ESTRO 2022 - Abstract Book

S941

Abstract book

ESTRO 2022

allowed. Recurrent or metastatic pts were excluded. For all pts, miR-9 was evaluated on Paraffin-embedded samples using Droplet Digital PCR Assay (ddPCR). To evaluate the impact of miR-9 on survival, the median of expression level was used as cut off. After treatment, follow up was performed every 3 months with clinical examination, fibrolaryngoscopy, and radiologic/metabolic imaging. RFS was evaluated with Kaplan Meyer method. Results Median age of the 35 pts was 65 years (range 44-81 years). Twenty-six out of 35 pts were male (74%). Current smokers and former smokers were 14 (40%) and 9 (26%), respectively. Alcohol abuse was found in 17 (48%) pts. HNSCC originated from OP, HP and L in 30 (86%), 1 (3%) and 4 (11%), respectively. HPV status was detected in 16 out of 35 pts and resulted HPV+ in only 5 pts. TNM stage was III and IV in 14 (39%) and 21 (61%) pts, respectively. Pts treated with RT+CTX and RT+CTX+other were 26 (74%) and 9 (26%), respectively. The cut-off of miR-9 expression was 75,819 reads: 18 (58%) showed high levels of miR-9 expression. Complete response, Partial response and progressive disease was assessed in 18 (48%), 11 (26%) and 6 (26%) pts, respectively. Pts with higher miR-9 expression experienced worse PFS (p=0,0382) with respect to pts with low miR-9 expression (fig. 1). Conclusion Our preliminary data suggest that high expression of miR-9 identifies a subset of HNSCC pts with decreased PFS after RT+CTX. Further evaluations are ongoing, in particular to evaluate the impact of miR-9 on overall survival in this cohort and in the subgroup of pts unfit for chemotherapy and treated with radical RT+CTX. Purpose or Objective Irradiating brain or head & neck tumor with curative or prophylactic intent, results in dose to the healthy surrounding brain possibly resulting is clinical relevant side effects like neurocognitive decline. Preservation of neurocognitive function is of paramount importance to maintain the quality of life of the treated patients. Prediction models have the potential to identify patients at high risk of developing radiation-induced neurocognitive burden. This study summarizes and evaluates available prediction models for estimating the risk of neurocognitive decline after cranial irradiation. Materials and Methods MEDLINE was searched on 4 March 2021 for publications containing relevant truncation and MeSH terms related to “radiotherapy”, “brain”, “prediction model”, and “neurocognitive impairments” (e.g., memory dysfunction, learning and attention deficits, problem-solving incompetence, psychological disorders). Two independent reviewers excluded studies according the following criteria: lack of model specifications, no predictor in multivariate analysis, or no adult population. Quality of prediction models was assessed using 14 common methodological considerations in machine learning proposed by Andaur Navarro CL et al. (PMID: 33177137), including data source, data preparation, hyper-parameter tuning, model building strategy, test of interaction terms, and applying shrinkage or penalization methods. Results Of 3,351 studies reviewed, 27 studies met the pre-defined eligibility criteria. Included studies were published between 1996 and 2021 with a median sample size of 119 and 55.6% male patients. Nineteen studies developed a prediction model for patients with primary brain or head & neck tumors and eight studies included patients with metastatic brain tumors. Four studies assessed the effect of prophylactic cranial irradiation. Hopkins Verbal Learning Test-Revised (n=7, 26%), Montreal Cognitive Assessment (n=3, 12%), and Mini Mental State Examination (n=2, 7%) were the most frequent neurocognitive outcome assessment tools. All studies used regression (n=14 linear, n=8 logistic, and n=5 cox proportional hazard) as the machine learning method. Further details of the included studies are described in Table 1. The median quality score was 2 out of 14 and only one study assessed the area under the receiver operating characteristic curve (Figure 1). PO-1108 Predicting radiation-induced neurocognitive decline in patients with brain or head & neck tumor F. Tohidinezhad 1 , D. Di Perri 1 , C. M.L. Zegers 1 , A. Dekker 1 , W. Van Elmpt 1 , D. Eekers 1 , A. Traverso 1 1 Maastricht University Medical Center, Department of Radiation Oncology (Maastro Clinic, Maastricht, The Netherlands