Artificial Intelligence (AI) has revolutionized the management of non-small-cell lung cancer (NSCLC) by enhancing different aspects, including staging, prognosis assessment, treatment prediction, response evaluation, recurrence/prognosis prediction, and personalized prognostic assessment. AI algorithms may accurately classify NSCLC stages using machine learning techniques and deep imaging data analysis. This could potentially improve precision and efficiency in staging, facilitating personalized treatment decisions. Furthermore, there are data suggesting the potential application of AI-based models in predicting prognosis in terms of survival rates and disease progression by integrating clinical, imaging and molecular data. In the present narrative review, we will analyze the preliminary studies reporting on how AI algorithms could predict responses to various treatment modalities, such as surgery, radiotherapy, chemotherapy, targeted therapy, and immunotherapy. There is robust evidence suggesting that AI also plays a crucial role in predicting the likelihood of tumor recurrence after surgery and the pattern of failure, which has significant implications for tailoring adjuvant treatments. The successful implementation of AI in personalized prognostic assessment requires the integration of different data sources, including clinical, molecular, and imaging data. Machine learning (ML) and deep learning (DL) techniques enable AI models to analyze these data and generate personalized prognostic predictions, allowing for a precise and individualized approach to patient care. However, challenges relating to data quality, interpretability, and the ability of AI models to generalize need to be addressed. Collaboration among clinicians, data scientists, and regulators is critical for the responsible implementation of AI and for maximizing its benefits in providing a more personalized prognostic assessment. Continued research, validation, and collaboration are essential to fully exploit the potential of AI in NSCLC management and improve patient outcomes. Herein, we have summarized the state of the art of applications of AI in lung cancer for predicting staging, prognosis, and pattern of recurrence after treatment in order to provide to the readers a large comprehensive overview of this challenging issue.

Background: Pembrolizumab is approved in monotherapy for the first-line (1L) of advanced or metastatic NSCLC patients with high PD-L1 (≥50%). Despite a proportion of patients achieve long-term survival, about one-third of patients experience detrimental survival outcomes, including early death, hyperprogression, and fast progression. The impact of clinical factors on early progression (EP) development has not been widely explored. Methods: We designed a retrospective, multicenter study involving five Italian centers, in patients with metastatic NSCLC with PD-L1 ≥ 50%, treated with Pembrolizumab in a 1L setting. EP was defined as a progressive disease within three months from pembrolizumab initiation. Baseline clinical factors of patients with and without EP were collected and analyzed. Logistic regression was performed to identify clinical factors associated with EP and an EP prognostic score was developed based on the logistic model. Results: Overall, 321 out of 336 NSCLC patients treated with 1L pembrolizumab provided all the data for the analysis. EP occurred in 137 (42.7%) patients; the median PFS was 3.8 months (95% CI: 2.9–4.7), and median OS was not reached in the entire study population. Sex, Eastern Cooperative Oncology Group (ECOG) performance status (PS), steroids, metastatic sites ≥2, and the presence of liver/pleural metastasis were confirmed as independent factors for EP by multivariate analysis. By combining these factors, we developed an EP prognostic score ranging from 0–13, with three-risk group stratification: 0–2 (good prognosis), 3–6 (intermediate prognosis), and 7–13 (poor prognosis). The area under the curve (AUC) of the model was 0.76 (95% CI: 0.70–0.81). Conclusions: We identified six clinical factors independently associated with EP. We developed a prognostic score model for EP-risk to potentially improve clinical practice and patient selection for 1L pembrolizumab in NSCLC with high PD-L1, in the real-world clinical setting.

Background: Only few ES-SCLC patients experience long-term survival benefit by maintenance IT. Adipokines-induced metabolic meta-inflammation has been related to enhanced responsiveness to IT in obese patients; however, their prognostic role in SCLC is currently controversial. Methods: Pre-treatment CT scan was used for determining distribution of abdominal adiposity, and blood samples were collected at fasting for measuring glycemia, insulin, ghrelin, leptin and adipokines (TNF-α, IFN-γ, IL-6 and MCP-1). Patients with known history of DM type II or metabolic syndrome with HOMA index > 2.5 were considered insulin resistant (IR). Results: In ES-SCLC pts receiving maintenance IT, increased leptin concentration and higher leptin/visceral adipose tissue (VAT) ratio were significantly associated with prolonged PFS. By applying a hierarchical clustering algorithm, we identified a cluster of patients characterized by higher leptin values and lower pro-inflammatory cytokines (TNF-α, IFN-γ and IL-6) who experienced longer PFS (13.2 vs 8.05 months; HR: 0.42 [0.18–0.93] p = 0.02) and OS (18.04 vs 12.09 mo; HR: 0.53 [0.25–1.29] p = 0.07). Conclusions: Adipokines can play a crucial role to determining effectiveness of anti-cancer immunotherapy. The role of metabolic immune dysfunctions needs further pre-clinical validation and is currently investigated in the larger prospective cohort.

MAURIS is an Italian multicenter, open-label, phase IIIb ongoing trial, aiming at evaluating the safety and effectiveness of atezolizumab + carboplatin/etoposide in patients with newly diagnosed, extensive-stage small-cell lung cancer (ES-SCLC). The primary objective is the safety evaluation. Patients received atezolizumab + carboplatin/etoposide Q3W for 4-6 cycles in the induction phase, followed by atezolizumab maintenance Q3W. We presented the interim analysis on safety (referring to the induction phase) and clinical effectiveness, in all patients (N = 154) and in subgroups that received ≤3 (N = 23), 4 (N = 43), and 5-6 cycles (N = 89) of induction. At a median follow-up of 10.5 months, 139 patients (90.3%) discontinued treatment. Serious adverse events occurred in 29.9% of patients overall, and the rate was lower in patients with 5-6 cycles (19.1%) than in those with 4 (34.9%) or ≤3 (63.6%) cycles. Immune-mediated adverse events were reported in 14.9%, 15.7%, 11.6%, and 18.2% of patients, overall and by subgroup, respectively. The median overall survival and progression-free survival were 10.7 and 5.5 months, respectively. Overall, 111 patients (71.6%) had a tumor response. Interim results provide further evidences about safety and efficacy profile of atezolizumab + carboplatin/etoposide treatment in a ES-SCLC patient population closer to that observed in clinical practice. Eudract No. 2019-001146-17, NCT04028050.

Lung cancer is one of the most aggressive malignancies, classified into two major histological subtypes: non-small cell lung cancer (NSCLC), that accounts for about 85% of new diagnosis, and small cell lung cancer (SCLC), the other 15%. In the case of NSCLC, comprehensive genome sequencing has allowed the identification of an increasing number of actionable targets, which have become the cornerstone of treatment in the advanced setting. On the other hand, the concept of oncogene-addiction is lacking in SCLC, and the only innovation of the last 30 years has been the introduction of immune checkpoint inhibitors in extensive stage disease. Dysregulation of cell cycle is a fundamental step in carcinogenesis, and Aurora kinases (AURKs) are a family of serine/threonine kinases that play a crucial role in the correct advance through the steps of the cycle. Hyperexpression of Aurora kinases is a common protumorigenic pathway in many cancer types, including NSCLC and SCLC; in addition, different mechanisms of resistance to anticancer drugs rely on AURK expression. Hence, small molecule inhibitors of AURKs have been developed in recent years and tested in several malignancies, with different results. The aim of this review is to analyze the current evidences of AURK inhibition in lung cancer, starting from preclinical rationale to finish with clinical trials available up to now.