RESUMO
AIMS: The objective of this study was to develop a two-year overall survival model for inoperable stage I-III non-small cell lung cancer (NSCLC) patients using routine radiation oncology data over a federated (distributed) learning network and evaluate the potential of decision support for curative versus palliative radiotherapy. METHODS: A federated infrastructure of data extraction, de-identification, standardisation, image analysis, and modelling was installed for seven clinics to obtain clinical and imaging features and survival information for patients treated in 2011-2019. A logistic regression model was trained for the 2011-2016 curative patient cohort and validated for the 2017-2019 cohort. Features were selected with univariate and model-based analysis and optimised using bootstrapping. System performance was assessed by the receiver operating characteristic (ROC) and corresponding area under curve (AUC), C-index, calibration metrics and Kaplan-Meier survival curves, with risk groups defined by model probability quartiles. Decision support was evaluated using a case-control analysis using propensity matching between treatment groups. RESULTS: 1655 patient datasets were included. The overall model AUC was 0.68. Fifty-eight percent of patients treated with palliative radiotherapy had a low-to-moderate risk prediction according to the model, with survival times not significantly different (p = 0.87 and 0.061) from patients treated with curative radiotherapy classified as high-risk by the model. When survival was simulated by risk group and model-indicated treatment, there was an estimated 11% increase in survival rate at two years (p < 0.01). CONCLUSION: Federated learning over multiple institution data can be used to develop and validate decision support systems for lung cancer while quantifying the potential impact of their use in practice. This paves the way for personalised medicine, where decisions can be based more closely on individual patient details from routine care.
RESUMO
PURPOSE: The standard management of rectal cancer continues to be defined by the results of randomized, clinical trials exploring the optimal timing and use of adjuvant chemotherapy and radiation therapy in relation to surgery. The patient with rectal cancer who is elderly and/or has significant comorbidities and the patient who refuses surgery are clinical contexts for which there is limited current data to guide decision making. METHODS: A retrospective analysis was performed at six Australian centers of patients with rectal cancer treated with radiation therapy or chemoradiation alone because of excessive operative risk or patient refusal of surgery. RESULTS: We identified 48 patients treated between August 1998 and June 2005 with a median age of 76 (range, 49-94) years. Twenty-four patients (50 percent) were considered medically inoperable and 24 patients refused surgery. Treatment was with chemoradiation (with 5-fluorouracil) in 36 patients and radiotherapy alone in 12 patients; 93 percent completed the planned therapy. A clinical complete response was seen in 56 percent and a partial response in 30 percent of patients. At a median follow-up of 49 months, 18 patients have disease progression, including 10 of 24 in the medically inoperable group and 8 of 24 in the refused surgery group. Of the 25 deceased patients, 16 died from progressive disease and 9 from noncancer causes. CONCLUSIONS: Chemoradiation or radiotherapy alone is a safe alternative that results in significant progression-free and overall survival times in patients who are considered medically inoperable or refuse to undergo surgery. Ultimately, however, many patients will progress.
