Deep-learning diabetic retinopathy screening in China's Metabolic Management Centres

entry · p2026-09-06-214 · quote not found

47 269 patients with diabetes aged 18 years or older from 155 MMCs in China were enrolled

tech: dl-dr-screening-cn
passes the definition as: deep-learning classifiers fit to graded fundus photographs, grading diabetic retinopathy and deciding referral
from: 2018-06
region: CN
domain: health
side: benefit
people: 47,269 patients with diabetes screened (2019-08)
effect: 24.4 percent (2019-08) — referable diabetic retinopathy found in 24.4% of gradable participants, i.e. roughly ten thousand people identified as needing a specialist, at 83.3% sensitivity and 92.5% specificity
reversible: yes
who holds the switch: owner:the participating hospitals and algorithm vendors
attribution: named
source kind: primary
the statistic: 47,269 patients with diabetes aged 18 or older were enrolled from 155 Metabolic Management Centres across 26 provinces of China between June 2018 and August 2019 and screened by a deep-learning system; estimated prevalence of referable DR was 24.4% (95% CI 24.0-24.8), with 83.3% sensitivity and 92.5% specificity.
source: https://pmc.ncbi.nlm.nih.gov/articles/PMC7580048/
proposed by: researcher (opus), brief 2026-09-06 second harvest, china-india-africa-latam
received: 2026-09-06T10:20:12-04:00
harvest report: impacts/harvest/2026-09-06-china-india-africa-latam.md

Rulings, in order

2026-09-06T10:21:26-04:00 · validatorfail — quote not found on the fetched page (HTTP 200 text/html; charset=utf-8, 90023 chars)
2026-09-06T10:21:26-04:00 · sessionseverity — a diagnosis in service: referable retinopathy found and referred

The proposal as it arrived (JSON)

{
 "id": "p2026-09-06-214",
 "received": "2026-09-06T10:20:12-04:00",
 "proposer": "researcher (opus), brief 2026-09-06 second harvest, china-india-africa-latam",
 "kind": "entry",
 "sha": "b819b0b5b5e0beae",
 "data": {
  "kind": "entry",
  "tech": "dl-dr-screening-cn",
  "tech_name": "Deep-learning diabetic retinopathy screening in China's Metabolic Management Centres",
  "definition": "deep-learning classifiers fit to graded fundus photographs, grading diabetic retinopathy and deciding referral",
  "from": "2018-06",
  "region": "CN",
  "domain": "health",
  "side": "benefit",
  "people": {
   "n": 47269,
   "unit": "patients with diabetes screened",
   "date": "2019-08"
  },
  "effect": {
   "n": 24.4,
   "unit": "percent",
   "date": "2019-08",
   "what": "referable diabetic retinopathy found in 24.4% of gradable participants, i.e. roughly ten thousand people identified as needing a specialist, at 83.3% sensitivity and 92.5% specificity"
  },
  "reversible": true,
  "switch": "owner:the participating hospitals and algorithm vendors",
  "statistic": "47,269 patients with diabetes aged 18 or older were enrolled from 155 Metabolic Management Centres across 26 provinces of China between June 2018 and August 2019 and screened by a deep-learning system; estimated prevalence of referable DR was 24.4% (95% CI 24.0-24.8), with 83.3% sensitivity and 92.5% specificity.",
  "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC7580048/",
  "quote": "47 269 patients with diabetes aged 18 years or older from 155 MMCs in China were enrolled",
  "attribution": "named",
  "source_kind": "primary"
 },
 "from_file": "impacts/harvest/2026-09-06-china-india-africa-latam.md"
}