Machine learning to refine prognostic and predictive nodal burden thresholds for post-operative radiotherapy in completely resected stage III-N2 non-small cell lung cancer

Zarinshenas, Reza; Ladbury, Colton; McGee, Heather M.; Raz, Dan J.; Erhunmwunsee, Loretta; Pathak, Ranjan; Glaser, Scott; Salgia, Ravi; Williams, Terence M.; Amini, Arya

doi:10.1016/j.radonc.2022.05.019

Cited by 10 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A propensity score matched analysis suggested patients with N2 squamous cell lung cancer benefited from PORT ( 63 ). Moreover, A machine learning-based model was developed to predict the prognosis of patients with N2 disease and suggested that patients with a high lymph node burden or lymph node ratio might benefit from PORT ( 64 ).…”

Section: Discussionmentioning

confidence: 99%

Research landscape and trends of lung cancer radiotherapy: A bibliometric analysis

Liu

Jiang²,

Lin³

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

Backgroundradiotherapy is one of the major treatments for lung cancer and has been a hot research area for years. This bibliometric analysis aims to present the research trends on lung cancer radiotherapy.MethodOn August 31, 2022, the authors identified 9868 articles on lung cancer radiotherapy by the Web of Science (Science Citation Indexing Expanded database) and extracted their general information and the total number of citations. A bibliometric analysis was carried out to present the research landscape, demonstrate the research trends, and determine the most cited papers (top-papers) as well as top-journals on lung cancer radiotherapy. After that, the authors analyzed the recent research hotspots based on the latest publications in top-journals.ResultsThese 9868 papers were cited a total of 268,068 times. “Durvalumab after chemoradiotherapy in stage III non–small-cell lung cancer” published in 2017 by Antonia et al.was the most cited article (2110 citations). Among the journals, New England Journal of Medicine was most influential. Moreover, J. Clin. Oncol. and Int. J. Radiat. Oncol. Biol. Phys. was both influential and productive. Corresponding authors represented the USA (2610 articles) and China mainland (2060 articles) took part in most publications and articles with corresponding authors from Netherlands were most cited (46.12 citations per paper). Chemoradiotherapy was the hottest research area, and stereotactic body radiotherapy has become a research hotspot since 2006. Radiotherapy plus immunotherapy has been highly focused since 2019.ConclusionsThis bibliometric analysis comprehensively and quantitatively presents the research trends and hotspots based on 9868 relevant articles, and further suggests future research directions. The researchers can benefit in selecting journals and in finding potential collaborators. This study can help researchers gain a comprehensive picture of the research landscape, historical development, and recent hotspots in lung cancer radiotherapy and can provide inspiration for future research.

show abstract

Section: Discussionmentioning

confidence: 99%

Research landscape and trends of lung cancer radiotherapy: A bibliometric analysis

Liu

Jiang²,

Lin³

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“… 60 , 61 However, certain populations may still benefit from treatment. In work by Zarinshenas et al., 62 an XGBoost ML model was used to identify patients who may still benefit from PORT on the basis of nodal burden. The model identified positive nodal count thresholds of ≥3 and positive nodal ratios of ≥0.34 as predictive of benefit from PORT, achieving a concordance index of 0.65, outperforming Cox regression.…”

Section: Treatmentmentioning

confidence: 99%

Integration of artificial intelligence in lung cancer: Rise of the machine

Ladbury¹,

Amini²,

Govindarajan³

et al. 2023

Cell Reports Medicine

Self Cite

View full text Add to dashboard Cite

“…Dependence plots generated by XAI can be useful for identification of predictive thresholds. Ladbury et al ( 44 ) and Zarinshenas et al ( 45 ) examined the prognostic and predictive value of nodal burden in endometrial cancer and locally advanced non-small cell lung cancer (NSCLC), respectively, with associated XAI plots aiding in addressing controversies in the field. In endometrial cancer, via qualitative inspection of SHAP plots, XAI facilitated identification of a threshold of four or more positive nodes where treatment with adjuvant chemoradiation achieved optimal outcomes, while chemotherapy alone had a neutral effect and radiation alone had a deleterious effect.…”

Section: Utilization Of Xai In Oncology Researchmentioning

confidence: 99%

“…[Credit: ref. ( 45 )]. SHAP, SHapley Additive exPlanations; PORT, post-operative radiotherapy; NSCLC, non-small cell lung cancer.…”

Section: Utilization Of Xai In Oncology Researchmentioning

confidence: 99%

Utilization of model-agnostic explainable artificial intelligence frameworks in oncology: a narrative review

Ladbury¹,

Zarinshenas²,

Semwal³

et al. 2022

Transl Cancer Res TCR

Self Cite

View full text Add to dashboard Cite

Background and Objective: Machine learning (ML) models are increasingly being utilized in oncology research for use in the clinic. However, while more complicated models may provide improvements in predictive or prognostic power, a hurdle to their adoption are limits of model interpretability, wherein the inner workings can be perceived as a "black box". Explainable artificial intelligence (XAI) frameworks including Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) are novel, model-agnostic approaches that aim to provide insight into the inner workings of the "black box" by producing quantitative visualizations of how model predictions are calculated. In doing so, XAI can transform complicated ML models into easily understandable charts and interpretable sets of rules, which can give providers with an intuitive understanding of the knowledge generated, thus facilitating the deployment of such models in routine clinical workflows.Methods: We performed a comprehensive, non-systematic review of the latest literature to define use cases of model-agnostic XAI frameworks in oncologic research. The examined database was PubMed/MEDLINE.

show abstract

Machine learning to refine prognostic and predictive nodal burden thresholds for post-operative radiotherapy in completely resected stage III-N2 non-small cell lung cancer

Cited by 10 publications

References 27 publications

Research landscape and trends of lung cancer radiotherapy: A bibliometric analysis

Research landscape and trends of lung cancer radiotherapy: A bibliometric analysis

Integration of artificial intelligence in lung cancer: Rise of the machine

Utilization of model-agnostic explainable artificial intelligence frameworks in oncology: a narrative review

Contact Info

Product

Resources

About