Distributed learning on 20 000+ lung cancer patients - The Personal Health Train.

BACKGROUND AND PURPOSE: Access to healthcare data is indispensable for scientific progress and innovation. Sharing healthcare data is time-consuming and notoriously difficult due to privacy and regulatory concerns. The Personal Health Train (PHT) provides a privacy-by-design infrastructure connecting FAIR (Findable, Accessible, Interoperable, Reusable) data sources and allows distributed data analysis and machine learning. Patient data never leaves a healthcare institute. MATERIALS AND METHODS: Lung cancer patient-specific databases (tumor staging and post-treatment survival information) of oncology departments were translated according to a FAIR data model and stored locally in a graph database. Software was installed locally to enable deployment of distributed machine learning algorithms via a central server. Algorithms (MATLAB, code and documentation publicly available) are patient privacy-preserving as only summary statistics and regression coefficients are exchanged with the central server. A logistic regression model to predict post-treatment two-year survival was trained and evaluated by receiver operating characteristic curves (ROC), root mean square prediction error (RMSE) and calibration plots. RESULTS: In 4 months, we connected databases with 23 203 patient cases across 8 healthcare institutes in 5 countries (Amsterdam, Cardiff, Maastricht, Manchester, Nijmegen, Rome, Rotterdam, Shanghai) using the PHT. Summary statistics were computed across databases. A distributed logistic regression model predicting post-treatment two-year survival was trained on 14 810 patients treated between 1978 and 2011 and validated on 8 393 patients treated between 2012 and 2015. CONCLUSION: The PHT infrastructure demonstrably overcomes patient privacy barriers to healthcare data sharing and enables fast data analyses across multiple institutes from different countries with different regulatory regimens. This infrastructure promotes global evidence-based medicine while prioritizing patient privacy.

Prognostic factors for local control and survival for inoperable pulmonary colorectal oligometastases treated with stereotactic body radiotherapy.

PURPOSE: The study aimed to evaluate overall survival and local control, and to identify factors independently associated with overall survival (OS) and local control (LC). MATERIALS AND METHODS: This retrospective study examined 118 patients with primary colorectal cancer, in whom 202 inoperable pulmonary oligometastases were treated with stereotactic body radiotherapy between 2005 and 2015. Primary endpoint was to evaluate OS and identify prognostic factors associated with OS. Secondary aim was to evaluate LC and identify prognostic factors associated with LC. RESULTS: Median follow-up was 31 months (range 3-88 months). Median OS was 39.2 months (95% CI 34.8-43.6 months). Two-, three-, and five-year OS was 69%, 55% and 36%, respectively. LC at 2-, 3-, and 5-year was 83%, 81% and 77% respectively. Factors independently associated with OS in the multivariable analysis included BED10 ≥ 100 Gy (HR 0.52), male gender (HR 0.52), age < 70 years (HR 0.52) and presence of single metastasis (HR 0.37). BED10 < 100 Gy (HR 3.67) and pre-SBRT chemotherapy (HR 2.66) were independently associated with poor LC in a multivariable analysis. CONCLUSIONS: SBRT was associated with 2- year OS of 69% and 2-year LC of 83%. SBRT dose ≥ 100 Gy BED10 was independently associated with both better overall survival and local control.