Deep learning to estimate durable clinical benefit and prognosis from patients with non-small cell lung cancer treated with PD-1/PD-L1 blockade

Decision model for durable clinical benefit from front- or late-line immunotherapy alone or with chemotherapy in non-small cell lung cancer

BACKGROUND

Predictive biomarkers and models of immune checkpoint inhibitors (ICIs) have been extensively studied in non-small cell lung cancer (NSCLC). However, evidence for many biomarkers remains inconclusive, and the opaqueness of machine learning models hinders practicality. We aimed to provide compelling evidence for biomarkers and develop a transparent decision tree model.

METHODS

We consolidated data from 3,288 ICI-treated patients with NSCLC across real-world multicenter, public cohorts and the Choice-01 trial (ClinicalTrials.gov: NCT03856411). Over 50 features were examined for predicting durable clinical benefits (DCBs) from ICIs. Noteworthy biomarkers were identified to establish a decision tree model. Additionally, we explored the tumor microenvironment and peripheral CD8+ programmed death-1 (PD-1)+ T cell receptor (TCR) profiles.

FINDINGS

Multivariate logistic regression analysis identified tumor histology, PD-ligand 1 (PD-L1) expression, tumor mutational burden, line, and regimen of ICI treatment as significant factors. Mutation subtypes of EGFR, KRAS, KEAP1, STK11, and disruptive TP53 mutations were associated with DCB. The decision tree (DT10) model, using the ten clinicopathological and genomic markers, showed superior performance in predicting DCB in the training set (area under the curve [AUC] = 0.82) and consistently outperformed other models in test sets. DT10-predicted-DCB patients manifested longer survival, an enriched inflamed tumor immune phenotype (67%), and higher peripheral TCR diversity, whereas the DT10-predicted-NDB (non-durable benefit) group showed an enriched desert immune phenotype (86%) and higher peripheral TCR clonality.

CONCLUSIONS

The model effectively predicted DCB after front-/subsequent-line ICI treatment, with or without chemotherapy, for squamous and non-squamous lung cancer, offering clinicians valuable insights into efficacy prediction using cost-effective variables.

FUNDING

This study was supported by the National Key R&D Program of China.

Artificial Intelligence and Machine Learning in Predicting the Response to Immunotherapy in Non-small Cell Lung Carcinoma: A Systematic Review

Non-small cell lung carcinoma (NSCLC) is a prevalent and aggressive form of lung cancer, with a poor prognosis for metastatic disease. Immunotherapy, particularly immune checkpoint inhibitors (ICIs), has revolutionized the management of NSCLC, but response rates are highly variable. Identifying reliable predictive biomarkers is crucial to optimize patient selection and treatment outcomes. This systematic review aimed to evaluate the current state of artificial intelligence (AI) and machine learning (ML) applications in predicting the response to immunotherapy in NSCLC. A comprehensive literature search identified 19 studies that met the inclusion criteria. The studies employed diverse AI/ML techniques, including deep learning, artificial neural networks, support vector machines, and gradient boosting methods, applied to various data modalities such as medical imaging, genomic data, clinical variables, and immunohistochemical markers. Several studies demonstrated the ability of AI/ML models to accurately predict immunotherapy response, progression-free survival, and overall survival in NSCLC patients. However, challenges remain in data availability, quality, and interpretability of these models. Efforts have been made to develop interpretable AI/ML techniques, but further research is needed to improve transparency and explainability. Additionally, translating AI/ML models from research settings to clinical practice poses challenges related to regulatory approval, data privacy, and integration into existing healthcare systems. Nonetheless, the successful implementation of AI/ML models could enable personalized treatment strategies, improve treatment outcomes, and reduce unnecessary toxicities and healthcare costs associated with ineffective treatments.

Informing immunotherapy with multi-omics driven machine learning

Progress in sequencing technologies and clinical experiments has revolutionized immunotherapy on solid and hematologic malignancies. However, the benefits of immunotherapy are limited to specific patient subsets, posing challenges for broader application. To improve its effectiveness, identifying biomarkers that can predict patient response is crucial. Machine learning (ML) play a pivotal role in harnessing multi-omic cancer datasets and unlocking new insights into immunotherapy. This review provides an overview of cutting-edge ML models applied in omics data for immunotherapy analysis, including immunotherapy response prediction and immunotherapy-relevant tumor microenvironment identification. We elucidate how ML leverages diverse data types to identify significant biomarkers, enhance our understanding of immunotherapy mechanisms, and optimize decision-making process. Additionally, we discuss current limitations and challenges of ML in this rapidly evolving field. Finally, we outline future directions aimed at overcoming these barriers and improving the efficiency of ML in immunotherapy research.

A novel sub-regional radiomics model to predict immunotherapy response in non-small cell lung carcinoma

BACKGROUND

Identifying precise biomarkers of immunotherapy response for non-small cell lung carcinoma (NSCLC) before treatment is challenging. This study aimed to construct and investigate the potential performance of a sub-regional radiomics model (SRRM) as a novel tumor biomarker in predicting the response of patients with NSCLC treated with immune checkpoint inhibitors, and test whether its predictive performance is superior to that of conventional radiomics, tumor mutational burden (TMB) score and programmed death ligand-1 (PD-L1) expression.

METHODS

We categorized 264 patients from retrospective databases of two centers into training (n = 159) and validation (n = 105) cohorts. Radiomic features were extracted from three sub-regions of the tumor region of interest using the K-means method. We extracted 1,896 features from each sub-region, resulting in 5688 features per sample. The least absolute shrinkage and selection operator regression method was used to select sub-regional radiomic features. The SRRM was constructed and validated using the support vector machine algorithm. We used next-generation sequencing to classify patients from the two cohorts into high TMB (≥ 10 muts/Mb) and low TMB (< 10 muts/Mb) groups; immunohistochemistry was performed to assess PD-L1 expression in formalin-fixed, paraffin-embedded tumor sections, with high expression defined as ≥ 50% of tumor cells being positive. Associations between the SRRM and progression-free survival (PFS) and variant genes were assessed.

RESULTS

Eleven sub-regional radiomic features were employed to develop the SRRM. The areas under the receiver operating characteristic curve (AUCs) of the proposed SRRM were 0.90 (95% confidence interval [CI] 0.84-0.96) and 0.86 (95% CI 0.76-0.95) in the training and validation cohorts, respectively. The SRRM (low vs. high; cutoff value = 0.936) was significantly associated with PFS in the training (hazard ratio [HR] = 0.35 [0.24-0.50], P < 0.001) and validation (HR = 0.42 [0.26-0.67], P = 0.001) cohorts. A significant correlation between the SRRM and three variant genes (H3C4, PAX5, and EGFR) was observed. In the validation cohort, the SRRM demonstrated a higher AUC (0.86, P < 0.001) than that for PD-L1 expression (0.66, P = 0.034) and TMB score (0.54, P = 0.552).

CONCLUSIONS

The SRRM had better predictive performance and was superior to conventional radiomics, PD-L1 expression, and TMB score. The SRRM effectively stratified the progression-free survival (PFS) risk among patients with NSCLC receiving immunotherapy.

Determining the prognosis of Lung cancer from mutated genes using a deep learning survival model: a large multi-center study

BACKGROUND

Gene status has become the focus of prognosis prediction. Furthermore, deep learning has frequently been implemented in medical imaging to diagnose, prognosticate, and evaluate treatment responses in patients with cancer. However, few deep learning survival (DLS) models based on mutational genes that are directly associated with patient prognosis in terms of progression-free survival (PFS) or overall survival (OS) have been reported. Additionally, DLS models have not been applied to determine IO-related prognosis based on mutational genes. Herein, we developed a deep learning method to predict the prognosis of patients with lung cancer treated with or without immunotherapy (IO).

METHODS

Samples from 6542 patients from different centers were subjected to genome sequencing. A DLS model based on multi-panels of somatic mutations was trained and validated to predict OS in patients treated without IO and PFS in patients treated with IO.

RESULTS

In patients treated without IO, the DLS model (low vs. high DLS) was trained using the training MSK-MET cohort (HR = 0.241 [0.213-0.273], P < 0.001) and tested in the inter-validation MSK-MET cohort (HR = 0.175 [0.148-0.206], P < 0.001). The DLS model was then validated with the OncoSG, MSK-CSC, and TCGA-LUAD cohorts (HR = 0.420 [0.272-0.649], P < 0.001; HR = 0.550 [0.424-0.714], P < 0.001; HR = 0.215 [0.159-0.291], P < 0.001, respectively). Subsequently, it was fine-tuned and retrained in patients treated with IO. The DLS model (low vs. high DLS) could predict PFS and OS in the MIND, MSKCC, and POPLAR/OAK cohorts (P < 0.001, respectively). Compared with tumor-node-metastasis staging, the COX model, tumor mutational burden, and programmed death-ligand 1 expression, the DLS model had the highest C-index in patients treated with or without IO.

CONCLUSIONS

The DLS model based on mutational genes can robustly predict the prognosis of patients with lung cancer treated with or without IO.

Advances in efficacy prediction and monitoring of neoadjuvant immunotherapy for non-small cell lung cancer

The use of immune checkpoint inhibitors (ICIs) has become mainstream in the treatment of non-small cell lung cancer (NSCLC). The idea of harnessing the immune system to fight cancer is fast developing. Neoadjuvant treatment in NSCLC is undergoing unprecedented change. Chemo-immunotherapy combinations not only seem to achieve population-wide treating coverage irrespective of PD-L1 expression but also enable achieving a pathological complete response (pCR). Despite these recent advancements in neoadjuvant chemo-immunotherapy, not all patients respond favorably to treatment with ICIs plus chemo and may even suffer from severe immune-related adverse effects (irAEs). Similar to selection for target therapy, identifying patients most likely to benefit from chemo-immunotherapy may be valuable. Recently, several prognostic and predictive factors associated with the efficacy of neoadjuvant immunotherapy in NSCLC, such as tumor-intrinsic biomarkers, tumor microenvironment biomarkers, liquid biopsies, microbiota, metabolic profiles, and clinical characteristics, have been described. However, a specific and sensitive biomarker remains to be identified. Recently, the construction of prediction models for ICI therapy using novel tools, such as multi-omics factors, proteomic tests, host immune classifiers, and machine learning algorithms, has gained attention. In this review, we provide a comprehensive overview of the different positive prognostic and predictive factors in treating preoperative patients with ICIs, highlight the recent advances made in the efficacy prediction of neoadjuvant immunotherapy, and provide an outlook for joint predictors.