Abstract

Idiopathic pulmonary fibrosis (IPF) identifies a specific entity characterized by chronic, progres-sive fibrosing interstitial pneumonia of unknown cause, still lacking effective therapies. Notably, the incidence of lung cancer in patients already affected by IPF is significantly higher than the expected. Recent advances in the knowledge of cancer immune mi-croenvironment have allowed a paradigm shift in cancer therapy.  We here presents exhaustive data from 32 patients fearturing lung cancer and co-exihisting IPF who came at our observation from 2017 till the end of 2022. The average age of lung cancer diagnosis was 72.3 years whereas that of IPF was 68.6 years, the average Charlson comordity index was 4.9. Female patients were the 28% of the evaluated cases. The most frequent tumor hystotype was adenocarcinoma (66.6%) and in about half of the cases (52%) cancer was diagnosed at early stage (TNM I-II-IIIA). Those patients underwent sublobar surgery (51%) or stereotactic radiotherapy (49%); advanced cases where treated with chemotherapy. The 38% of patients are still alive. The entire dataset was then analysed by using the JMP partition algorithm (JMP-Statistical Discoveries. From SAS) which is able to search all possible splits of best response predictors. The partition algorithm chooses optimum splits from many possible trees, making it a powerful modelling, and data discovery tool. Quite unexpectedly this approach showed that IPF related features (therapy and respiratory function) are associated to patients outcome (prediction) irrespective of those associated to the concomitant tumor (histology and stage).