EUVIMEDEUVIMED entdecken
BeobachtungsstudieOpen Access · CC BY-NC 4.0

Real-World Experience With Artificial Intelligence-Enabled Natural Language Processing for Identification and Management of Incidental Lung Nodules

Real-World-Erfahrung mit KI-gestützter natürlicher Sprachverarbeitung zur Identifikation und Steuerung von inzidentellen Lungenknoten

Shelby Ploucher, Andrew D Nguyen, Rida Altaf, Zaim Khan, Zilipah Cruz, Luis Herrera, Ali Jiwani, Jennifer Tseng, Kim Styrvoky iD

Therapeutic Advances in Respiratory Disease · 2026-10 · 20

DOI: 10.1177/17534666261501246 ↗

Auf einen Blick

Nach Einführung einer KI-NLP-Plattform wurden mehr inzidentelle Lungenknoten gefunden, häufiger in Akutversorgung. Die Autoren sehen keine zurechenbaren Effekte auf Malignitätsdiagnose oder Behandlungszeit.

Fragestellung

Beschreibt die Studie die Identifikation, Nachsorge und Zeit bis zur Krebsbehandlung nach Einführung einer KI-gestützten NLP-Plattform für inzidentelle Lungenknoten?

Methode

Einzentrische retrospektive Beobachtungsstudie bei Erwachsenen mit ILNs zwischen April 2023 und Mai 2024; prä-AI über Diagnosecodes, post-AI über NLP-basierte KI; deskriptive Auswertung ohne formale Vergleichstests.

Ergebnisse

1.098 Patient:innen mit ILNs: 228 von 6.828 prä-AI-Bildgebungen (3,3 %) und 870 von 9.902 post-AI-Bildgebungen (8,8 %). Follow-up-Empfehlung: 85,5 % vs. 64,7 %; dokumentierte Abschlussrate: 85,6 % vs. 73,5 %; Malignität: 12,3 % vs. 1,7 %; mediane Zeit Bildgebung–Biopsie: 78 vs. 120 Tage.

Einschränkungen

Keine formalen Vergleichstests; unterschiedliche Populationen vor und nach Einführung der KI, daher keine Attribution der Unterschiede an die Plattform.

Schlussfolgerung der Autor:innen

Die post-AI-Kohorte umfasste mehr identifizierte ILNs und einen höheren Anteil aus Akutversorgung. Unterschiede in Malignitätsdiagnose und Behandlungszeiten sind wegen der nicht vergleichbaren Identifikation nicht der Plattform zuzuordnen.

Kernaussagen

  • Mehr ILNs nach KI-Einführung identifiziert
  • Mehr Fälle aus stationärer, Notaufnahme- und ambulanter Versorgung
  • Effekte auf Diagnose und Timing nicht kausal der Plattform zuordenbar

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

Kurz gefasst

Beobachtungsstudie in der Zeitschrift Therapeutic Advances in Respiratory Disease, online erschienen am 27.10.2026. Verfasst von Shelby Ploucher und 8 weiteren Autor:innen. Beteiligte Einrichtung: Hematology/Oncology Fellowship, Department of Graduate Medical Education, Orlando Health Cancer Institute, Orlando, FL, USA. Hauptthemen laut MEDLINE: Natural Language Processing, Artificial Intelligence, Lung Neoplasms, Multiple Pulmonary Nodules. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Incidental lung nodules (ILNs) are common, but adherence to guideline-recommended follow-up is variable, which may contribute to delayed diagnosis of malignancy. Artificial intelligence (AI) platforms using natural language processing (NLP) may improve identification, but their impact on clinical management and outcomes remains uncertain.

Objectives

This study describes ILN identification, follow-up management, and timeliness of cancer treatment after implementation of an AI-enabled NLP platform at a large health system.

Design

Single-center retrospective observational study.

Methods

Adults with ILNs identified on imaging between April 2023 and May 2024 were included. The pre-AI cohort was identified using diagnosis codes, while the post-AI cohort was identified using an NLP-based AI platform. Because these methods captured different populations, no formal comparative testing was performed, and outcomes were summarized descriptively.

Results

A total of 1,098 patients with ILNs were identified: 228 from 6,828 pre-AI imaging studies (3.3%) and 870 from 9,902 post-AI imaging studies (8.8%). Most pre-AI ILNs were identified on outpatient imaging (74%), while post-AI ILNs were identified in inpatient (35%), emergency department (26%), and outpatient (39%) settings. A follow-up recommendation was documented for 195 of 228 pre-AI patients (85.5%) and 563 of 870 post-AI patients (64.7%). Among these patients, completion was documented for 167 of 195 (85.6%) and 414 of 563 (73.5%), respectively. Malignancy was documented in 28 of 228 pre-AI patients (12.3%) and 15 of 870 post-AI patients (1.7%). Median imaging-to-biopsy time was 78 days pre-AI and 120 days post-AI; biopsy-to-treatment and imaging-to-treatment intervals were similar.

Conclusion

The post-AI cohort included more identified ILNs and a greater proportion from acute-care settings than the historical pre-AI cohort. Because identification methods were not comparable, observed differences in documented malignancy diagnosis and treatment timing cannot be attributed to the platform. Effective implementation requires defined clinical ownership and follow-up infrastructure.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingArtificial IntelligenceLung NeoplasmsMultiple Pulmonary NodulesSolitary Pulmonary NoduleHumansRetrospective StudiesFemaleMaleIncidental FindingsMiddle AgedAgedGuideline AdherenceTime Factors

Stichwörter der Autor:innen

artificial intelligencefollow-up adherenceincidental lung nodulelung cancernatural language processing

Autor:innen und Institutionen

  • Hematology/Oncology Fellowship, Department of Graduate Medical Education, Orlando Health Cancer Institute, Orlando, FL, USA.
  • Oncology Quality, Orlando Health Cancer Institute, Orlando, FL, USA.
  • Internal Medicine Residency, Department of Graduate Medical Education, Orlando Regional Medical Center, Orlando, FL, USA.
  • Oncology Service Line, Orlando Health Cancer Institute, Orlando, FL, USA.
  • Section of Thoracic Surgery, Division of Thoracic Oncology, Department of Surgical Oncology, Orlando Health Cancer Institute, Orlando, FL, USA.
  • Section of Interventional Pulmonology, Division of Thoracic Oncology, Department of Surgical Oncology, Orlando Health Cancer Institute, Orlando, FL, USA.

ORCID-Profile: Kim Styrvoky

Zitieren

APA

Ploucher, S., Nguyen, A. D., Altaf, R., Khan, Z., Cruz, Z., Herrera, L., Jiwani, A., Tseng, J., & Styrvoky, K. (2026). Real-World Experience With Artificial Intelligence-Enabled Natural Language Processing for Identification and Management of Incidental Lung Nodules. Therapeutic Advances in Respiratory Disease, 20. https://doi.org/10.1177/17534666261501246

Vancouver

Ploucher S, Nguyen AD, Altaf R, Khan Z, Cruz Z, Herrera L, et al. Real-World Experience With Artificial Intelligence-Enabled Natural Language Processing for Identification and Management of Incidental Lung Nodules. Therapeutic Advances in Respiratory Disease. 2026;20. doi:10.1177/17534666261501246

BibTeX
@article{Ploucher2026,
  author = {Ploucher, Shelby and Nguyen, Andrew D and Altaf, Rida and Khan, Zaim and Cruz, Zilipah and Herrera, Luis and Jiwani, Ali and Tseng, Jennifer and Styrvoky, Kim},
  title = {Real-World Experience With Artificial Intelligence-Enabled Natural Language Processing for Identification and Management of Incidental Lung Nodules},
  journal = {Therapeutic Advances in Respiratory Disease},
  year = {2026},
  volume = {20},
  doi = {10.1177/17534666261501246}
}
Kostenlos starten →