A prospective study comparing the predictions of doctors versus models for treatment outcome of lung cancer patients: A step toward individualized care and shared decision making

Abstract

Background Decision Support Systems, based on statistical prediction models, have the potential to change the way medicine is being practiced, but their application is currently hampered by the astonishing lack of impact studies. Showing the theoretical benefit of using these models could stimulate conductance of such studies. In addition, it would pave the way for developing more advanced models, based on genomics, proteomics and imaging information, to further improve the performance of the models. Purpose In this prospective single-center study, previously developed and validated statistical models were used to predict the two-year survival (2yrS), dyspnea (DPN), and dysphagia (DPH) outcomes for lung cancer patients treated with chemo radiation. These predictions were compared to probabilities provided by doctors and guideline-based recommendations currently used. We hypothesized that model predictions would significantly outperform predictions from doctors. Materials and Methods Experienced radiation oncologists (ROs) predicted all outcomes at two timepoints: 1) after the first consultation of the patient, and 2) after the radiation treatment plan was made. Differences in the performances of doctors and models were assessed using Area under the Curve (AUC) analysis. Results A total number of 155 patients were included. At timepoint #1 the differences in AUCs between the ROs and the models were 0.15, 0.17, and 0.20 (for 2yrS, DPN, and DPH respectively), with p-values of 0.02, 0.07, and 0.03. Comparable differences at timepoint #2 were not statistically significant due to the limited number of patients. Comparison to guideline-based recommendations also favored the models. Conclusions The models substantially outperformed ROs’ predictions and guideline-based recommendations currently used in clinical practice. Identification of risk groups on the basis of the models facilitates individualized treatment, and should be further investigated in clinical impact studies.

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

“…The DSS had a reasonable discriminatory performance in the clinical cohort and was able to identify patients with a good prognosis but could not discriminate between a medium and poor prognosis. The observed AUC (0.69) is better than physician predicted outcomes (AUC 0.56) as was recently shown in a prospective study [20].…”

Multivariable normal-tissue complication modeling of acute esophageal toxicity in advanced stage non-small cell lung cancer patients treated with intensity-modulated (chemo-)radiotherapy

“…These findings even more imply the need for this study as the increased conformality of IMRT paved the way for treatment intensification strategies such as dose escalation. These strategies may increase AET and therefore it is important to be able to adequately predict AET by means of a predictive model, in particular because model based predictions outperform the predictions of physicians [32]. Our IMRT-based predictive model for AET may guide future dose prescription and treatment planning to keep toxicity within acceptable levels.…”

Investigation of a Patient Reported Outcome tool to assess radiotherapy-related toxicity prospectively in patients with lung cancer

“…Discrepancies between patients' and clinicians' reported toxicity and the feasibility of PRO tools have also been shown in lung cancer in the context of systemic treatment and in other tumour sites [8,11,[19][20][21]. Besides PRO tools, predictive models for survival, oesophageal and pulmonary toxicity have shown significantly better accuracy compared to clinicians' predictions [22,23]. In addition, the use of imaging techniques such as 2-…”