Qure.ai qXR chest X-ray AI for tuberculosis

entry · p2026-09-06-218 · validated

approximately a 15.8% increase in TB case detection could be attributed to qXR

tech: qxr-tb-screening
passes the definition as: a deep-learning chest X-ray classifier fit to radiologist-labelled radiographs, flagging presumptive pulmonary TB
from: 2018-12
region: IN
domain: health
side: benefit
people: 8,303 people who received both AI and radiologist chest X-ray reads (2020-02)
effect: 15.8 percent (2020-02) — increase in TB case detection attributed to qXR - cases the AI flagged that radiologists had not called presumptive
reversible: yes
who holds the switch: owner:Qure.ai and the participating labs
attribution: named
source kind: primary
the statistic: In Nagpur, India, between December 2018 and February 2020, 8,303 of 8,731 individuals (95.1%) received both qXR AI and radiologist chest X-ray reads; 2,303 (27.7%) were flagged with radiological signs of TB and 213 were confirmed with TB (37 clinical, 176 microbiological). Roughly a 15.8% increase in TB case detection was attributed to qXR; bacteriological notifications rose 50% over baseline.
source: https://journals.plos.org/digitalhealth/article?id=10.1371%2Fjournal.pdig.0000404
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 · validatorpass — quote found on the fetched page (exact match; HTTP 200 text/html;charset=UTF-8)
2026-09-06T10:21:26-04:00 · sessionseverity — a diagnosis in service: TB cases found that radiologists had not flagged

The proposal as it arrived (JSON)

{
 "id": "p2026-09-06-218",
 "received": "2026-09-06T10:20:12-04:00",
 "proposer": "researcher (opus), brief 2026-09-06 second harvest, china-india-africa-latam",
 "kind": "entry",
 "sha": "68bb1dce4a1d7b28",
 "data": {
  "kind": "entry",
  "tech": "qxr-tb-screening",
  "tech_name": "Qure.ai qXR chest X-ray AI for tuberculosis",
  "definition": "a deep-learning chest X-ray classifier fit to radiologist-labelled radiographs, flagging presumptive pulmonary TB",
  "from": "2018-12",
  "region": "IN",
  "domain": "health",
  "side": "benefit",
  "people": {
   "n": 8303,
   "unit": "people who received both AI and radiologist chest X-ray reads",
   "date": "2020-02"
  },
  "effect": {
   "n": 15.8,
   "unit": "percent",
   "date": "2020-02",
   "what": "increase in TB case detection attributed to qXR - cases the AI flagged that radiologists had not called presumptive"
  },
  "reversible": true,
  "switch": "owner:Qure.ai and the participating labs",
  "statistic": "In Nagpur, India, between December 2018 and February 2020, 8,303 of 8,731 individuals (95.1%) received both qXR AI and radiologist chest X-ray reads; 2,303 (27.7%) were flagged with radiological signs of TB and 213 were confirmed with TB (37 clinical, 176 microbiological). Roughly a 15.8% increase in TB case detection was attributed to qXR; bacteriological notifications rose 50% over baseline.",
  "source": "https://journals.plos.org/digitalhealth/article?id=10.1371%2Fjournal.pdig.0000404",
  "quote": "approximately a 15.8% increase in TB case detection could be attributed to qXR",
  "attribution": "named",
  "source_kind": "primary"
 },
 "from_file": "impacts/harvest/2026-09-06-china-india-africa-latam.md"
}