EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Software with artificial intelligence-derived algorithms for detecting and analysing lung nodules in CT scans: systematic review and economic evaluation

Software mit aus KI abgeleiteten Algorithmen zur Erkennung und Analyse von Lungenknoten in CT-Scans: systematische Übersicht und ökonomische Bewertung

Julia Geppert iD, Peter Auguste iD, Asra Asgharzadeh iD, Hesam Ghiasvand iD, Mubarak Patel iD, Anna Brown iD, Surangi Jayakody iD, Emma Helm iD, Dan Todkill iD, Jason Madan iD, Chris Stinton iD, Daniel Gallacher iD und 2 weitere

Health Technology Assessment · 2025-05 · 1-234

DOI: 10.3310/jytw8921 ↗

Auf einen Blick

Die Übersicht zu CT-Aufnahmen zeigt: KI-unterstützte Software kann die Erkennung und Beurteilung von Lungenknoten verbessern. Direkte klinische Wirksamkeitsdaten und belastbare Kosteneffektivität fehlen.

Fragestellung

Wie genau, klinisch wirksam und kosteneffektiv ist Software mit KI-Algorithmen zur Detektion und Analyse von Lungenknoten in Thorax-CTs im Vergleich zum unassistierten Befundlesen?

Methode

Systematische Übersicht und de-novo-Kosteneffektivitätsanalyse; Suche 2012 bis Januar 2022, Firmen-Einreichungen bis 31. August 2022; Bewertung mit QUADAS-2, QUADAS-C und COSMIN.

Ergebnisse

27 Studien, alle mit hohem Verzerrungsrisiko. KI verbesserte meist die Detektion von Knoten (3 Studien; Sensitivität 0,43–0,68 vs. 0,79–0,99) bei ähnlicher oder niedrigerer Spezifität (0,77–1,00 vs. 0,81–0,97).

Einschränkungen

Heterogene, spärliche und niedrigwertige Evidenz; geringe Anwendbarkeit; große Unsicherheit bei der Verknüpfung von Testgüte mit klinischen und ökonomischen Endpunkten.

Schlussfolgerung der Autor:innen

KI-unterstützte CT-Analyse kann Variabilität reduzieren und die Konsistenz der Beurteilung von Lungenknoten verbessern. Verlässliche Kosteneffektivitäts-Schätzungen sind mit der aktuellen Evidenz nicht möglich.

Kernaussagen

  • KI-Assistenz verbesserte meist die Detektion von Lungenknoten
  • Lesezeit von Radiolog:innen sank in Forschungssituationen meist
  • Keine direkten Studien zu klinischer Wirksamkeit oder Kosteneffektivität

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Systematische Übersicht in der Zeitschrift Health Technology Assessment, 2025-05. Verfasst von Julia Geppert und 13 weiteren Autor:innen. Beteiligte Einrichtung: Warwick Evidence/Warwick Screening, Warwick Medical School, University of Warwick, Coventry, UK. Hauptthemen laut MEDLINE: Artificial Intelligence, Tomography, X-Ray Computed, Lung Neoplasms, Algorithms. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 96 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Health Technology Assessment programme.

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Lung cancer is one of the most common types of cancer and the leading cause of cancer death in the United Kingdom. Artificial intelligence-based software has been developed to reduce the number of missed or misdiagnosed lung nodules on computed tomography images.

Objective

To assess the accuracy, clinical effectiveness and cost-effectiveness of using software with artificial intelligence-derived algorithms to assist in the detection and analysis of lung nodules in computed tomography scans of the chest compared with unassisted reading.

Design

Systematic review and de novo cost-effectiveness analysis.

Methods

Searches were undertaken from 2012 to January 2022. Company submissions were accepted until 31 August 2022. Study quality was assessed using the revised tool for the quality assessment of diagnostic accuracy studies (QUADAS-2), the extension to QUADAS-2 for assessing risk of bias in comparative accuracy studies (QUADAS-C) and the COnsensus-based Standards for the selection of health status Measurement INstruments (COSMIN) checklist. Outcomes were synthesised narratively. Two decision trees were used for cost-effectiveness: (1) a simple decision tree for the detection of actionable nodules and (2) a decision tree reflecting the full clinical pathways for people undergoing chest computed tomography scans. Models estimated incremental cost-effectiveness ratios, cost per correct detection of an actionable nodule, and cost per cancer detected and treated. We undertook scenario and sensitivity analyses.

Results

Twenty-seven studies were included. All were rated as being at high risk of bias. Twenty-four of the included studies used retrospective data sets. Seventeen compared readers with and without artificial intelligence software. One reported prospective screening experiences before and after artificial intelligence software implementation. The remaining studies either evaluated stand-alone artificial intelligence or provided only non-comparative evidence. (1) Artificial intelligence assistance generally improved the detection of any nodules compared with unaided reading (three studies; average per-person sensitivity 0.43–0.68 for unaided and 0.79–0.99 for artificial intelligence-assisted reading), with similar or lower specificity (three studies; 0.77–1.00 for unaided and 0.81–0.97 for artificial intelligence-assisted reading). Nodule diameters were similar or significantly larger with semiautomatic measurements than with manual measurements. Intra-reader and inter-reader agreement in nodule size measurement and in risk classification generally improved with artificial intelligence assistance or were comparable to those with unaided reading. However, the effect on measurement accuracy is unclear. (2) Radiologist reading time generally decreased with artificial intelligence assistance in research settings. (3) Artificial intelligence assistance tended to increase allocated risk categories as defined by clinical guidelines. (4) No relevant clinical effectiveness and cost-effectiveness studies were identified. (5) The de novo cost-effectiveness analysis suggested that for symptomatic and incidental populations, artificial intelligence-assisted computed tomography image analysis dominated the unaided radiologist in cost per correct detection of an actionable nodule. However, when relevant costs and quality-adjusted life-years from the full clinical pathway were included, artificial intelligence-assisted computed tomography reading was dominated by the unaided reader. For screening, artificial intelligence-assisted computed tomography image analysis was cost-effective in the base case and all sensitivity and scenario analyses.

Limitations

Due to the heterogeneity, sparseness, low quality and low applicability of the clinical effectiveness evidence and the major challenges in linking test accuracy evidence to clinical and economic outcomes, the findings presented here are highly uncertain and provide indicators/frameworks for future assessment.

Conclusions

Artificial intelligence-assisted analysis of computed tomography scan images may reduce variability of and improve consistency in the measurement and clinical management of lung nodules. Artificial intelligence may increase nodule and cancer detection but may also increase the number of patients undergoing computed tomography surveillance unnecessarily. No direct comparative evidence was found, and nor was any direct evidence found on clinical outcomes and cost-effectiveness. Artificial intelligence-assisted image analysis may be cost-effective in screening for lung cancer but not for symptomatic populations. However, reliable estimates of cost-effectiveness cannot be obtained with current evidence. Study registration This study is registered as PROSPERO CRD42021298449. Funding This award was funded by the National Institute for Health and Care Research (NIHR) Evidence Synthesis programme (NIHR award ref: NIHR135325) and is published in full in Health Technology Assessment ; Vol. 29, No. 14. See the NIHR Funding and Awards website for further award information.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceTomography, X-Ray ComputedLung NeoplasmsAlgorithmsSoftwareMultiple Pulmonary NodulesHumansCost-Benefit AnalysisUnited Kingdom

Stichwörter der Autor:innen

ARTIFICIAL INTELLIGENCECOST-EFFECTIVENESS ANALYSISEARLY DETECTION OF CANCERLUNG NEOPLASMSSOFTWARESYSTEMATIC REVIEWTOMOGRAPHYX-RAY COMPUTED

Autor:innen und Institutionen

  • Warwick Evidence/Warwick Screening, Warwick Medical School, University of Warwick, Coventry, UK.
  • Population Health Science, University of Bristol, Bristol, UK.
  • Research Centre for Healthcare and Communities, Coventry University, Coventry, UK.
  • University Hospitals Coventry and Warwickshire, Coventry, UK.
  • Warwick Clinical Trials Unit, Warwick Medical School, University of Warwick, Coventry, UK.

ORCID-Profile: Julia Geppert, Peter Auguste, Asra Asgharzadeh, Hesam Ghiasvand, Mubarak Patel, Anna Brown, Surangi Jayakody, Emma Helm, Dan Todkill, Jason Madan, Chris Stinton, Daniel Gallacher, Sian Taylor-Phillips, Yen-Fu Chen

Förderung

  • Health Technology Assessment programme

Zitieren

APA

Geppert, J., Auguste, P., Asgharzadeh, A., Ghiasvand, H., Patel, M., Brown, A., Jayakody, S., Helm, E., Todkill, D., Madan, J., Stinton, C., Gallacher, D., Taylor-Phillips, S., & Chen, Y. F. (2025). Software with artificial intelligence-derived algorithms for detecting and analysing lung nodules in CT scans: systematic review and economic evaluation. Health Technology Assessment, 1-234. https://doi.org/10.3310/jytw8921

Vancouver

Geppert J, Auguste P, Asgharzadeh A, Ghiasvand H, Patel M, Brown A, et al. Software with artificial intelligence-derived algorithms for detecting and analysing lung nodules in CT scans: systematic review and economic evaluation. Health Technology Assessment. 2025:1-234. doi:10.3310/jytw8921

BibTeX
@article{Geppert2025,
  author = {Geppert, Julia and Auguste, Peter and Asgharzadeh, Asra and Ghiasvand, Hesam and Patel, Mubarak and Brown, Anna and Jayakody, Surangi and Helm, Emma and Todkill, Dan and Madan, Jason and Stinton, Chris and Gallacher, Daniel and Taylor-Phillips, Sian and Chen, Yen-Fu},
  title = {Software with artificial intelligence-derived algorithms for detecting and analysing lung nodules in CT scans: systematic review and economic evaluation},
  journal = {Health Technology Assessment},
  year = {2025},
  pages = {1--234},
  doi = {10.3310/jytw8921}
}
Kostenlos starten →