Automatic Detection of Acute Bacterial Pneumonia from Chest X-ray Reports
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
OBJECTIVE: To evaluate the performance of a natural language processing system in extracting pneumonia-related concepts from chest x-ray reports. DESIGN: Four physicians, three lay persons, a natural language processing system, and two keyword searches (designated AAKS and KS) detected the presence or absence of three pneumonia-related concepts and inferred the presence or absence of acute bacterial pneumonia from 292 chest x-ray reports. Gold standard: Majority vote of three independent physicians. Reliability of the gold standard was measured. OUTCOME MEASURES: Recall, precision, specificity, and agreement (using Finn's R: statistic) with respect to the gold standard. Differences between the physicians and the other subjects were tested using the McNemar test for each pneumonia concept and for the disease inference of acute bacterial pneumonia. RESULTS: Reliability of the reference standard ranged from 0.86 to 0.96. Recall, precision, specificity, and agreement (Finn R:) for the inference on acute bacterial pneumonia were, respectively, 0.94, 0.87, 0.91, and 0.84 for physicians; 0.95, 0.78, 0.85, and 0.75 for natural language processing system; 0.46, 0.89, 0.95, and 0.54 for lay persons; 0.79, 0.63, 0.71, and 0.49 for AAKS; and 0.87, 0.70, 0.77, and 0.62 for KS. The McNemar pairwise comparisons showed differences between one physician and the natural language processing system for the infiltrate concept and between another physician and the natural language processing system for the inference on acute bacterial pneumonia. The comparisons also showed that most physicians were significantly different from the other subjects in all pneumonia concepts and the disease inference. CONCLUSION: In extracting pneumonia related concepts from chest x-ray reports, the performance of the natural language processing system was similar to that of physicians and better than that of lay persons and keyword searches. The encoded pneumonia information has the potential to support several pneumonia-related applications used in our institution. The applications include a decision support system called the antibiotic assistant, a computerized clinical protocol for pneumonia, and a quality assurance application in the radiology department.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Fiszman et al showed that introducing NLP for reading the chest X-ray reports would assist the antibiotic assistant system to alert physicians for the possible need for anti-infective therapy.43”
From Artificial intelligence in healthcare: past, present and future (2017) · cites this paper as [43]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
(1988) · Cited by 16,582
Generalizability theory: a primer
(1992) · Choice Reviews Online · doi:10.5860/choice.29-4192 · Cited by 1,298
Natural Language Understanding
(2021) · AI Assistants · doi:10.7551/mitpress/12761.003.0007 · Cited by 1,271
A Computer-Assisted Management Program for Antibiotics and Other Antiinfective Agents
Evans, R. S., Pestotnik, S. L., Classen, D. C., Clemmer, T. P., Weaver, L. K., Orme, J. F., Lloyd, J. F., & Burke, J. P. (1998) · New England Journal of Medicine · doi:10.1056/nejm199801223380406 · Cited by 1,061
Self-citationNiederman, M. S., Bass, J. B., Campbell, G. D., Fein, A. M., Grossman, R. F., Mandell, L. A., Marrie, T. J., Sarosi, G. A., Torres, A., & Yu, V. L. (1993) · American Review of Respiratory Disease · doi:10.1164/ajrccm/148.5.1418 · Cited by 1,045
A General Natural-language Text Processor for Clinical Radiology
Friedman, C., Alderson, P. O., Austin, J. H. M., Cimino, J. J., & Johnson, S. B. (1994) · Journal of the American Medical Informatics Association · doi:10.1136/jamia.1994.95236146 · Cited by 778
A COMPUTER-ASSISTED MANAGEMENT PROGRAM FOR ANTIBIOTICS AND OTHER ANTIINFECTIVE AGENTS
Vans, R. S. C. E., Estotnik, S. T. L. P., Lassen, D. A. C. C., Lemmer, T., Eaver, L. I. K. W., Rme, J. A. F. O., Loyd, J. A. F. L., & Urke, J. O. P. B. (1998) · Cited by 692
The Reliability of Clinical Methods, Data and Judgments: (First of Two Parts)
Koran, L. M. (1975) · New England Journal of Medicine · doi:10.1056/nejm197509252931307 · Cited by 649
Niederman (1993) · Medical Entomology and Zoology · Cited by 624
BRENNER, H., & GEFELLER, O. (1997) · Statistics in Medicine · doi:10.1002/(sici)1097-0258(19970515)16:9<981::aid-sim510>3.0.co;2-n · Cited by 488
Research works printed but not linked: 6
- Friedman C, Alderson PO, Austin JH, Cimino JJ, Johnson SB. A general natural-language text processor for clinical radiology. J Am Med Inform Assoc. 1994;1:161–74. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Sager N, Lyman M, Bucknall C, Nhan N, Tick LJ. Natural language processing and the representation of clinical data. J Am Med Inform Assoc. 1994;1:142–60. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Hughes, 1988, M.D. computing : computers in medical practice, 5, 22
- Hripcsak G, Kuperman GJ, Friedman C, Heitjan DF. A reliability study for evaluating information extraction from radiology reports. J Am Med Inform Assoc. 1999;6:143–50. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Zar JH. Biostatistical Analysis. Englewood Cliffs, N.J.: Prentice Hall, 1974.
- 1984, The American Psychologist, 39, 22, 10.1037/0003-066x.39.1.22 · doi:10.1037/0003-066x.39.1.22 · Paper page
Cited by
Items 201–251 of 251
Informatics Approaches to Participant Recruitment
Weng, C., & Embí, P. J. (2012) · Computers in health care · doi:10.1007/978-1-84882-448-5_5 · Cited by 4
A Neoteric Variant of Deep Learning Network for Chest Radiograph Automated Annotation
Sultana, S., Hussain, S. S., Hashmani, M. A., Fayez, F. A., & Umair, M. (2021) · International Conference on Computer and Information Sciences · doi:10.1109/iccoins49721.2021.9497215 · Cited by 6
King, A. J., Potter, K. M., Seaman, J. B., Chiyka, E. A., Hileman, B. A., Cooper, G. F., Mowery, D. L., Angus, D. C., & Kahn, J. M. (2023) · American Journal of Critical Care · doi:10.4037/ajcc2023755 · Cited by 7
Munna, M. S., & Hossain, Q. D. (2022) · International Conference on Sustainable Technologies for Industry 5.0 (STI) · doi:10.1109/sti56238.2022.10103279 · Cited by 4
“Fiszman [16] introduced SymText, an NLP-based method for predicting pneumonia from a description of an X-Ray image.”
MethodThe Strategic Efficacy of Artificial Intelligence (AI) in Medical Tourism
Gbobaniyi, O., Tincani, D., & Emelone, P. (2024) · Advances in hospitality, tourism and the services industry (AHTSI) book series · doi:10.4018/979-8-3693-2248-2.ch005 · Cited by 5
Gundlapalli, A. V., Delgado, J. C., Jackson, B. R., Tricot, G. J. K., & Hill, H. R. (2009) · PubMed Central · Cited by 4
Bridging the Text-Image Gap: a Decision Support Tool for Real-Time PACS Browsing
Sevenster, M., van Ommering, R., & Qian, Y. (2011) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-011-9414-x · Cited by 4
Monitoring Patient Safety in Health Care: Building the Case for Surrogate Measures
Gaynes, R. P., & Platt, R. G. (2006) · The Joint Commission Journal on Quality and Patient Safety · doi:10.1016/s1553-7250(06)32013-2 · Cited by 4
Automated classification of the narrative of medical reports using natural language processing
Goldstein, I. J. (2011) · Scholars Archive - University at Albany (University at Albany, State University of New York) · doi:10.54014/7weq-ywav · Cited by 4
“The narratives of these reports contain a variety of useful information that can support syndromic surveillance (Shapiro, 2004), billing (Puckett, 1986), decision support (Fiszman et al., 2000), and problem list generation (Sibanda, He, Szolovits, & Uzuner, 2006).”
BackgroundLocalization and Multi-label Classification of Thoracic Diseases Using Deep Learning
Siddiqui, A., Chavan, S. B., Ansari, S. F., & Bhavathankar, P. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-16-6723-7_24 · Cited by 3
Informatics Approaches to Participant Recruitment
Weng, C., & Embí, P. J. (2023) · Health informatics · doi:10.1007/978-3-031-27173-1_12 · Cited by 3
Artificial Intelligence in Medicine: Opportunities and Challenges
Darvishmohammadi, T., Özkal, A., & Özkal, A. S. (2024) · Black Sea Journal of Engineering and Science · doi:10.34248/bsengineering.1499831 · Cited by 4
Artificial Intelligence in Healthcare Data Science with Knowledge Engineering
Asha, S., Devi, V. K., & Vaishnavi, G. S. (2022) · Wiley eBooks · doi:10.1002/9781119792550.ch12 · Cited by 3
Public Health Surveillance: The Role of Clinical Information Systems
D, M. M. W. M., Espino, J. U., Tsui, F.-C., & Aryel, R. M. (2004) · Springer eBooks · doi:10.1007/978-1-4757-4041-7_39 · Cited by 3
Castilla, A. C. (2007) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.5.2007.tde-16022009-165641 · Cited by 3
Medical Information Technology
Lagor, C., Lord, W. P., Chbat, N. W., Schaffer, J. D., & Wendler, T. (2006) · Kluwer Academic Publishers eBooks · doi:10.1007/1-4020-4384-8_22 · Cited by 3
Abbas, M. A., Bukhari, S. U. K., Bokhari, S. K. A., & Niazi, M. (2020) · medRxiv · doi:10.1101/2020.12.03.20243550 · Cited by 3
“The use of machine learning helped improve the algorithms, but the accuracy of the systems was pretty low [5,6] This paper presents a new hybrid approach to do the binary classification between pneumonia and healthy patients using CRX images.”
MethodArtificial Intelligence Applications in Pneumonia: Diagnosis and Outcome Prediction
Zhu, M., Bak, M., & Gao, C. A. (2026) · Current Pulmonology Reports · doi:10.1007/s13665-026-00411-9 · Cited by 2
“Factors such as variation in imaging techniques, laboratory test methods, The literature in adult pneumonia NLP remains domi - nated by radiology report–based diagnosis [ 71] and case identification [ 72 , 73 ] with limited work for surveillance, and early detection uses.”
Role of Artificial Intelligence (AI) in Infection Control
Ellahham, S. H. (2023) · International Journal of Science and Research (IJSR) · doi:10.21275/sr21929143532 · Cited by 2
“Antibiotic assistant is a real-time NLP-based decision support system, which is used in radiology departments for the clinical control of pneumonia [17].”
InfluentialRomano, R., Rokach, L., & Maimon, O. (2006) · Lecture notes in computer science · doi:10.1007/11780991_26 · Cited by 2
“Researchers in medical informatics suggested methods for automatically extracting information contained in narrative reports for decision support [ 6 ], guideline implementation [10], and detection and management of epidemics [12].”
MethodA systematic review of automated medical coding and classification systems
Stanfill, M. H. (2009) · doi:10.6083/m4xs5scg · Cited by 2
SPEECH TO CHART: SPEECH RECOGNITION AND NATURAL LANGUAGE PROCESSING FOR DENTAL CHARTING
Irwin, R. Y. (2009) · D-Scholarship@Pitt (University of Pittsburgh) · Cited by 2
Goldstein, I., & Uzuner, Ö. (2010) · Cited by 2
A Lightweight Object Detection Model to Detect Pneumonia Types
Munna, M. S., & Hossain, Q. D. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-2322-9_45 · Cited by 2
Anomaly Detection in Time Series Radiotherapy Treatment Data
Sipes, T., Karimabadi, H., Jiang, S. B., Moore, K. L., Li, N., & Barr, J. R. (2014) · IEEE International Conference on Semantic Computing (ICSC) · doi:10.1109/icsc.2014.64 · Cited by 1
“Also, some HIT tools have been developed to detect adverse events in narrative clinical reports, which contain important clinical information and are becoming increasingly available in electronic form [10, 12-21].”
BackgroundGeneration of Novel Synthetic Portable Chest X-Ray Images for Automatic COVID-19 Screening
Iglesias, D., de Moura, J., Novo, J., & Ortega, M. (2022) · Advances in medical diagnosis, treatment, and care (AMDTC) book series · doi:10.4018/978-1-6684-2304-2.ch008 · Cited by 1
Wall, S. P., Mayorga, O., Banfield, C. E., Wall, M. E., Aisic, I., Auerbach, C., & Gennis, P. (2006) · Annals of Emergency Medicine · doi:10.1016/j.annemergmed.2006.06.031 · Cited by 1
Ballerio, S. (2009) · Cited by 1
Informatics Approaches to Participant Recruitment
Weng, C., & Embí, P. J. (2019) · Health informatics · doi:10.1007/978-3-319-98779-8_6 · Cited by 1
The radiological report: a compromise between structured reporting and natural language processing
Nobel, J. M. (2023) · Research Publications (Maastricht University) · doi:10.26481/dis.20230928jn · Cited by 10
Indexation et apprentissage de termes et de relations à partir de comptes rendus de radiologie
Ramadier, L. (2016) · theses.fr (ABES) · doi:10.70675/d23802d1z93ddz4c69z95bez37b08e238a4b · Cited by 5
Role of preferred terminology in the classification of medical reports
Goldstein, I., & Uzuner, Ö. (2009) · International Symposium on Computer and Information Sciences · doi:10.1109/iscis.2009.5291823
“The narratives of these reports can be used for many important applications including syndromic surveillance [3], billing [4], decision support systems [5], and problem list generation [6].”
BackgroundInformation extraction from radiology reports mingled two languages
Kwak, M., Jung, S., & Choi, J. (2005) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/health.2005.1500443
“[4]-[6] In past studies, some researchers have investigated automatic text processing system such as MEDLEE [7], SPRUS [SI, and CAPIS [93$ which are using IE technique to adjust radiology dictation text.”
MethodApproaches to Assertion Classification Machine Learning and Rule-based
Uzuner, Ö., Zhang, X., & Sibanda, T. C. (2010)
Chapman, W. W. (2012) · J. Willard Marriott Library · doi:10.26053/0h-14ta-2qg0
Self-citationLacey, A. (2019) · Cronfa (Swansea University) · doi:10.23889/suthesis.48905
Mevik, K. (2019) · NORA - Norwegian Open Research Archives
Artificial Intelligence in Health Care: Ethical Challenges
Sareen, R. (2021) · Journal of Pulmonary Medicine · Cited by 2
Deep Learning Approach for Diagnosis of Pneumonia
Arora, R., Saini, I., & Sood, N. (2021) · International Conference on Communication, Computing and Industry 4.0 (C2I4) · doi:10.1109/c2i454156.2021.9689384
Multiple Deep Learning Approaches to Detect Pneumonia with Chest X-Ray
Ramdevputra, D., Ramdevputra, D., Shekhada, A., & Shah, A. (2023) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2023.53278
Sağlık Hizmetlerinde Yapay Zeka: Geçmiş, Bugün ve Gelecek
YURTSEVEN, E. (2023) · doi:10.59287/sbyc.530
Pneumonia Detection Using Deep Learning: A Bibliometric Study
Jatwani, R., & Sharma, P. K. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-43145-6_16
The Impact of AI on Radiology Reporting
Nobel, J. M. (2024) · Imaging informatics for healthcare professionals · doi:10.1007/978-3-031-68942-0_9
Raj, A., Jha, A., Dabral, O., Upadhyay, A., Sahu, S., & Kumar, B. (2024) · IEEE Conference on Information and Communication Technology (CICT) · doi:10.1109/cict64037.2024.10899631
“Fiszman et al. [16] developed an NLP tool that detected acute bacterial pneumonia from chest X-rays with efficiency comparable to physicians.”
The Role of Complex Digital Interventions to Improve Pneumonia Care
Wackerbarth, J., Carr, J. R., & Dean, N. C. (2026) · Clinics in Chest Medicine · doi:10.1016/j.ccm.2025.12.016
Dhande, N. M., & Sinha, A. (2026) · International Journal of Artificial Intelligence and Machine Learning · doi:10.51483/ijaiml.6.6s.2026.610-626
zimolzak/spep-nlp: Initial release (getting Zenodo DOI)
Zimolzak, A. (2024) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.13265180
Bullard, J. (2015) · RIT Scholar Works (Rochester Institute of Technology)
Metadata
- Authors
- Fiszman, M., Chapman, W. W., Aronsky, D., Evans, R. S., & Haug, P. J.
- Affiliations
- University of Utah (US)
- Venue
- Journal of the American Medical Informatics Association
- Publisher
- Oxford University Press (OUP)
- Published
- 2000-11-01
- Volume
- 7
- Issue
- 6
- Pages
- 593-604
- ISSN
- 1067-5027 (ISSN-L)
- 1527-974X
- PMC
- PMC129668
- OpenAlex
- W2125726375
- Cited by
- 250
- References
- 34
- Citations by year
- 2026: 2 · 2025: 1 · 2024: 10 · 2023: 15 · 2022: 12 · 2021: 13 · 2020: 17 · 2019: 12 · 2018: 4 · 2017: 13 · 2016: 9 · 2015: 8 · 2014: 6 · 2013: 10 · 2012: 12
- FWCI
- 2.41
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Journal of the American Medical Informatics Association (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Institutes of Health (5r01hl053427-03, 5r01lm006539-03)
- National Heart, Lung, and Blood Institute (HL53427)
- U.S. National Library of Medicine (LM06539)
- Topics
- Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Medicine › Epidemiology › Pneumonia and Respiratory Infections
- Keywords
- acute bacterial pneumonia, chest X-ray reports, natural language processing, radiology report interpretation, infiltrates, keyword search, physician agreement, quality assurance in radiology
- MeSH terms
- Acute Disease, Algorithms, Diagnosis, Computer-Assisted, Humans, Lung, Natural Language Processing, Radiography, Thoracic, Reproducibility of Results, Pneumonia, Bacterial
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.