Search

IntroductionArtificial Intelligence (AI) methods are being increasingly investigated as a means to generate predictive models applicable in the clinical practice. In this study, we developed a model to predict the efficacy of immunotherapy (IO) in patients with advanced non-small cell lung cancer (NSCLC) using eXplainable AI (XAI) Machine Learning (ML) methods.MethodsWe prospectively collected real-world data from patients with an advanced NSCLC condition receiving immune-checkpoint inhibitors (ICIs) either as a single agent or in combination with chemotherapy. With regards to six different outcomes - Disease Control Rate (DCR), Objective Response Rate (ORR), 6 and 24-month Overall Survival (OS6 and OS24), 3-months Progression-Free Survival (PFS3) and Time to Treatment Failure (TTF3) - we evaluated five different classification ML models: CatBoost (CB), Logistic Regression (LR), Neural Network (NN), Random Forest (RF) and Support Vector Machine (SVM). We used the Shapley Additive Explanation (SHAP) values to explain model predictions.ResultsOf 480 patients included in the study 407 received immunotherapy and 73 chemo- and immunotherapy. From all the ML models, CB performed the best for OS6 and TTF3, (accuracy 0.83 and 0.81, respectively). CB and LR reached accuracy of 0.75 and 0.73 for the outcome DCR. SHAP for CB demonstrated that the feature that strongly influences models’ prediction for all three outcomes was Neutrophil to Lymphocyte Ratio (NLR). Performance Status (ECOG-PS) was an important feature for the outcomes OS6 and TTF3, while PD-L1, Line of IO and chemo-immunotherapy appeared to be more important in predicting DCR.ConclusionsIn this study we developed a ML algorithm based on real-world data, explained by SHAP techniques, and able to accurately predict the efficacy of immunotherapy in sets of NSCLC patients.

Among the several next-generation tyrosine kinase inhibitors (TKIs) tested against uncommon EFGR alterations, poziotinib has been demonstrated to be a powerful agent for metastatic non-small-cell lung cancer (mNSCLC) with aberrations in HER2 exon 20, and FDA approval is being sought in the previously-treated population. Poziotinib has also shown activity in mNSCLC with aberrations in EGFR exon 20. Herein, we report the first published case of a patient affected by mNSCLC harbouring an EGFR exon 20 insertion (EGFRex20ins) mutation who achieved a complete response (CR) under treatment with poziotinib as part of the ZENITH20 trial. In January 2021, a former smoker 62-year-old female patient was diagnosed with relapse, after two surgeries and post-operative chemotherapy of mNSCLC, at liver and retroperitoneal nodes. Given the identification by Next Generation Sequencing (NGS) of EGFRex20ins mutation, she was enrolled in ZENITH20-cohort 5 trial, a phase 2 multicentre study aimed to assess the efficacy and safety of poziotinib in patients with EGFR or HER2 exon 20 insertion mutations. Poziotinib as first-line systemic therapy for metastatic disease was initiated at the end of January 2021 and administrated at the initial dosage of 8 mg orally twice daily (BID). The most common side effects from the beginning of the treatment included alopecia, macular skin rash, diarrhoea, xerostomia, and conjunctivitis. Due to these adverse events, poziotinib was discontinued during the first 3 months and then reduced to 6 mg orally BID in April 2021. After the dose de-escalation, the adverse events ameliorated, and the patient better tolerated the treatment without further interruption. Since the first reevaluation (after 4 weeks of therapy), the treatment with poziotinib resulted to be remarkably effective, with a partial response (PR) subsequently confirmed in May and July 2021. Then, in October 2021, a CT scan confirmed a CR, maintained with good tolerance at the last reevaluation in February 2022. Treatment is still ongoing at the same dosage. In this case, poziotinib has represented a successful and well-tolerated first-line treatment alternative to chemotherapy in this patient with EGFR exon 20 insertion mutated mNSCLC.