Prospective Multi-Site Validation of AI to Detect Tuberculosis and Chest X-Ray Abnormalities
The CXR TB AI was noninferior to radiologists for active pulmonary TB triaging in a population with a high TB and HIV burden. Neither the TB AI nor the radiologists met WHO recommendations for sensitivity in the study population. AI can also be used to detect other CXR abnormalities in the same population.
Authors
- Shravya Shetty (ORCID: https://orcid.org/0000-0003-3783-3172)
- Monde Muyoyeta (ORCID: https://orcid.org/0000-0003-3609-5403)
- Krishnan Eswaran (ORCID: https://orcid.org/0000-0003-0241-5771)
- Daniel I Golden (ORCID: https://orcid.org/0000-0002-1114-3184)
- Katherine Chou (ORCID: https://orcid.org/0000-0002-4680-3381)
- Atilla P. Kiraly (ORCID: https://orcid.org/0000-0002-6613-3581)
- Nsala Sanjase (ORCID: https://orcid.org/0000-0001-6103-0068)
- Andrew Sellergren (ORCID: https://orcid.org/0000-0002-5260-8013)
- Daniel Tse (ORCID: https://orcid.org/0000-0001-5315-8539)
- Shahar Jamshy (ORCID: https://orcid.org/0000-0002-6363-716X)
- Charles T. Lau (ORCID: https://orcid.org/0000-0002-3136-9711)
- Zaid Nabulsi (ORCID: https://orcid.org/0009-0001-2078-0142)
- Minyoi Mubita Maimbolwa (ORCID: https://orcid.org/0000-0002-1770-0359)
- Yossi Matias (ORCID: https://orcid.org/0000-0003-3960-6002)
- Greg S. Corrado (ORCID: https://orcid.org/0000-0001-8817-0992)
- Sahar Kazemzadeh (ORCID: https://orcid.org/0009-0008-6640-6288)
- Yun Liu (ORCID: https://orcid.org/0000-0003-4079-8275)
- Rory Pilgrim (ORCID: https://orcid.org/0009-0005-2582-8722)
- Brian Shuma (ORCID: https://orcid.org/0000-0002-0708-7570)
- Arnav Agharwal (ORCID: https://orcid.org/0009-0005-6078-9407)
- Christina Chen (ORCID: https://orcid.org/0000-0001-6786-0054)
- Shruthi Prabhakara (ORCID: https://orcid.org/0000-0002-9489-7415)
- Jin Yu
- E H Wu (ORCID: https://orcid.org/0009-0001-2106-3137)
Institutions
- Google (United States) (US)
- Centre for Infectious Disease Research in Zambia (ZM)
- Deerfield (United States) (US)
Publication Details
- Journal
- NEJM AI
- Published
- 2024-09-26
- DOI
- https://doi.org/10.1056/aioa2400018
- Citations
- 12
- Primary Topic
- COVID-19 diagnosis using AI
- Type
- article
- Field-Weighted Citation Impact
- 4.85
Funders
- Bill and Melinda Gates Foundation