610"
      }
    ]
  },
  "paired_incident": null,
  "headline": "Google DR screening in Thailand matches specialists at 94.7%",
  "metric": "94.7% accuracy for vision-threatening DR, 2,412 referrals",
  "comparator": {
    "against": "regional retina specialist over-readers, measured against an adjudicated reference standard from fellowship-trained retina specialists",
    "before": "an accuracy of 93·5 (91·7-95·0; p=0·17), a sensitivity of 84·8% (79·4-90·0; p=0·024), and specificity of 95·5% (94·1-96·7; p=0·98)",
    "after": "an accuracy of 94·7% (95% CI 93·0-96·2), sensitivity of 91·4% (87·1-95·0), and specificity of 95·4% (94·1-96·7)",
    "basis": "measured",
    "quote": "For vision-threatening diabetic retinopathy, the deep-learning system had an accuracy of 94·7% (95% CI 93·0-96·2), sensitivity of 91·4% (87·1-95·0), and specificity of 95·4% (94·1-96·7). The retina specialist over-readers had an accuracy of 93·5 (91·7-95·0; p=0·17), a sensitivity of 84·8% (79·4-90·0; p=0·024), and specificity of 95·5% (94·1-96·7; p=0·98).",
    "url": "https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=TITLE:%22Real-time%20diabetic%20retinopathy%20screening%20by%20deep%20learning%20in%20a%20multisite%20national%20screening%20programme%22&resultType=core&format=json"
  },
  "later": {
    "status": "scaled",
    "date": "2026-09-23",
    "note": "A Nature Medicine comment of 23 September 2026 by the Google and partner-site authors describes scaling the same deep-learning screening tool across India, Thailand and Australia; an October 2026 AI Weekly alert summarizing it says the model, ARDA, has now screened more than one million patients, with Perceptra licensed to run screening in Thailand.",
    "quote": "Scaling a successful deep learning tool across three highly distinct settings – in India, Thailand and Australia — offers cross-cutting insights that may inform the expansion of healthcare artificial intelligence globally.",
    "url": "https://www.nature.com/articles/s41591-026-04643-9"
  },
  "value": null,
  "developer_country": "United States",
  "deployer_country": "Thailand",
  "unrated_because": null,
  "brief_notes": null,
  "brief": null,
  "revisions": [
    {
      "date": "2026-10-20",
      "change": "Record drafted from the cited sources.",
      "source": null,
      "editor": "AIBD"
    },
    {
      "date": "2026-10-20",
      "change": "Merged a second write-up of the same study: added the 2022 Life replication in the same Thai program.",
      "source": null,
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Benefit type set to Improved Physical Health under Trustible's full taxonomy of 23 types; it was Improved Accessibility among the six first used.",
      "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.",
      "source": "https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=TITLE:%22Real-time%20diabetic%20retinopathy%20screening%20by%20deep%20learning%20in%20a%20multisite%20national%20screening%20programme%22&resultType=core&format=json; https://www.nature.com/articles/s41591-026-04643-9; https://aiweekly.co/alerts/google-arda-eye-ai-tops-a-million-patients-in-three-countries",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
      "source": "https://en.wikipedia.org/wiki/Google; https://en.wikipedia.org/wiki/Ministry_of_Public_Health_(Thailand)",
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Prose pass: account, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
      "source": null,
      "editor": "AIBD"
    },
    {
      "date": "2026-10-21",
      "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.",
      "source": null,
      "editor": "AIBD"
    }
  ],
  "confidence": "reported",
  "shade": "medium",
  "claim_status": "Independently reported",
  "claim_basis": "Sources: two independent news reports, one other independent source, the makers' peer-reviewed study and the makers' other. The cited evidence includes no independent study or report and no finding by a regulator or court.",
  "profile": {
    "case_id": "AIBD-0275",
    "catalog_version": "1.0.0",
    "source_fingerprint": "0adfb886600678a53c3c7a6c0d4ba16d4dfa39acb3a54e9ff9f660087546e588",
    "collection_refs": [
      {
        "collection_id": "aibd",
        "version": "snapshot-8bf7cfec9cb185aa"
      },
      {
        "collection_id": "aibd",
        "version": "2026-10-25"
      },
      {
        "collection_id": "viator",
        "version": "2026-10-25"
      }
    ],
    "source_ids": [
      "AIBD-0275-source-0001",
      "AIBD-0275-source-0002",
      "AIBD-0275-source-0003",
      "AIBD-0275-source-0004",
      "AIBD-0275-source-0005"
    ],
    "families": {
      "strategic assessments": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "evaluations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "monetary observations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      },
      "institutional decisions": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "record_ids": []
      }
    },
    "fields": {
      "actors[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "developer": "Google (Google Health)",
            "deployer": "Thailand national diabetic retinopathy screening program (Ministry of Public Health guidelines) with Rajavithi Hospital, Bangkok"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "developer",
            "deployer"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "actors[].ownership_control": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "ai_contribution": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ai_role": {
              "status": "assessed",
              "statement": "The deep-learning grades and referral recommendations were delivered in real time with specialist over-reading as a safety net. Accuracy figures come from the vendor-funded, vendor co-authored prospective study. An independent news account of Google's field study records substantial image rejection and nurse frustration."
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ai_role"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "ai_relationship": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "category": "benefit created",
            "ai_role": {
              "status": "assessed",
              "statement": "The deep-learning grades and referral recommendations were delivered in real time with specialist over-reading as a safety net. Accuracy figures come from the vendor-funded, vendor co-authored prospective study. An independent news account of Google's field study records substantial image rejection and nurse frustration."
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ai_role",
            "category"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].alternatives": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].assessor_date": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].depth": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "personal",
                "depth": 2,
                "reason": "7,651 patients received real-time grading with specialist-level accuracy and 2,412 were referred."
              },
              {
                "group": "organizational",
                "depth": 1,
                "reason": "Real-time results in primary care; field reporting notes speed gains when the system worked and rejections and connectivity problems when it did not."
              },
              {
                "group": "societal",
                "reason": "No population-level vision outcome reported."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].display_confidence": {
        "state": "value_present",
        "value": {
          "kind": "structured",
          "data": {
            "confidence": "medium",
            "evidence_word": "reported",
            "claim_status": "Independently reported",
            "basis": "Sources: two independent news reports, one other independent source, the makers' peer-reviewed study and the makers' other. The cited evidence includes no independent study or report and no finding by a regulator or court.",
            "interpretation": "Existing display rule preserved; the richer outcome-specific confidence question still needs review."
          }
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Derived from the existing case display properties; not a new evidentiary judgment.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].rationale": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "personal",
                "depth": 2,
                "reason": "7,651 patients received real-time grading with specialist-level accuracy and 2,412 were referred."
              },
              {
                "group": "organizational",
                "depth": 1,
                "reason": "Real-time results in primary care; field reporting notes speed gains when the system worked and rejections and connectivity problems when it did not."
              },
              {
                "group": "societal",
                "reason": "No population-level vision outcome reported."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "assessments[].rubric_version": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].status_basis": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "assessments[].target": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "personal",
                "depth": 2,
                "reason": "7,651 patients received real-time grading with specialist-level accuracy and 2,412 were referred."
              },
              {
                "group": "organizational",
                "depth": 1,
                "reason": "Real-time results in primary care; field reporting notes speed gains when the system worked and rejections and connectivity problems when it did not."
              },
              {
                "group": "societal",
                "reason": "No population-level vision outcome reported."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "availability": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "brief": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "case_kind": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "case_links[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].evidence_links": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].evidence_strength": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].missingness": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "claims[].proposition": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "cross_border_flows[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "decisions[].action_outcome": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].grounds": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].institution_task": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "decisions[].success_criterion": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "institutional decisions"
      },
      "deployment_stage": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "economics[].amount": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].costs[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].counterfactual": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].currency_price_basis": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].gross_net": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].measure_type": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].period_unit": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].realization": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].recipient_payer": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].return_payback": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "economics[].valuation_method": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "monetary observations"
      },
      "evaluations[].ai_uplift": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].comparator": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].design": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].effect": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].exposure": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].id": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].measurement_method": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].metric": {
        "state": "not_assessed",
        "provenance": {
          "kind": "legacy_record",
          "basis": "Mapped from the existing case description without a new external source review.",
          "record_fields": [
            "metric"
          ],
          "source_refs": []
        },
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations",
        "display": {
          "answer": "94.7% accuracy for vision-threatening DR, 2,412 referrals",
          "editor_note": ""
        }
      },
      "evaluations[].reproduction_materials": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].setting_sample": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "evaluations[].uncertainty_limitations": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "evaluations"
      },
      "external_references[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "follow_up[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "later": {
              "status": "scaled",
              "date": "2026-09-23",
              "note": "A Nature Medicine comment of 23 September 2026 by the Google and partner-site authors describes scaling the same deep-learning screening tool across India, Thailand and Australia; an October 2026 AI Weekly alert summarizing it says the model, ARDA, has now screened more than one million patients, with Perceptra licensed to run screening in Thailand.",
              "quote": "Scaling a successful deep learning tool across three highly distinct settings – in India, Thailand and Australia — offers cross-cutting insights that may inform the expansion of healthcare artificial intelligence globally.",
              "url": "https://www.nature.com/articles/s41591-026-04643-9"
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "later"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "human_oversight": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "id": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "id": "AIBD-0275"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "id"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "infrastructure_dependencies[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].beneficiaries": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].beneficiary_count": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].benefit_type": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "benefit_type": "Improved Physical Health"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "benefit_type"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].claim": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "account": "Ruamviboonsuk et al. (Lancet Digital Health, 7 March 2022) report a prospective interventional cohort study funded by Google and Rajavithi Hospital with Google Health co-authors. It deployed a deep-learning system at nine primary-care sites of Thailand's national diabetic retinopathy screening program between 12 December 2018 and 29 March 2020. Of 7,940 patients screened, 7,651 were analyzed and 2,412 (31.5%) were referred for retinopathy, macular edema, ungradable images or low acuity. For vision-threatening retinopathy the system's accuracy was 94.7%, sensitivity 91.4% and specificity 95.4%. The retina-specialist over-readers scored 93.5%, 84.8% and 95.5%. MIT Technology Review (27 April 2020) reported Google's own field study of the deployment in 11 clinics. Over a fifth of images were rejected, nurses were frustrated by rejections and slow internet, and when it worked the system sped screening. The Nation Thailand (10 February 2025) reported Google and Perceptra planning AI screening for about 1 million people in Thailand over a decade. It cited over 600,000 patients screened with the model globally. The paper's abstract is among the sources.",
            "benefit_type": "Improved Physical Health"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "account",
            "benefit_type"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].distribution": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].duration": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].id": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].stakeholder_group": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "ratings": [
              {
                "group": "personal",
                "depth": 2,
                "reason": "7,651 patients received real-time grading with specialist-level accuracy and 2,412 were referred."
              },
              {
                "group": "organizational",
                "depth": 1,
                "reason": "Real-time results in primary care; field reporting notes speed gains when the system worked and rejections and connectivity problems when it did not."
              },
              {
                "group": "societal",
                "reason": "No population-level vision outcome reported."
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "ratings"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "outcomes[].status": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].tradeoffs": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "outcomes[].unexpected": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "unexpected": false,
            "purpose": "Real-time automated grading of fundus photographs for diabetic retinopathy in a national screening program"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "unexpected",
            "purpose"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "places[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "location": "Thailand (nine primary-care sites)",
            "developer_country": "United States",
            "deployer_country": "Thailand"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "location",
            "developer_country",
            "deployer_country"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "purpose": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "purpose": "Real-time automated grading of fundus photographs for diabetic retinopathy in a national screening program"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "purpose"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "record_dates": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "date_observed": "2022-03-07",
            "revisions": [
              {
                "date": "2026-10-20",
                "change": "Record drafted from the cited sources.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-20",
                "change": "Merged a second write-up of the same study: added the 2022 Life replication in the same Thai program.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Benefit type set to Improved Physical Health under Trustible's full taxonomy of 23 types; it was Improved Accessibility among the six first used.",
                "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.",
                "source": "https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=TITLE:%22Real-time%20diabetic%20retinopathy%20screening%20by%20deep%20learning%20in%20a%20multisite%20national%20screening%20programme%22&resultType=core&format=json; https://www.nature.com/articles/s41591-026-04643-9; https://aiweekly.co/alerts/google-arda-eye-ai-tops-a-million-patients-in-three-countries",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
                "source": "https://en.wikipedia.org/wiki/Google; https://en.wikipedia.org/wiki/Ministry_of_Public_Health_(Thailand)",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Prose pass: account, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.",
                "editor": "AIBD"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "date_observed",
            "revisions"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "replication.attempts[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "replication": {
              "produced_by": [
                "Fundus photography at primary-care sites",
                "Real-time deep-learning grading with referral recommendations",
                "Retina-specialist over-reading as a safety mechanism"
              ],
              "must_hold": [
                "Image quality sufficient for grading (a fifth of images were rejected in the 2020 field study)",
                "Reliable connectivity",
                "Referral pathways able to absorb referrals"
              ],
              "echoes": [
                {
                  "date": "2025-02-10",
                  "setting": "Google-Perceptra program to screen about 1 million people in Thailand over a decade (announcement)",
                  "outcome": "unknown",
                  "source": "https://www.nationthailand.com/business/tech/40046121"
                },
                {
                  "date": "2022-10-15",
                  "setting": "Same Thai community-based national screening program, 4,852 participants and eight non-mydriatic camera types: the deep-learning algorithm showed better sensitivity, specificity and kappa than human graders (Srinivasan et al., Life)",
                  "outcome": "recurred",
                  "source": "https://doi.org/10.3390/life12101610"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "replication.conditions": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "replication": {
              "produced_by": [
                "Fundus photography at primary-care sites",
                "Real-time deep-learning grading with referral recommendations",
                "Retina-specialist over-reading as a safety mechanism"
              ],
              "must_hold": [
                "Image quality sufficient for grading (a fifth of images were rejected in the 2020 field study)",
                "Reliable connectivity",
                "Referral pathways able to absorb referrals"
              ],
              "echoes": [
                {
                  "date": "2025-02-10",
                  "setting": "Google-Perceptra program to screen about 1 million people in Thailand over a decade (announcement)",
                  "outcome": "unknown",
                  "source": "https://www.nationthailand.com/business/tech/40046121"
                },
                {
                  "date": "2022-10-15",
                  "setting": "Same Thai community-based national screening program, 4,852 participants and eight non-mydriatic camera types: the deep-learning algorithm showed better sensitivity, specificity and kappa than human graders (Srinivasan et al., Life)",
                  "outcome": "recurred",
                  "source": "https://doi.org/10.3390/life12101610"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "revision_history[]": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "revisions": [
              {
                "date": "2026-10-20",
                "change": "Record drafted from the cited sources.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-20",
                "change": "Merged a second write-up of the same study: added the 2022 Life replication in the same Thai program.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Benefit type set to Improved Physical Health under Trustible's full taxonomy of 23 types; it was Improved Accessibility among the six first used.",
                "source": "https://trustible.ai/post/a-framework-for-measuring-the-benefits-of-ai/",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Added what the benefit is measured against, what happened since, the model version from the cited sources.",
                "source": "https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=TITLE:%22Real-time%20diabetic%20retinopathy%20screening%20by%20deep%20learning%20in%20a%20multisite%20national%20screening%20programme%22&resultType=core&format=json; https://www.nature.com/articles/s41591-026-04643-9; https://aiweekly.co/alerts/google-arda-eye-ai-tops-a-million-patients-in-three-countries",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Country of the developer and the deployer added from the organization's own site or a registry.",
                "source": "https://en.wikipedia.org/wiki/Google; https://en.wikipedia.org/wiki/Ministry_of_Public_Health_(Thailand)",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Prose pass: account, the system's part rewritten in shorter sentences with abbreviations expanded; facts, figures and quotations unchanged.",
                "editor": "AIBD"
              },
              {
                "date": "2026-10-21",
                "change": "Notes about which sources could be read were reworded for readers; facts, figures and quotations unchanged.",
                "editor": "AIBD"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "revisions"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sector": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "domain": "Health; ophthalmology",
            "segment": "People with diabetes due for retinopathy screening"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "domain",
            "segment"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].access_version": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "sources[].citation_locator": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "evidence": [
              {
                "kind": "peer-reviewed study",
                "citation": "Ruamviboonsuk P, Tiwari R, Sayres R, et al. Lancet Digit Health 4(4):e235-e244 (2022)",
                "title": "Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study",
                "url": "https://doi.org/10.1016/s2589-7500(22)00017-6",
                "date": "2022-03-07",
                "written_by": "makers",
                "quote": "A deep-learning system can deliver real-time diabetic retinopathy detection capability similar to retina specialists in community-based screening settings."
              },
              {
                "kind": "news report",
                "citation": "Heaven WD. MIT Technology Review, 27 Apr 2020",
                "title": "Google's medical AI was super accurate in a lab. Real life was a different story.",
                "url": "https://www.technologyreview.com/2020/04/27/1000658/google-medical-ai-accurate-lab-real-life-clinic-covid-diabetes-retina-disease/",
                "date": "2020-04-27",
                "written_by": "independent",
                "quote": "Nurses felt frustrated, especially when they believed the rejected scans showed no signs of disease and the follow-up appointments were unnecessary."
              },
              {
                "kind": "news report",
                "citation": "The Nation Thailand, 10 Feb 2025",
                "title": "Google, Perceptra offer AI-powered diabetic retinopathy screening",
                "url": "https://www.nationthailand.com/business/tech/40046121",
                "date": "2025-02-10",
                "written_by": "independent",
                "quote": "From initial research to the first patient screening in Thailand, we are committed to translating the potential of AI into meaningful change."
              },
              {
                "kind": "other",
                "citation": "Nature Medicine 32:3525-3527 (23 Sep 2026). Comment by Google and partner-site authors on scaling deep-learning diabetic retinopathy screening across India, Thailand and Australia.",
                "title": "Nature Medicine comment on scaling a deep learning diabetic retinopathy tool across India, Thailand and Australia",
                "url": "https://www.nature.com/articles/s41591-026-04643-9",
                "date": "2026-09-23",
                "written_by": "makers"
              },
              {
                "kind": "other",
                "citation": "AI Weekly (6 Oct 2026). Google ARDA eye AI tops a million patients in three countries.",
                "title": "Google ARDA eye AI tops a million patients in three countries",
                "url": "https://aiweekly.co/alerts/google-arda-eye-ai-tops-a-million-patients-in-three-countries",
                "date": "2026-10-06",
                "written_by": "independent"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "evidence"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].id": {
        "state": "value_present",
        "value": {
          "kind": "identifiers",
          "identifiers": [
            "AIBD-0275-source-0001",
            "AIBD-0275-source-0002",
            "AIBD-0275-source-0003",
            "AIBD-0275-source-0004",
            "AIBD-0275-source-0005"
          ],
          "role": "Existing evidence items, in their original order"
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Stable within the fingerprinted record version; no source content or source review has been added.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "complete"
      },
      "sources[].language": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "sources[].relationship": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "evidence": [
              {
                "kind": "peer-reviewed study",
                "citation": "Ruamviboonsuk P, Tiwari R, Sayres R, et al. Lancet Digit Health 4(4):e235-e244 (2022)",
                "title": "Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study",
                "url": "https://doi.org/10.1016/s2589-7500(22)00017-6",
                "date": "2022-03-07",
                "written_by": "makers",
                "quote": "A deep-learning system can deliver real-time diabetic retinopathy detection capability similar to retina specialists in community-based screening settings."
              },
              {
                "kind": "news report",
                "citation": "Heaven WD. MIT Technology Review, 27 Apr 2020",
                "title": "Google's medical AI was super accurate in a lab. Real life was a different story.",
                "url": "https://www.technologyreview.com/2020/04/27/1000658/google-medical-ai-accurate-lab-real-life-clinic-covid-diabetes-retina-disease/",
                "date": "2020-04-27",
                "written_by": "independent",
                "quote": "Nurses felt frustrated, especially when they believed the rejected scans showed no signs of disease and the follow-up appointments were unnecessary."
              },
              {
                "kind": "news report",
                "citation": "The Nation Thailand, 10 Feb 2025",
                "title": "Google, Perceptra offer AI-powered diabetic retinopathy screening",
                "url": "https://www.nationthailand.com/business/tech/40046121",
                "date": "2025-02-10",
                "written_by": "independent",
                "quote": "From initial research to the first patient screening in Thailand, we are committed to translating the potential of AI into meaningful change."
              },
              {
                "kind": "other",
                "citation": "Nature Medicine 32:3525-3527 (23 Sep 2026). Comment by Google and partner-site authors on scaling deep-learning diabetic retinopathy screening across India, Thailand and Australia.",
                "title": "Nature Medicine comment on scaling a deep learning diabetic retinopathy tool across India, Thailand and Australia",
                "url": "https://www.nature.com/articles/s41591-026-04643-9",
                "date": "2026-09-23",
                "written_by": "makers"
              },
              {
                "kind": "other",
                "citation": "AI Weekly (6 Oct 2026). Google ARDA eye AI tops a million patients in three countries.",
                "title": "Google ARDA eye AI tops a million patients in three countries",
                "url": "https://aiweekly.co/alerts/google-arda-eye-ai-tops-a-million-patients-in-three-countries",
                "date": "2026-10-06",
                "written_by": "independent"
              }
            ]
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "evidence"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "sources[].upstream_sources": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "strategic_assessments[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial",
        "family": "strategic assessments"
      },
      "summary": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "summary": "At nine primary-care sites (Dec 2018-Mar 2020) Google's deep-learning system graded fundus photos in real time, 94.7% accuracy for vision-threatening DR, 2,412 referrals; a fifth of images rejected.",
            "account": "Ruamviboonsuk et al. (Lancet Digital Health, 7 March 2022) report a prospective interventional cohort study funded by Google and Rajavithi Hospital with Google Health co-authors. It deployed a deep-learning system at nine primary-care sites of Thailand's national diabetic retinopathy screening program between 12 December 2018 and 29 March 2020. Of 7,940 patients screened, 7,651 were analyzed and 2,412 (31.5%) were referred for retinopathy, macular edema, ungradable images or low acuity. For vision-threatening retinopathy the system's accuracy was 94.7%, sensitivity 91.4% and specificity 95.4%. The retina-specialist over-readers scored 93.5%, 84.8% and 95.5%. MIT Technology Review (27 April 2020) reported Google's own field study of the deployment in 11 clinics. Over a fifth of images were rejected, nurses were frustrated by rejections and slow internet, and when it worked the system sped screening. The Nation Thailand (10 February 2025) reported Google and Perceptra planning AI screening for about 1 million people in Thailand over a decade. It cited over 600,000 patients screened with the model globally. The paper's abstract is among the sources."
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "summary",
            "account"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].autonomy_permissions": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].component_role": {
        "state": "value_present",
        "value": {
          "kind": "text",
          "text": "The model graded retinal images for signs of diabetic retinopathy and recommended referral."
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Restated the mechanical task already described in the existing system and AI-role fields. No new source review is claimed.",
          "record_fields": [
            "system",
            "ai_role"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].deployment_configuration": {
        "state": "value_present",
        "value": {
          "kind": "text",
          "text": "The deployment used the Automated Retinal Disease Assessment system, ARDA."
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Separated the model, software, hardware, or operation already described in the existing record. No new source review is claimed.",
          "record_fields": [
            "model_version",
            "system",
            "ai_role"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].inputs_outputs": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].model_name": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "systems[].model_version": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "model_version": "ARDA"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "model_version"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial",
        "display": {
          "answer": "Exact release not established.",
          "editor_note": ""
        }
      },
      "systems[].product_name": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "system": "Google Health deep-learning diabetic retinopathy screening system"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "system"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "systems[].provider": {
        "state": "value_present",
        "value": {
          "kind": "structured",
          "data": {
            "application_developer": "Google (Google Health)"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Mapped from the existing case description without a new external source review.",
          "record_fields": [
            "developer"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "taxonomy_crosswalks[]": {
        "state": "not_assessed",
        "review_state": "not_assessed",
        "coverage": "partial"
      },
      "title": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "title": "Google deep-learning DR screening in Thailand's national program: 7,651 patients, specialist-level accuracy",
            "headline": "Google DR screening in Thailand matches specialists at 94.7%"
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "title",
            "headline"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      },
      "version": {
        "state": "value_present",
        "value": {
          "kind": "identifiers",
          "identifiers": [
            "0adfb886600678a53c3c7a6c0d4ba16d4dfa39acb3a54e9ff9f660087546e588"
          ],
          "role": "SHA-256 of normalized original case data"
        },
        "provenance": {
          "kind": "curatorial",
          "basis": "Deterministic content version assigned by the local migration.",
          "record_fields": [],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "complete"
      },
      "workflow": {
        "state": "value_present",
        "value": {
          "kind": "record_fields",
          "fields": {
            "account": "Ruamviboonsuk et al. (Lancet Digital Health, 7 March 2022) report a prospective interventional cohort study funded by Google and Rajavithi Hospital with Google Health co-authors. It deployed a deep-learning system at nine primary-care sites of Thailand's national diabetic retinopathy screening program between 12 December 2018 and 29 March 2020. Of 7,940 patients screened, 7,651 were analyzed and 2,412 (31.5%) were referred for retinopathy, macular edema, ungradable images or low acuity. For vision-threatening retinopathy the system's accuracy was 94.7%, sensitivity 91.4% and specificity 95.4%. The retina-specialist over-readers scored 93.5%, 84.8% and 95.5%. MIT Technology Review (27 April 2020) reported Google's own field study of the deployment in 11 clinics. Over a fifth of images were rejected, nurses were frustrated by rejections and slow internet, and when it worked the system sped screening. The Nation Thailand (10 February 2025) reported Google and Perceptra planning AI screening for about 1 million people in Thailand over a decade. It cited over 600,000 patients screened with the model globally. The paper's abstract is among the sources.",
            "replication": {
              "produced_by": [
                "Fundus photography at primary-care sites",
                "Real-time deep-learning grading with referral recommendations",
                "Retina-specialist over-reading as a safety mechanism"
              ],
              "must_hold": [
                "Image quality sufficient for grading (a fifth of images were rejected in the 2020 field study)",
                "Reliable connectivity",
                "Referral pathways able to absorb referrals"
              ],
              "echoes": [
                {
                  "date": "2025-02-10",
                  "setting": "Google-Perceptra program to screen about 1 million people in Thailand over a decade (announcement)",
                  "outcome": "unknown",
                  "source": "https://www.nationthailand.com/business/tech/40046121"
                },
                {
                  "date": "2022-10-15",
                  "setting": "Same Thai community-based national screening program, 4,852 participants and eight non-mydriatic camera types: the deep-learning algorithm showed better sensitivity, specificity and kappa than human graders (Srinivasan et al., Life)",
                  "outcome": "recurred",
                  "source": "https://doi.org/10.3390/life12101610"
                }
              ]
            }
          }
        },
        "provenance": {
          "kind": "legacy_record",
          "basis": "Preserved from the existing AIBD record; external sources were not rechecked.",
          "record_fields": [
            "account",
            "replication"
          ],
          "source_refs": []
        },
        "review_state": "record_mapped",
        "coverage": "partial"
      }
    },
    "summary": {
      "total": 91,
      "addressed": 91,
      "known": 32,
      "reviewed": 0,
      "record_mapped": 32,
      "not_assessed": 59,
      "complete": false,
      "by_state": {
        "value_present": 32,
        "not_reported": 0,
        "unresolved": 0,
        "not_assessed": 59,
        "not_applicable": 0,
        "withheld": 0,
        "source_unavailable": 0
      }
    }
  }
}