Rapid Learning in Practice: A Lung Cancer Survival Decision Support System in Routine Patient Care Data

Dekker, André; Holloway, Lois; Vinod, Shalini; Delaney, Geoff P.; Oberije, Cary; Lambin, Philippe; Thwaites, David

doi:10.1016/j.ijrobp.2014.05.1908

Cited by 11 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Increasing the numbers of patient records eligible to be entered into the modelling process can enable the addition of more model parameters and strengthen model performance. For this study the data quality was very high in comparison to similar studies [20] where less than 5 percent of the treated patient records were usable after data mining while in this study over 30 percent of the treated patient records have been included. This can be explained by a previous retrospective study in this patient group.…”

Section: Discussionmentioning

confidence: 91%

Implementation of a rapid learning platform: Predicting 2-year survival in laryngeal carcinoma patients in a clinical setting

et al. 2016

View full text Add to dashboard Cite

Background and PurposeTo improve quality and personalization of oncology health care, decision aid tools are needed to advise physicians and patients. The aim of this work is to demonstrate the clinical relevance of a survival prediction model as a first step to multi institutional rapid learning and compare this to a clinical trial dataset.Materials and MethodsData extraction and mining tools were used to collect uncurated input parameters from Illawarra Cancer Care Centre's (clinical cohort) oncology information system. Prognosis categories previously established from the Maastricht Radiation Oncology (training cohort) dataset, were applied to the clinical cohort and the radiotherapy only arm of the RTOG-9111 (trial cohort).ResultsData mining identified 125 laryngeal carcinoma patients, ending up with 52 patients in the clinical cohort who were eligible to be evaluated by the model to predict 2-year survival and 177 for the trial cohort. The model was able to classify patients and predict survival in the clinical cohort, but for the trial cohort it failed to do so.ConclusionsThe technical infrastructure and model is able to support the prognosis prediction of laryngeal carcinoma patients in a clinical cohort. The model does not perform well for the highly selective patient population in the trial cohort.

show abstract

Section: Discussionmentioning

confidence: 91%

Implementation of a rapid learning platform: Predicting 2-year survival in laryngeal carcinoma patients in a clinical setting

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Dekker et al . showed benefit of a decision support system for radiotherapy in NSCLC, although this needs to be prospectively evaluated in clinical practice . Discussion of all medically inoperable patients at lung cancer MDMs may also reduce clinician bias by involving other clinicians such as respiratory physicians in determining suitaibility for curative radiotherapy.…”

Section: Discussionmentioning

confidence: 99%

Radiotherapy patterns of care for stage I and II non‐small cell lung cancer in Sydney, Australia

Nguyen

Wong²,

Beydoun

et al. 2018

J Med Imag Rad Onc

View full text Add to dashboard Cite

Introduction: Curative radiotherapy is guideline treatment for inoperable patients of good performance status with Stage I & II Non-Small Cell Lung Cancer (NSCLC). The aim of this study was to evaluate radiotherapy patterns of care in these patients, the reasons for palliative treatment and the proportion of patients suitable for curative stereotactic ablative body radiotherapy (SABR). Methods: Electronic oncology databases at three institutions were queried to retrieve data on patients with inoperable Stage I & II NSCLC seen in radiation oncology clinics between 1/1/2008 and 31/12/2014. Suitability for SABR was defined as peripheral tumours less than 5 cm in size. Factors associated with curative treatment were determined using univariate and multivariate analyses. Results: Three-hundred-and-twelve patients were identified of whom 178 (57%) received curative radiotherapy, 58 (19%) palliative radiotherapy and 76 (24%) no radiotherapy. The main reason for receiving palliative rather than curative treatment was COPD or poor pulmonary function (26%). Method of diagnosis (P = 0.031), Simplified Comorbidity Score (P = 0.003), ECOG performance status (P = 0.016), FEV1% (P = 0.040), treating institution (P < 0.0001) and time period (P = 0.016) were associated with curative radiotherapy on multivariate analysis. In patients with T1-2N0M0 NSCLC, 19 (31%) who did not receive treatment and 7 (21%) who underwent palliative radiotherapy were technically and clinically suitable for SABR. Conclusion: Only 57% of patients with Stage I-II NSCLC were treated with curative radiotherapy. Patient factors were the predominant reason for palliative treatment, however, treating institution also played a role. A considerable proportion of patients who underwent palliative or no radiotherapy were suitable for SABR treatment.

show abstract

“…In the prognostic model with clinical variables only, patients in quartiles 2 & 3 were combined to create an intermediate risk group, following a previously published method. [20] (Fig. 5 Enhanced staging algorithms are required to improve the accuracy of staging, which informs clinicians of the likely prognosis and provides subsequent patient risk stratification.…”

Section: Prognostic Model Developed With Clinical Features Onlymentioning

confidence: 99%

External validation of a prognostic model incorporating quantitative PET image features in oesophageal cancer

Foley

Shi

Whybra

et al. 2019

Radiotherapy and Oncology

View full text Add to dashboard Cite

Aim Enhanced prognostic models are required to improve risk stratification of patients with esophageal cancer so treatment decisions can be optimised. The primary aim was to externally validate a published prognostic model incorporating PET image features. Transferability of the model was compared using only clinical variables. Methods This was a Transparent Reporting of a multivariate prediction model for Individual Prognosis Or Diagnosis (TRIPOD) type 3 study. The model was validated against patients treated with neoadjuvant chemoradiotherapy according to the Neoadjuvant chemoradiotherapy plus surgery versus surgery alone for esophageal or junctional cancer (CROSS) trial regimen using pre-and post-harmonised image features. The Kaplan-Meier method with log-rank significance tests assessed risk strata discrimination. A Cox proportional hazards model assessed model calibration. Primary outcome was overall survival (OS). Results Between 2010 and 2015, 449 patients were included in the development (n=302), internal validation (n=101) and external validation (n=46) cohorts. No statistically significant difference in OS between patient quartiles was demonstrated in prognostic models incorporating PET image features (X 2 =1.42, df=3, p=0.70) or exclusively clinical variables (age, disease stage and treatment; X 2 =1.19, df=3, p=0.75). The calibration slope β of both models was not significantly different from unity (p=0.29 and 0.29, respectively). Risk groups defined using only clinical variables suggested differences in OS, although these were not statistically significant (X 2 =0.71, df=2, p=0.70). Conclusion The prognostic model did not enable significant discrimination between the validation risk groups, but a second model with exclusively clinical variables suggested some transferable prognostic ability. PET harmonisation did not significantly change the results of model validation.

show abstract

Rapid Learning in Practice: A Lung Cancer Survival Decision Support System in Routine Patient Care Data

Cited by 11 publications

References 11 publications

Implementation of a rapid learning platform: Predicting 2-year survival in laryngeal carcinoma patients in a clinical setting

Implementation of a rapid learning platform: Predicting 2-year survival in laryngeal carcinoma patients in a clinical setting

Radiotherapy patterns of care for stage I and II non‐small cell lung cancer in Sydney, Australia

External validation of a prognostic model incorporating quantitative PET image features in oesophageal cancer

Contact Info

Product

Resources

About