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.

Prophylactic radiotherapy for the prevention of procedure-tract metastases after surgical and large-bore pleural procedures in malignant pleural mesothelioma (SMART): a multicentre, open-label, phase 3, randomised controlled trial.

BACKGROUND: The use of prophylactic radiotherapy to prevent procedure-tract metastases (PTMs) in malignant pleural mesothelioma remains controversial, and clinical practice varies worldwide. We aimed to compare prophylactic radiotherapy with deferred radiotherapy (given only when a PTM developed) in a suitably powered trial. METHODS: We did a multicentre, open-label, phase 3, randomised controlled trial in 22 UK hospitals of patients with histocytologically proven mesothelioma who had undergone large-bore pleural interventions in the 35 days prior to recruitment. Eligible patients were randomised (1:1), using a computer-generated sequence, to receive immediate radiotherapy (21 Gy in three fractions within 42 days of the pleural intervention) or deferred radiotherapy (same dose given within 35 days of PTM diagnosis). Randomisation was minimised by histological subtype, surgical versus non-surgical procedure, and pleural procedure (indwelling pleural catheter vs other). The primary outcome was the incidence of PTM within 7 cm of the site of pleural intervention within 12 months from randomisation, assessed in the intention-to-treat population. This trial is registered with ISRCTN, number ISRCTN72767336. FINDINGS: Between Dec 23, 2011, and Aug 4, 2014, we randomised 203 patients to receive immediate radiotherapy (n=102) or deferred radiotherapy (n=101). The patients were well matched at baseline. No significant difference was seen in PTM incidence in the immediate and deferred radiotherapy groups (nine [9%] vs 16 [16%]; odds ratio 0·51 [95% CI 0·19-1·32]; p=0·14). The only serious adverse event related to a PTM or radiotherapy was development of a painful PTM within the radiotherapy field that required hospital admission for symptom control in one patient who received immediate radiotherapy. Common adverse events of immediate radiotherapy were skin toxicity (grade 1 in 50 [54%] and grade 2 in four [4%] of 92 patients vs grade 1 in three [60%] and grade 2 in two [40%] of five patients in the deferred radiotherapy group who received radiotherapy for a PTM) and tiredness or lethargy (36 [39%] in the immediate radiotherapy group vs two [40%] in the deferred radiotherapy group) within 3 months of receiving radiotherapy. INTERPRETATION: Routine use of prophylactic radiotherapy in all patients with mesothelioma after large-bore thoracic interventions is not justified. FUNDING: Research for Patient Benefit Programme from the UK National Institute for Health Research.