Machine learning reveals a PD-L1–independent prediction of response to immunotherapy of non-small cell lung cancer by gene expression context

Wiesweg, Marcel; Mairinger, Fabian; Reis, Henning; Goetz, Moritz; Kollmeier, Jens; Misch, Daniel; Stephan-Falkenau, Susann; Mairinger, Thomas; Walter, Robert Fred Henry; Hager, Thomas; Metzenmacher, Martin; Eberhardt, Wilfried; Zaun, Gregor; Köster, Johannes; Stuschke, Martin; Aigner, Clemens; Darwiche, Kaid; Schmid, Kurt Werner; Rahmann, Sven; Schüler, Martin

doi:10.1016/j.ejca.2020.09.015

Cited by 37 publications

(24 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although well developed in several areas of science and industry, especially for dealing with ‘big data’, the use of ML for clinical oncology has remained limited to date [ 14 , 23 ]. In particular, very few studies have investigated ML for prediction of response to immune-checkpoint blockade, and none has focused on the predictive value of blood counts [ 16 , 24 , 25 , 26 ]. In addition, the main limitation of such studies is the small sample size, despite being a critical determinant to ensure the robustness and generalizability of the results [ 27 ].…”

Section: Discussionmentioning

confidence: 99%

Machine Learning for Prediction of Immunotherapy Efficacy in Non-Small Cell Lung Cancer from Simple Clinical and Biological Data

Benzekry

Grangeon

Karlsen

et al. 2021

Cancers

View full text Add to dashboard Cite

Background: Immune checkpoint inhibitors (ICIs) are now a therapeutic standard in advanced non-small cell lung cancer (NSCLC), but strong predictive markers for ICIs efficacy are still lacking. We evaluated machine learning models built on simple clinical and biological data to individually predict response to ICIs. Methods: Patients with metastatic NSCLC who received ICI in second line or later were included. We collected clinical and hematological data and studied the association of this data with disease control rate (DCR), progression free survival (PFS) and overall survival (OS). Multiple machine learning (ML) algorithms were assessed for their ability to predict response. Results: Overall, 298 patients were enrolled. The overall response rate and DCR were 15.3% and 53%, respectively. Median PFS and OS were 3.3 and 11.4 months, respectively. In multivariable analysis, DCR was significantly associated with performance status (PS) and hemoglobin level (OR 0.58, p < 0.0001; OR 1.8, p < 0.001). These variables were also associated with PFS and OS and ranked top in random forest-based feature importance. Neutrophil-to-lymphocyte ratio was also associated with DCR, PFS and OS. The best ML algorithm was a random forest. It could predict DCR with satisfactory efficacy based on these three variables. Ten-fold cross-validated performances were: accuracy 0.68 ± 0.04, sensitivity 0.58 ± 0.08; specificity 0.78 ± 0.06; positive predictive value 0.70 ± 0.08; negative predictive value 0.68 ± 0.06; AUC 0.74 ± 0.03. Conclusion: Combination of simple clinical and biological data could accurately predict disease control rate at the individual level.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning for Prediction of Immunotherapy Efficacy in Non-Small Cell Lung Cancer from Simple Clinical and Biological Data

Benzekry

Grangeon

Karlsen

et al. 2021

Cancers

View full text Add to dashboard Cite

show abstract

“…Best et al selected specific spliced-RNA biomarker panels using likelihood ratio analysis of variance (ANOVA) statistics and then comparing healthy individuals to patients with cancer based on analysis of differential expression of spliced junctions [ 36 ]. Logistic regression analysis, ANOVA statistics, and an ensemble approach with random sub-sampling have been widely used to select important features [ 37 – 39 ]. Another way to reduce the dimension of potential features is using unsupervised-machine learning, such as least absolute shrinkage and selection operator (LASSO) regression or principal component analysis (PCA) [ 40 ].…”

Section: Ai In Medicine—concepts and Utilizationmentioning

confidence: 99%

“…Meanwhile, Wiesweg et al conducted machine learning approaches on RNA expression of a 770-gene panel covering immune-related genes in patients with advanced NSCLC, in combination with PD-L1 immunohistochemistry [ 39 ]. The model prediction plus PD-L1 positivity identified NSCLC patients with highly favorable outcomes.…”

Section: Development Of Immune Checkpoint Inhibitors (Icis) Treatment Of Nsclc Based On Ai Analysis Of Omics Datamentioning

confidence: 99%

The current issues and future perspective of artificial intelligence for developing new treatment strategy in non-small cell lung cancer: harmonization of molecular cancer biology and artificial intelligence

2021

View full text Add to dashboard Cite

Comprehensive analysis of omics data, such as genome, transcriptome, proteome, metabolome, and interactome, is a crucial technique for elucidating the complex mechanism of cancer onset and progression. Recently, a variety of new findings have been reported based on multi-omics analysis in combination with various clinical information. However, integrated analysis of multi-omics data is extremely labor intensive, making the development of new analysis technology indispensable. Artificial intelligence (AI), which has been under development in recent years, is quickly becoming an effective approach to reduce the labor involved in analyzing large amounts of complex data and to obtain valuable information that is often overlooked in manual analysis and experiments. The use of AI, such as machine learning approaches and deep learning systems, allows for the efficient analysis of massive omics data combined with accurate clinical information and can lead to comprehensive predictive models that will be desirable for further developing individual treatment strategies of immunotherapy and molecular target therapy. Here, we aim to review the potential of AI in the integrated analysis of omics data and clinical information with a special focus on recent advances in the discovery of new biomarkers and the future direction of personalized medicine in non-small lung cancer.

show abstract

“…Recent advances have explored the potential of ML models on outcome prediction of the anti-PD-1 therapy [7], [13]- [19]. Wiesweg et al [18] adopt learning models to predict the response to anti-PD-1 therapy of non-small cell lung cancer (NSCLC). Arbour et al develop a deep-learning model trained on radiology text reports to predict the gold-standard RECIST category [19].…”

Section: ) Prediction Of Deathmentioning

confidence: 99%

“…Paper [22] claims that missing data were minimal due to robust documentation and follow-up information. It is also observed that feature enhancement, a technique to create new features based on existing ones, is rarely used [23], while feature selection is more commonly considered [17], [18], [21], [22], [24]- [26]. In addition, despite working on a small dataset, none of the reviewed studied considered data augmentation, and none employed ensemble learning.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning-Aided Framework to Predict Outcomes of Anti-PD-1 Therapy for Patients With Gynecological Cancer on Incomplete Post-Marketing Surveillance Dataset

et al. 2021

View full text Add to dashboard Cite

Post-marketing surveillance of antineoplastic agents is performed to evaluate the efficacy and safety in patients aiming at expanding drug indications and discovering potential adverse events. The real-world data is fraught with missing values. Literature addressing different strategies for dealing with missing data in such a situation is scarce. Using machine learning (ML) algorithms for predicting therapeutic outcomes of PD-1/PD-L1 Inhibitors has attracted attention. However, training a predictive model usually requires imaging or biomarker information, which is rarely available in the post-marketing surveillance data. To address these challenges, we propose a ML-aided framework to predict the outcomes of Anti-PD-1 therapy for gynecological malignancy on a dataset with 117 patient samples, treated by Camrelizumab (with 50 patient samples), Sintilimab (44), and Toripalimab (23). Four therapeutic outcomes, including Response Evaluation Criteria in Solid Tumours (RECIST), organ adverse effect (AE), general AE, and death, are predicted. The proposed framework feeds the dataset into a learning pipeline consisting of imputation, feature engineering, model training, ensemble learning, and model selection to generate the final predictive model. We conduct experiments to justify several critical design choices, such as the specific feature engineering strategies and the SMOTE over-sampling technique. The final model for each learning task is selected from a large pool of model candidates based on a joint consideration of accuracy and F1. Moreover, we conduct thorough and visualized model analysis and gain a deeper understanding of model behavior and feature importance. The results, analysis, and findings demonstrate the superiority of the proposed learningaided framework.

show abstract

Machine learning reveals a PD-L1–independent prediction of response to immunotherapy of non-small cell lung cancer by gene expression context

Cited by 37 publications

References 30 publications

Machine Learning for Prediction of Immunotherapy Efficacy in Non-Small Cell Lung Cancer from Simple Clinical and Biological Data

Machine Learning for Prediction of Immunotherapy Efficacy in Non-Small Cell Lung Cancer from Simple Clinical and Biological Data

The current issues and future perspective of artificial intelligence for developing new treatment strategy in non-small cell lung cancer: harmonization of molecular cancer biology and artificial intelligence

A Machine Learning-Aided Framework to Predict Outcomes of Anti-PD-1 Therapy for Patients With Gynecological Cancer on Incomplete Post-Marketing Surveillance Dataset

Contact Info

Product

Resources

About