Prognosing post-treatment outcomes of head and neck cancer using structured data and machine learning: A systematic review
Prognose von Post-Therapie-Ergebnissen bei Kopf-Hals-Krebs mit strukturierten Daten und Machine Learning: systematische Übersicht
PLOS ONE · 24.07.2024 · 19 (7) · e0307531
DOI: 10.1371/journal.pone.0307531 ↗Auf einen Blick
Die systematische Übersicht fand, dass ML-Modelle bei Kopf-Hals-Krebs postoperative Überlebensergebnisse und Krankheitsprogression gut vorhersagten und klassische lineare Modelle meist übertrafen.
Fragestellung
Wie gut sagen ML-Modelle bei Kopf-Hals-Krebs posttherapeutisches Überleben und Krankheitsprogression auf Basis klinisch-pathologischer strukturierter Daten voraus?
Methode
Systematische Übersichtsarbeit; Suche in Medline, Scopus, Embase, Web of Science und Google Scholar. Beurteilt wurden Studien, die ML-Modelle entwickelten und validierten; Bias mit PROBAST.
Ergebnisse
34 Artikel aus 5.560 eindeutigen Treffern. Für Überleben lagen die C-Indexe der ML-Modelle bei 0,70–0,79 vs. 0,66–0,76 für Cox-Modelle; für Binary Classification lagen AUROC und F1-Scores in den angegebenen Bereichen.
Einschränkungen
Für Krankheitsprogression wurden keine Time-to-event-Metriken berichtet; externe Validierungen und multizentrische Datensätze fehlten in den meisten Studien.
Schlussfolgerung der Autor:innen
ML-Modelle zeigten großes Potenzial zur Vorhersage von posttherapeutischem Überleben und Krankheitsprogression und schnitten konsistent besser ab als traditionelle lineare Modelle und Nomogramme.
Kernaussagen
- 34 eingeschlossene Artikel
- ML-Modelle übertrafen Cox-Modelle bei Überlebensvorhersagen
- Externen Validierungen und multizentrische Datensätze werden gefordert
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 PLOS ONE, online erschienen am 24.07.2024. Verfasst von Mohammad Moharrami und 7 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Dentistry, University of Toronto, Toronto, Canada. Hauptthemen laut MEDLINE: Head and Neck Neoplasms, Machine Learning. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 92 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: World Health Organization, Canada Graduate Scholarship-Doctoral (CGS-D) from the Canadian Institute of Health Research.
Abstract (Originalsprache)
Background
This systematic review aimed to evaluate the performance of machine learning (ML) models in predicting post-treatment survival and disease progression outcomes, including recurrence and metastasis, in head and neck cancer (HNC) using clinicopathological structured data.
Methods
A systematic search was conducted across the Medline, Scopus, Embase, Web of Science, and Google Scholar databases. The methodological characteristics and performance metrics of studies that developed and validated ML models were assessed. The risk of bias was evaluated using the Prediction model Risk Of Bias ASsessment Tool (PROBAST).
Results
Out of 5,560 unique records, 34 articles were included. For survival outcome, the ML model outperformed the Cox proportional hazards model in time-to-event analyses for HNC, with a concordance index of 0.70–0.79 vs. 0.66–0.76, and for all sub-sites including oral cavity (0.73–0.89 vs. 0.69–0.77) and larynx (0.71–0.85 vs. 0.57–0.74). In binary classification analysis, the area under the receiver operating characteristics (AUROC) of ML models ranged from 0.75–0.97, with an F1-score of 0.65–0.89 for HNC; AUROC of 0.61–0.91 and F1-score of 0.58–0.86 for the oral cavity; and AUROC of 0.76–0.97 and F1-score of 0.63–0.92 for the larynx. Disease-specific survival outcomes showed higher performance than overall survival outcomes, but the performance of ML models did not differ between three- and five-year follow-up durations. For disease progression outcomes, no time-to-event metrics were reported for ML models. For binary classification of the oral cavity, the only evaluated subsite, the AUROC ranged from 0.67 to 0.97, with F1-scores between 0.53 and 0.89.
Conclusions
ML models have demonstrated considerable potential in predicting post-treatment survival and disease progression, consistently outperforming traditional linear models and their derived nomograms. Future research should incorporate more comprehensive treatment features, emphasize disease progression outcomes, and establish model generalizability through external validations and the use of multicenter datasets.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Faculty of Dentistry, University of Toronto, Toronto, Canada.
- Department of Dental Oncology, Princess Margaret Cancer Centre, Toronto, Canada.
- Topic Group Dental Diagnostics and Digital Dentistry, ITU/WHO Focus Group AI on Health, Geneva, Switzerland.
- Chronic Disease and Injury Prevention Department, Health Promotion, Public Health Ontario, Toronto, Canada.
- Program in Child Health Evaluative Sciences, The Hospital for Sick Children, Toronto, Canada.
- Radiation Oncology, Princess Margaret Cancer Center, University of Toronto, Toronto, Canada.
ORCID-Profile: Mohammad Moharrami, Erin Watson
Förderung
- World Health Organization
- Canada Graduate Scholarship-Doctoral (CGS-D) from the Canadian Institute of Health Research
Zitieren
APA
Moharrami, M., Azimian Zavareh, P., Watson, E., Singhal, S., Johnson, A. E. W., Hosni, A., Quinonez, C., & Glogauer, M. (2024). Prognosing post-treatment outcomes of head and neck cancer using structured data and machine learning: A systematic review. PLOS ONE, 19(7), e0307531. https://doi.org/10.1371/journal.pone.0307531
Vancouver
Moharrami M, Azimian Zavareh P, Watson E, Singhal S, Johnson AEW, Hosni A, et al. Prognosing post-treatment outcomes of head and neck cancer using structured data and machine learning: A systematic review. PLOS ONE. 2024;19(7):e0307531. doi:10.1371/journal.pone.0307531
BibTeX
@article{Moharrami2024,
author = {Moharrami, Mohammad and Azimian Zavareh, Parnia and Watson, Erin and Singhal, Sonica and Johnson, Alistair E W and Hosni, Ali and Quinonez, Carlos and Glogauer, Michael},
title = {Prognosing post-treatment outcomes of head and neck cancer using structured data and machine learning: A systematic review},
journal = {PLOS ONE},
year = {2024},
volume = {19},
number = {7},
pages = {e0307531},
doi = {10.1371/journal.pone.0307531}
}
EUVIMED