An evaluation of automated chest radiography reading software for tuberculosis screening among public- and private-sector patients
Copyright ©ERS 2017..
Computer-aided reading (CAR) of medical images is becoming increasingly common, but few studies exist for CAR in tuberculosis (TB). We designed a prospective study evaluating CAR for chest radiography (CXR) as a triage tool before Xpert MTB/RIF (Xpert).Consecutively enrolled adults in Dhaka, Bangladesh, with TB symptoms received CXR and Xpert. Each image was scored by CAR and graded by a radiologist. We compared CAR with the radiologist for sensitivity and specificity, area under the receiver operating characteristic curve (AUC), and calculated the potential Xpert tests saved.A total of 18 036 individuals were enrolled. TB prevalence by Xpert was 15%. The radiologist graded 49% of CXRs as abnormal, resulting in 91% sensitivity and 58% specificity. At a similar sensitivity, CAR had a lower specificity (41%), saving fewer (36%) Xpert tests. The AUC for CAR was 0.74 (95% CI 0.73-0.75). CAR performance declined with increasing age. The radiologist grading was superior across all sub-analyses.Using CAR can save Xpert tests, but the radiologist's specificity was superior. Differentiated CAR thresholds may be required for different populations. Access to, and costs of, human readers must be considered when deciding to use CAR software. More studies are needed to evaluate CAR using different screening approaches.
| Errataetall: |
CommentIn: Eur Respir J. 2017 May 21;49(5):. - PMID 28529204 |
|---|---|
| Medienart: |
E-Artikel |
| Erscheinungsjahr: |
2017 |
|---|---|
| Erschienen: |
2017 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:49 |
|---|---|
| Enthalten in: |
The European respiratory journal - 49(2017), 5 vom: 05. Mai |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Rahman, Md Toufiq [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 22.03.2018 Date Revised 12.11.2023 published: Electronic-Print CommentIn: Eur Respir J. 2017 May 21;49(5):. - PMID 28529204 Citation Status MEDLINE |
|---|
| doi: |
10.1183/13993003.02159-2016 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM272114197 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM272114197 | ||
| 003 | DE-627 | ||
| 005 | 20231224234158.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231224s2017 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1183/13993003.02159-2016 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n0907.xml |
| 035 | |a (DE-627)NLM272114197 | ||
| 035 | |a (NLM)28529202 | ||
| 035 | |a (PII)1602159 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Rahman, Md Toufiq |e verfasserin |4 aut | |
| 245 | 1 | 3 | |a An evaluation of automated chest radiography reading software for tuberculosis screening among public- and private-sector patients |
| 264 | 1 | |c 2017 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 22.03.2018 | ||
| 500 | |a Date Revised 12.11.2023 | ||
| 500 | |a published: Electronic-Print | ||
| 500 | |a CommentIn: Eur Respir J. 2017 May 21;49(5):. - PMID 28529204 | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright ©ERS 2017. | ||
| 520 | |a Computer-aided reading (CAR) of medical images is becoming increasingly common, but few studies exist for CAR in tuberculosis (TB). We designed a prospective study evaluating CAR for chest radiography (CXR) as a triage tool before Xpert MTB/RIF (Xpert).Consecutively enrolled adults in Dhaka, Bangladesh, with TB symptoms received CXR and Xpert. Each image was scored by CAR and graded by a radiologist. We compared CAR with the radiologist for sensitivity and specificity, area under the receiver operating characteristic curve (AUC), and calculated the potential Xpert tests saved.A total of 18 036 individuals were enrolled. TB prevalence by Xpert was 15%. The radiologist graded 49% of CXRs as abnormal, resulting in 91% sensitivity and 58% specificity. At a similar sensitivity, CAR had a lower specificity (41%), saving fewer (36%) Xpert tests. The AUC for CAR was 0.74 (95% CI 0.73-0.75). CAR performance declined with increasing age. The radiologist grading was superior across all sub-analyses.Using CAR can save Xpert tests, but the radiologist's specificity was superior. Differentiated CAR thresholds may be required for different populations. Access to, and costs of, human readers must be considered when deciding to use CAR software. More studies are needed to evaluate CAR using different screening approaches | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 700 | 1 | |a Codlin, Andrew J |e verfasserin |4 aut | |
| 700 | 1 | |a Rahman, Md Mahfuzur |e verfasserin |4 aut | |
| 700 | 1 | |a Nahar, Ayenun |e verfasserin |4 aut | |
| 700 | 1 | |a Reja, Mehdi |e verfasserin |4 aut | |
| 700 | 1 | |a Islam, Tariqul |e verfasserin |4 aut | |
| 700 | 1 | |a Qin, Zhi Zhen |e verfasserin |4 aut | |
| 700 | 1 | |a Khan, Md Abdus Shakur |e verfasserin |4 aut | |
| 700 | 1 | |a Banu, Sayera |e verfasserin |4 aut | |
| 700 | 1 | |a Creswell, Jacob |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t The European respiratory journal |d 1989 |g 49(2017), 5 vom: 05. Mai |w (DE-627)NLM012664782 |x 0903-1936 |7 nnns |
| 773 | 1 | 8 | |g volume:49 |g year:2017 |g number:5 |g day:05 |g month:05 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1183/13993003.02159-2016 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 49 |j 2017 |e 5 |b 05 |c 05 | ||