Artificial intelligence-based point-of-care lung ultrasound for screening COVID-19 pneumoniae: Comparison with CT scans
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Background: Although lung ultrasound has been reported to be a portable, cost-effective, and accurate method to detect pneumonia, it has not been widely used because of the difficulty in its interpretation. Here, we aimed to investigate the effectiveness of a novel artificial intelligence-based automated pneumonia detection method using point-of-care lung ultrasound (AI-POCUS) for the coronavirus disease 2019 (COVID-19). Methods: We enrolled consecutive patients admitted with COVID-19 who underwent computed tomography (CT) in August and September 2021. A 12-zone AI-POCUS was performed by a novice observer using a pocket-size device within 24 h of the CT scan. Fifteen control subjects were also scanned. Additionally, the accuracy of the simplified 8-zone scan excluding the dorsal chest, was assessed. More than three B-lines detected in one lung zone were considered zone-level positive, and the presence of positive AI-POCUS in any lung zone was considered patient-level positive. The sample size calculation was not performed given the retrospective all-comer nature of the study. Results: A total of 577 lung zones from 56 subjects (59.4 ± 14.8 years, 23% female) were evaluated using AI-POCUS. The mean number of days from disease onset was 9, and 14% of patients were under mechanical ventilation. The CT-validated pneumonia was seen in 71.4% of patients at total 577 lung zones (53.3%). The 12-zone AI-POCUS for detecting CT-validated pneumonia in the patient-level showed the accuracy of 94.5% (85.1%– 98.1%), sensitivity of 92.3% (79.7%– 97.3%), specificity of 100% (80.6%– 100%), positive predictive value of 95.0% (89.6% - 97.7%), and Kappa of 0.33 (0.27–0.40). When simplified with 8-zone scan, the accuracy, sensitivity, and sensitivity were 83.9% (72.2%– 91.3%), 77.5% (62.5%– 87.7%), and 100% (80.6%– 100%), respectively. The zone-level accuracy, sensitivity, and specificity of AI-POCUS were 65.3% (61.4%– 69.1%), 37.2% (32.0%– 42.7%), and 97.8% (95.2%– 99.0%), respectively. Interpretation: AI-POCUS using the novel pocket-size ultrasound system showed excellent agreement with CT-validated COVID-19 pneumonia, even when used by a novice observer.
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
Figures





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.
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
Characteristics of SARS-CoV-2 and COVID-19
Hu, B., Guo, H., Zhou, P., & Shi, Z.-L. (2021) · Nature Reviews Microbiology · doi:10.1038/s41579-020-00459-7 · Cited by 5,291
Wiersinga, W. J., Rhodes, A., Cheng, A. C., Peacock, S. J., & Prescott, H. C. (2020) · JAMA · doi:10.1001/jama.2020.12839 · Cited by 4,609
Probable Inference, the Law of Succession, and Statistical Inference
Wilson, E. B. (1927) · Journal of the American Statistical Association · doi:10.1080/01621459.1927.10502953 · Cited by 4,476
WHO Coronavirus Disease (COVID-19) Dashboard
(2020) · Bangladesh Physiotherapy Journal · doi:10.46945/bpj.10.1.03.01 · Cited by 3,806
International evidence-based recommendations for point-of-care lung ultrasound
International Liaison Committee on Lung Ultrasound (ILC-LUS) for the International Consensus Conference on Lung Ultrasound (ICC-LUS), Volpicelli, G., Elbarbary, M., Blaivas, M., Lichtenstein, D. A., Mathis, G., Kirkpatrick, A. W., Melniker, L., Gargani, L., Noble, V. E., et al. (2012) · Intensive Care Medicine · doi:10.1007/s00134-012-2513-4 · Cited by 2,874
The Comet-tail Artifact: An Ultrasound Sign of Alveolar-Interstitial Syndrome
LICHTENSTEIN, D., MÉZIÈRE, G., BIDERMAN, P., GEPNER, A., & BARRÉ, O. (1997) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/ajrccm.156.5.96-07096 · Cited by 1,075
A deep learning system for differential diagnosis of skin diseases
Liu, Y., Jain, A., Eng, C., Way, D. H., Lee, K., Bui, P., Kanada, K., de Oliveira Marinho, G., Gallegos, J., Gabriele, S., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0842-3 · Cited by 853 · cited 1×
“Recent advancements in AI technology, more specifically machine learning, have enabled automated image recognition with similar or even higher accuracy compared to expert clinicians, and the application of such technologies to POCUS has been enthusiastically studied [10, 11, 24, 25].”
BackgroundPotential association between COVID-19 mortality and health-care resource availability
Ji, Y., Ma, Z., Peppelenbosch, M. P., & Pan, Q. (2020) · The Lancet Global Health · doi:10.1016/s2214-109x(20)30068-1 · Cited by 736
Roy, S., Menapace, W., Oei, S., Luijten, B., Fini, E., Saltori, C., Huijben, I., Chennakeshava, N., Mento, F., Sentelli, A., et al. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2994459 · Cited by 597
Lung Ultrasound for Critically Ill Patients
Mojoli, F., Bouhemad, B., Mongodi, S., & Lichtenstein, D. (2019) · American Journal of Respiratory and Critical Care Medicine · doi:10.1164/rccm.201802-0236ci · Cited by 513
Cited by
Kim, J., Maranna, S., Watson, C. A., & Parange, N. (2025) · The American Journal of Emergency Medicine · doi:10.1016/j.ajem.2025.03.029 · Cited by 46
Yu, Y., Gomez-Cabello, C. A., Haider, S. A., Genovese, A., Prabha, S., Trabilsy, M., Collaco, B. G., Wood, N. G., Bagaria, S., Tao, C., et al. (2025) · Diagnostics · doi:10.3390/diagnostics15172204 · Cited by 32
“Studies have successfully employed AI to diagnose pneumonia and COVID-19 using lung ultrasound imagery [11,12], detect diabetic retinopathy from retinal fundus images [13], and correctly classify benign versus malignant skin lesions [14], highlighting significant potential in diagnostic…”
Kayarian, F. B., Patel, D., O'Brien, J. R., Schraft, E. K., & Gottlieb, M. A. (2024) · The American Journal of Emergency Medicine · doi:10.1016/j.ajem.2024.03.023 · Cited by 28
Venkatayogi, N., Gupta, M., Gupta, A., Nallaparaju, S., Cheemalamarri, N., Gilari, K., Pathak, S., Vishwanath, K., Soney, C., Bhattacharya, T., et al. (2023) · Applied Sciences · doi:10.3390/app13148427 · Cited by 26
Kagiyama, N., Abe, Y., Kusunose, K., Kato, N., Kaneko, T., Murata, A., Ota, M., Shibayama, K., Izumo, M., & Watanabe, H. (2024) · Scientific Reports · doi:10.1038/s41598-024-65557-5 · Cited by 26
“Advanced algorithms enabled by recent advancements in deep learning, like the one employed in our AI-POCUS application, are capable of compensating for some of the inherent limitations of handheld devices by optimizing image processing and analysis 20,21 .”
MethodSelf-citationArtificial intelligence in respiratory care
Karthika, M., Sreedharan, J. K., Shevade, M., Mathew, C. S., & Ray, S. (2024) · Frontiers in Digital Health · doi:10.3389/fdgth.2024.1502434 · Cited by 24
Mika, S., Gola, W., Gil-Mika, M., Wilk, M., & Misiołek, H. (2024) · Journal of Personalized Medicine · doi:10.3390/jpm14030286 · Cited by 15
“At the same time, it significantly reduces the time needed to learn how to perform imaging and the time to acquire clinically significant images, and it improves the accuracy of the obtained results [2,10,12,13].”
BackgroundNekoui, M., Bolouri, S. E. S., Forouzandeh, A., Dehghan, M., Zonoobi, D., Jaremko, J. L., Buchanan, B. M., Nagdev, A. D., & Kapur, J. (2024) · Diagnostics · doi:10.3390/diagnostics14222526 · Cited by 14
Dadon, Z., Rav-Acha, M., Orlev, A., Carasso, S., Glikson, M., Gottlieb, S., & Alpert, E. A. (2024) · Diagnostics · doi:10.3390/diagnostics14070767 · Cited by 14
“In the field of lung imaging, it has been shown to be accurate in identifying the presence or absence of lung sliding (one of the main ultrasonographic signs for pneumothorax) [37], pneumonia in pediatric patients [38], COVID-19 pneumonia [39], and fluid overload in dialysis patients [40].”
BackgroundThe Promise of Artificial Intelligence-Assisted Point-of-Care Ultrasonography in Perioperative Care
Serrano, R. A., & Smeltz, A. M. (2024) · Journal of Cardiothoracic and Vascular Anesthesia · doi:10.1053/j.jvca.2024.01.034 · Cited by 12
Point-of-care ultrasound use in austere environments: A scoping review
Anderson, A., & Theophanous, R. G. (2024) · PLoS ONE · doi:10.1371/journal.pone.0312017 · Cited by 13
Artificial Intelligence in Lung Ultrasound
Chu, D. L., Liteplo, A. S., Duggan, N. M., Hutchinson, A. B., & Shokoohi, H. (2024) · Current Pulmonology Reports · doi:10.1007/s13665-024-00344-1 · Cited by 11
New perspectives on the use of artificial intelligence in the ultrasound evaluation of lung diseases
Boccatonda, A., & Piscaglia, F. (2024) · Journal of Ultrasound · doi:10.1007/s40477-023-00866-5 · Cited by 7
“[17] Therefore, AI-based lung ultrasound demonstrated an excellent agreement with computed tomography (CT)-validated COVID-19 pneumonia, even when used by not expert sonographers.”
InfluentialAI-Enhanced POCUS in Emergency Care
Puticiu, M. I., Cimpoesu, D. C., POP, F. B.-D., Ciumanghel, I., Rotaru, L. T., Opriță, B., Butoi, M. A., Belghiru, V. I., Tat, R. M., & Golea, A. C. (2026) · Diagnostics · doi:10.3390/diagnostics16020353 · Cited by 11
COVID-19 and Children: Reflections after Three Years
Camporesi, A., Vetrugno, L., & Buonsenso, D. (2023) · Children · doi:10.3390/children11010010 · Cited by 7
Ultrasound Beyond Joints: A Review of Extra-Articular Applications in Rheumatology
D’Ignazio, E., Corradini, D., Cazenave, T., Bixio, R., Baldi, C., Ubhi, H. K., Smith, K., Wakefield, R. J., Emery, P., & Matteo, A. D. (2025) · Current Rheumatology Reports · doi:10.1007/s11926-025-01186-9 · Cited by 7
“Additionally, B-lines can appear in various other pathological lung conditions, such as pulmonary edema, infection, chronic obstructive pulmonary disease, chronic heart failure, and acute respiratory distress syndrome, as well as in healthy individuals, which complicates ILD diagnosis [27–29].”
Jing, S., Tie, X., Wei, Y., Zhou, R., Zou, T., Qin, Y., Zeng, X., Li, Y., & Yin, W. (2025) · Frontiers in Medicine · doi:10.3389/fmed.2025.1622604 · Cited by 9
Morshed, A., Shihab, A. A., Jahin, M. A., Nahian, M. J. A., Sarker, M. M. H., Wadud, M. S. I., Uddin, M. I., Siraji, M. I., Anjum, N., Shristy, S. R., et al. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-20802-5 · Cited by 6
Artificial intelligence in respiratory therapy: Opportunities and ethical challenges
Satapathy, P., Padhi, B. K., & Khathlan, N. A. (2023) · Respiratory Medicine · doi:10.1016/j.rmed.2023.107342 · Cited by 5
Campbell, E. A., Goodtree, H., Gillani, S., Oyefolu, O., Kelly, A., Rivers, C., & Watson, C. R. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1745684 · Cited by 5
Chest ultrasound for lung cancer: present and future
Sekiya, M. (2024) · Journal of Medical Ultrasonics · doi:10.1007/s10396-024-01476-2 · Cited by 4
“%) in the screening of pneumonia images in COVID-19 patients [12].”
Emerging Role of Transcutaneous Ultrasound in the Diagnostic of Lung Cancer
Trenker, C., Dohse, M., Findeisen, H., Schüler, A., & Görg, C. (2025) · Cancers · doi:10.3390/cancers17233873 · Cited by 3
Ultrasound image abnormalities associated with the development of ovine pulmonary adenocarcinoma
Collie, D., Meehan, J., Brown, H. K., Chang, Z., Cousens, C., Moore, S. J., Todd, H., Griffiths, D. J., Storer, N., Eckert, C. E., et al. (2025) · Research in Veterinary Science · doi:10.1016/j.rvsc.2025.105786 · Cited by 2
Hsu, N., Lin, Y., Tsai, H., Liao, C., & Hsu, C. (2026) · Diagnostics · doi:10.3390/diagnostics16020192 · Cited by 2
“Therefore, protocols incorporating more than eight scanning zones are recommended to improve coverage, as studies showed that higher acquisition zones rendered higher sensitivity and specificity [58,59].”
Lightowler, M. S., Sander, J.-V., Sánchez, G. G. D. C., González, M. M., Güerri‐Fernández, R., Navarro, M. D. L., Nackers, F., Stratta, E., Lanusse, C., & Huerga, H. (2024) · Journal of Clinical Medicine · doi:10.3390/jcm13113282 · Cited by 2
“These developments have been demonstrated in assessing the extend of COVID-19 pneumonia [41] and diagnosing COVID-19 pneumonia compared to CT [42].”
BackgroundArtificial Intelligence in Point-of-Care Ultrasound
Adhikari, S. (2025) · Springer eBooks · doi:10.1007/978-3-031-86341-7_21 · Cited by 1
Cao, P., Xu, J., Zhao, Y., Ni, Q., Li, Y., Chen, H., Song, M., Shang, J., Yu, M., Ding, X., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112024 · Cited by 2
The evolution and future of point of care ultrasound in the perioperative period: narrative review
Dabo-Trubelja, A., & Perioperative, D. (2025) · Journal of Clinical Monitoring and Computing · doi:10.1007/s10877-025-01398-5 · Cited by 1
Imaging Modalities to Diagnose Pneumonia
Lanspa, M. J. (2026) · Clinics in Chest Medicine · doi:10.1016/j.ccm.2025.12.010 · Cited by 1
Thoracic Ultrasound in Others Scenarios: An Expanding Tool
Romero‐Romero, B., Botana‐Rial, M., Martínez, R. C., Elías-Hernández, T., Rodrigues-Gomes, R. M., & Valdivia, M. (2024) · Open Respiratory Archives · doi:10.1016/j.opresp.2025.100420 · Cited by 1
Bai, F., Yin, H., Zhang, S., Wei, D., Wang, J., & Yi, M. (2025) · PLoS ONE · doi:10.1371/journal.pone.0328067 · Cited by 1
“The LUS is consistent with the CT classification [19,22].”
Kamal, S., Noreen, S., Ahmad, H., & Zubair, M. (2026) · Sonography · doi:10.1002/sono.70083
Hetta, H. F., Ahmed, R., Haseeb, A., Bukhari, S. Q., Alatawi, Z., Mahrous, A. J., Elrggal, M. E., Masri, M. A., & Kotb, A. A. (2026) · Diagnostics · doi:10.3390/diagnostics16152402
“Overall, the study demonstrated the reliability of AI-POCUS in detecting pneumonia, even in inexperienced hands [133].”
Alghamdi, B. M., Alrewily, E. M., & Alghamdi, S. S. (2026) · Ultrasound Quarterly · doi:10.1097/ruq.0000000000000753
Mattson, J. R., Deshpande, K., & Pradhan, D. R. (2026) · Breathe · doi:10.1183/20734735.0058-2026
“Utilising AI, novices can help diagnose deep vein thrombosis and pneumonia with high sensitivity and specificity [11, 16, 17] and estimate left ventricular ejection fraction (LVEF) accurately when compared to expert cardiologists [18].”
Ultrasound in Pneumothorax Detection Rapid and Accurate Pulmonary Assessment
Nelluri, K. D. D., Alaparthi, B., Kakani, A. K., Indusree, G., Rajeswari, D. M. N., & Kamepalli, S. (2026) · doi:10.1002/9781394409778.ch1
Metadata
- Authors
- Kuroda, Y., Kaneko, T., Yoshikawa, H., Uchiyama, S., Nagata, Y., Matsushita, Y., Hiki, M., Minamino, T., Takahashi, K., Daida, H., & Kagiyama, N.
- Affiliations
- Juntendo University (JP)
- Corresponding author
- Kagiyama, Nobuyuki
- ORCID
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2023-03-16
- Volume
- 18
- Issue
- 3
- Pages
- e0281127
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC10019704
- OpenAlex
- W4327566817
- Cited by
- 36
- References
- 27
- Citations by year
- 2026: 9 · 2025: 11 · 2024: 13 · 2023: 3
- FWCI
- 7.46
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS ONE (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Japan Society for the Promotion of Science (21K18086)
- Topics
- Health Sciences › Medicine › Critical Care and Intensive Care Medicine › Ultrasound in Clinical Applications
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- point-of-care lung ultrasound, COVID-19 pneumonia, artificial intelligence, B-lines, diagnostic accuracy, pneumonia screening, portable ultrasound, mechanical ventilation, point-of-care testing, resource-limited settings
- MeSH terms
- COVID-19, Artificial Intelligence, Female, Humans, Lung, Male, Pneumonia, Retrospective Studies, Tomography, X-Ray Computed, Point-of-Care Systems
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.