The impact of decision tools during oncological consultation with lung cancer patients: A systematic review within the I3LUNG project

INTRODUCTION

To date, lung cancer is one of the most lethal diagnoses worldwide. A variety of lung cancer treatments and modalities are available, which are generally presented during the patient and doctor consultation. The implementation of decision tools to facilitate patient's decision-making and the management of their healthcare process during medical consultation is fundamental. Studies have demonstrated that decision tools are helpful to promote health management and decision-making of lung cancer patients during consultations. The main aim of the present work within the I3LUNG project is to systematically review the implementation of decision tools to facilitate medical consultation about oncological treatments for lung cancer patients.

METHODS

In the present study, we conducted a systematic review following the PRISMA guidelines. We used an electronic computer-based search involving three databases, as follows: Embase, PubMed, and Scopus. 10 articles met the inclusion criteria and were included. They explicitly refer to decision tools in the oncological context, with lung cancer patients.

RESULTS

The discussion highlights the most encouraging results about the positive role of decision aids during medical consultations about oncological treatments, especially regarding anxiety, decision-making, and patient knowledge. However, no one main decision aid tool emerged as essential. Opting for a more recent timeframe to select eligible articles might shed light on the current array of decision aid tools available.

CONCLUSION

Future review efforts could utilize alternative search strategies to explore other lung cancer-specific outcomes during medical consultations for treatment decisions and the implementation of decision aid tools. Engaging with experts in the fields of oncology, patient decision-making, or health communication could provide valuable insights and recommendations for relevant literature or research directions that may not be readily accessible through traditional search methods. The development of guidelines for future research were provided with the aim to promote decision aids focused on patients' needs.

APOLLO 11 Project, Consortium in Advanced Lung Cancer Patients Treated With Innovative Therapies: Integration of Real-World Data and Translational Research

INTRODUCTION

Despite several therapeutic efforts, lung cancer remains a highly lethal disease. Novel therapeutic approaches encompass immune-checkpoint inhibitors, targeted therapeutics and antibody-drug conjugates, with different results. Several studies have been aimed at identifying biomarkers able to predict benefit from these therapies and create a prediction model of response, despite this there is a lack of information to help clinicians in the choice of therapy for lung cancer patients with advanced disease. This is primarily due to the complexity of lung cancer biology, where a single or few biomarkers are not sufficient to provide enough predictive capability to explain biologic differences; other reasons include the paucity of data collected by single studies performed in heterogeneous unmatched cohorts and the methodology of analysis. In fact, classical statistical methods are unable to analyze and integrate the magnitude of information from multiple biological and clinical sources (eg, genomics, transcriptomics, and radiomics).

METHODS AND OBJECTIVES

APOLLO11 is an Italian multicentre, observational study involving patients with a diagnosis of advanced lung cancer (NSCLC and SCLC) treated with innovative therapies. Retrospective and prospective collection of multiomic data, such as tissue- (eg, for genomic, transcriptomic analysis) and blood-based biologic material (eg, ctDNA, PBMC), in addition to clinical and radiological data (eg, for radiomic analysis) will be collected. The overall aim of the project is to build a consortium integrating different datasets and a virtual biobank from participating Italian lung cancer centers. To face with the large amount of data provided, AI and ML techniques will be applied will be applied to manage this large dataset in an effort to build an R-Model, integrating retrospective and prospective population-based data. The ultimate goal is to create a tool able to help physicians and patients to make treatment decisions.

CONCLUSION

APOLLO11 aims to propose a breakthrough approach in lung cancer research, replacing the old, monocentric viewpoint towards a multicomprehensive, multiomic, multicenter model. Multicenter cancer datasets incorporating common virtual biobank and new methodologic approaches including artificial intelligence, machine learning up to deep learning is the road to the future in oncology launched by this project.

Real-world data to build explainable trustworthy artificial intelligence models for prediction of immunotherapy efficacy in NSCLC patients

Introduction

Artificial 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.

Methods

We 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.

Results

Of 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.

Conclusions

In 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.

Integrating clinical and biological prognostic biomarkers in patients with advanced NSCLC treated with immunotherapy: the DEMo score system

Background

Several biomarkers have been separately described to select patients for immunotherapy (IO), but few studies integrate these markers. Di Maio, EPSILoN and the plasma microRNA signature classifier (MSC), are three different clinico, biochemical and molecular markers able to independently predict prognosis in non-small cell lung cancer (NSCLC).

Methods

Complete data such as sex, histology, ECOG-PS, stage, smoking status, presence of liver metastasis, LDH and neutrophils-to-lymphocyte ratio were collected to generate Di Maio and EPSILoN. The MSC risk level was prospectively assessed in plasma samples collected at baseline IO. The 3 markers were integrated into the DEMo score system prospectively tested in a cohort of 200 advanced NSCLC patients treated with IO. Endpoints were overall survival (OS), progression-free survival (PFS) and overall response rate (ORR).

Results

DEMo separated patients in 7-risk groups whose median OS had a trend ranging from 29.7 to 1.5 months (P<0.0001). When comparing patients with the lowest (n=29) and the highest (n=35) DEMo scores ORR was 45% and 3%, respectively (P<0.0001). Considering the 53 PD-L1 ≥50% patients, DEMo identified a group of 13 (25%) patients who benefit less from IO in terms of both OS (HR: 8.81; 95% CI: 2.87–20.01) and PFS (HR: 6.82; 95% CI: 2.57–18.10). Twelve out of 111 (11%) patients who most benefit from IO according to OS (HR: 0.21; 95% CI: 0.07–0.62) and PFS (HR: 0.28; 95% CI: 0.12–0.65) were identified by DEMo in the PD-L1 <50% group.

Conclusions

The DEMo prognostic score system stratified NSCLC patients treated with IO better than each single marker. The proper use of DEMo according to PD-L1 could improve selection in IO regimens.

An Ensemble Approach for Cognitive Fault Detection and Isolation in Sensor Networks

Cognitive fault detection and diagnosis systems are systems able to provide timely information about possibly occurring faults without requiring any a priori knowledge about the process generating the data or the possible faults. This ability is crucial in sensor network scenarios where a priori information about the data generating process, the noise level or the dictionary of the possibly occurring faults is generally hard to obtain. We here present a novel cognitive fault detection and isolation system for sensor networks. The proposed solution relies on the modeling of spatial and temporal relationships present in the acquired datastreams and an ensemble of Hidden Markov Model change-detection tests working in the space of estimated parameters for fault detection and isolation purposes. The effectiveness of the proposed solution has been evaluated on both synthetically generated and real datasets.