ESTRO 37 Abstract book

S195

ESTRO 37

2 The Royal Marsden Hospital, Haemato-Oncology Unit, London, United Kingdom 3 The Royal Marsden Hospital, Radiology, London, United Kingdom 4 The Institute of Cancer Research and The Royal Marsden NHS Foundation Trust, Joint Department of Physics, Sutton, United Kingdom 5 The Royal Marsden Hospital, Department of Radiotherapy & Haemato-Oncology Unit, London, United Kingdom Purpose or Objective Total body irradiation (TBI) remains a key component of conditioning regimes for allogeneic haemopoietic stem cell transplant (HSCT), with radiation-induced interstitial pneumonitis (IP) and chronic kidney disease (CKD) the most significant sequalae. The reported rates of IP post TBI are between 11-31%, with an associated mortality rate of nearly 50%; the rates of renal dysfunction are as high as 44%. We have undertaken a retrospective service evaluation of all patients treated at The Royal Marsden since the introduction of a forward planned intensity modulated radiotherapy technique (FP IMRT) for TBI, assessing the incidence of IP and CKD in patients undergoing full intensity HSCT. Material and Methods 74 adult patients were identified, treated with TBI between July 2009 and February 2016 since the introduction of FP IMRT-based TBI. All received 14.4 Gy in 8 fractions over 4 days, prescribed at 100%; the lungs and kidneys both receiving a reduced mean dose of between 12-12.5 Gy. IP was defined as multilobar infiltrates on CT with symptoms of dyspnoea, and renal dysfunction was defined as an eGFR <60 for >3 months. Results The patients in this series received treatment for the following diagnosis: ALL (n=34); AML (n=32), T-LBL (n=3), CML-BC (2) and CNS relapse of NHL (n=1).The median age at start of TBI was 27.6 years (range 17.0-46.1 yrs). The estimated 4 year overall survival and progression free survival rate was 71% (58%-80%) and 65% (52%-76%) respectively with a median follow up time of survivors of 3.9 years (range 1.2-7.7 yrs). We found the rates of IP due to any cause to be 30% with 16 (73%) of these 22 patients having positive microbiological evidence of infection at that time. The rates of idiopathic IP was 8% (CTCAE Grade ≥1), with only 2 patients suffering with IP of CTCAE grade ≥ 3. The median time after TBI for developing IP was 146 days (range 10-406 days). Seven patients (9.5%) died from chest sepsis a median of 246 days after TBI (range 89- 2413 days). Of the 52 long term survivors only two developed CKD, one of which had biopsy confirming thrombotic microangiopathy. Conclusion This novel FP IMRT based TBI technique, with reduced dose to the lungs and kidneys, has resulted in significantly lower rates of radiation-induced IP and CKD compared to the literature. Idiopathic IP of CTCAE Grade ≥3 was observed in just 2.7% of patients. The rate of long term risk of renal dysfunction is very low, with 1 secondary to thrombotic microangiopathy, which can be associated with GVHD or radiation related. This series has confirmed FP IMRT- based TBI to be both safe and effective conditioning for full intensity HSCT. OC-0387 Treatment information improve machine learning survival prediction in soft tissue sarcoma patients J.C. Peeken 1 , T. Goldberg 2 , C. Knie 1 , B. Komboz 2 , M. Bernhofer 3 , F. Pasa 4 , K.A. Kessel 1 , P. Tafti 2 , B. Rost 3 , F. Nüsslin 1 , A. Braun 2 , S.E. Combs 1 1 Klinikum rechts der Isar- TU München, Department of Radiationoncology, München, Germany 2 Allianz SE, Global Data and Analytics, Munich, Germany 3 Informatik 12- TU München, Department for

Bioinformatics and Computational Biology, Munich, Germany 4 Department of Physics- TU München, Chair of Biomedical Physics-, Munich, Germany Purpose or Objective Current prognostic models for soft tissue sarcomas (STS) are solely based on staging information. Treatment- related data or response-associated information are currently not regarded. Inclusion of such information could help to improve post-therapeutic risk-assessment. To this end, we created pre- and post-therapeutic machine learning-based prognostic models and compared their performance. Material and Methods A single center retrospective cohort of 136 STS patients treated with radiation was analyzed for patients characteristics, staging information, treatment modalities and radiation therapy-specific information. For neoadjuvant patients, postoperative MRI and pathology reports were analyzed for signs of response. Random forest machine learning-based models were used to predict patient’s death and disease progression at two years (2y). For pre-therapeutic models staging information, including histology and anatomic site, were used as input features. For post-treatment models therapy-related data was added. To evaluate the importance of single features for model performance, the reduction in AUC after exclusion of the respective feature was determined. Results The prognostic models achieved high performances up to an area under the curve (AUC) of 0.88 (see Figure 1). Pre- treatment models predicting 2y survival, 2y local and systemic disease progression showed high performance achieving AUCs of 0.73, 076 and 0.63, respectively. Adding post-treatment features improved the overall performance for all three classification types: prediction of death (AUC of 0.87), and of local and systemic progress (AUC of 0.88 and 0.84, respectively). In the feature importance analysis, age appeared to be a strong discriminative feature for pre- and post-therapeutic models. For pre-treatment models, tumor side appeared to be among the most discriminative features with an impact of nearly 0.20 AUC. For post-treatment models, chemotherapy and radiotherapy-related features, such as the planning target volume and total dose, had preeminent importance for prognostic performance with AUC reductions up to 0.12. The volume of the primary tumor after radiotherapy and its relative decrease during radiation were used for prediction of systemic progression showing potential for response-assessment.

Figure 1:

Conclusion Machine learning-based prognostic models combining known prognostic factors with treatment- and response- related information showed high accuracy for individualized risk-assessment of death and disease progression outperforming pre-therapeutic models. These models could be used for adjustments of follow-up procedures in patients that received radiation therapy. OC-0388 Dexamethasone for prevention of pain flare; results from a phase 3 trial in painful bone metastases Y. Van der Linden 1 , P. Westhoff 2 , R. Stellato 3 , N. Kasperts 4 , A. Van Baardwijk 5 , K. De Vries 6 , A. Reyners 7 , A. De Graeff 8